removed print statements.

* Run ControlNet compile test in a separate subprocess

`torch.compile()` spawns several subprocesses and the GPU memory used
was not reclaimed after the test ran. This approach was taken from
`transformers`.

* Style

* Prepare a couple more compile tests to run in subprocess.

* Use require_torch_2 decorator.

* Test inpaint_compile in subprocess.

* Run img2img compile test in subprocess.

* Run stable diffusion compile test in subprocess.

* style

* Temporarily trigger on pr to test.

* Revert "Temporarily trigger on pr to test."

This reverts commit 82d76868dd.

.github/actions/setup-miniconda/action.yml

@@ -27,7 +27,7 @@ runs:
       - name: Get date
         id: get-date
         shell: bash
-        run: echo "::set-output name=today::$(/bin/date -u '+%Y%m%d')d"
+        run: echo "today=$(/bin/date -u '+%Y%m%d')d" >> $GITHUB_OUTPUT
       - name: Setup miniconda cache
         id: miniconda-cache
         uses: actions/cache@v2
@@ -143,4 +143,4 @@ runs:
                 echo "There is ${AVAIL}KB free space left in $MOUNT, continue"
               fi
             fi
-          done
+          done

.github/workflows/build_documentation.yml

@@ -5,7 +5,7 @@ on:
     branches:
       - main
       - doc-builder*
-      - v*-release
+      - v*-patch
 
 jobs:
    build:

.github/workflows/pr_tests.yml

@@ -21,26 +21,26 @@ jobs:
       fail-fast: false
       matrix:
         config:
-          - name: Fast PyTorch CPU tests on Ubuntu
-            framework: pytorch
+          - name: Fast PyTorch Pipeline CPU tests
+            framework: pytorch_pipelines
             runner: docker-cpu
             image: diffusers/diffusers-pytorch-cpu
-            report: torch_cpu
-          - name: Fast Flax CPU tests on Ubuntu
+            report: torch_cpu_pipelines
+          - name: Fast PyTorch Models & Schedulers CPU tests
+            framework: pytorch_models
+            runner: docker-cpu
+            image: diffusers/diffusers-pytorch-cpu
+            report: torch_cpu_models_schedulers
+          - name: Fast Flax CPU tests
             framework: flax
             runner: docker-cpu
             image: diffusers/diffusers-flax-cpu
             report: flax_cpu
-          - name: Fast ONNXRuntime CPU tests on Ubuntu
-            framework: onnxruntime
-            runner: docker-cpu
-            image: diffusers/diffusers-onnxruntime-cpu
-            report: onnx_cpu
-          - name: PyTorch Example CPU tests on Ubuntu
+          - name: PyTorch Example CPU tests
             framework: pytorch_examples
             runner: docker-cpu
             image: diffusers/diffusers-pytorch-cpu
-            report: torch_cpu
+            report: torch_example_cpu
 
     name: ${{ matrix.config.name }}
 
@@ -64,20 +64,26 @@ jobs:
       run: |
         apt-get update && apt-get install libsndfile1-dev -y
         python -m pip install -e .[quality,test]
-        python -m pip install -U git+https://github.com/huggingface/transformers
-        python -m pip install git+https://github.com/huggingface/accelerate
 
     - name: Environment
       run: |
         python utils/print_env.py
 
-    - name: Run fast PyTorch CPU tests
-      if: ${{ matrix.config.framework == 'pytorch' }}
+    - name: Run fast PyTorch Pipeline CPU tests
+      if: ${{ matrix.config.framework == 'pytorch_pipelines' }}
       run: |
         python -m pytest -n 2 --max-worker-restart=0 --dist=loadfile \
           -s -v -k "not Flax and not Onnx" \
           --make-reports=tests_${{ matrix.config.report }} \
-          tests/
+          tests/pipelines
+
+    - name: Run fast PyTorch Model Scheduler CPU tests
+      if: ${{ matrix.config.framework == 'pytorch_models' }}
+      run: |
+        python -m pytest -n 2 --max-worker-restart=0 --dist=loadfile \
+          -s -v -k "not Flax and not Onnx" \
+          --make-reports=tests_${{ matrix.config.report }} \
+          tests/models tests/schedulers tests/others
 
     - name: Run fast Flax TPU tests
       if: ${{ matrix.config.framework == 'flax' }}
@@ -85,15 +91,7 @@ jobs:
         python -m pytest -n 2 --max-worker-restart=0 --dist=loadfile \
           -s -v -k "Flax" \
           --make-reports=tests_${{ matrix.config.report }} \
-          tests/
-
-    - name: Run fast ONNXRuntime CPU tests
-      if: ${{ matrix.config.framework == 'onnxruntime' }}
-      run: |
-        python -m pytest -n 2 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "Onnx" \
-          --make-reports=tests_${{ matrix.config.report }} \
-          tests/
+          tests
 
     - name: Run example PyTorch CPU tests
       if: ${{ matrix.config.framework == 'pytorch_examples' }}
@@ -112,56 +110,3 @@ jobs:
       with:
         name: pr_${{ matrix.config.report }}_test_reports
         path: reports
-
-  run_fast_tests_apple_m1:
-    name: Fast PyTorch MPS tests on MacOS
-    runs-on: [ self-hosted, apple-m1 ]
-
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: Clean checkout
-      shell: arch -arch arm64 bash {0}
-      run: |
-        git clean -fxd
-
-    - name: Setup miniconda
-      uses: ./.github/actions/setup-miniconda
-      with:
-        python-version: 3.9
-
-    - name: Install dependencies
-      shell: arch -arch arm64 bash {0}
-      run: |
-        ${CONDA_RUN} python -m pip install --upgrade pip
-        ${CONDA_RUN} python -m pip install -e .[quality,test]
-        ${CONDA_RUN} python -m pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cpu
-        ${CONDA_RUN} python -m pip install git+https://github.com/huggingface/accelerate
-        ${CONDA_RUN} python -m pip install -U git+https://github.com/huggingface/transformers
-
-    - name: Environment
-      shell: arch -arch arm64 bash {0}
-      run: |
-        ${CONDA_RUN} python utils/print_env.py
-
-    - name: Run fast PyTorch tests on M1 (MPS)
-      shell: arch -arch arm64 bash {0}
-      env:
-        HF_HOME: /System/Volumes/Data/mnt/cache
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
-      run: |
-        ${CONDA_RUN} python -m pytest -n 0 -s -v --make-reports=tests_torch_mps tests/
-
-    - name: Failure short reports
-      if: ${{ failure() }}
-      run: cat reports/tests_torch_mps_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v2
-      with:
-        name: pr_torch_mps_test_reports
-        path: reports

.github/workflows/push_tests.yml

@@ -61,8 +61,6 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install -e .[quality,test]
-        python -m pip install -U git+https://github.com/huggingface/transformers
-        python -m pip install git+https://github.com/huggingface/accelerate
 
     - name: Environment
       run: |
@@ -72,6 +70,9 @@ jobs:
       if: ${{ matrix.config.framework == 'pytorch' }}
       env:
         HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+        # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
+        CUBLAS_WORKSPACE_CONFIG: :16:8 
+
       run: |
         python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
           -s -v -k "not Flax and not Onnx" \
@@ -131,8 +132,6 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install -e .[quality,test,training]
-        python -m pip install git+https://github.com/huggingface/accelerate
-        python -m pip install -U git+https://github.com/huggingface/transformers
 
     - name: Environment
       run: |

.github/workflows/push_tests_fast.yml

@@ -1,4 +1,4 @@
-name: Slow tests on main
+name: Fast tests on main
 
 on:
   push:
@@ -38,7 +38,7 @@ jobs:
             framework: pytorch_examples
             runner: docker-cpu
             image: diffusers/diffusers-pytorch-cpu
-            report: torch_cpu
+            report: torch_example_cpu
 
     name: ${{ matrix.config.name }}
 
@@ -62,8 +62,6 @@ jobs:
       run: |
         apt-get update && apt-get install libsndfile1-dev -y
         python -m pip install -e .[quality,test]
-        python -m pip install -U git+https://github.com/huggingface/transformers
-        python -m pip install git+https://github.com/huggingface/accelerate
 
     - name: Environment
       run: |
@@ -110,56 +108,3 @@ jobs:
       with:
         name: pr_${{ matrix.config.report }}_test_reports
         path: reports
-
-  run_fast_tests_apple_m1:
-    name: Fast PyTorch MPS tests on MacOS
-    runs-on: [ self-hosted, apple-m1 ]
-
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: Clean checkout
-      shell: arch -arch arm64 bash {0}
-      run: |
-        git clean -fxd
-
-    - name: Setup miniconda
-      uses: ./.github/actions/setup-miniconda
-      with:
-        python-version: 3.9
-
-    - name: Install dependencies
-      shell: arch -arch arm64 bash {0}
-      run: |
-        ${CONDA_RUN} python -m pip install --upgrade pip
-        ${CONDA_RUN} python -m pip install -e .[quality,test]
-        ${CONDA_RUN} python -m pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cpu
-        ${CONDA_RUN} python -m pip install git+https://github.com/huggingface/accelerate
-        ${CONDA_RUN} python -m pip install -U git+https://github.com/huggingface/transformers
-
-    - name: Environment
-      shell: arch -arch arm64 bash {0}
-      run: |
-        ${CONDA_RUN} python utils/print_env.py
-
-    - name: Run fast PyTorch tests on M1 (MPS)
-      shell: arch -arch arm64 bash {0}
-      env:
-        HF_HOME: /System/Volumes/Data/mnt/cache
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
-      run: |
-        ${CONDA_RUN} python -m pytest -n 0 -s -v --make-reports=tests_torch_mps tests/
-
-    - name: Failure short reports
-      if: ${{ failure() }}
-      run: cat reports/tests_torch_mps_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v2
-      with:
-        name: pr_torch_mps_test_reports
-        path: reports

.github/workflows/push_tests_mps.yml

@@ -0,0 +1,68 @@
+name: Fast mps tests on main
+
+on:
+  push:
+    branches:
+      - main
+
+env:
+  DIFFUSERS_IS_CI: yes
+  HF_HOME: /mnt/cache
+  OMP_NUM_THREADS: 8
+  MKL_NUM_THREADS: 8
+  PYTEST_TIMEOUT: 600
+  RUN_SLOW: no
+
+jobs:
+  run_fast_tests_apple_m1:
+    name: Fast PyTorch MPS tests on MacOS
+    runs-on: [ self-hosted, apple-m1 ]
+
+    steps:
+    - name: Checkout diffusers
+      uses: actions/checkout@v3
+      with:
+        fetch-depth: 2
+
+    - name: Clean checkout
+      shell: arch -arch arm64 bash {0}
+      run: |
+        git clean -fxd
+
+    - name: Setup miniconda
+      uses: ./.github/actions/setup-miniconda
+      with:
+        python-version: 3.9
+
+    - name: Install dependencies
+      shell: arch -arch arm64 bash {0}
+      run: |
+        ${CONDA_RUN} python -m pip install --upgrade pip
+        ${CONDA_RUN} python -m pip install -e .[quality,test]
+        ${CONDA_RUN} python -m pip install torch torchvision torchaudio
+        ${CONDA_RUN} python -m pip install accelerate --upgrade
+        ${CONDA_RUN} python -m pip install transformers --upgrade
+
+    - name: Environment
+      shell: arch -arch arm64 bash {0}
+      run: |
+        ${CONDA_RUN} python utils/print_env.py
+
+    - name: Run fast PyTorch tests on M1 (MPS)
+      shell: arch -arch arm64 bash {0}
+      env:
+        HF_HOME: /System/Volumes/Data/mnt/cache
+        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+      run: |
+        ${CONDA_RUN} python -m pytest -n 0 -s -v --make-reports=tests_torch_mps tests/
+
+    - name: Failure short reports
+      if: ${{ failure() }}
+      run: cat reports/tests_torch_mps_failures_short.txt
+
+    - name: Test suite reports artifacts
+      if: ${{ always() }}
+      uses: actions/upload-artifact@v2
+      with:
+        name: pr_torch_mps_test_reports
+        path: reports

CONTRIBUTING.md

@@ -394,8 +394,15 @@ passes. You should run the tests impacted by your changes like this:
  ```bash
  $ pytest tests/<TEST_TO_RUN>.py
  ```
+ 
+Before you run the tests, please make sure you install the dependencies required for testing. You can do so 
+with this command:
 
-You can also run the full suite with the following command, but it takes
+ ```bash
+ $ pip install -e ".[test]"
+ ```
+
+You can run the full test suite with the following command, but it takes
 a beefy machine to produce a result in a decent amount of time now that
 Diffusers has grown a lot. Here is the command for it:
 

README.md

@@ -59,8 +59,9 @@ Generating outputs is super easy with 🤗 Diffusers. To generate an image from
 
 ```python
 from diffusers import DiffusionPipeline
+import torch
 
-pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")
+pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
 pipeline.to("cuda")
 pipeline("An image of a squirrel in Picasso style").images[0]
 ```
@@ -99,55 +100,11 @@ Check out the [Quickstart](https://huggingface.co/docs/diffusers/quicktour) to l
 
 | **Documentation**                                                   | **What can I learn?**                                                                                                                                                                           |
 |---------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| Tutorial                                                            | A basic crash course for learning how to use the library's most important features like using models and schedulers to build your own diffusion system, and training your own diffusion model.  |
-| Loading                                                             | Guides for how to load and configure all the components (pipelines, models, and schedulers) of the library, as well as how to use different schedulers.                                         |
-| Pipelines for inference                                             | Guides for how to use pipelines for different inference tasks, batched generation, controlling generated outputs and randomness, and how to contribute a pipeline to the library.               |
-| Optimization                                                        | Guides for how to optimize your diffusion model to run faster and consume less memory.                                                                                                          |
+| [Tutorial](https://huggingface.co/docs/diffusers/tutorials/tutorial_overview)                                                            | A basic crash course for learning how to use the library's most important features like using models and schedulers to build your own diffusion system, and training your own diffusion model.  |
+| [Loading](https://huggingface.co/docs/diffusers/using-diffusers/loading_overview)                                                             | Guides for how to load and configure all the components (pipelines, models, and schedulers) of the library, as well as how to use different schedulers.                                         |
+| [Pipelines for inference](https://huggingface.co/docs/diffusers/using-diffusers/pipeline_overview)                                             | Guides for how to use pipelines for different inference tasks, batched generation, controlling generated outputs and randomness, and how to contribute a pipeline to the library.               |
+| [Optimization](https://huggingface.co/docs/diffusers/optimization/opt_overview)                                                        | Guides for how to optimize your diffusion model to run faster and consume less memory.                                                                                                          |
 | [Training](https://huggingface.co/docs/diffusers/training/overview) | Guides for how to train a diffusion model for different tasks with different training techniques.                                                                                               |
-
-## Supported pipelines
-
-| Pipeline | Paper | Tasks |
-|---|---|:---:|
-| [alt_diffusion](./api/pipelines/alt_diffusion) | [**AltDiffusion**](https://arxiv.org/abs/2211.06679) | Image-to-Image Text-Guided Generation |
-| [audio_diffusion](./api/pipelines/audio_diffusion) | [**Audio Diffusion**](https://github.com/teticio/audio-diffusion.git) | Unconditional Audio Generation |
-| [controlnet](./api/pipelines/stable_diffusion/controlnet) | [**ControlNet with Stable Diffusion**](https://arxiv.org/abs/2302.05543) | Image-to-Image Text-Guided Generation |
-| [cycle_diffusion](./api/pipelines/cycle_diffusion) | [**Cycle Diffusion**](https://arxiv.org/abs/2210.05559) | Image-to-Image Text-Guided Generation |
-| [dance_diffusion](./api/pipelines/dance_diffusion) | [**Dance Diffusion**](https://github.com/williamberman/diffusers.git) | Unconditional Audio Generation |
-| [ddpm](./api/pipelines/ddpm) | [**Denoising Diffusion Probabilistic Models**](https://arxiv.org/abs/2006.11239) | Unconditional Image Generation |
-| [ddim](./api/pipelines/ddim) | [**Denoising Diffusion Implicit Models**](https://arxiv.org/abs/2010.02502) | Unconditional Image Generation |
-| [latent_diffusion](./api/pipelines/latent_diffusion) | [**High-Resolution Image Synthesis with Latent Diffusion Models**](https://arxiv.org/abs/2112.10752)| Text-to-Image Generation |
-| [latent_diffusion](./api/pipelines/latent_diffusion) | [**High-Resolution Image Synthesis with Latent Diffusion Models**](https://arxiv.org/abs/2112.10752)| Super Resolution Image-to-Image |
-| [latent_diffusion_uncond](./api/pipelines/latent_diffusion_uncond) | [**High-Resolution Image Synthesis with Latent Diffusion Models**](https://arxiv.org/abs/2112.10752) | Unconditional Image Generation |
-| [paint_by_example](./api/pipelines/paint_by_example) | [**Paint by Example: Exemplar-based Image Editing with Diffusion Models**](https://arxiv.org/abs/2211.13227) | Image-Guided Image Inpainting |
-| [pndm](./api/pipelines/pndm) | [**Pseudo Numerical Methods for Diffusion Models on Manifolds**](https://arxiv.org/abs/2202.09778) | Unconditional Image Generation |
-| [score_sde_ve](./api/pipelines/score_sde_ve) | [**Score-Based Generative Modeling through Stochastic Differential Equations**](https://openreview.net/forum?id=PxTIG12RRHS) | Unconditional Image Generation |
-| [score_sde_vp](./api/pipelines/score_sde_vp) | [**Score-Based Generative Modeling through Stochastic Differential Equations**](https://openreview.net/forum?id=PxTIG12RRHS) | Unconditional Image Generation |
-| [semantic_stable_diffusion](./api/pipelines/semantic_stable_diffusion) | [**Semantic Guidance**](https://arxiv.org/abs/2301.12247) | Text-Guided Generation |
-| [stable_diffusion_text2img](./api/pipelines/stable_diffusion/text2img) | [**Stable Diffusion**](https://stability.ai/blog/stable-diffusion-public-release) | Text-to-Image Generation |
-| [stable_diffusion_img2img](./api/pipelines/stable_diffusion/img2img) | [**Stable Diffusion**](https://stability.ai/blog/stable-diffusion-public-release) | Image-to-Image Text-Guided Generation |
-| [stable_diffusion_inpaint](./api/pipelines/stable_diffusion/inpaint) | [**Stable Diffusion**](https://stability.ai/blog/stable-diffusion-public-release) | Text-Guided Image Inpainting |
-| [stable_diffusion_panorama](./api/pipelines/stable_diffusion/panorama) | [**MultiDiffusion**](https://multidiffusion.github.io/) | Text-to-Panorama Generation |
-| [stable_diffusion_pix2pix](./api/pipelines/stable_diffusion/pix2pix) | [**InstructPix2Pix**](https://github.com/timothybrooks/instruct-pix2pix) | Text-Guided Image Editing|
-| [stable_diffusion_pix2pix_zero](./api/pipelines/stable_diffusion/pix2pix_zero) | [**Zero-shot Image-to-Image Translation**](https://pix2pixzero.github.io/) | Text-Guided Image Editing |
-| [stable_diffusion_attend_and_excite](./api/pipelines/stable_diffusion/attend_and_excite) | [**Attend and Excite for Stable Diffusion**](https://attendandexcite.github.io/Attend-and-Excite/) | Text-to-Image Generation |
-| [stable_diffusion_self_attention_guidance](./api/pipelines/stable_diffusion/self_attention_guidance) | [**Self-Attention Guidance**](https://ku-cvlab.github.io/Self-Attention-Guidance) | Text-to-Image Generation |
-| [stable_diffusion_image_variation](./stable_diffusion/image_variation) | [**Stable Diffusion Image Variations**](https://github.com/LambdaLabsML/lambda-diffusers#stable-diffusion-image-variations) | Image-to-Image Generation |
-| [stable_diffusion_latent_upscale](./stable_diffusion/latent_upscale) | [**Stable Diffusion Latent Upscaler**](https://twitter.com/StabilityAI/status/1590531958815064065) | Text-Guided Super Resolution Image-to-Image |
-| [stable_diffusion_2](./api/pipelines/stable_diffusion_2) | [**Stable Diffusion 2**](https://stability.ai/blog/stable-diffusion-v2-release) | Text-to-Image Generation |
-| [stable_diffusion_2](./api/pipelines/stable_diffusion_2) | [**Stable Diffusion 2**](https://stability.ai/blog/stable-diffusion-v2-release) | Text-Guided Image Inpainting |
-| [stable_diffusion_2](./api/pipelines/stable_diffusion_2) | [**Depth-Conditional Stable Diffusion**](https://github.com/Stability-AI/stablediffusion#depth-conditional-stable-diffusion) | Depth-to-Image Generation |
-| [stable_diffusion_2](./api/pipelines/stable_diffusion_2) | [**Stable Diffusion 2**](https://stability.ai/blog/stable-diffusion-v2-release) | Text-Guided Super Resolution Image-to-Image |
-| [stable_diffusion_safe](./api/pipelines/stable_diffusion_safe) | [**Safe Stable Diffusion**](https://arxiv.org/abs/2211.05105) | Text-Guided Generation |
-| [stable_unclip](./stable_unclip) | **Stable unCLIP** | Text-to-Image Generation |
-| [stable_unclip](./stable_unclip) | **Stable unCLIP** | Image-to-Image Text-Guided Generation |
-| [stochastic_karras_ve](./api/pipelines/stochastic_karras_ve) | [**Elucidating the Design Space of Diffusion-Based Generative Models**](https://arxiv.org/abs/2206.00364) | Unconditional Image Generation |
-| [unclip](./api/pipelines/unclip) | [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://arxiv.org/abs/2204.06125) | Text-to-Image Generation |
-| [versatile_diffusion](./api/pipelines/versatile_diffusion) | [Versatile Diffusion: Text, Images and Variations All in One Diffusion Model](https://arxiv.org/abs/2211.08332) | Text-to-Image Generation |
-| [versatile_diffusion](./api/pipelines/versatile_diffusion) | [Versatile Diffusion: Text, Images and Variations All in One Diffusion Model](https://arxiv.org/abs/2211.08332) | Image Variations Generation |
-| [versatile_diffusion](./api/pipelines/versatile_diffusion) | [Versatile Diffusion: Text, Images and Variations All in One Diffusion Model](https://arxiv.org/abs/2211.08332) | Dual Image and Text Guided Generation |
-| [vq_diffusion](./api/pipelines/vq_diffusion) | [Vector Quantized Diffusion Model for Text-to-Image Synthesis](https://arxiv.org/abs/2111.14822) | Text-to-Image Generation |
-
 ## Contribution
 
 We ❤️  contributions from the open-source community! 
@@ -160,6 +117,87 @@ You can look out for [issues](https://github.com/huggingface/diffusers/issues) y
 Also, say 👋 in our public Discord channel <a href="https://discord.gg/G7tWnz98XR"><img alt="Join us on Discord" src="https://img.shields.io/discord/823813159592001537?color=5865F2&logo=discord&logoColor=white"></a>. We discuss the hottest trends about diffusion models, help each other with contributions, personal projects or
 just hang out ☕.
 
+
+## Popular Tasks & Pipelines
+
+<table>
+  <tr>
+    <th>Task</th>
+    <th>Pipeline</th>
+    <th>🤗 Hub</th>
+  </tr>
+  <tr style="border-top: 2px solid black">
+    <td>Unconditional Image Generation</td>
+    <td><a href="./api/pipelines/ddpm"> DDPM </a></td>
+    <td><a href="https://huggingface.co/google/ddpm-ema-church-256"> google/ddpm-ema-church-256 </a></td>
+  </tr>
+  <tr style="border-top: 2px solid black">
+    <td>Text-to-Image</td>
+    <td><a href="./api/pipelines/stable_diffusion/text2img">Stable Diffusion Text-to-Image</a></td>
+      <td><a href="https://huggingface.co/runwayml/stable-diffusion-v1-5"> runwayml/stable-diffusion-v1-5 </a></td>
+  </tr>
+  <tr>
+    <td>Text-to-Image</td>
+    <td><a href="./api/pipelines/unclip">unclip</a></td>
+      <td><a href="https://huggingface.co/kakaobrain/karlo-v1-alpha"> kakaobrain/karlo-v1-alpha </a></td>
+  </tr>
+  <tr>
+    <td>Text-to-Image</td>
+    <td><a href="./api/pipelines/if">if</a></td>
+      <td><a href="https://huggingface.co/DeepFloyd/IF-I-XL-v1.0"> DeepFloyd/IF-I-XL-v1.0 </a></td>
+  </tr>
+  <tr style="border-top: 2px solid black">
+    <td>Text-guided Image-to-Image</td>
+    <td><a href="./api/pipelines/stable_diffusion/controlnet">Controlnet</a></td>
+      <td><a href="https://huggingface.co/lllyasviel/sd-controlnet-canny"> lllyasviel/sd-controlnet-canny </a></td>
+  </tr>
+  <tr>
+    <td>Text-guided Image-to-Image</td>
+    <td><a href="./api/pipelines/stable_diffusion/pix2pix">Instruct Pix2Pix</a></td>
+      <td><a href="https://huggingface.co/timbrooks/instruct-pix2pix"> timbrooks/instruct-pix2pix </a></td>
+  </tr>
+  <tr>
+    <td>Text-guided Image-to-Image</td>
+    <td><a href="./api/pipelines/stable_diffusion/img2img">Stable Diffusion Image-to-Image</a></td>
+      <td><a href="https://huggingface.co/runwayml/stable-diffusion-v1-5"> runwayml/stable-diffusion-v1-5 </a></td>
+  </tr>
+  <tr style="border-top: 2px solid black">
+    <td>Text-guided Image Inpainting</td>
+    <td><a href="./api/pipelines/stable_diffusion/inpaint">Stable Diffusion Inpaint</a></td>
+      <td><a href="https://huggingface.co/runwayml/stable-diffusion-inpainting"> runwayml/stable-diffusion-inpainting </a></td>
+  </tr>
+  <tr style="border-top: 2px solid black">
+    <td>Image Variation</td>
+    <td><a href="./stable_diffusion/image_variation">Stable Diffusion Image Variation</a></td>
+      <td><a href="https://huggingface.co/lambdalabs/sd-image-variations-diffusers"> lambdalabs/sd-image-variations-diffusers </a></td>
+  </tr>
+  <tr style="border-top: 2px solid black">
+    <td>Super Resolution</td>
+    <td><a href="./stable_diffusion/stable_diffusion/upscale">Stable Diffusion Upscale</a></td>
+      <td><a href="https://huggingface.co/stabilityai/stable-diffusion-x4-upscaler"> stabilityai/stable-diffusion-x4-upscaler </a></td>
+  </tr>
+  <tr>
+    <td>Super Resolution</td>
+    <td><a href="./stable_diffusion/latent_upscale">Stable Diffusion Latent Upscale</a></td>
+      <td><a href="https://huggingface.co/stabilityai/sd-x2-latent-upscaler"> stabilityai/sd-x2-latent-upscaler </a></td>
+  </tr>
+</table>
+
+## Popular libraries using 🧨 Diffusers
+
+- https://github.com/microsoft/TaskMatrix 
+- https://github.com/invoke-ai/InvokeAI 
+- https://github.com/apple/ml-stable-diffusion   
+- https://github.com/Sanster/lama-cleaner 
+- https://github.com/IDEA-Research/Grounded-Segment-Anything
+- https://github.com/ashawkey/stable-dreamfusion 
+- https://github.com/deep-floyd/IF  
+- https://github.com/bentoml/BentoML
+- https://github.com/bmaltais/kohya_ss
+- +3000 other amazing GitHub repositories 💪
+
+Thank you for using us ❤️
+
 ## Credits
 
 This library concretizes previous work by many different authors and would not have been possible without their great research and implementations. We'd like to thank, in particular, the following implementations which have helped us in our development and without which the API could not have been as polished today:

docker/diffusers-pytorch-cuda/Dockerfile

@@ -26,7 +26,7 @@ RUN python3 -m pip install --no-cache-dir --upgrade pip && \
     python3 -m pip install --no-cache-dir \
         torch \
         torchvision \
-        torchaudio \
+        torchaudio && \
     python3 -m pip install --no-cache-dir \
         accelerate \
         datasets \
@@ -37,6 +37,7 @@ RUN python3 -m pip install --no-cache-dir --upgrade pip && \
         numpy \
         scipy \
         tensorboard \
-        transformers
+        transformers \
+        omegaconf
 
 CMD ["/bin/bash"]

docs/source/en/_toctree.yml

@@ -4,7 +4,7 @@
   - local: quicktour
     title: Quicktour
   - local: stable_diffusion
-    title: Stable Diffusion
+    title: Effective and efficient diffusion
   - local: installation
     title: Installation
   title: Get started
@@ -25,7 +25,9 @@
     - local: using-diffusers/schedulers
       title: Load and compare different schedulers
     - local: using-diffusers/custom_pipeline_overview
-      title: Load and add custom pipelines
+      title: Load community pipelines
+    - local: using-diffusers/using_safetensors
+      title: Load safetensors
     - local: using-diffusers/kerascv
       title: Load KerasCV Stable Diffusion checkpoints
     title: Loading & Hub
@@ -42,22 +44,30 @@
       title: Text-guided image-inpainting
     - local: using-diffusers/depth2img
       title: Text-guided depth-to-image
+    - local: using-diffusers/textual_inversion_inference
+      title: Textual inversion
+    - local: training/distributed_inference
+      title: Distributed inference with multiple GPUs
     - local: using-diffusers/reusing_seeds
       title: Improve image quality with deterministic generation
     - local: using-diffusers/reproducibility
       title: Create reproducible pipelines
     - local: using-diffusers/custom_pipeline_examples
-      title: Community Pipelines
+      title: Community pipelines
     - local: using-diffusers/contribute_pipeline
-      title: How to contribute a Pipeline
-    - local: using-diffusers/using_safetensors
-      title: Using safetensors
+      title: How to contribute a community pipeline
+    - local: using-diffusers/stable_diffusion_jax_how_to
+      title: Stable Diffusion in JAX/Flax
     - local: using-diffusers/weighted_prompts
       title: Weighting Prompts
     title: Pipelines for Inference
   - sections:
     - local: training/overview
       title: Overview
+    - local: training/create_dataset
+      title: Create a dataset for training
+    - local: training/adapt_a_model
+      title: Adapt a model to a new task
     - local: training/unconditional_training
       title: Unconditional image generation
     - local: training/text_inversion
@@ -72,6 +82,8 @@
       title: ControlNet
     - local: training/instructpix2pix
       title: InstructPix2Pix Training
+    - local: training/custom_diffusion
+      title: Custom Diffusion
     title: Training
   - sections:
     - local: using-diffusers/rl
@@ -95,10 +107,14 @@
     title: ONNX
   - local: optimization/open_vino
     title: OpenVINO
+  - local: optimization/coreml
+    title: Core ML
   - local: optimization/mps
     title: MPS
   - local: optimization/habana
     title: Habana Gaudi
+  - local: optimization/tome
+    title: Token Merging
   title: Optimization/Special Hardware
 - sections:
   - local: conceptual/philosophy
@@ -136,6 +152,8 @@
       title: Audio Diffusion
     - local: api/pipelines/audioldm
       title: AudioLDM
+    - local: api/pipelines/controlnet
+      title: ControlNet
     - local: api/pipelines/cycle_diffusion
       title: Cycle Diffusion
     - local: api/pipelines/dance_diffusion
@@ -146,6 +164,8 @@
       title: DDPM
     - local: api/pipelines/dit
       title: DiT
+    - local: api/pipelines/if
+      title: IF
     - local: api/pipelines/latent_diffusion
       title: Latent Diffusion
     - local: api/pipelines/paint_by_example
@@ -161,7 +181,7 @@
     - local: api/pipelines/semantic_stable_diffusion
       title: Semantic Guidance
     - local: api/pipelines/spectrogram_diffusion
-      title: "Spectrogram Diffusion"
+      title: Spectrogram Diffusion
     - sections:
       - local: api/pipelines/stable_diffusion/overview
         title: Overview
@@ -189,10 +209,10 @@
         title: Self-Attention Guidance
       - local: api/pipelines/stable_diffusion/panorama
         title: MultiDiffusion Panorama
-      - local: api/pipelines/stable_diffusion/controlnet
-        title: Text-to-Image Generation with ControlNet Conditioning
       - local: api/pipelines/stable_diffusion/model_editing
         title: Text-to-Image Model Editing
+      - local: api/pipelines/stable_diffusion/diffedit
+        title: DiffEdit
       title: Stable Diffusion
     - local: api/pipelines/stable_diffusion_2
       title: Stable Diffusion 2
@@ -202,6 +222,8 @@
       title: Stochastic Karras VE
     - local: api/pipelines/text_to_video
       title: Text-to-Video
+    - local: api/pipelines/text_to_video_zero
+      title: Text-to-Video Zero
     - local: api/pipelines/unclip
       title: UnCLIP
     - local: api/pipelines/latent_diffusion_uncond
@@ -226,12 +248,16 @@
       title: DPM Discrete Scheduler
     - local: api/schedulers/dpm_discrete_ancestral
       title: DPM Discrete Scheduler with ancestral sampling
+    - local: api/schedulers/dpm_sde
+      title: DPMSolverSDEScheduler
     - local: api/schedulers/euler_ancestral
       title: Euler Ancestral Scheduler
     - local: api/schedulers/euler
       title: Euler scheduler
     - local: api/schedulers/heun
       title: Heun Scheduler
+    - local: api/schedulers/multistep_dpm_solver_inverse
+      title: Inverse Multistep DPM-Solver
     - local: api/schedulers/ipndm
       title: IPNDM
     - local: api/schedulers/lms_discrete

docs/source/en/api/loaders.mdx

@@ -28,3 +28,15 @@ API to load such adapter neural networks via the [`loaders.py` module](https://g
 ### UNet2DConditionLoadersMixin
 
 [[autodoc]] loaders.UNet2DConditionLoadersMixin
+
+### TextualInversionLoaderMixin
+
+[[autodoc]] loaders.TextualInversionLoaderMixin
+
+### LoraLoaderMixin
+
+[[autodoc]] loaders.LoraLoaderMixin
+
+### FromCkptMixin
+
+[[autodoc]] loaders.FromCkptMixin

docs/source/en/api/logging.mdx

@@ -61,7 +61,7 @@ verbose to the most verbose), those levels (with their corresponding int values
   critical errors.
 - `diffusers.logging.ERROR` (int value, 40): only report errors.
 - `diffusers.logging.WARNING` or `diffusers.logging.WARN` (int value, 30): only reports error and
-  warnings. This the default level used by the library.
+  warnings. This is the default level used by the library.
 - `diffusers.logging.INFO` (int value, 20): reports error, warnings and basic information.
 - `diffusers.logging.DEBUG` (int value, 10): report all information.
 

docs/source/en/api/pipelines/alt_diffusion.mdx

@@ -28,11 +28,11 @@ The abstract of the paper is the following:
 
 ## Tips
 
-- AltDiffusion is conceptually exactly the same as [Stable Diffusion](./api/pipelines/stable_diffusion/overview).
+- AltDiffusion is conceptually exactly the same as [Stable Diffusion](./stable_diffusion/overview).
 
 - *Run AltDiffusion*
 
-AltDiffusion can be tested very easily with the [`AltDiffusionPipeline`], [`AltDiffusionImg2ImgPipeline`] and the `"BAAI/AltDiffusion-m9"` checkpoint exactly in the same way it is shown in the [Conditional Image Generation Guide](./using-diffusers/conditional_image_generation) and the [Image-to-Image Generation Guide](./using-diffusers/img2img).
+AltDiffusion can be tested very easily with the [`AltDiffusionPipeline`], [`AltDiffusionImg2ImgPipeline`] and the `"BAAI/AltDiffusion-m9"` checkpoint exactly in the same way it is shown in the [Conditional Image Generation Guide](../../using-diffusers/conditional_image_generation) and the [Image-to-Image Generation Guide](../../using-diffusers/img2img).
 
 - *How to load and use different schedulers.*
 

docs/source/en/api/pipelines/audioldm.mdx

@@ -25,14 +25,14 @@ This pipeline was contributed by [sanchit-gandhi](https://huggingface.co/sanchit
 
 ## Text-to-Audio
 
-The [`AudioLDMPipeline`] can be used to load pre-trained weights from [cvssp/audioldm](https://huggingface.co/cvssp/audioldm) and generate text-conditional audio outputs:
+The [`AudioLDMPipeline`] can be used to load pre-trained weights from [cvssp/audioldm-s-full-v2](https://huggingface.co/cvssp/audioldm-s-full-v2) and generate text-conditional audio outputs:
 
 ```python
 from diffusers import AudioLDMPipeline
 import torch
 import scipy
 
-repo_id = "cvssp/audioldm"
+repo_id = "cvssp/audioldm-s-full-v2"
 pipe = AudioLDMPipeline.from_pretrained(repo_id, torch_dtype=torch.float16)
 pipe = pipe.to("cuda")
 
@@ -56,7 +56,7 @@ Inference:
 ### How to load and use different schedulers
 
 The AudioLDM pipeline uses [`DDIMScheduler`] scheduler by default. But `diffusers` provides many other schedulers
-that can be used with the AudioLDM pipeline such as [`PNDMScheduler`], [`LMSDiscreteScheduler`], [`EulerDiscreteScheduler`], 
+that can be used with the AudioLDM pipeline such as [`PNDMScheduler`], [`LMSDiscreteScheduler`], [`EulerDiscreteScheduler`],
 [`EulerAncestralDiscreteScheduler`] etc. We recommend using the [`DPMSolverMultistepScheduler`] as it's currently the fastest
 scheduler there is.
 
@@ -68,12 +68,14 @@ method, or pass the `scheduler` argument to the `from_pretrained` method of the
 >>> from diffusers import AudioLDMPipeline, DPMSolverMultistepScheduler
 >>> import torch
 
->>> pipeline = AudioLDMPipeline.from_pretrained("cvssp/audioldm", torch_dtype=torch.float16)
+>>> pipeline = AudioLDMPipeline.from_pretrained("cvssp/audioldm-s-full-v2", torch_dtype=torch.float16)
 >>> pipeline.scheduler = DPMSolverMultistepScheduler.from_config(pipeline.scheduler.config)
 
 >>> # or
->>> dpm_scheduler = DPMSolverMultistepScheduler.from_pretrained("cvssp/audioldm", subfolder="scheduler")
->>> pipeline = AudioLDMPipeline.from_pretrained("cvssp/audioldm", scheduler=dpm_scheduler, torch_dtype=torch.float16)
+>>> dpm_scheduler = DPMSolverMultistepScheduler.from_pretrained("cvssp/audioldm-s-full-v2", subfolder="scheduler")
+>>> pipeline = AudioLDMPipeline.from_pretrained(
+...     "cvssp/audioldm-s-full-v2", scheduler=dpm_scheduler, torch_dtype=torch.float16
+... )
 ```
 
 ## AudioLDMPipeline

docs/source/en/api/pipelines/controlnet.mdx

@@ -22,7 +22,7 @@ The abstract of the paper is the following:
 
 *We present a neural network structure, ControlNet, to control pretrained large diffusion models to support additional input conditions. The ControlNet learns task-specific conditions in an end-to-end way, and the learning is robust even when the training dataset is small (< 50k). Moreover, training a ControlNet is as fast as fine-tuning a diffusion model, and the model can be trained on a personal devices. Alternatively, if powerful computation clusters are available, the model can scale to large amounts (millions to billions) of data. We report that large diffusion models like Stable Diffusion can be augmented with ControlNets to enable conditional inputs like edge maps, segmentation maps, keypoints, etc. This may enrich the methods to control large diffusion models and further facilitate related applications.*
 
-This model was contributed by the amazing community contributor [takuma104](https://huggingface.co/takuma104) ❤️ .
+This model was contributed by the community contributor [takuma104](https://huggingface.co/takuma104) ❤️ .
 
 Resources:
 
@@ -33,7 +33,9 @@ Resources:
 
 | Pipeline | Tasks | Demo
 |---|---|:---:|
-| [StableDiffusionControlNetPipeline](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_controlnet.py) | *Text-to-Image Generation with ControlNet Conditioning* | [Colab Example](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/controlnet.ipynb)
+| [StableDiffusionControlNetPipeline](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/controlnet/pipeline_controlnet.py) | *Text-to-Image Generation with ControlNet Conditioning* | [Colab Example](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/controlnet.ipynb)
+| [StableDiffusionControlNetImg2ImgPipeline](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/controlnet/pipeline_controlnet_img2img.py) | *Image-to-Image Generation with ControlNet Conditioning* | 
+| [StableDiffusionControlNetInpaintPipeline](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/pipeline_controlnet_inpaint.py) | *Inpainting Generation with ControlNet Conditioning* | 
 
 ## Usage example
 
@@ -131,7 +133,7 @@ This should take only around 3-4 seconds on GPU (depending on hardware). The out
 ![img](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/vermeer_disco_dancing.png)
 
 
-**Note**: To see how to run all other ControlNet checkpoints, please have a look at [ControlNet with Stable Diffusion 1.5](#controlnet-with-stable-diffusion-1.5)
+**Note**: To see how to run all other ControlNet checkpoints, please have a look at [ControlNet with Stable Diffusion 1.5](#controlnet-with-stable-diffusion-1.5).
 
 <!-- TODO: add space -->
 
@@ -242,6 +244,41 @@ image.save("./multi_controlnet_output.png")
 
 <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/controlnet/multi_controlnet_output.png" width=600/>
 
+### Guess Mode
+
+Guess Mode is [a ControlNet feature that was implemented](https://github.com/lllyasviel/ControlNet#guess-mode--non-prompt-mode) after the publication of [the paper](https://arxiv.org/abs/2302.05543). The description states:
+
+>In this mode, the ControlNet encoder will try best to recognize the content of the input control map, like depth map, edge map, scribbles, etc, even if you remove all prompts.
+
+#### The core implementation:
+
+It adjusts the scale of the output residuals from ControlNet by a fixed ratio depending on the block depth. The shallowest DownBlock corresponds to `0.1`. As the blocks get deeper, the scale increases exponentially, and the scale for the output of the MidBlock becomes `1.0`. 
+
+Since the core implementation is just this, **it does not have any impact on prompt conditioning**. While it is common to use it without specifying any prompts, it is also possible to provide prompts if desired.
+
+#### Usage:
+
+Just specify `guess_mode=True` in the pipe() function. A `guidance_scale` between 3.0 and 5.0 is [recommended](https://github.com/lllyasviel/ControlNet#guess-mode--non-prompt-mode).
+```py
+from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
+import torch
+
+controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny")
+pipe = StableDiffusionControlNetPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", controlnet=controlnet).to(
+    "cuda"
+)
+image = pipe("", image=canny_image, guess_mode=True, guidance_scale=3.0).images[0]
+image.save("guess_mode_generated.png")
+```
+
+#### Output image comparison:
+Canny Control Example
+
+|no guess_mode with prompt|guess_mode without prompt|
+|---|---|
+|<a href="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare_guess_mode/output_images/diffusers/output_bird_canny_0.png"><img width="128" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare_guess_mode/output_images/diffusers/output_bird_canny_0.png"/></a>|<a href="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare_guess_mode/output_images/diffusers/output_bird_canny_0_gm.png"><img width="128" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare_guess_mode/output_images/diffusers/output_bird_canny_0_gm.png"/></a>|
+
+
 ## Available checkpoints
 
 ControlNet requires a *control image* in addition to the text-to-image *prompt*. 
@@ -249,7 +286,9 @@ Each pretrained model is trained using a different conditioning method that requ
 
 All checkpoints can be found under the authors' namespace [lllyasviel](https://huggingface.co/lllyasviel).
 
-### ControlNet with Stable Diffusion 1.5
+**13.04.2024 Update**: The author has released improved controlnet checkpoints v1.1 - see [here](#controlnet-v1.1).
+
+### ControlNet v1.0
 
 | Model Name | Control Image Overview| Control Image Example | Generated Image Example |
 |---|---|---|---|
@@ -262,6 +301,25 @@ All checkpoints can be found under the authors' namespace [lllyasviel](https://h
 |[lllyasviel/sd-controlnet-scribble](https://huggingface.co/lllyasviel/sd-controlnet_scribble)<br/> *Trained with human scribbles*  |A hand-drawn monochrome image with white outlines on a black background.|<a href="https://huggingface.co/takuma104/controlnet_dev/blob/main/gen_compare/control_images/converted/control_vermeer_scribble.png"><img width="64" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/control_images/converted/control_vermeer_scribble.png"/></a>|<a href="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_vermeer_scribble_0.png"><img width="64" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_vermeer_scribble_0.png"/></a> |
 |[lllyasviel/sd-controlnet-seg](https://huggingface.co/lllyasviel/sd-controlnet_seg)<br/>*Trained with semantic segmentation*  |An [ADE20K](https://groups.csail.mit.edu/vision/datasets/ADE20K/)'s segmentation protocol image.|<a href="https://huggingface.co/takuma104/controlnet_dev/blob/main/gen_compare/control_images/converted/control_room_seg.png"><img width="64" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/control_images/converted/control_room_seg.png"/></a>|<a href="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_room_seg_1.png"><img width="64" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_room_seg_1.png"/></a> |
 
+### ControlNet v1.1
+
+| Model Name | Control Image Overview| Condition Image | Control Image Example | Generated Image Example |
+|---|---|---|---|---|
+|[lllyasviel/control_v11p_sd15_canny](https://huggingface.co/lllyasviel/control_v11p_sd15_canny)<br/> | *Trained with canny edge detection* | A monochrome image with white edges on a black background.|<a href="https://huggingface.co/lllyasviel/control_v11p_sd15_canny/resolve/main/images/control.png"><img width="64" style="margin:0;padding:0;" src="https://huggingface.co/lllyasviel/control_v11p_sd15_canny/resolve/main/images/control.png"/></a>|<a href="https://huggingface.co/lllyasviel/control_v11p_sd15_canny/resolve/main/images/image_out.png"><img width="64" src="https://huggingface.co/lllyasviel/control_v11p_sd15_canny/resolve/main/images/image_out.png"/></a>|
+|[lllyasviel/control_v11e_sd15_ip2p](https://huggingface.co/lllyasviel/control_v11e_sd15_ip2p)<br/> | *Trained with pixel to pixel instruction* | No condition .|<a href="https://huggingface.co/lllyasviel/control_v11e_sd15_ip2p/resolve/main/images/control.png"><img width="64" style="margin:0;padding:0;" src="https://huggingface.co/lllyasviel/control_v11e_sd15_ip2p/resolve/main/images/control.png"/></a>|<a href="https://huggingface.co/lllyasviel/control_v11e_sd15_ip2p/resolve/main/images/image_out.png"><img width="64" src="https://huggingface.co/lllyasviel/control_v11e_sd15_ip2p/resolve/main/images/image_out.png"/></a>|
+|[lllyasviel/control_v11p_sd15_inpaint](https://huggingface.co/lllyasviel/control_v11p_sd15_inpaint)<br/> | Trained with image inpainting | No condition.|<a href="https://huggingface.co/lllyasviel/control_v11p_sd15_inpaint/resolve/main/images/control.png"><img width="64" style="margin:0;padding:0;" src="https://huggingface.co/lllyasviel/control_v11p_sd15_inpaint/resolve/main/images/control.png"/></a>|<a href="https://huggingface.co/lllyasviel/control_v11p_sd15_inpaint/resolve/main/images/output.png"><img width="64" src="https://huggingface.co/lllyasviel/control_v11p_sd15_inpaint/resolve/main/images/output.png"/></a>|
+|[lllyasviel/control_v11p_sd15_mlsd](https://huggingface.co/lllyasviel/control_v11p_sd15_mlsd)<br/> | Trained with multi-level line segment detection | An image with annotated line segments.|<a href="https://huggingface.co/lllyasviel/control_v11p_sd15_mlsd/resolve/main/images/control.png"><img width="64" style="margin:0;padding:0;" src="https://huggingface.co/lllyasviel/control_v11p_sd15_mlsd/resolve/main/images/control.png"/></a>|<a href="https://huggingface.co/lllyasviel/control_v11p_sd15_mlsd/resolve/main/images/image_out.png"><img width="64" src="https://huggingface.co/lllyasviel/control_v11p_sd15_mlsd/resolve/main/images/image_out.png"/></a>|
+|[lllyasviel/control_v11f1p_sd15_depth](https://huggingface.co/lllyasviel/control_v11f1p_sd15_depth)<br/> | Trained with depth estimation | An image with depth information, usually represented as a grayscale image.|<a href="https://huggingface.co/lllyasviel/control_v11f1p_sd15_depth/resolve/main/images/control.png"><img width="64" style="margin:0;padding:0;" src="https://huggingface.co/lllyasviel/control_v11f1p_sd15_depth/resolve/main/images/control.png"/></a>|<a href="https://huggingface.co/lllyasviel/control_v11f1p_sd15_depth/resolve/main/images/image_out.png"><img width="64" src="https://huggingface.co/lllyasviel/control_v11f1p_sd15_depth/resolve/main/images/image_out.png"/></a>|
+|[lllyasviel/control_v11p_sd15_normalbae](https://huggingface.co/lllyasviel/control_v11p_sd15_normalbae)<br/> | Trained with surface normal estimation | An image with surface normal information, usually represented as a color-coded image.|<a href="https://huggingface.co/lllyasviel/control_v11p_sd15_normalbae/resolve/main/images/control.png"><img width="64" style="margin:0;padding:0;" src="https://huggingface.co/lllyasviel/control_v11p_sd15_normalbae/resolve/main/images/control.png"/></a>|<a href="https://huggingface.co/lllyasviel/control_v11p_sd15_normalbae/resolve/main/images/image_out.png"><img width="64" src="https://huggingface.co/lllyasviel/control_v11p_sd15_normalbae/resolve/main/images/image_out.png"/></a>|
+|[lllyasviel/control_v11p_sd15_seg](https://huggingface.co/lllyasviel/control_v11p_sd15_seg)<br/> | Trained with image segmentation | An image with segmented regions, usually represented as a color-coded image.|<a href="https://huggingface.co/lllyasviel/control_v11p_sd15_seg/resolve/main/images/control.png"><img width="64" style="margin:0;padding:0;" src="https://huggingface.co/lllyasviel/control_v11p_sd15_seg/resolve/main/images/control.png"/></a>|<a href="https://huggingface.co/lllyasviel/control_v11p_sd15_seg/resolve/main/images/image_out.png"><img width="64" src="https://huggingface.co/lllyasviel/control_v11p_sd15_seg/resolve/main/images/image_out.png"/></a>|
+|[lllyasviel/control_v11p_sd15_lineart](https://huggingface.co/lllyasviel/control_v11p_sd15_lineart)<br/> | Trained with line art generation | An image with line art, usually black lines on a white background.|<a href="https://huggingface.co/lllyasviel/control_v11p_sd15_lineart/resolve/main/images/control.png"><img width="64" style="margin:0;padding:0;" src="https://huggingface.co/lllyasviel/control_v11p_sd15_lineart/resolve/main/images/control.png"/></a>|<a href="https://huggingface.co/lllyasviel/control_v11p_sd15_lineart/resolve/main/images/image_out.png"><img width="64" src="https://huggingface.co/lllyasviel/control_v11p_sd15_lineart/resolve/main/images/image_out.png"/></a>|
+|[lllyasviel/control_v11p_sd15s2_lineart_anime](https://huggingface.co/lllyasviel/control_v11p_sd15s2_lineart_anime)<br/> | Trained with anime line art generation | An image with anime-style line art.|<a href="https://huggingface.co/lllyasviel/control_v11p_sd15s2_lineart_anime/resolve/main/images/control.png"><img width="64" style="margin:0;padding:0;" src="https://huggingface.co/lllyasviel/control_v11p_sd15s2_lineart_anime/resolve/main/images/control.png"/></a>|<a href="https://huggingface.co/lllyasviel/control_v11p_sd15s2_lineart_anime/resolve/main/images/image_out.png"><img width="64" src="https://huggingface.co/lllyasviel/control_v11p_sd15s2_lineart_anime/resolve/main/images/image_out.png"/></a>|
+|[lllyasviel/control_v11p_sd15_openpose](https://huggingface.co/lllyasviel/control_v11p_sd15s2_lineart_anime)<br/> | Trained with human pose estimation | An image with human poses, usually represented as a set of keypoints or skeletons.|<a href="https://huggingface.co/lllyasviel/control_v11p_sd15_openpose/resolve/main/images/control.png"><img width="64" style="margin:0;padding:0;" src="https://huggingface.co/lllyasviel/control_v11p_sd15_openpose/resolve/main/images/control.png"/></a>|<a href="https://huggingface.co/lllyasviel/control_v11p_sd15_openpose/resolve/main/images/image_out.png"><img width="64" src="https://huggingface.co/lllyasviel/control_v11p_sd15_openpose/resolve/main/images/image_out.png"/></a>|
+|[lllyasviel/control_v11p_sd15_scribble](https://huggingface.co/lllyasviel/control_v11p_sd15_scribble)<br/> | Trained with scribble-based image generation | An image with scribbles, usually random or user-drawn strokes.|<a href="https://huggingface.co/lllyasviel/control_v11p_sd15_scribble/resolve/main/images/control.png"><img width="64" style="margin:0;padding:0;" src="https://huggingface.co/lllyasviel/control_v11p_sd15_scribble/resolve/main/images/control.png"/></a>|<a href="https://huggingface.co/lllyasviel/control_v11p_sd15_scribble/resolve/main/images/image_out.png"><img width="64" src="https://huggingface.co/lllyasviel/control_v11p_sd15_scribble/resolve/main/images/image_out.png"/></a>|
+|[lllyasviel/control_v11p_sd15_softedge](https://huggingface.co/lllyasviel/control_v11p_sd15_softedge)<br/> | Trained with soft edge image generation | An image with soft edges, usually to create a more painterly or artistic effect.|<a href="https://huggingface.co/lllyasviel/control_v11p_sd15_softedge/resolve/main/images/control.png"><img width="64" style="margin:0;padding:0;" src="https://huggingface.co/lllyasviel/control_v11p_sd15_softedge/resolve/main/images/control.png"/></a>|<a href="https://huggingface.co/lllyasviel/control_v11p_sd15_softedge/resolve/main/images/image_out.png"><img width="64" src="https://huggingface.co/lllyasviel/control_v11p_sd15_softedge/resolve/main/images/image_out.png"/></a>|
+|[lllyasviel/control_v11e_sd15_shuffle](https://huggingface.co/lllyasviel/control_v11e_sd15_shuffle)<br/> | Trained with image shuffling | An image with shuffled patches or regions.|<a href="https://huggingface.co/lllyasviel/control_v11e_sd15_shuffle/resolve/main/images/control.png"><img width="64" style="margin:0;padding:0;" src="https://huggingface.co/lllyasviel/control_v11e_sd15_shuffle/resolve/main/images/control.png"/></a>|<a href="https://huggingface.co/lllyasviel/control_v11e_sd15_shuffle/resolve/main/images/image_out.png"><img width="64" src="https://huggingface.co/lllyasviel/control_v11e_sd15_shuffle/resolve/main/images/image_out.png"/></a>|
+|[lllyasviel/control_v11f1e_sd15_tile](https://huggingface.co/lllyasviel/control_v11f1e_sd15_tile)<br/> | Trained with image tiling | A blurry image or part of an image .|<a href="https://huggingface.co/lllyasviel/control_v11f1e_sd15_tile/resolve/main/images/original.png"><img width="64" style="margin:0;padding:0;" src="https://huggingface.co/lllyasviel/control_v11f1e_sd15_tile/resolve/main/images/original.png"/></a>|<a href="https://huggingface.co/lllyasviel/control_v11f1e_sd15_tile/resolve/main/images/output.png"><img width="64" src="https://huggingface.co/lllyasviel/control_v11f1e_sd15_tile/resolve/main/images/output.png"/></a>|
+
 ## StableDiffusionControlNetPipeline
 [[autodoc]] StableDiffusionControlNetPipeline
 	- all
@@ -272,6 +330,31 @@ All checkpoints can be found under the authors' namespace [lllyasviel](https://h
 	- disable_vae_slicing
 	- enable_xformers_memory_efficient_attention
 	- disable_xformers_memory_efficient_attention
+	- load_textual_inversion
+
+## StableDiffusionControlNetImg2ImgPipeline
+[[autodoc]] StableDiffusionControlNetImg2ImgPipeline
+	- all
+	- __call__
+	- enable_attention_slicing
+	- disable_attention_slicing
+	- enable_vae_slicing
+	- disable_vae_slicing
+	- enable_xformers_memory_efficient_attention
+	- disable_xformers_memory_efficient_attention
+	- load_textual_inversion
+
+## StableDiffusionControlNetInpaintPipeline
+[[autodoc]] StableDiffusionControlNetInpaintPipeline
+	- all
+	- __call__
+	- enable_attention_slicing
+	- disable_attention_slicing
+	- enable_vae_slicing
+	- disable_vae_slicing
+	- enable_xformers_memory_efficient_attention
+	- disable_xformers_memory_efficient_attention
+	- load_textual_inversion
 
 ## FlaxStableDiffusionControlNetPipeline
 [[autodoc]] FlaxStableDiffusionControlNetPipeline

docs/source/en/api/pipelines/if.mdx

@@ -0,0 +1,523 @@
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# IF
+
+## Overview
+
+DeepFloyd IF is a novel state-of-the-art open-source text-to-image model with a high degree of photorealism and language understanding. 
+The model is a modular composed of a frozen text encoder and three cascaded pixel diffusion modules: 
+- Stage 1: a base model that generates 64x64 px image based on text prompt,
+- Stage 2: a 64x64 px => 256x256 px super-resolution model, and a
+- Stage 3: a 256x256 px => 1024x1024 px super-resolution model
+Stage 1 and Stage 2 utilize a frozen text encoder based on the T5 transformer to extract text embeddings, 
+which are then fed into a UNet architecture enhanced with cross-attention and attention pooling. 
+Stage 3 is [Stability's x4 Upscaling model](https://huggingface.co/stabilityai/stable-diffusion-x4-upscaler).
+The result is a highly efficient model that outperforms current state-of-the-art models, achieving a zero-shot FID score of 6.66 on the COCO dataset. 
+Our work underscores the potential of larger UNet architectures in the first stage of cascaded diffusion models and depicts a promising future for text-to-image synthesis.
+
+## Usage
+
+Before you can use IF, you need to accept its usage conditions. To do so:
+1. Make sure to have a [Hugging Face account](https://huggingface.co/join) and be logged in
+2. Accept the license on the model card of [DeepFloyd/IF-I-XL-v1.0](https://huggingface.co/DeepFloyd/IF-I-XL-v1.0). Accepting the license on the stage I model card will auto accept for the other IF models.
+3. Make sure to login locally. Install `huggingface_hub`
+```sh
+pip install huggingface_hub --upgrade
+```
+
+run the login function in a Python shell
+
+```py
+from huggingface_hub import login
+
+login()
+```
+
+and enter your [Hugging Face Hub access token](https://huggingface.co/docs/hub/security-tokens#what-are-user-access-tokens).
+
+Next we install `diffusers` and dependencies:
+
+```sh
+pip install diffusers accelerate transformers safetensors
+```
+
+The following sections give more in-detail examples of how to use IF. Specifically:
+
+- [Text-to-Image Generation](#text-to-image-generation)
+- [Image-to-Image Generation](#text-guided-image-to-image-generation)
+- [Inpainting](#text-guided-inpainting-generation)
+- [Reusing model weights](#converting-between-different-pipelines)
+- [Speed optimization](#optimizing-for-speed)
+- [Memory optimization](#optimizing-for-memory)
+
+**Available checkpoints**
+- *Stage-1*
+  - [DeepFloyd/IF-I-XL-v1.0](https://huggingface.co/DeepFloyd/IF-I-XL-v1.0)
+  - [DeepFloyd/IF-I-L-v1.0](https://huggingface.co/DeepFloyd/IF-I-L-v1.0)
+  - [DeepFloyd/IF-I-M-v1.0](https://huggingface.co/DeepFloyd/IF-I-M-v1.0)
+
+- *Stage-2*
+  - [DeepFloyd/IF-II-L-v1.0](https://huggingface.co/DeepFloyd/IF-II-L-v1.0)
+  - [DeepFloyd/IF-II-M-v1.0](https://huggingface.co/DeepFloyd/IF-II-M-v1.0)
+
+- *Stage-3*
+  - [stabilityai/stable-diffusion-x4-upscaler](https://huggingface.co/stabilityai/stable-diffusion-x4-upscaler)
+
+**Demo**
+[![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/DeepFloyd/IF)
+
+**Google Colab**
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/deepfloyd_if_free_tier_google_colab.ipynb)
+
+### Text-to-Image Generation
+
+By default diffusers makes use of [model cpu offloading](https://huggingface.co/docs/diffusers/optimization/fp16#model-offloading-for-fast-inference-and-memory-savings)
+to run the whole IF pipeline with as little as 14 GB of VRAM.
+
+```python
+from diffusers import DiffusionPipeline
+from diffusers.utils import pt_to_pil
+import torch
+
+# stage 1
+stage_1 = DiffusionPipeline.from_pretrained("DeepFloyd/IF-I-XL-v1.0", variant="fp16", torch_dtype=torch.float16)
+stage_1.enable_model_cpu_offload()
+
+# stage 2
+stage_2 = DiffusionPipeline.from_pretrained(
+    "DeepFloyd/IF-II-L-v1.0", text_encoder=None, variant="fp16", torch_dtype=torch.float16
+)
+stage_2.enable_model_cpu_offload()
+
+# stage 3
+safety_modules = {
+    "feature_extractor": stage_1.feature_extractor,
+    "safety_checker": stage_1.safety_checker,
+    "watermarker": stage_1.watermarker,
+}
+stage_3 = DiffusionPipeline.from_pretrained(
+    "stabilityai/stable-diffusion-x4-upscaler", **safety_modules, torch_dtype=torch.float16
+)
+stage_3.enable_model_cpu_offload()
+
+prompt = 'a photo of a kangaroo wearing an orange hoodie and blue sunglasses standing in front of the eiffel tower holding a sign that says "very deep learning"'
+generator = torch.manual_seed(1)
+
+# text embeds
+prompt_embeds, negative_embeds = stage_1.encode_prompt(prompt)
+
+# stage 1
+image = stage_1(
+    prompt_embeds=prompt_embeds, negative_prompt_embeds=negative_embeds, generator=generator, output_type="pt"
+).images
+pt_to_pil(image)[0].save("./if_stage_I.png")
+
+# stage 2
+image = stage_2(
+    image=image,
+    prompt_embeds=prompt_embeds,
+    negative_prompt_embeds=negative_embeds,
+    generator=generator,
+    output_type="pt",
+).images
+pt_to_pil(image)[0].save("./if_stage_II.png")
+
+# stage 3
+image = stage_3(prompt=prompt, image=image, noise_level=100, generator=generator).images
+image[0].save("./if_stage_III.png")
+```
+
+### Text Guided Image-to-Image Generation
+
+The same IF model weights can be used for text-guided image-to-image translation or image variation.
+In this case just make sure to load the weights using the [`IFInpaintingPipeline`] and [`IFInpaintingSuperResolutionPipeline`] pipelines.
+
+**Note**: You can also directly move the weights of the text-to-image pipelines to the image-to-image pipelines
+without loading them twice by making use of the [`~DiffusionPipeline.components()`] function as explained [here](#converting-between-different-pipelines).
+
+```python
+from diffusers import IFImg2ImgPipeline, IFImg2ImgSuperResolutionPipeline, DiffusionPipeline
+from diffusers.utils import pt_to_pil
+
+import torch
+
+from PIL import Image
+import requests
+from io import BytesIO
+
+# download image
+url = "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg"
+response = requests.get(url)
+original_image = Image.open(BytesIO(response.content)).convert("RGB")
+original_image = original_image.resize((768, 512))
+
+# stage 1
+stage_1 = IFImg2ImgPipeline.from_pretrained("DeepFloyd/IF-I-XL-v1.0", variant="fp16", torch_dtype=torch.float16)
+stage_1.enable_model_cpu_offload()
+
+# stage 2
+stage_2 = IFImg2ImgSuperResolutionPipeline.from_pretrained(
+    "DeepFloyd/IF-II-L-v1.0", text_encoder=None, variant="fp16", torch_dtype=torch.float16
+)
+stage_2.enable_model_cpu_offload()
+
+# stage 3
+safety_modules = {
+    "feature_extractor": stage_1.feature_extractor,
+    "safety_checker": stage_1.safety_checker,
+    "watermarker": stage_1.watermarker,
+}
+stage_3 = DiffusionPipeline.from_pretrained(
+    "stabilityai/stable-diffusion-x4-upscaler", **safety_modules, torch_dtype=torch.float16
+)
+stage_3.enable_model_cpu_offload()
+
+prompt = "A fantasy landscape in style minecraft"
+generator = torch.manual_seed(1)
+
+# text embeds
+prompt_embeds, negative_embeds = stage_1.encode_prompt(prompt)
+
+# stage 1
+image = stage_1(
+    image=original_image,
+    prompt_embeds=prompt_embeds,
+    negative_prompt_embeds=negative_embeds,
+    generator=generator,
+    output_type="pt",
+).images
+pt_to_pil(image)[0].save("./if_stage_I.png")
+
+# stage 2
+image = stage_2(
+    image=image,
+    original_image=original_image,
+    prompt_embeds=prompt_embeds,
+    negative_prompt_embeds=negative_embeds,
+    generator=generator,
+    output_type="pt",
+).images
+pt_to_pil(image)[0].save("./if_stage_II.png")
+
+# stage 3
+image = stage_3(prompt=prompt, image=image, generator=generator, noise_level=100).images
+image[0].save("./if_stage_III.png")
+```
+
+### Text Guided Inpainting Generation
+
+The same IF model weights can be used for text-guided image-to-image translation or image variation.
+In this case just make sure to load the weights using the [`IFInpaintingPipeline`] and [`IFInpaintingSuperResolutionPipeline`] pipelines.
+
+**Note**: You can also directly move the weights of the text-to-image pipelines to the image-to-image pipelines
+without loading them twice by making use of the [`~DiffusionPipeline.components()`] function as explained [here](#converting-between-different-pipelines).
+
+```python
+from diffusers import IFInpaintingPipeline, IFInpaintingSuperResolutionPipeline, DiffusionPipeline
+from diffusers.utils import pt_to_pil
+import torch
+
+from PIL import Image
+import requests
+from io import BytesIO
+
+# download image
+url = "https://huggingface.co/datasets/diffusers/docs-images/resolve/main/if/person.png"
+response = requests.get(url)
+original_image = Image.open(BytesIO(response.content)).convert("RGB")
+original_image = original_image
+
+# download mask
+url = "https://huggingface.co/datasets/diffusers/docs-images/resolve/main/if/glasses_mask.png"
+response = requests.get(url)
+mask_image = Image.open(BytesIO(response.content))
+mask_image = mask_image
+
+# stage 1
+stage_1 = IFInpaintingPipeline.from_pretrained("DeepFloyd/IF-I-XL-v1.0", variant="fp16", torch_dtype=torch.float16)
+stage_1.enable_model_cpu_offload()
+
+# stage 2
+stage_2 = IFInpaintingSuperResolutionPipeline.from_pretrained(
+    "DeepFloyd/IF-II-L-v1.0", text_encoder=None, variant="fp16", torch_dtype=torch.float16
+)
+stage_2.enable_model_cpu_offload()
+
+# stage 3
+safety_modules = {
+    "feature_extractor": stage_1.feature_extractor,
+    "safety_checker": stage_1.safety_checker,
+    "watermarker": stage_1.watermarker,
+}
+stage_3 = DiffusionPipeline.from_pretrained(
+    "stabilityai/stable-diffusion-x4-upscaler", **safety_modules, torch_dtype=torch.float16
+)
+stage_3.enable_model_cpu_offload()
+
+prompt = "blue sunglasses"
+generator = torch.manual_seed(1)
+
+# text embeds
+prompt_embeds, negative_embeds = stage_1.encode_prompt(prompt)
+
+# stage 1
+image = stage_1(
+    image=original_image,
+    mask_image=mask_image,
+    prompt_embeds=prompt_embeds,
+    negative_prompt_embeds=negative_embeds,
+    generator=generator,
+    output_type="pt",
+).images
+pt_to_pil(image)[0].save("./if_stage_I.png")
+
+# stage 2
+image = stage_2(
+    image=image,
+    original_image=original_image,
+    mask_image=mask_image,
+    prompt_embeds=prompt_embeds,
+    negative_prompt_embeds=negative_embeds,
+    generator=generator,
+    output_type="pt",
+).images
+pt_to_pil(image)[0].save("./if_stage_II.png")
+
+# stage 3
+image = stage_3(prompt=prompt, image=image, generator=generator, noise_level=100).images
+image[0].save("./if_stage_III.png")
+```
+
+### Converting between different pipelines
+
+In addition to being loaded with `from_pretrained`, Pipelines can also be loaded directly from each other.
+
+```python
+from diffusers import IFPipeline, IFSuperResolutionPipeline
+
+pipe_1 = IFPipeline.from_pretrained("DeepFloyd/IF-I-XL-v1.0")
+pipe_2 = IFSuperResolutionPipeline.from_pretrained("DeepFloyd/IF-II-L-v1.0")
+
+
+from diffusers import IFImg2ImgPipeline, IFImg2ImgSuperResolutionPipeline
+
+pipe_1 = IFImg2ImgPipeline(**pipe_1.components)
+pipe_2 = IFImg2ImgSuperResolutionPipeline(**pipe_2.components)
+
+
+from diffusers import IFInpaintingPipeline, IFInpaintingSuperResolutionPipeline
+
+pipe_1 = IFInpaintingPipeline(**pipe_1.components)
+pipe_2 = IFInpaintingSuperResolutionPipeline(**pipe_2.components)
+```
+
+### Optimizing for speed
+
+The simplest optimization to run IF faster is to move all model components to the GPU.
+
+```py
+pipe = DiffusionPipeline.from_pretrained("DeepFloyd/IF-I-XL-v1.0", variant="fp16", torch_dtype=torch.float16)
+pipe.to("cuda")
+```
+
+You can also run the diffusion process for a shorter number of timesteps.
+
+This can either be done with the `num_inference_steps` argument
+
+```py
+pipe("<prompt>", num_inference_steps=30)
+```
+
+Or with the `timesteps` argument
+
+```py
+from diffusers.pipelines.deepfloyd_if import fast27_timesteps
+
+pipe("<prompt>", timesteps=fast27_timesteps)
+```
+
+When doing image variation or inpainting, you can also decrease the number of timesteps
+with the strength argument. The strength argument is the amount of noise to add to 
+the input image which also determines how many steps to run in the denoising process.
+A smaller number will vary the image less but run faster.
+
+```py
+pipe = IFImg2ImgPipeline.from_pretrained("DeepFloyd/IF-I-XL-v1.0", variant="fp16", torch_dtype=torch.float16)
+pipe.to("cuda")
+
+image = pipe(image=image, prompt="<prompt>", strength=0.3).images
+```
+
+You can also use [`torch.compile`](../../optimization/torch2.0). Note that we have not exhaustively tested `torch.compile`
+with IF and it might not give expected results.
+
+```py
+import torch
+
+pipe = DiffusionPipeline.from_pretrained("DeepFloyd/IF-I-XL-v1.0", variant="fp16", torch_dtype=torch.float16)
+pipe.to("cuda")
+
+pipe.text_encoder = torch.compile(pipe.text_encoder)
+pipe.unet = torch.compile(pipe.unet)
+```
+
+### Optimizing for memory
+
+When optimizing for GPU memory, we can use the standard diffusers cpu offloading APIs.
+
+Either the model based CPU offloading,
+
+```py
+pipe = DiffusionPipeline.from_pretrained("DeepFloyd/IF-I-XL-v1.0", variant="fp16", torch_dtype=torch.float16)
+pipe.enable_model_cpu_offload()
+```
+
+or the more aggressive layer based CPU offloading.
+
+```py
+pipe = DiffusionPipeline.from_pretrained("DeepFloyd/IF-I-XL-v1.0", variant="fp16", torch_dtype=torch.float16)
+pipe.enable_sequential_cpu_offload()
+```
+
+Additionally, T5 can be loaded in 8bit precision
+
+```py
+from transformers import T5EncoderModel
+
+text_encoder = T5EncoderModel.from_pretrained(
+    "DeepFloyd/IF-I-XL-v1.0", subfolder="text_encoder", device_map="auto", load_in_8bit=True, variant="8bit"
+)
+
+from diffusers import DiffusionPipeline
+
+pipe = DiffusionPipeline.from_pretrained(
+    "DeepFloyd/IF-I-XL-v1.0",
+    text_encoder=text_encoder,  # pass the previously instantiated 8bit text encoder
+    unet=None,
+    device_map="auto",
+)
+
+prompt_embeds, negative_embeds = pipe.encode_prompt("<prompt>")
+```
+
+For CPU RAM constrained machines like google colab free tier where we can't load all 
+model components to the CPU at once, we can manually only load the pipeline with
+the text encoder or unet when the respective model components are needed.
+
+```py
+from diffusers import IFPipeline, IFSuperResolutionPipeline
+import torch
+import gc
+from transformers import T5EncoderModel
+from diffusers.utils import pt_to_pil
+
+text_encoder = T5EncoderModel.from_pretrained(
+    "DeepFloyd/IF-I-XL-v1.0", subfolder="text_encoder", device_map="auto", load_in_8bit=True, variant="8bit"
+)
+
+# text to image
+
+pipe = DiffusionPipeline.from_pretrained(
+    "DeepFloyd/IF-I-XL-v1.0",
+    text_encoder=text_encoder,  # pass the previously instantiated 8bit text encoder
+    unet=None,
+    device_map="auto",
+)
+
+prompt = 'a photo of a kangaroo wearing an orange hoodie and blue sunglasses standing in front of the eiffel tower holding a sign that says "very deep learning"'
+prompt_embeds, negative_embeds = pipe.encode_prompt(prompt)
+
+# Remove the pipeline so we can re-load the pipeline with the unet
+del text_encoder
+del pipe
+gc.collect()
+torch.cuda.empty_cache()
+
+pipe = IFPipeline.from_pretrained(
+    "DeepFloyd/IF-I-XL-v1.0", text_encoder=None, variant="fp16", torch_dtype=torch.float16, device_map="auto"
+)
+
+generator = torch.Generator().manual_seed(0)
+image = pipe(
+    prompt_embeds=prompt_embeds,
+    negative_prompt_embeds=negative_embeds,
+    output_type="pt",
+    generator=generator,
+).images
+
+pt_to_pil(image)[0].save("./if_stage_I.png")
+
+# Remove the pipeline so we can load the super-resolution pipeline
+del pipe
+gc.collect()
+torch.cuda.empty_cache()
+
+# First super resolution
+
+pipe = IFSuperResolutionPipeline.from_pretrained(
+    "DeepFloyd/IF-II-L-v1.0", text_encoder=None, variant="fp16", torch_dtype=torch.float16, device_map="auto"
+)
+
+generator = torch.Generator().manual_seed(0)
+image = pipe(
+    image=image,
+    prompt_embeds=prompt_embeds,
+    negative_prompt_embeds=negative_embeds,
+    output_type="pt",
+    generator=generator,
+).images
+
+pt_to_pil(image)[0].save("./if_stage_II.png")
+```
+
+
+## Available Pipelines:
+
+| Pipeline | Tasks | Colab
+|---|---|:---:|
+| [pipeline_if.py](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/deepfloyd_if/pipeline_if.py) | *Text-to-Image Generation* | - |
+| [pipeline_if_superresolution.py](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/deepfloyd_if/pipeline_if.py) | *Text-to-Image Generation* | - |
+| [pipeline_if_img2img.py](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/deepfloyd_if/pipeline_if_img2img.py) | *Image-to-Image Generation* | - |
+| [pipeline_if_img2img_superresolution.py](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/deepfloyd_if/pipeline_if_img2img_superresolution.py) | *Image-to-Image Generation* | - |
+| [pipeline_if_inpainting.py](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/deepfloyd_if/pipeline_if_inpainting.py) | *Image-to-Image Generation* | - |
+| [pipeline_if_inpainting_superresolution.py](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/deepfloyd_if/pipeline_if_inpainting_superresolution.py) | *Image-to-Image Generation* | - |
+
+## IFPipeline
+[[autodoc]] IFPipeline
+	- all
+	- __call__
+
+## IFSuperResolutionPipeline
+[[autodoc]] IFSuperResolutionPipeline
+	- all
+	- __call__
+
+## IFImg2ImgPipeline
+[[autodoc]] IFImg2ImgPipeline
+	- all
+	- __call__
+
+## IFImg2ImgSuperResolutionPipeline
+[[autodoc]] IFImg2ImgSuperResolutionPipeline
+	- all
+	- __call__
+
+## IFInpaintingPipeline
+[[autodoc]] IFInpaintingPipeline
+	- all
+	- __call__
+
+## IFInpaintingSuperResolutionPipeline
+[[autodoc]] IFInpaintingSuperResolutionPipeline
+	- all
+	- __call__

docs/source/en/api/pipelines/overview.mdx

@@ -46,11 +46,14 @@ available a colab notebook to directly try them out.
 |---|---|:---:|:---:|
 | [alt_diffusion](./alt_diffusion) | [**AltDiffusion**](https://arxiv.org/abs/2211.06679) | Image-to-Image Text-Guided Generation | -
 | [audio_diffusion](./audio_diffusion) | [**Audio Diffusion**](https://github.com/teticio/audio_diffusion.git) | Unconditional Audio Generation |
-| [controlnet](./api/pipelines/stable_diffusion/controlnet) | [**ControlNet with Stable Diffusion**](https://arxiv.org/abs/2302.05543) | Image-to-Image Text-Guided Generation | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/controlnet.ipynb)
+| [controlnet](./api/pipelines/controlnet) | [**ControlNet with Stable Diffusion**](https://arxiv.org/abs/2302.05543) | Image-to-Image Text-Guided Generation | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/controlnet.ipynb)
 | [cycle_diffusion](./cycle_diffusion) | [**Cycle Diffusion**](https://arxiv.org/abs/2210.05559) | Image-to-Image Text-Guided Generation |
 | [dance_diffusion](./dance_diffusion) | [**Dance Diffusion**](https://github.com/williamberman/diffusers.git) | Unconditional Audio Generation |
 | [ddpm](./ddpm) | [**Denoising Diffusion Probabilistic Models**](https://arxiv.org/abs/2006.11239) | Unconditional Image Generation |
 | [ddim](./ddim) | [**Denoising Diffusion Implicit Models**](https://arxiv.org/abs/2010.02502) | Unconditional Image Generation |
+| [if](./if) | [**IF**](https://github.com/deep-floyd/IF) | Image Generation | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/deepfloyd_if_free_tier_google_colab.ipynb)
+| [if_img2img](./if) | [**IF**](https://github.com/deep-floyd/IF) | Image-to-Image Generation | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/deepfloyd_if_free_tier_google_colab.ipynb)
+| [if_inpainting](./if) | [**IF**](https://github.com/deep-floyd/IF) | Image-to-Image Generation | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/deepfloyd_if_free_tier_google_colab.ipynb)
 | [latent_diffusion](./latent_diffusion) | [**High-Resolution Image Synthesis with Latent Diffusion Models**](https://arxiv.org/abs/2112.10752)| Text-to-Image Generation | 
 | [latent_diffusion](./latent_diffusion) | [**High-Resolution Image Synthesis with Latent Diffusion Models**](https://arxiv.org/abs/2112.10752)| Super Resolution Image-to-Image | 
 | [latent_diffusion_uncond](./latent_diffusion_uncond) | [**High-Resolution Image Synthesis with Latent Diffusion Models**](https://arxiv.org/abs/2112.10752) | Unconditional Image Generation | 
@@ -83,6 +86,7 @@ available a colab notebook to directly try them out.
 | [versatile_diffusion](./versatile_diffusion) | [Versatile Diffusion: Text, Images and Variations All in One Diffusion Model](https://arxiv.org/abs/2211.08332) | Image Variations Generation | 
 | [versatile_diffusion](./versatile_diffusion) | [Versatile Diffusion: Text, Images and Variations All in One Diffusion Model](https://arxiv.org/abs/2211.08332) | Dual Image and Text Guided Generation | 
 | [vq_diffusion](./vq_diffusion) | [Vector Quantized Diffusion Model for Text-to-Image Synthesis](https://arxiv.org/abs/2111.14822) | Text-to-Image Generation | 
+| [text_to_video_zero](./text_to_video_zero) | [Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators](https://arxiv.org/abs/2303.13439) | Text-to-Video Generation |
 
 
 **Note**: Pipelines are simple examples of how to play around with the diffusion systems as described in the corresponding papers. 

docs/source/en/api/pipelines/repaint.mdx

@@ -60,7 +60,7 @@ pipe = pipe.to("cuda")
 
 generator = torch.Generator(device="cuda").manual_seed(0)
 output = pipe(
-    original_image=original_image,
+    image=original_image,
     mask_image=mask_image,
     num_inference_steps=250,
     eta=0.0,

docs/source/en/api/pipelines/semantic_stable_diffusion.mdx

@@ -24,11 +24,11 @@ The abstract of the paper is the following:
 
 | Pipeline | Tasks | Colab | Demo
 |---|---|:---:|:---:|
-| [pipeline_semantic_stable_diffusion.py](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/semantic_stable_diffusion/pipeline_semantic_stable_diffusion) | *Text-to-Image Generation* |  [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/ml-research/semantic-image-editing/blob/main/examples/SemanticGuidance.ipynb) | [Coming Soon](https://huggingface.co/AIML-TUDA)
+| [pipeline_semantic_stable_diffusion.py](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/semantic_stable_diffusion/pipeline_semantic_stable_diffusion.py) | *Text-to-Image Generation* |  [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/ml-research/semantic-image-editing/blob/main/examples/SemanticGuidance.ipynb) | [Coming Soon](https://huggingface.co/AIML-TUDA)
 
 ## Tips
 
-- The Semantic Guidance pipeline can be used with any [Stable Diffusion](./api/pipelines/stable_diffusion/text2img) checkpoint.
+- The Semantic Guidance pipeline can be used with any [Stable Diffusion](./stable_diffusion/text2img) checkpoint.
 
 ### Run Semantic Guidance
 
@@ -67,7 +67,7 @@ out = pipe(
 )
 ```
 
-For more examples check the colab notebook.
+For more examples check the Colab notebook.
 
 ## StableDiffusionSafePipelineOutput
 [[autodoc]] pipelines.semantic_stable_diffusion.SemanticStableDiffusionPipelineOutput

docs/source/en/api/pipelines/spectrogram_diffusion.mdx

@@ -30,7 +30,7 @@ As depicted above the model takes as input a MIDI file and tokenizes it into a s
 
 | Pipeline | Tasks | Colab
 |---|---|:---:|
-| [pipeline_spectrogram_diffusion.py](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/spectrogram_diffusion/pipeline_spectrogram_diffusion) | *Unconditional Audio Generation* | - |
+| [pipeline_spectrogram_diffusion.py](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/spectrogram_diffusion/pipeline_spectrogram_diffusion.py) | *Unconditional Audio Generation* | - |
 
 
 ## Example usage

docs/source/en/api/pipelines/stable_diffusion/depth2img.mdx

@@ -30,4 +30,7 @@ Available Checkpoints are:
 	- enable_attention_slicing
 	- disable_attention_slicing
 	- enable_xformers_memory_efficient_attention
-	- disable_xformers_memory_efficient_attention
+	- disable_xformers_memory_efficient_attention
+	- load_textual_inversion
+	- load_lora_weights
+	- save_lora_weights

docs/source/en/api/pipelines/stable_diffusion/diffedit.mdx

@@ -0,0 +1,360 @@
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# Zero-shot Diffusion-based Semantic Image Editing with Mask Guidance
+
+## Overview
+
+[DiffEdit: Diffusion-based semantic image editing with mask guidance](https://arxiv.org/abs/2210.11427) by Guillaume Couairon, Jakob Verbeek, Holger Schwenk, and Matthieu Cord.
+
+The abstract of the paper is the following:
+
+*Image generation has recently seen tremendous advances, with diffusion models allowing to synthesize convincing images for a large variety of text prompts. In this article, we propose DiffEdit, a method to take advantage of text-conditioned diffusion models for the task of semantic image editing, where the goal is to edit an image based on a text query. Semantic image editing is an extension of image generation, with the additional constraint that the generated image should be as similar as possible to a given input image. Current editing methods based on diffusion models usually require to provide a mask, making the task much easier by treating it as a conditional inpainting task. In contrast, our main contribution is able to automatically generate a mask highlighting regions of the input image that need to be edited, by contrasting predictions of a diffusion model conditioned on different text prompts. Moreover, we rely on latent inference to preserve content in those regions of interest and show excellent synergies with mask-based diffusion. DiffEdit achieves state-of-the-art editing performance on ImageNet. In addition, we evaluate semantic image editing in more challenging settings, using images from the COCO dataset as well as text-based generated images.*
+
+Resources:
+
+* [Paper](https://arxiv.org/abs/2210.11427).
+* [Blog Post with Demo](https://blog.problemsolversguild.com/technical/research/2022/11/02/DiffEdit-Implementation.html).
+* [Implementation on Github](https://github.com/Xiang-cd/DiffEdit-stable-diffusion/).
+
+## Tips 
+
+* The pipeline can generate masks that can be fed into other inpainting pipelines. Check out the code examples below to know more.
+* In order to generate an image using this pipeline, both an image mask (manually specified or generated using `generate_mask`)
+and a set of partially inverted latents (generated using `invert`) _must_ be provided as arguments when calling the pipeline to generate the final edited image.
+Refer to the code examples below for more details.
+* The function `generate_mask` exposes two prompt arguments, `source_prompt` and `target_prompt`,
+that let you control the locations of the semantic edits in the final image to be generated. Let's say,
+you wanted to translate from "cat" to "dog". In this case, the edit direction will be "cat -> dog". To reflect
+this in the generated mask, you simply have to set the embeddings related to the phrases including "cat" to
+`source_prompt_embeds` and "dog" to `target_prompt_embeds`. Refer to the code example below for more details.
+* When generating partially inverted latents using `invert`, assign a caption or text embedding describing the
+overall image to the `prompt` argument to help guide the inverse latent sampling process. In most cases, the
+source concept is sufficently descriptive to yield good results, but feel free to explore alternatives.
+Please refer to [this code example](#generating-image-captions-for-inversion) for more details.
+* When calling the pipeline to generate the final edited image, assign the source concept to `negative_prompt`
+and the target concept to `prompt`. Taking the above example, you simply have to set the embeddings related to
+the phrases including "cat" to `negative_prompt_embeds` and "dog" to `prompt_embeds`. Refer to the code example
+below for more details.
+* If you wanted to reverse the direction in the example above, i.e., "dog -> cat", then it's recommended to:
+    * Swap the `source_prompt` and `target_prompt` in the arguments to `generate_mask`.
+    * Change the input prompt for `invert` to include "dog".
+    * Swap the `prompt` and `negative_prompt` in the arguments to call the pipeline to generate the final edited image.
+* Note that the source and target prompts, or their corresponding embeddings, can also be automatically generated. Please, refer to [this discussion](#generating-source-and-target-embeddings) for more details.
+
+## Available Pipelines:
+
+| Pipeline | Tasks
+|---|---|
+| [StableDiffusionDiffEditPipeline](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_diffedit.py) | *Text-Based Image Editing*
+
+<!-- TODO: add Colab -->
+
+## Usage example
+
+### Based on an input image with a caption
+
+When the pipeline is conditioned on an input image, we first obtain partially inverted latents from the input image using a
+`DDIMInverseScheduler` with the help of a caption. Then we generate an editing mask to identify relevant regions in the image using the source and target prompts. Finally, 
+the inverted noise and generated mask is used to start the generation process. 
+
+First, let's load our pipeline: 
+
+```py
+import torch
+from diffusers import DDIMScheduler, DDIMInverseScheduler, StableDiffusionPix2PixZeroPipeline
+
+sd_model_ckpt = "stabilityai/stable-diffusion-2-1"
+pipeline = StableDiffusionDiffEditPipeline.from_pretrained(
+    sd_model_ckpt,
+    torch_dtype=torch.float16,
+    safety_checker=None,
+)
+pipeline.scheduler = DDIMScheduler.from_config(pipeline.scheduler.config)
+pipeline.inverse_scheduler = DDIMInverseScheduler.from_config(pipeline.scheduler.config)
+pipeline.enable_model_cpu_offload()
+pipeline.enable_vae_slicing()
+generator = torch.manual_seed(0)
+```
+
+Then, we load an input image to edit using our method: 
+
+```py
+from diffusers.utils import load_image
+
+img_url = "https://github.com/Xiang-cd/DiffEdit-stable-diffusion/raw/main/assets/origin.png"
+raw_image = load_image(img_url).convert("RGB").resize((768, 768))
+```
+
+Then, we employ the source and target prompts to generate the editing mask:
+
+```py
+# See the "Generating source and target embeddings" section below to
+# automate the generation of these captions with a pre-trained model like Flan-T5 as explained below.
+
+source_prompt = "a bowl of fruits"
+target_prompt = "a basket of fruits"
+mask_image = pipeline.generate_mask(
+    image=raw_image,
+    source_prompt=source_prompt,
+    target_prompt=target_prompt,
+    generator=generator,
+)
+```
+
+Then, we employ the caption and the input image to get the inverted latents: 
+
+```py 
+inv_latents = pipeline.invert(prompt=source_prompt, image=raw_image, generator=generator).latents
+```
+
+Now, generate the image with the inverted latents and semantically generated mask: 
+
+```py
+image = pipeline(
+    prompt=target_prompt,
+    mask_image=mask_image,
+    image_latents=inv_latents,
+    generator=generator,
+    negative_prompt=source_prompt,
+).images[0]
+image.save("edited_image.png")
+```
+
+## Generating image captions for inversion
+
+The authors originally used the source concept prompt as the caption for generating the partially inverted latents. However, we can also leverage open source and public image captioning models for the same purpose.
+Below, we provide an end-to-end example with the [BLIP](https://huggingface.co/docs/transformers/model_doc/blip) model
+for generating captions.
+
+First, let's load our automatic image captioning model:
+
+```py
+import torch
+from transformers import BlipForConditionalGeneration, BlipProcessor
+
+captioner_id = "Salesforce/blip-image-captioning-base"
+processor = BlipProcessor.from_pretrained(captioner_id)
+model = BlipForConditionalGeneration.from_pretrained(captioner_id, torch_dtype=torch.float16, low_cpu_mem_usage=True)
+```
+
+Then, we define a utility to generate captions from an input image using the model:
+
+```py
+@torch.no_grad()
+def generate_caption(images, caption_generator, caption_processor):
+    text = "a photograph of"
+
+    inputs = caption_processor(images, text, return_tensors="pt").to(device="cuda", dtype=caption_generator.dtype)
+    caption_generator.to("cuda")
+    outputs = caption_generator.generate(**inputs, max_new_tokens=128)
+
+    # offload caption generator
+    caption_generator.to("cpu")
+
+    caption = caption_processor.batch_decode(outputs, skip_special_tokens=True)[0]
+    return caption
+```
+
+Then, we load an input image for conditioning and obtain a suitable caption for it: 
+
+```py
+from diffusers.utils import load_image
+
+img_url = "https://github.com/Xiang-cd/DiffEdit-stable-diffusion/raw/main/assets/origin.png"
+raw_image = load_image(img_url).convert("RGB").resize((768, 768))
+caption = generate_caption(raw_image, model, processor)
+```
+
+Then, we employ the generated caption and the input image to get the inverted latents: 
+
+```py
+from diffusers import DDIMInverseScheduler, DDIMScheduler
+
+pipeline = StableDiffusionDiffEditPipeline.from_pretrained(
+    "stabilityai/stable-diffusion-2-1", torch_dtype=torch.float16
+)
+pipeline = pipeline.to("cuda")
+pipeline.enable_model_cpu_offload()
+pipeline.enable_vae_slicing()
+
+pipeline.scheduler = DDIMScheduler.from_config(pipeline.scheduler.config)
+pipeline.inverse_scheduler = DDIMInverseScheduler.from_config(pipeline.scheduler.config)
+
+generator = torch.manual_seed(0)
+inv_latents = pipeline.invert(prompt=caption, image=raw_image, generator=generator).latents
+```
+
+Now, generate the image with the inverted latents and semantically generated mask from our source and target prompts: 
+
+```py
+source_prompt = "a bowl of fruits"
+target_prompt = "a basket of fruits"
+
+mask_image = pipeline.generate_mask(
+    image=raw_image,
+    source_prompt=source_prompt,
+    target_prompt=target_prompt,
+    generator=generator,
+)
+
+image = pipeline(
+    prompt=target_prompt,
+    mask_image=mask_image,
+    image_latents=inv_latents,
+    generator=generator,
+    negative_prompt=source_prompt,
+).images[0]
+image.save("edited_image.png")
+```
+
+## Generating source and target embeddings 
+
+The authors originally required the user to manually provide the source and target prompts for discovering
+edit directions. However, we can also leverage open source and public models for the same purpose.
+Below, we provide an end-to-end example with the [Flan-T5](https://huggingface.co/docs/transformers/model_doc/flan-t5) model
+for generating source an target embeddings.
+
+**1. Load the generation model**:
+
+```py
+import torch
+from transformers import AutoTokenizer, T5ForConditionalGeneration
+
+tokenizer = AutoTokenizer.from_pretrained("google/flan-t5-xl")
+model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-xl", device_map="auto", torch_dtype=torch.float16)
+```
+
+**2. Construct a starting prompt**: 
+
+```py
+source_concept = "bowl"
+target_concept = "basket"
+
+source_text = f"Provide a caption for images containing a {source_concept}. "
+"The captions should be in English and should be no longer than 150 characters."
+
+target_text = f"Provide a caption for images containing a {target_concept}. "
+"The captions should be in English and should be no longer than 150 characters."
+```
+
+Here, we're interested in the "bowl -> basket" direction. 
+
+**3. Generate prompts**:
+
+We can use a utility like so for this purpose. 
+
+```py
+@torch.no_grad
+def generate_prompts(input_prompt):
+    input_ids = tokenizer(input_prompt, return_tensors="pt").input_ids.to("cuda")
+
+    outputs = model.generate(
+        input_ids, temperature=0.8, num_return_sequences=16, do_sample=True, max_new_tokens=128, top_k=10
+    )
+    return tokenizer.batch_decode(outputs, skip_special_tokens=True)
+```
+
+And then we just call it to generate our prompts:
+
+```py
+source_prompts = generate_prompts(source_text)
+target_prompts = generate_prompts(target_text)
+```
+
+We encourage you to play around with the different parameters supported by the
+`generate()` method ([documentation](https://huggingface.co/docs/transformers/main/en/main_classes/text_generation#transformers.generation_tf_utils.TFGenerationMixin.generate)) for the generation quality you are looking for.
+
+**4. Load the embedding model**: 
+
+Here, we need to use the same text encoder model used by the subsequent Stable Diffusion model.
+
+```py 
+from diffusers import StableDiffusionDiffEditPipeline 
+
+pipeline = StableDiffusionDiffEditPipeline.from_pretrained(
+    "stabilityai/stable-diffusion-2-1", torch_dtype=torch.float16
+)
+pipeline = pipeline.to("cuda")
+pipeline.enable_model_cpu_offload()
+pipeline.enable_vae_slicing()
+
+generator = torch.manual_seed(0)
+```
+
+**5. Compute embeddings**:
+
+```py 
+import torch 
+
+@torch.no_grad()
+def embed_prompts(sentences, tokenizer, text_encoder, device="cuda"):
+    embeddings = []
+    for sent in sentences:
+        text_inputs = tokenizer(
+            sent,
+            padding="max_length",
+            max_length=tokenizer.model_max_length,
+            truncation=True,
+            return_tensors="pt",
+        )
+        text_input_ids = text_inputs.input_ids
+        prompt_embeds = text_encoder(text_input_ids.to(device), attention_mask=None)[0]
+        embeddings.append(prompt_embeds)
+    return torch.concatenate(embeddings, dim=0).mean(dim=0).unsqueeze(0)
+
+source_embeddings = embed_prompts(source_prompts, pipeline.tokenizer, pipeline.text_encoder)
+target_embeddings = embed_prompts(target_captions, pipeline.tokenizer, pipeline.text_encoder)
+```
+
+And you're done! Now, you can use these embeddings directly while calling the pipeline: 
+
+```py
+from diffusers import DDIMInverseScheduler, DDIMScheduler
+from diffusers.utils import load_image
+
+pipeline.scheduler = DDIMScheduler.from_config(pipeline.scheduler.config)
+pipeline.inverse_scheduler = DDIMInverseScheduler.from_config(pipeline.scheduler.config)
+
+img_url = "https://github.com/Xiang-cd/DiffEdit-stable-diffusion/raw/main/assets/origin.png"
+raw_image = load_image(img_url).convert("RGB").resize((768, 768))
+
+
+mask_image = pipeline.generate_mask(
+    image=raw_image,
+    source_prompt_embeds=source_embeds,
+    target_prompt_embeds=target_embeds,
+    generator=generator,
+)
+
+inv_latents = pipeline.invert(
+    prompt_embeds=source_embeds,
+    image=raw_image,
+    generator=generator,
+).latents
+
+images = pipeline(
+    mask_image=mask_image,
+    image_latents=inv_latents,
+    prompt_embeds=target_embeddings,
+    negative_prompt_embeds=source_embeddings,
+    generator=generator,
+).images
+images[0].save("edited_image.png")
+```
+
+## StableDiffusionDiffEditPipeline
+[[autodoc]] StableDiffusionDiffEditPipeline
+    - all
+    - generate_mask
+    - invert
+	- __call__

docs/source/en/api/pipelines/stable_diffusion/image_variation.mdx

@@ -14,7 +14,7 @@ specific language governing permissions and limitations under the License.
 
 ## StableDiffusionImageVariationPipeline
 
-[`StableDiffusionImageVariationPipeline`] lets you generate variations from an input image using Stable Diffusion. It uses a fine-tuned version of Stable Diffusion model, trained by  [Justin Pinkney](https://www.justinpinkney.com/) (@Buntworthy) at [Lambda](https://lambdalabs.com/)
+[`StableDiffusionImageVariationPipeline`] lets you generate variations from an input image using Stable Diffusion. It uses a fine-tuned version of Stable Diffusion model, trained by  [Justin Pinkney](https://www.justinpinkney.com/) (@Buntworthy) at [Lambda](https://lambdalabs.com/).
 
 The original codebase can be found here:
 [Stable Diffusion Image Variations](https://github.com/LambdaLabsML/lambda-diffusers#stable-diffusion-image-variations)
@@ -28,4 +28,4 @@ Available Checkpoints are:
 	- enable_attention_slicing
 	- disable_attention_slicing
 	- enable_xformers_memory_efficient_attention
-	- disable_xformers_memory_efficient_attention
+	- disable_xformers_memory_efficient_attention

docs/source/en/api/pipelines/stable_diffusion/img2img.mdx

@@ -30,7 +30,11 @@ proposed by Chenlin Meng, Yutong He, Yang Song, Jiaming Song, Jiajun Wu, Jun-Yan
 	- disable_attention_slicing
 	- enable_xformers_memory_efficient_attention
 	- disable_xformers_memory_efficient_attention
+	- load_textual_inversion
+	- from_ckpt
+	- load_lora_weights
+	- save_lora_weights
 
 [[autodoc]] FlaxStableDiffusionImg2ImgPipeline
 	- all
-	- __call__
+	- __call__

docs/source/en/api/pipelines/stable_diffusion/inpaint.mdx

@@ -31,7 +31,10 @@ Available checkpoints are:
 	- disable_attention_slicing
 	- enable_xformers_memory_efficient_attention
 	- disable_xformers_memory_efficient_attention
+	- load_textual_inversion
+	- load_lora_weights
+	- save_lora_weights
 
 [[autodoc]] FlaxStableDiffusionInpaintPipeline
 	- all
-	- __call__
+	- __call__

docs/source/en/api/pipelines/stable_diffusion/overview.mdx

@@ -36,6 +36,7 @@ For more details about how Stable Diffusion works and how it differs from the ba
 | [StableDiffusionAttendAndExcitePipeline](./attend_and_excite) | **Experimental** – *Text-to-Image Generation * | | [Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models](https://huggingface.co/spaces/AttendAndExcite/Attend-and-Excite)
 | [StableDiffusionPix2PixZeroPipeline](./pix2pix_zero) | **Experimental** – *Text-Based Image Editing * | | [Zero-shot Image-to-Image Translation](https://arxiv.org/abs/2302.03027)
 | [StableDiffusionModelEditingPipeline](./model_editing) | **Experimental** – *Text-to-Image Model Editing * | | [Editing Implicit Assumptions in Text-to-Image Diffusion Models](https://arxiv.org/abs/2303.08084)
+| [StableDiffusionDiffEditPipeline](./diffedit) | **Experimental** – *Text-Based Image Editing * | | [DiffEdit: Diffusion-based semantic image editing with mask guidance](https://arxiv.org/abs/2210.11427)
 
 
 

docs/source/en/api/pipelines/stable_diffusion/pix2pix.mdx

@@ -68,3 +68,6 @@ images[0].save("snowy_mountains.png")
 [[autodoc]] StableDiffusionInstructPix2PixPipeline
 	- __call__
 	- all
+	- load_textual_inversion
+	- load_lora_weights
+	- save_lora_weights

docs/source/en/api/pipelines/stable_diffusion/self_attention_guidance.mdx

@@ -14,25 +14,26 @@ specific language governing permissions and limitations under the License.
 
 ## Overview
 
-[Self-Attention Guidance](https://arxiv.org/abs/2210.00939) by Susung Hong et al.
+[Improving Sample Quality of Diffusion Models Using Self-Attention Guidance](https://arxiv.org/abs/2210.00939) by Susung Hong et al.
 
 The abstract of the paper is the following:
 
-*Denoising diffusion models (DDMs) have been drawing much attention for their appreciable sample quality and diversity. Despite their remarkable performance, DDMs remain black boxes on which further study is necessary to take a profound step. Motivated by this, we delve into the design of conventional U-shaped diffusion models. More specifically, we investigate the self-attention modules within these models through carefully designed experiments and explore their characteristics. In addition, inspired by the studies that substantiate the effectiveness of the guidance schemes, we present plug-and-play diffusion guidance, namely Self-Attention Guidance (SAG), that can drastically boost the performance of existing diffusion models. Our method, SAG, extracts the intermediate attention map from a diffusion model at every iteration and selects tokens above a certain attention score for masking and blurring to obtain a partially blurred input. Subsequently, we measure the dissimilarity between the predicted noises obtained from feeding the blurred and original input to the diffusion model and leverage it as guidance. With this guidance, we observe apparent improvements in a wide range of diffusion models, e.g., ADM, IDDPM, and Stable Diffusion, and show that the results further improve by combining our method with the conventional guidance scheme. We provide extensive ablation studies to verify our choices.*
+*Denoising diffusion models (DDMs) have attracted attention for their exceptional generation quality and diversity. This success is largely attributed to the use of class- or text-conditional diffusion guidance methods, such as classifier and classifier-free guidance. In this paper, we present a more comprehensive perspective that goes beyond the traditional guidance methods. From this generalized perspective, we introduce novel condition- and training-free strategies to enhance the quality of generated images. As a simple solution, blur guidance improves the suitability of intermediate samples for their fine-scale information and structures, enabling diffusion models to generate higher quality samples with a moderate guidance scale. Improving upon this, Self-Attention Guidance (SAG) uses the intermediate self-attention maps of diffusion models to enhance their stability and efficacy. Specifically, SAG adversarially blurs only the regions that diffusion models attend to at each iteration and guides them accordingly. Our experimental results show that our SAG improves the performance of various diffusion models, including ADM, IDDPM, Stable Diffusion, and DiT. Moreover, combining SAG with conventional guidance methods leads to further improvement.*
 
 Resources:
 
 * [Project Page](https://ku-cvlab.github.io/Self-Attention-Guidance).
 * [Paper](https://arxiv.org/abs/2210.00939).
 * [Original Code](https://github.com/KU-CVLAB/Self-Attention-Guidance).
-* [Demo](https://colab.research.google.com/github/SusungHong/Self-Attention-Guidance/blob/main/SAG_Stable.ipynb).
+* [Hugging Face Demo](https://huggingface.co/spaces/susunghong/Self-Attention-Guidance).
+* [Colab Demo](https://colab.research.google.com/github/SusungHong/Self-Attention-Guidance/blob/main/SAG_Stable.ipynb).
 
 
 ## Available Pipelines:
 
 | Pipeline | Tasks | Demo
 |---|---|:---:|
-| [StableDiffusionSAGPipeline](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_sag.py) | *Text-to-Image Generation* | [Colab](https://colab.research.google.com/github/SusungHong/Self-Attention-Guidance/blob/main/SAG_Stable.ipynb) |
+| [StableDiffusionSAGPipeline](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_sag.py) | *Text-to-Image Generation* | [🤗 Space](https://huggingface.co/spaces/susunghong/Self-Attention-Guidance) |
 
 ## Usage example
 

docs/source/en/api/pipelines/stable_diffusion/text2img.mdx

@@ -39,6 +39,10 @@ Available Checkpoints are:
 	- disable_xformers_memory_efficient_attention
 	- enable_vae_tiling
 	- disable_vae_tiling
+	- load_textual_inversion
+	- from_ckpt
+	- load_lora_weights
+	- save_lora_weights
 
 [[autodoc]] FlaxStableDiffusionPipeline
 	- all

docs/source/en/api/pipelines/stable_diffusion_safe.mdx

@@ -28,11 +28,11 @@ The abstract of the paper is the following:
 
 ## Tips
 
-- Safe Stable Diffusion may also be used with weights of [Stable Diffusion](./api/pipelines/stable_diffusion/text2img).
+- Safe Stable Diffusion may also be used with weights of [Stable Diffusion](./stable_diffusion/text2img).
 
 ### Run Safe Stable Diffusion
 
-Safe Stable Diffusion can be tested very easily with the [`StableDiffusionPipelineSafe`], and the `"AIML-TUDA/stable-diffusion-safe"` checkpoint exactly in the same way it is shown in the [Conditional Image Generation Guide](./using-diffusers/conditional_image_generation).
+Safe Stable Diffusion can be tested very easily with the [`StableDiffusionPipelineSafe`], and the `"AIML-TUDA/stable-diffusion-safe"` checkpoint exactly in the same way it is shown in the [Conditional Image Generation Guide](../../using-diffusers/conditional_image_generation).
 
 ### Interacting with the Safety Concept
 

docs/source/en/api/pipelines/stable_unclip.mdx

@@ -32,12 +32,50 @@ we do not add any additional noise to the image embeddings i.e. `noise_level = 0
 	* [stabilityai/stable-diffusion-2-1-unclip](https://hf.co/stabilityai/stable-diffusion-2-1-unclip)
 	* [stabilityai/stable-diffusion-2-1-unclip-small](https://hf.co/stabilityai/stable-diffusion-2-1-unclip-small)
 * Text-to-image 
-	* Coming soon!
+	* [stabilityai/stable-diffusion-2-1-unclip-small](https://hf.co/stabilityai/stable-diffusion-2-1-unclip-small)
 
 ### Text-to-Image Generation
+Stable unCLIP can be leveraged for text-to-image generation by pipelining it with the prior model of KakaoBrain's open source DALL-E 2 replication [Karlo](https://huggingface.co/kakaobrain/karlo-v1-alpha)
 
-Coming soon!
+```python
+import torch
+from diffusers import UnCLIPScheduler, DDPMScheduler, StableUnCLIPPipeline
+from diffusers.models import PriorTransformer
+from transformers import CLIPTokenizer, CLIPTextModelWithProjection
 
+prior_model_id = "kakaobrain/karlo-v1-alpha"
+data_type = torch.float16
+prior = PriorTransformer.from_pretrained(prior_model_id, subfolder="prior", torch_dtype=data_type)
+
+prior_text_model_id = "openai/clip-vit-large-patch14"
+prior_tokenizer = CLIPTokenizer.from_pretrained(prior_text_model_id)
+prior_text_model = CLIPTextModelWithProjection.from_pretrained(prior_text_model_id, torch_dtype=data_type)
+prior_scheduler = UnCLIPScheduler.from_pretrained(prior_model_id, subfolder="prior_scheduler")
+prior_scheduler = DDPMScheduler.from_config(prior_scheduler.config)
+
+stable_unclip_model_id = "stabilityai/stable-diffusion-2-1-unclip-small"
+
+pipe = StableUnCLIPPipeline.from_pretrained(
+    stable_unclip_model_id,
+    torch_dtype=data_type,
+    variant="fp16",
+    prior_tokenizer=prior_tokenizer,
+    prior_text_encoder=prior_text_model,
+    prior=prior,
+    prior_scheduler=prior_scheduler,
+)
+
+pipe = pipe.to("cuda")
+wave_prompt = "dramatic wave, the Oceans roar, Strong wave spiral across the oceans as the waves unfurl into roaring crests; perfect wave form; perfect wave shape; dramatic wave shape; wave shape unbelievable; wave; wave shape spectacular"
+
+images = pipe(prompt=wave_prompt).images
+images[0].save("waves.png")
+```
+<Tip warning={true}>
+
+For text-to-image we use `stabilityai/stable-diffusion-2-1-unclip-small` as it was trained on CLIP ViT-L/14 embedding, the same as the Karlo model prior. [stabilityai/stable-diffusion-2-1-unclip](https://hf.co/stabilityai/stable-diffusion-2-1-unclip) was trained on OpenCLIP ViT-H, so we don't recommend its use. 
+
+</Tip>
 
 ### Text guided Image-to-Image Variation
 

docs/source/en/api/pipelines/text_to_video_zero.mdx

@@ -0,0 +1,240 @@
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# Zero-Shot Text-to-Video Generation 
+
+## Overview
+
+
+[Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators](https://arxiv.org/abs/2303.13439) by
+Levon Khachatryan,
+Andranik Movsisyan,
+Vahram Tadevosyan,
+Roberto Henschel,
+[Zhangyang Wang](https://www.ece.utexas.edu/people/faculty/atlas-wang), Shant Navasardyan, [Humphrey Shi](https://www.humphreyshi.com).
+
+Our method Text2Video-Zero enables zero-shot video generation using either
+1. A textual prompt, or
+2. A prompt combined with guidance from poses or edges, or 
+3. Video Instruct-Pix2Pix, i.e., instruction-guided video editing.
+
+Results are temporally consistent and follow closely the guidance and textual prompts.
+
+![teaser-img](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/t2v_zero_teaser.png)
+
+The abstract of the paper is the following:
+
+*Recent text-to-video generation approaches rely on computationally heavy training and require large-scale video datasets. In this paper, we introduce a new task of zero-shot text-to-video generation and propose a low-cost approach (without any training or optimization) by leveraging the power of existing text-to-image synthesis methods (e.g., Stable Diffusion), making them suitable for the video domain.
+Our key modifications include (i) enriching the latent codes of the generated frames with motion dynamics to keep the global scene and the background time consistent; and (ii) reprogramming frame-level self-attention using a new cross-frame attention of each frame on the first frame, to preserve the context, appearance, and identity of the foreground object.
+Experiments show that this leads to low overhead, yet high-quality and remarkably consistent video generation. Moreover, our approach is not limited to text-to-video synthesis but is also applicable to other tasks such as conditional and content-specialized video generation, and Video Instruct-Pix2Pix, i.e., instruction-guided video editing.
+As experiments show, our method performs comparably or sometimes better than recent approaches, despite not being trained on additional video data.*
+
+
+
+Resources:
+
+* [Project Page](https://text2video-zero.github.io/)
+* [Paper](https://arxiv.org/abs/2303.13439)
+* [Original Code](https://github.com/Picsart-AI-Research/Text2Video-Zero)
+
+
+## Available Pipelines:
+
+| Pipeline | Tasks | Demo
+|---|---|:---:|
+| [TextToVideoZeroPipeline](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/text_to_video_synthesis/pipeline_text_to_video_zero.py) | *Zero-shot Text-to-Video Generation* | [🤗 Space](https://huggingface.co/spaces/PAIR/Text2Video-Zero)
+
+
+## Usage example
+
+### Text-To-Video
+
+To generate a video from prompt, run the following python command
+```python
+import torch
+import imageio
+from diffusers import TextToVideoZeroPipeline
+
+model_id = "runwayml/stable-diffusion-v1-5"
+pipe = TextToVideoZeroPipeline.from_pretrained(model_id, torch_dtype=torch.float16).to("cuda")
+
+prompt = "A panda is playing guitar on times square"
+result = pipe(prompt=prompt).images
+result = [(r * 255).astype("uint8") for r in result]
+imageio.mimsave("video.mp4", result, fps=4)
+```
+You can change these parameters in the pipeline call:
+* Motion field strength (see the [paper](https://arxiv.org/abs/2303.13439), Sect. 3.3.1):
+    * `motion_field_strength_x` and `motion_field_strength_y`. Default: `motion_field_strength_x=12`, `motion_field_strength_y=12`
+* `T` and `T'` (see the [paper](https://arxiv.org/abs/2303.13439), Sect. 3.3.1)
+    * `t0` and `t1` in the range `{0, ..., num_inference_steps}`. Default: `t0=45`, `t1=48`
+* Video length:
+    * `video_length`, the number of frames video_length to be generated. Default: `video_length=8`
+
+
+### Text-To-Video with Pose Control
+To generate a video from prompt with additional pose control
+
+1. Download a demo video
+
+    ```python
+    from huggingface_hub import hf_hub_download
+
+    filename = "__assets__/poses_skeleton_gifs/dance1_corr.mp4"
+    repo_id = "PAIR/Text2Video-Zero"
+    video_path = hf_hub_download(repo_type="space", repo_id=repo_id, filename=filename)
+    ```
+
+
+2. Read video containing extracted pose images
+    ```python
+    from PIL import Image
+    import imageio
+
+    reader = imageio.get_reader(video_path, "ffmpeg")
+    frame_count = 8
+    pose_images = [Image.fromarray(reader.get_data(i)) for i in range(frame_count)]
+    ```
+    To extract pose from actual video, read [ControlNet documentation](./stable_diffusion/controlnet).
+
+3. Run `StableDiffusionControlNetPipeline` with our custom attention processor
+
+    ```python
+    import torch
+    from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
+    from diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_zero import CrossFrameAttnProcessor
+
+    model_id = "runwayml/stable-diffusion-v1-5"
+    controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-openpose", torch_dtype=torch.float16)
+    pipe = StableDiffusionControlNetPipeline.from_pretrained(
+        model_id, controlnet=controlnet, torch_dtype=torch.float16
+    ).to("cuda")
+
+    # Set the attention processor
+    pipe.unet.set_attn_processor(CrossFrameAttnProcessor(batch_size=2))
+    pipe.controlnet.set_attn_processor(CrossFrameAttnProcessor(batch_size=2))
+
+    # fix latents for all frames
+    latents = torch.randn((1, 4, 64, 64), device="cuda", dtype=torch.float16).repeat(len(pose_images), 1, 1, 1)
+
+    prompt = "Darth Vader dancing in a desert"
+    result = pipe(prompt=[prompt] * len(pose_images), image=pose_images, latents=latents).images
+    imageio.mimsave("video.mp4", result, fps=4)
+    ```
+
+
+### Text-To-Video with Edge Control
+
+To generate a video from prompt with additional pose control,
+follow the steps described above for pose-guided generation using [Canny edge ControlNet model](https://huggingface.co/lllyasviel/sd-controlnet-canny).
+
+
+### Video Instruct-Pix2Pix
+
+To perform text-guided video editing (with [InstructPix2Pix](./stable_diffusion/pix2pix)):
+
+1. Download a demo video
+
+    ```python
+    from huggingface_hub import hf_hub_download
+
+    filename = "__assets__/pix2pix video/camel.mp4"
+    repo_id = "PAIR/Text2Video-Zero"
+    video_path = hf_hub_download(repo_type="space", repo_id=repo_id, filename=filename)
+    ```
+
+2. Read video from path
+    ```python
+    from PIL import Image
+    import imageio
+
+    reader = imageio.get_reader(video_path, "ffmpeg")
+    frame_count = 8
+    video = [Image.fromarray(reader.get_data(i)) for i in range(frame_count)]
+    ```
+
+3. Run `StableDiffusionInstructPix2PixPipeline` with our custom attention processor
+    ```python
+    import torch
+    from diffusers import StableDiffusionInstructPix2PixPipeline
+    from diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_zero import CrossFrameAttnProcessor
+
+    model_id = "timbrooks/instruct-pix2pix"
+    pipe = StableDiffusionInstructPix2PixPipeline.from_pretrained(model_id, torch_dtype=torch.float16).to("cuda")
+    pipe.unet.set_attn_processor(CrossFrameAttnProcessor(batch_size=3))
+
+    prompt = "make it Van Gogh Starry Night style"
+    result = pipe(prompt=[prompt] * len(video), image=video).images
+    imageio.mimsave("edited_video.mp4", result, fps=4)
+    ```
+
+
+### DreamBooth specialization 
+
+Methods **Text-To-Video**, **Text-To-Video with Pose Control** and **Text-To-Video with Edge Control**
+can run with custom [DreamBooth](../training/dreambooth) models, as shown below for
+[Canny edge ControlNet model](https://huggingface.co/lllyasviel/sd-controlnet-canny) and
+[Avatar style DreamBooth](https://huggingface.co/PAIR/text2video-zero-controlnet-canny-avatar) model
+
+1. Download a demo video
+
+    ```python
+    from huggingface_hub import hf_hub_download
+
+    filename = "__assets__/canny_videos_mp4/girl_turning.mp4"
+    repo_id = "PAIR/Text2Video-Zero"
+    video_path = hf_hub_download(repo_type="space", repo_id=repo_id, filename=filename)
+    ```
+
+2. Read video from path
+    ```python
+    from PIL import Image
+    import imageio
+
+    reader = imageio.get_reader(video_path, "ffmpeg")
+    frame_count = 8
+    video = [Image.fromarray(reader.get_data(i)) for i in range(frame_count)]
+    ```
+
+3. Run `StableDiffusionControlNetPipeline` with custom trained DreamBooth model
+    ```python
+    import torch
+    from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
+    from diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_zero import CrossFrameAttnProcessor
+
+    # set model id to custom model
+    model_id = "PAIR/text2video-zero-controlnet-canny-avatar"
+    controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", torch_dtype=torch.float16)
+    pipe = StableDiffusionControlNetPipeline.from_pretrained(
+        model_id, controlnet=controlnet, torch_dtype=torch.float16
+    ).to("cuda")
+
+    # Set the attention processor
+    pipe.unet.set_attn_processor(CrossFrameAttnProcessor(batch_size=2))
+    pipe.controlnet.set_attn_processor(CrossFrameAttnProcessor(batch_size=2))
+
+    # fix latents for all frames
+    latents = torch.randn((1, 4, 64, 64), device="cuda", dtype=torch.float16).repeat(len(pose_images), 1, 1, 1)
+
+    prompt = "oil painting of a beautiful girl avatar style"
+    result = pipe(prompt=[prompt] * len(pose_images), image=pose_images, latents=latents).images
+    imageio.mimsave("video.mp4", result, fps=4)
+    ```
+
+You can filter out some available DreamBooth-trained models with [this link](https://huggingface.co/models?search=dreambooth).
+
+
+
+## TextToVideoZeroPipeline
+[[autodoc]] TextToVideoZeroPipeline
+	- all
+	- __call__

docs/source/en/api/pipelines/versatile_diffusion.mdx

@@ -20,7 +20,7 @@ The abstract of the paper is the following:
 
 ## Tips
 
-- VersatileDiffusion is conceptually very similar as [Stable Diffusion](./api/pipelines/stable_diffusion/overview),  but instead of providing just a image data stream conditioned on text, VersatileDiffusion provides both a image and text data stream and can be conditioned on both text and image.
+- VersatileDiffusion is conceptually very similar as [Stable Diffusion](./stable_diffusion/overview),  but instead of providing just a image data stream conditioned on text, VersatileDiffusion provides both a image and text data stream and can be conditioned on both text and image.
 
 ### *Run VersatileDiffusion*
 

docs/source/en/api/schedulers/ddim.mdx

@@ -10,7 +10,7 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
 specific language governing permissions and limitations under the License.
 -->
 
-# Denoising diffusion implicit models (DDIM)
+# Denoising Diffusion Implicit Models (DDIM)
 
 ## Overview
 
@@ -24,4 +24,4 @@ The original codebase of this paper can be found here: [ermongroup/ddim](https:/
 For questions, feel free to contact the author on [tsong.me](https://tsong.me/).
 
 ## DDIMScheduler
-[[autodoc]] DDIMScheduler
+[[autodoc]] DDIMScheduler

docs/source/en/api/schedulers/ddpm.mdx

@@ -10,7 +10,7 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
 specific language governing permissions and limitations under the License.
 -->
 
-# Denoising diffusion probabilistic models (DDPM)
+# Denoising Diffusion Probabilistic Models (DDPM)
 
 ## Overview
 
@@ -24,4 +24,4 @@ We present high quality image synthesis results using diffusion probabilistic mo
 The original paper can be found [here](https://arxiv.org/abs/2010.02502).
 
 ## DDPMScheduler
-[[autodoc]] DDPMScheduler
+[[autodoc]] DDPMScheduler

docs/source/en/api/schedulers/dpm_sde.mdx

@@ -0,0 +1,23 @@
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# DPM Stochastic Scheduler inspired by Karras et. al paper
+
+## Overview
+
+Inspired by Stochastic Sampler from [Karras et. al](https://arxiv.org/abs/2206.00364).
+Scheduler ported from @crowsonkb's https://github.com/crowsonkb/k-diffusion library:
+
+All credit for making this scheduler work goes to [Katherine Crowson](https://github.com/crowsonkb/)
+
+## DPMSolverSDEScheduler
+[[autodoc]] DPMSolverSDEScheduler

docs/source/en/api/schedulers/euler_ancestral.mdx

@@ -14,8 +14,8 @@ specific language governing permissions and limitations under the License.
 
 ## Overview
 
-Ancestral sampling with Euler method steps. Based on the original (k-diffusion)[https://github.com/crowsonkb/k-diffusion/blob/481677d114f6ea445aa009cf5bd7a9cdee909e47/k_diffusion/sampling.py#L72] implementation by Katherine Crowson.
+Ancestral sampling with Euler method steps. Based on the original [k-diffusion](https://github.com/crowsonkb/k-diffusion/blob/481677d114f6ea445aa009cf5bd7a9cdee909e47/k_diffusion/sampling.py#L72) implementation by Katherine Crowson.
 Fast scheduler which often times generates good outputs with 20-30 steps.
 
 ## EulerAncestralDiscreteScheduler
-[[autodoc]] EulerAncestralDiscreteScheduler
+[[autodoc]] EulerAncestralDiscreteScheduler

docs/source/en/api/schedulers/multistep_dpm_solver_inverse.mdx

@@ -0,0 +1,22 @@
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# Inverse Multistep DPM-Solver (DPMSolverMultistepInverse)
+
+## Overview
+
+This scheduler is the inverted scheduler of [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://arxiv.org/abs/2206.00927) and [DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models
+](https://arxiv.org/abs/2211.01095) by Cheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen, Chongxuan Li, and Jun Zhu.
+The implementation is mostly based on the DDIM inversion definition of [Null-text Inversion for Editing Real Images using Guided Diffusion Models](https://arxiv.org/pdf/2211.09794.pdf) and the ad-hoc notebook implementation for DiffEdit latent inversion [here](https://github.com/Xiang-cd/DiffEdit-stable-diffusion/blob/main/diffedit.ipynb).
+
+## DPMSolverMultistepInverseScheduler
+[[autodoc]] DPMSolverMultistepInverseScheduler

docs/source/en/api/schedulers/score_sde_ve.mdx

@@ -10,11 +10,11 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
 specific language governing permissions and limitations under the License.
 -->
 
-# variance exploding stochastic differential equation (VE-SDE) scheduler
+# Variance Exploding Stochastic Differential Equation (VE-SDE) scheduler
 
 ## Overview
 
 Original paper can be found [here](https://arxiv.org/abs/2011.13456).
 
 ## ScoreSdeVeScheduler
-[[autodoc]] ScoreSdeVeScheduler
+[[autodoc]] ScoreSdeVeScheduler

docs/source/en/api/schedulers/score_sde_vp.mdx

@@ -10,7 +10,7 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
 specific language governing permissions and limitations under the License.
 -->
 
-# Variance preserving stochastic differential equation (VP-SDE) scheduler
+# Variance Preserving Stochastic Differential Equation (VP-SDE) scheduler
 
 ## Overview
 
@@ -23,4 +23,4 @@ Score SDE-VP is under construction.
 </Tip>
 
 ## ScoreSdeVpScheduler
-[[autodoc]] schedulers.scheduling_sde_vp.ScoreSdeVpScheduler
+[[autodoc]] schedulers.scheduling_sde_vp.ScoreSdeVpScheduler

docs/source/en/api/schedulers/unipc.mdx

@@ -16,7 +16,7 @@ specific language governing permissions and limitations under the License.
 
 UniPC is a training-free framework designed for the fast sampling of diffusion models, which consists of a corrector (UniC) and a predictor (UniP) that share a unified analytical form and support arbitrary orders.
 
-For more details about the method, please refer to the [[paper]](https://arxiv.org/abs/2302.04867) and the [[code]](https://github.com/wl-zhao/UniPC).
+For more details about the method, please refer to the [paper](https://arxiv.org/abs/2302.04867) and the [code](https://github.com/wl-zhao/UniPC).
 
 Fast Sampling of Diffusion Models with Exponential Integrator.
 

docs/source/en/conceptual/contribution.mdx

@@ -170,7 +170,7 @@ please have a look at the next sections.
 
 For all of the following contributions, you will need to open a PR. It is explained in detail how to do so in the [Opening a pull requst](#how-to-open-a-pr) section.
 
-### 4. Fixing a "Good first issue"
+### 4. Fixing a `Good first issue`
 
 *Good first issues* are marked by the [Good first issue](https://github.com/huggingface/diffusers/issues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22) label. Usually, the issue already
 explains how a potential solution should look so that it is easier to fix.
@@ -275,7 +275,7 @@ Once an example script works, please make sure to add a comprehensive `README.md
 
 If you are contributing to the official training examples, please also make sure to add a test to [examples/test_examples.py](https://github.com/huggingface/diffusers/blob/main/examples/test_examples.py). This is not necessary for non-official training examples.
 
-### 8. Fixing a "Good second issue"
+### 8. Fixing a `Good second issue`
 
 *Good second issues* are marked by the [Good second issue](https://github.com/huggingface/diffusers/issues?q=is%3Aopen+is%3Aissue+label%3A%22Good+second+issue%22) label. Good second issues are
 usually more complicated to solve than [Good first issues](https://github.com/huggingface/diffusers/issues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22).

docs/source/en/index.mdx

@@ -53,11 +53,14 @@ The library has three main components:
 |---|---|:---:|
 | [alt_diffusion](./api/pipelines/alt_diffusion) | [AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities](https://arxiv.org/abs/2211.06679) | Image-to-Image Text-Guided Generation |
 | [audio_diffusion](./api/pipelines/audio_diffusion) | [Audio Diffusion](https://github.com/teticio/audio-diffusion.git) | Unconditional Audio Generation |
-| [controlnet](./api/pipelines/stable_diffusion/controlnet) | [Adding Conditional Control to Text-to-Image Diffusion Models](https://arxiv.org/abs/2302.05543) | Image-to-Image Text-Guided Generation |
+| [controlnet](./api/pipelines/controlnet) | [Adding Conditional Control to Text-to-Image Diffusion Models](https://arxiv.org/abs/2302.05543) | Image-to-Image Text-Guided Generation |
 | [cycle_diffusion](./api/pipelines/cycle_diffusion) | [Unifying Diffusion Models' Latent Space, with Applications to CycleDiffusion and Guidance](https://arxiv.org/abs/2210.05559) | Image-to-Image Text-Guided Generation |
 | [dance_diffusion](./api/pipelines/dance_diffusion) | [Dance Diffusion](https://github.com/williamberman/diffusers.git) | Unconditional Audio Generation |
 | [ddpm](./api/pipelines/ddpm) | [Denoising Diffusion Probabilistic Models](https://arxiv.org/abs/2006.11239) | Unconditional Image Generation |
 | [ddim](./api/pipelines/ddim) | [Denoising Diffusion Implicit Models](https://arxiv.org/abs/2010.02502) | Unconditional Image Generation |
+| [if](./if) | [**IF**](./api/pipelines/if) | Image Generation |
+| [if_img2img](./if) | [**IF**](./api/pipelines/if) | Image-to-Image Generation |
+| [if_inpainting](./if) | [**IF**](./api/pipelines/if) | Image-to-Image Generation |
 | [latent_diffusion](./api/pipelines/latent_diffusion) | [High-Resolution Image Synthesis with Latent Diffusion Models](https://arxiv.org/abs/2112.10752)| Text-to-Image Generation |
 | [latent_diffusion](./api/pipelines/latent_diffusion) | [High-Resolution Image Synthesis with Latent Diffusion Models](https://arxiv.org/abs/2112.10752)| Super Resolution Image-to-Image |
 | [latent_diffusion_uncond](./api/pipelines/latent_diffusion_uncond) | [High-Resolution Image Synthesis with Latent Diffusion Models](https://arxiv.org/abs/2112.10752) | Unconditional Image Generation |
@@ -73,7 +76,7 @@ The library has three main components:
 | [stable_diffusion_pix2pix](./api/pipelines/stable_diffusion/pix2pix) | [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://arxiv.org/abs/2211.09800)  | Text-Guided Image Editing|
 | [stable_diffusion_pix2pix_zero](./api/pipelines/stable_diffusion/pix2pix_zero) | [Zero-shot Image-to-Image Translation](https://pix2pixzero.github.io/) | Text-Guided Image Editing |
 | [stable_diffusion_attend_and_excite](./api/pipelines/stable_diffusion/attend_and_excite) | [Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models](https://arxiv.org/abs/2301.13826) | Text-to-Image Generation |
-| [stable_diffusion_self_attention_guidance](./api/pipelines/stable_diffusion/self_attention_guidance) | [Improving Sample Quality of Diffusion Models Using Self-Attention Guidance](https://arxiv.org/abs/2210.00939) | Text-to-Image Generation |
+| [stable_diffusion_self_attention_guidance](./api/pipelines/stable_diffusion/self_attention_guidance) | [Improving Sample Quality of Diffusion Models Using Self-Attention Guidance](https://arxiv.org/abs/2210.00939) | Text-to-Image Generation Unconditional Image Generation |
 | [stable_diffusion_image_variation](./stable_diffusion/image_variation) | [Stable Diffusion Image Variations](https://github.com/LambdaLabsML/lambda-diffusers#stable-diffusion-image-variations) | Image-to-Image Generation |
 | [stable_diffusion_latent_upscale](./stable_diffusion/latent_upscale) | [Stable Diffusion Latent Upscaler](https://twitter.com/StabilityAI/status/1590531958815064065) | Text-Guided Super Resolution Image-to-Image |
 | [stable_diffusion_model_editing](./api/pipelines/stable_diffusion/model_editing) | [Editing Implicit Assumptions in Text-to-Image Diffusion Models](https://time-diffusion.github.io/) | Text-to-Image Model Editing |
@@ -90,4 +93,4 @@ The library has three main components:
 | [versatile_diffusion](./api/pipelines/versatile_diffusion) | [Versatile Diffusion: Text, Images and Variations All in One Diffusion Model](https://arxiv.org/abs/2211.08332) | Text-to-Image Generation |
 | [versatile_diffusion](./api/pipelines/versatile_diffusion) | [Versatile Diffusion: Text, Images and Variations All in One Diffusion Model](https://arxiv.org/abs/2211.08332) | Image Variations Generation |
 | [versatile_diffusion](./api/pipelines/versatile_diffusion) | [Versatile Diffusion: Text, Images and Variations All in One Diffusion Model](https://arxiv.org/abs/2211.08332) | Dual Image and Text Guided Generation |
-| [vq_diffusion](./api/pipelines/vq_diffusion) | [Vector Quantized Diffusion Model for Text-to-Image Synthesis](https://arxiv.org/abs/2111.14822) | Text-to-Image Generation |
+| [vq_diffusion](./api/pipelines/vq_diffusion) | [Vector Quantized Diffusion Model for Text-to-Image Synthesis](https://arxiv.org/abs/2111.14822) | Text-to-Image Generation |

docs/source/en/installation.mdx

@@ -12,9 +12,9 @@ specific language governing permissions and limitations under the License.
 
 # Installation
 
-Install 🤗 Diffusers for whichever deep learning library you’re working with.
+Install 🤗 Diffusers for whichever deep learning library you're working with.
 
-🤗 Diffusers is tested on Python 3.7+, PyTorch 1.7.0+ and flax. Follow the installation instructions below for the deep learning library you are using:
+🤗 Diffusers is tested on Python 3.7+, PyTorch 1.7.0+ and Flax. Follow the installation instructions below for the deep learning library you are using:
 
 - [PyTorch](https://pytorch.org/get-started/locally/) installation instructions.
 - [Flax](https://flax.readthedocs.io/en/latest/) installation instructions.
@@ -37,27 +37,28 @@ Activate the virtual environment:
 source .env/bin/activate
 ```
 
-Now you're ready to install 🤗 Diffusers with the following command:
-
-**For PyTorch**
+🤗 Diffusers also relies on the 🤗 Transformers library, and you can install both with the following command:
 
+<frameworkcontent>
+<pt>
 ```bash
-pip install diffusers["torch"]
+pip install diffusers["torch"] transformers
 ```
-
-**For Flax**
-
+</pt>
+<jax>
 ```bash
-pip install diffusers["flax"]
+pip install diffusers["flax"] transformers
 ```
+</jax>
+</frameworkcontent>
 
 ## Install from source
 
-Before intsalling `diffusers` from source, make sure you have `torch` and `accelerate` installed.
+Before installing 🤗 Diffusers from source, make sure you have `torch` and 🤗 Accelerate installed.
 
-For `torch` installation refer to the `torch` [docs](https://pytorch.org/get-started/locally/#start-locally).
+For `torch` installation, refer to the `torch` [installation](https://pytorch.org/get-started/locally/#start-locally) guide.
 
-To install `accelerate`
+To install 🤗 Accelerate:
 
 ```bash
 pip install accelerate
@@ -74,7 +75,7 @@ The `main` version is useful for staying up-to-date with the latest developments
 For instance, if a bug has been fixed since the last official release but a new release hasn't been rolled out yet.
 However, this means the `main` version may not always be stable.
 We strive to keep the `main` version operational, and most issues are usually resolved within a few hours or a day.
-If you run into a problem, please open an [Issue](https://github.com/huggingface/transformers/issues), so we can fix it even sooner!
+If you run into a problem, please open an [Issue](https://github.com/huggingface/diffusers/issues/new/choose), so we can fix it even sooner!
 
 ## Editable install
 
@@ -90,21 +91,22 @@ git clone https://github.com/huggingface/diffusers.git
 cd diffusers
 ```
 
-**For PyTorch**
-
-```
+<frameworkcontent>
+<pt>
+```bash
 pip install -e ".[torch]"
 ```
-
-**For Flax**
-
-```
+</pt>
+<jax>
+```bash
 pip install -e ".[flax]"
 ```
+</jax>
+</frameworkcontent>
 
 These commands will link the folder you cloned the repository to and your Python library paths.
 Python will now look inside the folder you cloned to in addition to the normal library paths.
-For example, if your Python packages are typically installed in `~/anaconda3/envs/main/lib/python3.7/site-packages/`, Python will also search the folder you cloned to: `~/diffusers/`.
+For example, if your Python packages are typically installed in `~/anaconda3/envs/main/lib/python3.7/site-packages/`, Python will also search the `~/diffusers/` folder you cloned to.
 
 <Tip warning={true}>
 

docs/source/en/optimization/coreml.mdx

@@ -0,0 +1,167 @@
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# How to run Stable Diffusion with Core ML
+
+[Core ML](https://developer.apple.com/documentation/coreml) is the model format and machine learning library supported by Apple frameworks. If you are interested in running Stable Diffusion models inside your macOS or iOS/iPadOS apps, this guide will show you how to convert existing PyTorch checkpoints into the Core ML format and use them for inference with Python or Swift.
+
+Core ML models can leverage all the compute engines available in Apple devices: the CPU, the GPU, and the Apple Neural Engine (or ANE, a tensor-optimized accelerator available in Apple Silicon Macs and modern iPhones/iPads). Depending on the model and the device it's running on, Core ML can mix and match compute engines too, so some portions of the model may run on the CPU while others run on GPU, for example.
+
+<Tip>
+
+You can also run the `diffusers` Python codebase on Apple Silicon Macs using the `mps` accelerator built into PyTorch. This approach is explained in depth in [the mps guide](mps), but it is not compatible with native apps.
+
+</Tip>
+
+## Stable Diffusion Core ML Checkpoints
+
+Stable Diffusion weights (or checkpoints) are stored in the PyTorch format, so you need to convert them to the Core ML format before we can use them inside native apps.
+
+Thankfully, Apple engineers developed [a conversion tool](https://github.com/apple/ml-stable-diffusion#-converting-models-to-core-ml) based on `diffusers` to convert the PyTorch checkpoints to Core ML.
+
+Before you convert a model, though, take a moment to explore the Hugging Face Hub – chances are the model you're interested in is already available in Core ML format:
+
+- the [Apple](https://huggingface.co/apple) organization includes Stable Diffusion versions 1.4, 1.5, 2.0 base, and 2.1 base
+- [coreml](https://huggingface.co/coreml) organization includes custom DreamBoothed and finetuned models
+- use this [filter](https://huggingface.co/models?pipeline_tag=text-to-image&library=coreml&p=2&sort=likes) to return all available Core ML checkpoints
+
+If you can't find the model you're interested in, we recommend you follow the instructions for [Converting Models to Core ML](https://github.com/apple/ml-stable-diffusion#-converting-models-to-core-ml) by Apple.
+
+## Selecting the Core ML Variant to Use
+
+Stable Diffusion models can be converted to different Core ML variants intended for different purposes:
+
+- The type of attention blocks used. The attention operation is used to "pay attention" to the relationship between different areas in the image representations and to understand how the image and text representations are related. Attention is compute- and memory-intensive, so different implementations exist that consider the hardware characteristics of different devices. For Core ML Stable Diffusion models, there are two attention variants:
+    * `split_einsum` ([introduced by Apple](https://machinelearning.apple.com/research/neural-engine-transformers)) is optimized for ANE devices, which is available in modern iPhones, iPads and M-series computers.
+    * The "original" attention (the base implementation used in `diffusers`) is only compatible with CPU/GPU and not ANE. It can be *faster* to run your model on CPU + GPU using `original` attention than ANE. See [this performance benchmark](https://huggingface.co/blog/fast-mac-diffusers#performance-benchmarks) as well as some [additional measures provided by the community](https://github.com/huggingface/swift-coreml-diffusers/issues/31) for additional details.
+
+- The supported inference framework.
+    * `packages` are suitable for Python inference. This can be used to test converted Core ML models before attempting to integrate them inside native apps, or if you want to explore Core ML performance but don't need to support native apps. For example, an application with a web UI could perfectly use a Python Core ML backend.
+    * `compiled` models are required for Swift code. The `compiled` models in the Hub split the large UNet model weights into several files for compatibility with iOS and iPadOS devices. This corresponds to the [`--chunk-unet` conversion option](https://github.com/apple/ml-stable-diffusion#-converting-models-to-core-ml). If you want to support native apps, then you need to select the `compiled` variant.
+
+The official Core ML Stable Diffusion [models](https://huggingface.co/apple/coreml-stable-diffusion-v1-4/tree/main) include these variants, but the community ones may vary:
+
+```
+coreml-stable-diffusion-v1-4
+├── README.md
+├── original
+│   ├── compiled
+│   └── packages
+└── split_einsum
+    ├── compiled
+    └── packages
+```
+
+You can download and use the variant you need as shown below.
+
+## Core ML Inference in Python
+
+Install the following libraries to run Core ML inference in Python:
+
+```bash
+pip install huggingface_hub
+pip install git+https://github.com/apple/ml-stable-diffusion
+```
+
+### Download the Model Checkpoints
+
+To run inference in Python, use one of the versions stored in the `packages` folders because the `compiled` ones are only compatible with Swift. You may choose whether you want to use `original` or `split_einsum` attention.
+
+This is how you'd download the `original` attention variant from the Hub to a directory called `models`:
+
+```Python
+from huggingface_hub import snapshot_download
+from pathlib import Path
+
+repo_id = "apple/coreml-stable-diffusion-v1-4"
+variant = "original/packages"
+
+model_path = Path("./models") / (repo_id.split("/")[-1] + "_" + variant.replace("/", "_"))
+snapshot_download(repo_id, allow_patterns=f"{variant}/*", local_dir=model_path, local_dir_use_symlinks=False)
+print(f"Model downloaded at {model_path}")
+```
+
+
+### Inference[[python-inference]]
+
+Once you have downloaded a snapshot of the model, you can test it using Apple's Python script.
+
+```shell
+python -m python_coreml_stable_diffusion.pipeline --prompt "a photo of an astronaut riding a horse on mars" -i models/coreml-stable-diffusion-v1-4_original_packages -o </path/to/output/image> --compute-unit CPU_AND_GPU --seed 93
+```
+
+`<output-mlpackages-directory>` should point to the checkpoint you downloaded in the step above, and `--compute-unit` indicates the hardware you want to allow for inference. It must be one of the following options: `ALL`, `CPU_AND_GPU`, `CPU_ONLY`, `CPU_AND_NE`. You may also provide an optional output path, and a seed for reproducibility.
+
+The inference script assumes you're using the original version of the Stable Diffusion model, `CompVis/stable-diffusion-v1-4`. If you use another model, you *have* to specify its Hub id in the inference command line, using the `--model-version` option. This works for models already supported and custom models you trained or fine-tuned yourself.
+
+For example, if you want to use [`runwayml/stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5):
+
+```shell
+python -m python_coreml_stable_diffusion.pipeline --prompt "a photo of an astronaut riding a horse on mars" --compute-unit ALL -o output --seed 93 -i models/coreml-stable-diffusion-v1-5_original_packages --model-version runwayml/stable-diffusion-v1-5
+```
+
+
+## Core ML inference in Swift
+
+Running inference in Swift is slightly faster than in Python because the models are already compiled in the `mlmodelc` format. This is noticeable on app startup when the model is loaded but shouldn’t be noticeable if you run several generations afterward.
+
+### Download
+
+To run inference in Swift on your Mac, you need one of the `compiled` checkpoint versions. We recommend you download them locally using Python code similar to the previous example, but with one of the `compiled` variants:
+
+```Python
+from huggingface_hub import snapshot_download
+from pathlib import Path
+
+repo_id = "apple/coreml-stable-diffusion-v1-4"
+variant = "original/compiled"
+
+model_path = Path("./models") / (repo_id.split("/")[-1] + "_" + variant.replace("/", "_"))
+snapshot_download(repo_id, allow_patterns=f"{variant}/*", local_dir=model_path, local_dir_use_symlinks=False)
+print(f"Model downloaded at {model_path}")
+```
+
+### Inference[[swift-inference]]
+
+To run inference, please clone Apple's repo:
+
+```bash
+git clone https://github.com/apple/ml-stable-diffusion
+cd ml-stable-diffusion
+```
+
+And then use Apple's command line tool, [Swift Package Manager](https://www.swift.org/package-manager/#):
+
+```bash
+swift run StableDiffusionSample --resource-path models/coreml-stable-diffusion-v1-4_original_compiled --compute-units all "a photo of an astronaut riding a horse on mars"
+```
+
+You have to specify in `--resource-path` one of the checkpoints downloaded in the previous step, so please make sure it contains compiled Core ML bundles with the extension `.mlmodelc`. The `--compute-units` has to be one of these values: `all`, `cpuOnly`, `cpuAndGPU`, `cpuAndNeuralEngine`.
+
+For more details, please refer to the [instructions in Apple's repo](https://github.com/apple/ml-stable-diffusion).
+
+
+## Supported Diffusers Features
+
+The Core ML models and inference code don't support many of the features, options, and flexibility of 🧨 Diffusers. These are some of the limitations to keep in mind:
+
+- Core ML models are only suitable for inference. They can't be used for training or fine-tuning.
+- Only two schedulers have been ported to Swift, the default one used by Stable Diffusion and `DPMSolverMultistepScheduler`, which we ported to Swift from our `diffusers` implementation. We recommend you use `DPMSolverMultistepScheduler`, since it produces the same quality in about half the steps.
+- Negative prompts, classifier-free guidance scale, and image-to-image tasks are available in the inference code. Advanced features such as depth guidance, ControlNet, and latent upscalers are not available yet.
+
+Apple's [conversion and inference repo](https://github.com/apple/ml-stable-diffusion) and our own [swift-coreml-diffusers](https://github.com/huggingface/swift-coreml-diffusers) repos are intended as technology demonstrators to enable other developers to build upon. 
+
+If you feel strongly about any missing features, please feel free to open a feature request or, better yet, a contribution PR :)
+
+## Native Diffusers Swift app
+
+One easy way to run Stable Diffusion on your own Apple hardware is to use [our open-source Swift repo](https://github.com/huggingface/swift-coreml-diffusers), based on `diffusers` and Apple's conversion and inference repo. You can study the code, compile it with [Xcode](https://developer.apple.com/xcode/) and adapt it for your own needs. For your convenience, there's also a [standalone Mac app in the App Store](https://apps.apple.com/app/diffusers/id1666309574), so you can play with it without having to deal with the code or IDE. If you are a developer and have determined that Core ML is the best solution to build your Stable Diffusion app, then you can use the rest of this guide to get started with your project. We can't wait to see what you'll build :)

docs/source/en/optimization/fp16.mdx

@@ -60,8 +60,10 @@ image = pipe(prompt).images[0]
 ```
 
 <Tip warning={true}>
+
   It is strongly discouraged to make use of [`torch.autocast`](https://pytorch.org/docs/stable/amp.html#torch.autocast) in any of the pipelines as it can lead to black images and is always slower than using pure 
   float16 precision.
+  
 </Tip>
 
 ## Sliced attention for additional memory savings
@@ -202,6 +204,8 @@ image = pipe(prompt).images[0]
 
 **Note**: When using `enable_sequential_cpu_offload()`, it is important to **not** move the pipeline to CUDA beforehand or else the gain in memory consumption will only be minimal. See [this issue](https://github.com/huggingface/diffusers/issues/1934) for more information.
 
+**Note**: `enable_sequential_cpu_offload()` is a stateful operation that installs hooks on the models.
+
 
 <a name="model_offloading"></a>
 ## Model offloading for fast inference and memory savings
@@ -251,6 +255,11 @@ image = pipe(prompt).images[0]
 This feature requires `accelerate` version 0.17.0 or larger.
 </Tip>
 
+**Note**: `enable_model_cpu_offload()` is a stateful operation that installs hooks on the models and state on the pipeline. In order to properly offload
+models after they are called, it is required that the entire pipeline is run and models are called in the order the pipeline expects them to be. Exercise caution
+if models are re-used outside the context of the pipeline after hooks have been installed. See [accelerate](https://huggingface.co/docs/accelerate/v0.18.0/en/package_reference/big_modeling#accelerate.hooks.remove_hook_from_module)
+for further docs on removing hooks.
+
 ## Using Channels Last memory format
 
 Channels last memory format is an alternative way of ordering NCHW tensors in memory preserving dimensions ordering. Channels last tensors ordered in such a way that channels become the densest dimension (aka storing images pixel-per-pixel). Since not all operators currently support channels last format it may result in a worst performance, so it's better to try it and see if it works for your model.

docs/source/en/optimization/habana.mdx

@@ -16,8 +16,8 @@ specific language governing permissions and limitations under the License.
 
 ## Requirements
 
-- Optimum Habana 1.4 or later, [here](https://huggingface.co/docs/optimum/habana/installation) is how to install it.
-- SynapseAI 1.8.
+- Optimum Habana 1.5 or later, [here](https://huggingface.co/docs/optimum/habana/installation) is how to install it.
+- SynapseAI 1.9.
 
 
 ## Inference Pipeline
@@ -64,7 +64,16 @@ For more information, check out Optimum Habana's [documentation](https://hugging
 
 Here are the latencies for Habana first-generation Gaudi and Gaudi2 with the [Habana/stable-diffusion](https://huggingface.co/Habana/stable-diffusion) Gaudi configuration (mixed precision bf16/fp32):
 
+- [Stable Diffusion v1.5](https://huggingface.co/runwayml/stable-diffusion-v1-5) (512x512 resolution):
+
 |                        | Latency (batch size = 1) | Throughput (batch size = 8) |
 | ---------------------- |:------------------------:|:---------------------------:|
-| first-generation Gaudi | 4.29s                    | 0.283 images/s              |
-| Gaudi2                 | 1.54s                    | 0.904 images/s              |
+| first-generation Gaudi | 4.22s                    | 0.29 images/s               |
+| Gaudi2                 | 1.70s                    | 0.925 images/s              |
+
+- [Stable Diffusion v2.1](https://huggingface.co/stabilityai/stable-diffusion-2-1) (768x768 resolution):
+
+|                        | Latency (batch size = 1) | Throughput                      |
+| ---------------------- |:------------------------:|:-------------------------------:|
+| first-generation Gaudi | 23.3s                    | 0.045 images/s (batch size = 2) |
+| Gaudi2                 | 7.75s                    | 0.14 images/s (batch size = 5)  |

docs/source/en/optimization/tome.mdx

@@ -0,0 +1,116 @@
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# Token Merging
+
+Token Merging (introduced in [Token Merging: Your ViT But Faster](https://arxiv.org/abs/2210.09461)) works by merging the redundant tokens / patches progressively in the forward pass of a Transformer-based network. It can speed up the inference latency of the underlying network.
+
+After Token Merging (ToMe) was released, the authors released [Token Merging for Fast Stable Diffusion](https://arxiv.org/abs/2303.17604), which introduced a version of ToMe which is more compatible with Stable Diffusion. We can use ToMe to gracefully speed up the inference latency of a [`DiffusionPipeline`]. This doc discusses how to apply ToMe to the [`StableDiffusionPipeline`], the expected speedups, and the qualitative aspects of using ToMe on the [`StableDiffusionPipeline`]. 
+
+## Using ToMe
+
+The authors of ToMe released a convenient Python library called [`tomesd`](https://github.com/dbolya/tomesd) that lets us apply ToMe to a [`DiffusionPipeline`] like so:
+
+```diff
+from diffusers import StableDiffusionPipeline
+import tomesd
+
+pipeline = StableDiffusionPipeline.from_pretrained(
+      "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16
+).to("cuda")
++ tomesd.apply_patch(pipeline, ratio=0.5)
+
+image = pipeline("a photo of an astronaut riding a horse on mars").images[0]
+```
+
+And that’s it! 
+
+`tomesd.apply_patch()` exposes [a number of arguments](https://github.com/dbolya/tomesd#usage) to let us strike a balance between the pipeline inference speed and the quality of the generated tokens. Amongst those arguments, the most important one is `ratio`. `ratio` controls the number of tokens that will be merged during the forward pass. For more details on `tomesd`, please refer to the original repository https://github.com/dbolya/tomesd and [the paper](https://arxiv.org/abs/2303.17604). 
+
+## Benchmarking `tomesd` with `StableDiffusionPipeline`
+
+We benchmarked the impact of using `tomesd` on [`StableDiffusionPipeline`] along with [xformers](https://huggingface.co/docs/diffusers/optimization/xformers) across different image resolutions. We used A100 and V100 as our test GPU devices with the following development environment (with Python 3.8.5):
+
+```bash
+- `diffusers` version: 0.15.1
+- Python version: 3.8.16
+- PyTorch version (GPU?): 1.13.1+cu116 (True)
+- Huggingface_hub version: 0.13.2
+- Transformers version: 4.27.2
+- Accelerate version: 0.18.0
+- xFormers version: 0.0.16
+- tomesd version: 0.1.2
+```
+
+We used this script for benchmarking: [https://gist.github.com/sayakpaul/27aec6bca7eb7b0e0aa4112205850335](https://gist.github.com/sayakpaul/27aec6bca7eb7b0e0aa4112205850335). Following are our findings: 
+
+### A100
+
+| Resolution | Batch size | Vanilla | ToMe | ToMe + xFormers | ToMe speedup (%) | ToMe + xFormers speedup (%) |
+| --- | --- | --- | --- | --- | --- | --- |
+| 512 | 10 | 6.88 | 5.26 | 4.69 | 23.54651163 | 31.83139535 |
+|  |  |  |  |  |  |  |
+| 768 | 10 | OOM | 14.71 | 11 |  |  |
+|  | 8 | OOM | 11.56 | 8.84 |  |  |
+|  | 4 | OOM | 5.98 | 4.66 |  |  |
+|  | 2 | 4.99 | 3.24 | 3.1 | 35.07014028 | 37.8757515 |
+|  | 1 | 3.29 | 2.24 | 2.03 | 31.91489362 | 38.29787234 |
+|  |  |  |  |  |  |  |
+| 1024 | 10 | OOM | OOM | OOM |  |  |
+|  | 8 | OOM | OOM | OOM |  |  |
+|  | 4 | OOM | 12.51 | 9.09 |  |  |
+|  | 2 | OOM | 6.52 | 4.96 |  |  |
+|  | 1 | 6.4 | 3.61 | 2.81 | 43.59375 | 56.09375 |
+
+***The timings reported here are in seconds. Speedups are calculated over the `Vanilla` timings.*** 
+
+### V100
+
+| Resolution | Batch size | Vanilla | ToMe | ToMe + xFormers | ToMe speedup (%) | ToMe + xFormers speedup (%) |
+| --- | --- | --- | --- | --- | --- | --- |
+| 512 | 10 | OOM | 10.03 | 9.29 |  |  |
+|  | 8 | OOM | 8.05 | 7.47 |  |  |
+|  | 4 | 5.7 | 4.3 | 3.98 | 24.56140351 | 30.1754386 |
+|  | 2 | 3.14 | 2.43 | 2.27 | 22.61146497 | 27.70700637 |
+|  | 1 | 1.88 | 1.57 | 1.57 | 16.4893617 | 16.4893617 |
+|  |  |  |  |  |  |  |
+| 768 | 10 | OOM | OOM | 23.67 |  |  |
+|  | 8 | OOM | OOM | 18.81 |  |  |
+|  | 4 | OOM | 11.81 | 9.7 |  |  |
+|  | 2 | OOM | 6.27 | 5.2 |  |  |
+|  | 1 | 5.43 | 3.38 | 2.82 | 37.75322284 | 48.06629834 |
+|  |  |  |  |  |  |  |
+| 1024 | 10 | OOM | OOM | OOM |  |  |
+|  | 8 | OOM | OOM | OOM |  |  |
+|  | 4 | OOM | OOM | 19.35 |  |  |
+|  | 2 | OOM | 13 | 10.78 |  |  |
+|  | 1 | OOM | 6.66 | 5.54 |  |  |
+
+As seen in the tables above, the speedup with `tomesd` becomes more pronounced for larger image resolutions. It is also interesting to note that with `tomesd`, it becomes possible to run the pipeline on a higher resolution, like 1024x1024. 
+
+It might be possible to speed up inference even further with [`torch.compile()`](https://huggingface.co/docs/diffusers/optimization/torch2.0). 
+
+## Quality
+
+As reported in [the paper](https://arxiv.org/abs/2303.17604), ToMe can preserve the quality of the generated images to a great extent while speeding up inference. By increasing the `ratio`, it is possible to further speed up inference, but that might come at the cost of a deterioration in the image quality. 
+
+To test the quality of the generated samples using our setup, we sampled a few prompts from the “Parti Prompts” (introduced in [Parti](https://parti.research.google/)) and performed inference with the [`StableDiffusionPipeline`] in the following settings:
+
+- Vanilla [`StableDiffusionPipeline`]
+- [`StableDiffusionPipeline`] + ToMe
+- [`StableDiffusionPipeline`] + ToMe + xformers
+
+We didn’t notice any significant decrease in the quality of the generated samples. Here are samples: 
+
+![tome-samples](https://huggingface.co/datasets/diffusers/docs-images/resolve/main/tome/tome_samples.png)
+
+You can check out the generated samples [here](https://wandb.ai/sayakpaul/tomesd-results/runs/23j4bj3i?workspace=). We used [this script](https://gist.github.com/sayakpaul/8cac98d7f22399085a060992f411ecbd) for conducting this experiment.

docs/source/en/optimization/torch2.0.mdx

@@ -12,19 +12,21 @@ specific language governing permissions and limitations under the License.
 
 # Accelerated PyTorch 2.0 support in Diffusers
 
-Starting from version `0.13.0`, Diffusers supports the latest optimization from the upcoming [PyTorch 2.0](https://pytorch.org/get-started/pytorch-2.0/) release. These include:
-1. Support for accelerated transformers implementation with memory-efficient attention – no extra dependencies required.
+Starting from version `0.13.0`, Diffusers supports the latest optimization from [PyTorch 2.0](https://pytorch.org/get-started/pytorch-2.0/). These include:
+1. Support for accelerated transformers implementation with memory-efficient attention – no extra dependencies (such as `xformers`) required.
 2. [torch.compile](https://pytorch.org/tutorials/intermediate/torch_compile_tutorial.html) support for extra performance boost when individual models are compiled.
 
 
 ## Installation
-To benefit from the accelerated attention implementation and `torch.compile`, you just need to install the latest versions of PyTorch 2.0 from `pip`, and make sure you are on diffusers 0.13.0 or later. As explained below, `diffusers` automatically uses the attention optimizations (but not `torch.compile`) when available.
+
+To benefit from the accelerated attention implementation and `torch.compile()`, you just need to install the latest versions of PyTorch 2.0 from pip, and make sure you are on diffusers 0.13.0 or later. As explained below, diffusers automatically uses the optimized attention processor ([`AttnProcessor2_0`](https://github.com/huggingface/diffusers/blob/1a5797c6d4491a879ea5285c4efc377664e0332d/src/diffusers/models/attention_processor.py#L798)) (but not `torch.compile()`)
+when PyTorch 2.0 is available.
 
 ```bash
 pip install --upgrade torch torchvision diffusers
 ```
 
-## Using accelerated transformers and torch.compile.
+## Using accelerated transformers and `torch.compile`.
 
 
 1. **Accelerated Transformers implementation**
@@ -46,13 +48,13 @@ pip install --upgrade torch torchvision diffusers
 
     If you want to enable it explicitly (which is not required), you can do so as shown below.
 
-    ```Python
+    ```diff
     import torch
     from diffusers import DiffusionPipeline
-    from diffusers.models.attention_processor import AttnProcessor2_0
+    + from diffusers.models.attention_processor import AttnProcessor2_0
 
     pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16).to("cuda")
-    pipe.unet.set_attn_processor(AttnProcessor2_0())
+    + pipe.unet.set_attn_processor(AttnProcessor2_0())
 
     prompt = "a photo of an astronaut riding a horse on mars"
     image = pipe(prompt).images[0]
@@ -60,151 +62,383 @@ pip install --upgrade torch torchvision diffusers
 
     This should be as fast and memory efficient as `xFormers`. More details [in our benchmark](#benchmark).
 
+    It is possible to revert to the vanilla attention processor ([`AttnProcessor`](https://github.com/huggingface/diffusers/blob/1a5797c6d4491a879ea5285c4efc377664e0332d/src/diffusers/models/attention_processor.py#L402)), which can be helpful to make the pipeline more deterministic, or if you need to convert a fine-tuned model to other formats such as [Core ML](https://huggingface.co/docs/diffusers/v0.16.0/en/optimization/coreml#how-to-run-stable-diffusion-with-core-ml). To use the normal attention processor you can use the [`~diffusers.UNet2DConditionModel.set_default_attn_processor`] function:
+
+    ```Python
+    import torch
+    from diffusers import DiffusionPipeline
+    from diffusers.models.attention_processor import AttnProcessor
+
+    pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16).to("cuda")
+    pipe.unet.set_default_attn_processor()
+
+    prompt = "a photo of an astronaut riding a horse on mars"
+    image = pipe(prompt).images[0]
+    ```
 
 2. **torch.compile**
 
-    To get an additional speedup, we can use the new `torch.compile` feature. To do so, we simply wrap our `unet` with `torch.compile`. For more information and different options, refer to the 
+    To get an additional speedup, we can use the new `torch.compile` feature. Since the UNet of the pipeline is usually the most computationally expensive, we wrap the `unet` with `torch.compile` leaving rest of the sub-models (text encoder and VAE) as is. For more information and different options, refer to the 
     [torch compile docs](https://pytorch.org/tutorials/intermediate/torch_compile_tutorial.html).
 
     ```python
-    import torch
-    from diffusers import DiffusionPipeline
-
-    pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16).to("cuda")
-    pipe.unet = torch.compile(pipe.unet)
-
-    batch_size = 10
-    prompt = "A photo of an astronaut riding a horse on marse."
+    pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
     images = pipe(prompt, num_inference_steps=steps, num_images_per_prompt=batch_size).images
     ```
 
-    Depending on the type of GPU, `compile()` can yield between 2-9% of _additional speed-up_ over the accelerated transformer optimizations. Note, however, that compilation is able to squeeze more performance improvements in more recent GPU architectures such as Ampere (A100, 3090), Ada (4090) and Hopper (H100).
+    Depending on the type of GPU, `compile()` can yield between **5% - 300%** of _additional speed-up_ over the accelerated transformer optimizations. Note, however, that compilation is able to squeeze more performance improvements in more recent GPU architectures such as Ampere (A100, 3090), Ada (4090) and Hopper (H100).
     
-    Compilation takes some time to complete, so it is best suited for situations where you need to prepare your pipeline once and then perform the same type of inference operations multiple times.
+    Compilation takes some time to complete, so it is best suited for situations where you need to prepare your pipeline once and then perform the same type of inference operations multiple times. Calling the compiled pipeline on a different image size will re-trigger compilation which can be expensive.
 
 
 ## Benchmark
 
-We conducted a simple benchmark on different GPUs to compare vanilla attention, xFormers, `torch.nn.functional.scaled_dot_product_attention` and `torch.compile+torch.nn.functional.scaled_dot_product_attention`.
-For the benchmark we used the [stable-diffusion-v1-4](https://huggingface.co/CompVis/stable-diffusion-v1-4) model with 50 steps. The `xFormers` benchmark is done using the `torch==1.13.1` version, while the accelerated transformers optimizations are tested using nightly versions of PyTorch 2.0. The tables below summarize the results we got.
+We conducted a comprehensive benchmark with PyTorch 2.0's efficient attention implementation and `torch.compile` across different GPUs and batch sizes for five of our most used pipelines. We used `diffusers 0.17.0.dev0`, which [makes sure `torch.compile()` is leveraged optimally](https://github.com/huggingface/diffusers/pull/3313).
 
-Please refer to [our featured blog post in the PyTorch site](https://pytorch.org/blog/accelerated-diffusers-pt-20/) for more details.
+### Benchmarking code 
 
-### FP16 benchmark
+#### Stable Diffusion text-to-image 
 
-The table below shows the benchmark results for inference using `fp16`. As we can see, `torch.nn.functional.scaled_dot_product_attention` is as fast as `xFormers` (sometimes slightly faster/slower) on all the GPUs we tested.
-And using `torch.compile` gives further speed-up of up of 10% over `xFormers`, but it's mostly noticeable on the A100 GPU.
+```python 
+from diffusers import DiffusionPipeline
+import torch
 
-___The time reported is in seconds.___
+path = "runwayml/stable-diffusion-v1-5"
 
-| GPU | Batch Size | Vanilla Attention | xFormers | PyTorch2.0 SDPA | SDPA + torch.compile | Speed over xformers (%) |
-| --- | --- | --- | --- | --- | --- | --- |
-| A100 | 1 | 2.69 | 2.7 | 1.98 | 2.47 | 8.52 |
-| A100 | 2 | 3.21 | 3.04 | 2.38 | 2.78 | 8.55 |
-| A100 | 4 | 5.27 | 3.91 | 3.89 | 3.53 | 9.72 |
-| A100 | 8 | 9.74 | 7.03 | 7.04 | 6.62 | 5.83 |
-| A100 | 10 | 12.02 | 8.7 | 8.67 | 8.45 | 2.87 |
-| A100 | 16 | 18.95 | 13.57 | 13.55 | 13.20 | 2.73 |
-| A100 | 32 (1) | OOM | 26.56 | 26.68 | 25.85 | 2.67 |
-| A100 | 64 | | 52.51 | 53.03 | 50.93 | 3.01 |
-| | | | | | | |
-| A10 | 4 | 13.94 | 9.81 | 10.01 | 9.35 | 4.69 |
-| A10 | 8 | 27.09 | 19 | 19.53 | 18.33 | 3.53 |
-| A10 | 10 | 33.69 | 23.53 | 24.19 | 22.52 | 4.29 |
-| A10 | 16 | OOM | 37.55 | 38.31 | 36.81 | 1.97 |
-| A10 | 32 (1) | | 77.19 | 78.43 | 76.64 | 0.71 |
-| A10 | 64 (1) | | 173.59 | 158.99 | 155.14 | 10.63 |
-| | | | | | | |
-| T4 | 4 | 38.81 | 30.09 | 29.74 | 27.55 | 8.44 |
-| T4 | 8 | OOM | 55.71 | 55.99 | 53.85 | 3.34 |
-| T4 | 10 | OOM | 68.96 | 69.86 | 65.35 | 5.23 |
-| T4 | 16 | OOM | 111.47 | 113.26  | 106.93  | 4.07 |
-| | | | | | | |
-| V100 | 4 | 9.84 | 8.16 | 8.09 | 7.65 | 6.25 |
-| V100 | 8 | OOM | 15.62 | 15.44 | 14.59 | 6.59 |
-| V100 | 10 | OOM | 19.52 | 19.28 | 18.18 | 6.86 |
-| V100 | 16 | OOM | 30.29 | 29.84 | 28.22 | 6.83 |
-| | | | | | | |
-| 3090 | 1 | 2.94 | 2.5 | 2.42 | 2.33 | 6.80 |
-| 3090 | 4 | 10.04 | 7.82 | 7.72 | 7.38 | 5.63 |
-| 3090 | 8 | 19.27 | 14.97 | 14.88 | 14.15 | 5.48 |
-| 3090 | 10| 24.08 | 18.7 | 18.62 | 18.12 | 3.10 |
-| 3090 | 16 | OOM | 29.06 | 28.88 | 28.2 | 2.96 |
-| 3090 | 32 (1) | | 58.05 | 57.42 | 56.28 | 3.05 |
-| 3090 | 64 (1) | | 126.54 | 114.27 | 112.21 | 11.32 |
-| | | | | | | |
-| 3090 Ti | 1 | 2.7 | 2.26 | 2.19 | 2.12 | 6.19 |
-| 3090 Ti | 4 | 9.07 | 7.14 | 7.00 | 6.71 | 6.02 |
-| 3090 Ti | 8 | 17.51 | 13.65 | 13.53 | 12.94 | 5.20 |
-| 3090 Ti | 10 (2) | 21.79 | 16.85 | 16.77 | 16.44 | 2.43 |
-| 3090 Ti | 16 | OOM | 26.1 | 26.04 | 25.53 | 2.18 |
-| 3090 Ti | 32 (1) | | 51.78 | 51.71 | 50.91 | 1.68 |
-| 3090 Ti | 64 (1) | | 112.02 | 102.78 | 100.89 | 9.94 |
-| | | | | | | |
-| 4090 | 1 | 4.47 | 3.98 | 1.28 | 1.21 | 69.60 |
-| 4090 | 4 | 10.48 | 8.37 | 3.76 | 3.56 | 57.47 |
-| 4090 | 8 | 14.33 | 10.22 | 7.43 | 6.99 | 31.60 |
-| 4090 | 16 | | 17.07 | 14.98 | 14.58 | 14.59 |
-| 4090 | 32 (1) | | 39.03 | 30.18 | 29.49 | 24.44 |
-| 4090 | 64 (1) | | 77.29 | 61.34 | 59.96 | 22.42 |
+run_compile = True  # Set True / False
+
+pipe = DiffusionPipeline.from_pretrained(path, torch_dtype=torch.float16)
+pipe = pipe.to("cuda")
+pipe.unet.to(memory_format=torch.channels_last)
+
+if run_compile:
+    print("Run torch compile")
+    pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+
+prompt = "ghibli style, a fantasy landscape with castles"
+
+for _ in range(3):
+    images = pipe(prompt=prompt).images
+```
+
+#### Stable Diffusion image-to-image 
+
+```python 
+from diffusers import StableDiffusionImg2ImgPipeline
+import requests
+import torch
+from PIL import Image
+from io import BytesIO
+
+url = "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg"
+
+response = requests.get(url)
+init_image = Image.open(BytesIO(response.content)).convert("RGB")
+init_image = init_image.resize((512, 512))
+
+path = "runwayml/stable-diffusion-v1-5"
+
+run_compile = True  # Set True / False
+
+pipe = StableDiffusionImg2ImgPipeline.from_pretrained(path, torch_dtype=torch.float16)
+pipe = pipe.to("cuda")
+pipe.unet.to(memory_format=torch.channels_last)
+
+if run_compile:
+    print("Run torch compile")
+    pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+
+prompt = "ghibli style, a fantasy landscape with castles"
+
+for _ in range(3):
+    image = pipe(prompt=prompt, image=init_image).images[0]
+```
+
+#### Stable Diffusion - inpainting
+
+```python 
+from diffusers import StableDiffusionInpaintPipeline
+import requests
+import torch
+from PIL import Image
+from io import BytesIO
+
+url = "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg"
+
+def download_image(url):
+    response = requests.get(url)
+    return Image.open(BytesIO(response.content)).convert("RGB")
 
 
-				
-### FP32 benchmark
+img_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png"
+mask_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png"
 
-The table below shows the benchmark results for inference using `fp32`. In this case, `torch.nn.functional.scaled_dot_product_attention` is faster than `xFormers` on all the GPUs we tested.
+init_image = download_image(img_url).resize((512, 512))
+mask_image = download_image(mask_url).resize((512, 512))
 
-Using `torch.compile` in addition to the accelerated transformers implementation can yield up to 19% performance improvement over `xFormers` in Ampere and Ada cards, and up to 20% (Ampere) or 28% (Ada) over vanilla attention.
+path = "runwayml/stable-diffusion-inpainting"
 
-| GPU | Batch Size | Vanilla Attention | xFormers | PyTorch2.0 SDPA | SDPA + torch.compile | Speed over xformers (%) | Speed over vanilla (%) |
-| --- | --- | --- | --- | --- | --- | --- | --- |
-| A100 | 1 | 4.97 | 3.86 | 2.6 | 2.86 | 25.91 | 42.45 |
-| A100 | 2 | 9.03 | 6.76 | 4.41 | 4.21 | 37.72 | 53.38 |
-| A100 | 4 | 16.70 | 12.42 | 7.94 | 7.54 | 39.29 | 54.85 |
-| A100 | 10 | OOM | 29.93 | 18.70 | 18.46 | 38.32 | |
-| A100 | 16 | | 47.08 | 29.41 | 29.04 | 38.32 | |
-| A100 | 32 | | 92.89 | 57.55 | 56.67 | 38.99 | |
-| A100 | 64 | | 185.3 | 114.8 | 112.98 | 39.03 | |
-| | | | | | | |
-| A10 | 1 | 10.59 | 8.81 | 7.51 | 7.35 | 16.57 | 30.59 |
-| A10 | 4 | 34.77 | 27.63 | 22.77 | 22.07 | 20.12 | 36.53 |
-| A10 | 8 | | 56.19 | 43.53 | 43.86 | 21.94 | |
-| A10 | 16 | | 116.49 | 88.56 | 86.64 | 25.62 | |
-| A10 | 32 | | 221.95 | 175.74 | 168.18 | 24.23 | |
-| A10 | 48 | | 333.23 | 264.84 | | 20.52 | |
-| | | | | | | |
-| T4 | 1 | 28.2 | 24.49 | 23.93 | 23.56 | 3.80 | 16.45 |
-| T4 | 2 | 52.77 | 45.7 | 45.88 | 45.06 | 1.40 | 14.61 |
-| T4 | 4 | OOM | 85.72 | 85.78 | 84.48 | 1.45 | |
-| T4 | 8 | | 149.64 | 150.75 | 148.4 | 0.83 | |
-| | | | | | | |
-| V100 | 1 | 7.4 | 6.84 | 6.8 | 6.66 | 2.63 | 10.00 |
-| V100 | 2 | 13.85 | 12.81 | 12.66 | 12.35 | 3.59 | 10.83 |
-| V100 | 4 | OOM | 25.73 | 25.31 | 24.78 | 3.69 | |
-| V100 | 8 | | 43.95 | 43.37 | 42.25 | 3.87 | |
-| V100 | 16 | | 84.99 | 84.73 | 82.55 | 2.87 | |
-| | | | | | | |
-| 3090 | 1 | 7.09 | 6.78 | 5.34 | 5.35 | 21.09 | 24.54 |
-| 3090 | 4 | 22.69 | 21.45 | 18.56 | 18.18 | 15.24 | 19.88 |
-| 3090 | 8 | | 42.59 | 36.68 | 35.61 | 16.39 | |
-| 3090 | 16 | | 85.35 | 72.93 | 70.18 | 17.77 | |
-| 3090 | 32 (1) | | 162.05 | 143.46 | 138.67 | 14.43 | |
-| | | | | | | |
-| 3090 Ti | 1 | 6.45 | 6.19 | 4.99 | 4.89 | 21.00 | 24.19 |
-| 3090 Ti | 4 | 20.32 | 19.31 | 17.02 | 16.48 | 14.66 | 18.90 |
-| 3090 Ti | 8 | | 37.93 | 33.21 | 32.24 | 15.00 | |
-| 3090 Ti | 16 | | 75.37 | 66.63 | 64.5 | 14.42 | |
-| 3090 Ti | 32 (1) | | 142.55 | 128.89 | 124.92 | 12.37 | |
-| | | | | | | |
-| 4090 | 1 | 5.54 | 4.99 | 2.66 | 2.58 | 48.30 | 53.43 |
-| 4090 | 4 | 13.67 | 11.4 | 8.81 | 8.46 | 25.79 | 38.11 |
-| 4090 | 8 |  | 19.79 | 17.55 | 16.62 | 16.02 |  |
-| 4090 | 16 |  | 38.62 | 35.65 | 34.07 | 11.78 |  |
-| 4090 | 32 (1) |  | 76.57 | 69.48 | 65.35 | 14.65 |  |
-| 4090 | 48 |  | 114.44 | 106.3 |  | 7.11 |  |
+run_compile = True  # Set True / False
+
+pipe = StableDiffusionInpaintPipeline.from_pretrained(path, torch_dtype=torch.float16)
+pipe = pipe.to("cuda")
+pipe.unet.to(memory_format=torch.channels_last)
+
+if run_compile:
+    print("Run torch compile")
+    pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+
+prompt = "ghibli style, a fantasy landscape with castles"
+
+for _ in range(3):
+    image = pipe(prompt=prompt, image=init_image, mask_image=mask_image).images[0]
+```
+
+#### ControlNet 
+
+```python 
+from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
+import requests
+import torch
+from PIL import Image
+from io import BytesIO
+
+url = "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg"
+
+response = requests.get(url)
+init_image = Image.open(BytesIO(response.content)).convert("RGB")
+init_image = init_image.resize((512, 512))
+
+path = "runwayml/stable-diffusion-v1-5"
+
+run_compile = True  # Set True / False
+controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", torch_dtype=torch.float16)
+pipe = StableDiffusionControlNetPipeline.from_pretrained(
+    path, controlnet=controlnet, torch_dtype=torch.float16
+)
+
+pipe = pipe.to("cuda")
+pipe.unet.to(memory_format=torch.channels_last)
+pipe.controlnet.to(memory_format=torch.channels_last)
+
+if run_compile:
+    print("Run torch compile")
+    pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+    pipe.controlnet = torch.compile(pipe.controlnet, mode="reduce-overhead", fullgraph=True)
+
+prompt = "ghibli style, a fantasy landscape with castles"
+
+for _ in range(3):
+    image = pipe(prompt=prompt, image=init_image).images[0]
+```
+
+#### IF text-to-image + upscaling
+
+```python 
+from diffusers import DiffusionPipeline
+import torch
+
+run_compile = True  # Set True / False
+
+pipe = DiffusionPipeline.from_pretrained("DeepFloyd/IF-I-M-v1.0", variant="fp16", text_encoder=None, torch_dtype=torch.float16)
+pipe.to("cuda")
+pipe_2 = DiffusionPipeline.from_pretrained("DeepFloyd/IF-II-M-v1.0", variant="fp16", text_encoder=None, torch_dtype=torch.float16)
+pipe_2.to("cuda")
+pipe_3 = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-x4-upscaler", torch_dtype=torch.float16)
+pipe_3.to("cuda")
 
 
-(1) Batch Size >= 32 requires enable_vae_slicing() because of https://github.com/pytorch/pytorch/issues/81665.
-This is required for PyTorch 1.13.1, and also for PyTorch 2.0 and large batch sizes.
+pipe.unet.to(memory_format=torch.channels_last)
+pipe_2.unet.to(memory_format=torch.channels_last)
+pipe_3.unet.to(memory_format=torch.channels_last)
 
-For more details about how this benchmark was run, please refer to [this PR](https://github.com/huggingface/diffusers/pull/2303) and to [the blog post](https://pytorch.org/blog/accelerated-diffusers-pt-20/).
+if run_compile:
+    pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+    pipe_2.unet = torch.compile(pipe_2.unet, mode="reduce-overhead", fullgraph=True)
+    pipe_3.unet = torch.compile(pipe_3.unet, mode="reduce-overhead", fullgraph=True)
+
+prompt = "the blue hulk"
+
+prompt_embeds = torch.randn((1, 2, 4096), dtype=torch.float16)
+neg_prompt_embeds = torch.randn((1, 2, 4096), dtype=torch.float16)
+
+for _ in range(3):
+    image = pipe(prompt_embeds=prompt_embeds, negative_prompt_embeds=neg_prompt_embeds, output_type="pt").images
+    image_2 = pipe_2(image=image, prompt_embeds=prompt_embeds, negative_prompt_embeds=neg_prompt_embeds, output_type="pt").images
+    image_3 = pipe_3(prompt=prompt, image=image, noise_level=100).images
+```
+
+To give you a pictorial overview of the possible speed-ups that can be obtained with PyTorch 2.0 and `torch.compile()`,
+here is a plot that shows relative speed-ups for the [Stable Diffusion text-to-image pipeline](StableDiffusionPipeline) across five
+different GPU families (with a batch size of 4):
+
+![t2i_speedup](https://huggingface.co/datasets/diffusers/docs-images/resolve/main/pt2_benchmarks/t2i_speedup.png)
+
+To give you an even better idea of how this speed-up holds for the other pipelines presented above, consider the following 
+plot that shows the benchmarking numbers from an A100 across three different batch sizes
+(with PyTorch 2.0 nightly and `torch.compile()`):
+
+![a100_numbers](https://huggingface.co/datasets/diffusers/docs-images/resolve/main/pt2_benchmarks/a100_numbers.png)
+
+_(Our benchmarking metric for the plots above is **number of iterations/second**)_
+
+But we reveal all the benchmarking numbers in the interest of transparency! 
+
+In the following tables, we report our findings in terms of the number of **_iterations processed per second_**. 
+
+### A100 (batch size: 1)
+
+| **Pipeline** | **torch 2.0 - <br>no compile** | **torch nightly - <br>no compile** | **torch 2.0 - <br>compile** | **torch nightly - <br>compile** |
+|:---:|:---:|:---:|:---:|:---:|
+| SD - txt2img | 21.66 | 23.13 | 44.03 | 49.74 |
+| SD - img2img | 21.81 | 22.40 | 43.92 | 46.32 |
+| SD - inpaint | 22.24 | 23.23 | 43.76 | 49.25 |
+| SD - controlnet | 15.02 | 15.82 | 32.13 | 36.08 |
+| IF | 20.21 / <br>13.84 / <br>24.00 | 20.12 / <br>13.70 / <br>24.03 | ❌ | 97.34 / <br>27.23 / <br>111.66 |
+
+### A100 (batch size: 4)
+
+| **Pipeline** | **torch 2.0 - <br>no compile** | **torch nightly - <br>no compile** | **torch 2.0 - <br>compile** | **torch nightly - <br>compile** |
+|:---:|:---:|:---:|:---:|:---:|
+| SD - txt2img | 11.6 | 13.12 | 14.62 | 17.27 |
+| SD - img2img | 11.47 | 13.06 | 14.66 | 17.25 |
+| SD - inpaint | 11.67 | 13.31 | 14.88 | 17.48 |
+| SD - controlnet | 8.28 | 9.38 | 10.51 | 12.41 |
+| IF | 25.02 | 18.04 | ❌ | 48.47 |
+
+### A100 (batch size: 16)
+
+| **Pipeline** | **torch 2.0 - <br>no compile** | **torch nightly - <br>no compile** | **torch 2.0 - <br>compile** | **torch nightly - <br>compile** |
+|:---:|:---:|:---:|:---:|:---:|
+| SD - txt2img | 3.04 | 3.6 | 3.83 | 4.68 |
+| SD - img2img | 2.98 | 3.58 | 3.83 | 4.67 |
+| SD - inpaint | 3.04 | 3.66 | 3.9 | 4.76 |
+| SD - controlnet | 2.15 | 2.58 | 2.74 | 3.35 |
+| IF | 8.78 | 9.82 | ❌ | 16.77 |
+
+### V100 (batch size: 1)
+
+| **Pipeline** | **torch 2.0 - <br>no compile** | **torch nightly - <br>no compile** | **torch 2.0 - <br>compile** | **torch nightly - <br>compile** |
+|:---:|:---:|:---:|:---:|:---:|
+| SD - txt2img | 18.99 | 19.14 | 20.95 | 22.17 |
+| SD - img2img | 18.56 | 19.18 | 20.95 | 22.11 |
+| SD - inpaint | 19.14 | 19.06 | 21.08 | 22.20 |
+| SD - controlnet | 13.48 | 13.93 | 15.18 | 15.88 |
+| IF |  20.01 / <br>9.08 / <br>23.34 | 19.79 / <br>8.98 / <br>24.10 | ❌ | 55.75 / <br>11.57 / <br>57.67 |
+
+### V100 (batch size: 4)
+
+| **Pipeline** | **torch 2.0 - <br>no compile** | **torch nightly - <br>no compile** | **torch 2.0 - <br>compile** | **torch nightly - <br>compile** |
+|:---:|:---:|:---:|:---:|:---:|
+| SD - txt2img | 5.96 | 5.89 | 6.83 | 6.86 |
+| SD - img2img | 5.90 | 5.91 | 6.81 | 6.82 |
+| SD - inpaint | 5.99 | 6.03 | 6.93 | 6.95 |
+| SD - controlnet | 4.26 | 4.29 | 4.92 | 4.93 |
+| IF | 15.41 | 14.76 | ❌ | 22.95 |
+
+### V100 (batch size: 16)
+
+| **Pipeline** | **torch 2.0 - <br>no compile** | **torch nightly - <br>no compile** | **torch 2.0 - <br>compile** | **torch nightly - <br>compile** |
+|:---:|:---:|:---:|:---:|:---:|
+| SD - txt2img | 1.66 | 1.66 | 1.92 | 1.90 |
+| SD - img2img | 1.65 | 1.65 | 1.91 | 1.89 |
+| SD - inpaint | 1.69 | 1.69 | 1.95 | 1.93 |
+| SD - controlnet | 1.19 | 1.19 | OOM after warmup | 1.36 |
+| IF | 5.43 | 5.29 | ❌ | 7.06 |
+
+### T4 (batch size: 1)
+
+| **Pipeline** | **torch 2.0 - <br>no compile** | **torch nightly - <br>no compile** | **torch 2.0 - <br>compile** | **torch nightly - <br>compile** |
+|:---:|:---:|:---:|:---:|:---:|
+| SD - txt2img | 6.9 | 6.95 | 7.3 | 7.56 |
+| SD - img2img | 6.84 | 6.99 | 7.04 | 7.55 |
+| SD - inpaint | 6.91 | 6.7 | 7.01 | 7.37 |
+| SD - controlnet | 4.89 | 4.86 | 5.35 | 5.48 |
+| IF | 17.42 / <br>2.47 / <br>18.52 | 16.96 / <br>2.45 / <br>18.69 | ❌ | 24.63 / <br>2.47 / <br>23.39 |
+
+### T4 (batch size: 4)
+
+| **Pipeline** | **torch 2.0 - <br>no compile** | **torch nightly - <br>no compile** | **torch 2.0 - <br>compile** | **torch nightly - <br>compile** |
+|:---:|:---:|:---:|:---:|:---:|
+| SD - txt2img | 1.79 | 1.79 | 2.03 | 1.99 |
+| SD - img2img | 1.77 | 1.77 | 2.05 | 2.04 |
+| SD - inpaint | 1.81 | 1.82 | 2.09 | 2.09 |
+| SD - controlnet | 1.34 | 1.27 | 1.47 | 1.46 |
+| IF | 5.79 |  5.61 | ❌ | 7.39 |
+
+### T4 (batch size: 16)
+
+| **Pipeline** | **torch 2.0 - <br>no compile** | **torch nightly - <br>no compile** | **torch 2.0 - <br>compile** | **torch nightly - <br>compile** |
+|:---:|:---:|:---:|:---:|:---:|
+| SD - txt2img | 2.34s | 2.30s | OOM after 2nd iteration | 1.99s |
+| SD - img2img | 2.35s | 2.31s | OOM after warmup | 2.00s |
+| SD - inpaint | 2.30s | 2.26s | OOM after 2nd iteration | 1.95s |
+| SD - controlnet | OOM after 2nd iteration | OOM after 2nd iteration | OOM after warmup | OOM after warmup |
+| IF * | 1.44 | 1.44 | ❌ | 1.94 |
+
+### RTX 3090 (batch size: 1)
+
+| **Pipeline** | **torch 2.0 - <br>no compile** | **torch nightly - <br>no compile** | **torch 2.0 - <br>compile** | **torch nightly - <br>compile** |
+|:---:|:---:|:---:|:---:|:---:|
+| SD - txt2img | 22.56 | 22.84 | 23.84 | 25.69 |
+| SD - img2img | 22.25 | 22.61 | 24.1 | 25.83 |
+| SD - inpaint | 22.22 | 22.54 | 24.26 | 26.02 |
+| SD - controlnet | 16.03 | 16.33 | 17.38 | 18.56 |
+| IF | 27.08 / <br>9.07 / <br>31.23 | 26.75 / <br>8.92 / <br>31.47 | ❌ | 68.08 / <br>11.16 / <br>65.29 |
+
+### RTX 3090 (batch size: 4)
+
+| **Pipeline** | **torch 2.0 - <br>no compile** | **torch nightly - <br>no compile** | **torch 2.0 - <br>compile** | **torch nightly - <br>compile** |
+|:---:|:---:|:---:|:---:|:---:|
+| SD - txt2img | 6.46 | 6.35 | 7.29 | 7.3 |
+| SD - img2img | 6.33 | 6.27 | 7.31 | 7.26 |
+| SD - inpaint | 6.47 | 6.4 | 7.44 | 7.39 |
+| SD - controlnet | 4.59 | 4.54 | 5.27 | 5.26 |
+| IF | 16.81 | 16.62 | ❌ | 21.57 |
+
+### RTX 3090 (batch size: 16)
+
+| **Pipeline** | **torch 2.0 - <br>no compile** | **torch nightly - <br>no compile** | **torch 2.0 - <br>compile** | **torch nightly - <br>compile** |
+|:---:|:---:|:---:|:---:|:---:|
+| SD - txt2img | 1.7 | 1.69 | 1.93 | 1.91 |
+| SD - img2img | 1.68 | 1.67 | 1.93 | 1.9 |
+| SD - inpaint | 1.72 | 1.71 | 1.97 | 1.94 |
+| SD - controlnet | 1.23 | 1.22 | 1.4 | 1.38 |
+| IF | 5.01 | 5.00 | ❌ | 6.33 |
+
+### RTX 4090 (batch size: 1)
+
+| **Pipeline** | **torch 2.0 - <br>no compile** | **torch nightly - <br>no compile** | **torch 2.0 - <br>compile** | **torch nightly - <br>compile** |
+|:---:|:---:|:---:|:---:|:---:|
+| SD - txt2img | 40.5 | 41.89 | 44.65 | 49.81 |
+| SD - img2img | 40.39 | 41.95 | 44.46 | 49.8 |
+| SD - inpaint | 40.51 | 41.88 | 44.58 | 49.72 |
+| SD - controlnet | 29.27 | 30.29 | 32.26 | 36.03 |
+| IF | 69.71 / <br>18.78 / <br>85.49 | 69.13 / <br>18.80 / <br>85.56 | ❌ | 124.60 / <br>26.37 / <br>138.79 |
+
+### RTX 4090 (batch size: 4)
+
+| **Pipeline** | **torch 2.0 - <br>no compile** | **torch nightly - <br>no compile** | **torch 2.0 - <br>compile** | **torch nightly - <br>compile** |
+|:---:|:---:|:---:|:---:|:---:|
+| SD - txt2img | 12.62 | 12.84 | 15.32 | 15.59 |
+| SD - img2img | 12.61 | 12,.79 | 15.35 | 15.66 |
+| SD - inpaint | 12.65 | 12.81 | 15.3 | 15.58 |
+| SD - controlnet | 9.1 | 9.25 | 11.03 | 11.22 |
+| IF | 31.88 | 31.14 | ❌ | 43.92 |
+
+### RTX 4090 (batch size: 16)
+
+| **Pipeline** | **torch 2.0 - <br>no compile** | **torch nightly - <br>no compile** | **torch 2.0 - <br>compile** | **torch nightly - <br>compile** |
+|:---:|:---:|:---:|:---:|:---:|
+| SD - txt2img | 3.17 | 3.2 | 3.84 | 3.85 |
+| SD - img2img | 3.16 | 3.2 | 3.84 | 3.85 |
+| SD - inpaint | 3.17 | 3.2 | 3.85 | 3.85 |
+| SD - controlnet | 2.23 | 2.3 | 2.7 | 2.75 |
+| IF | 9.26 | 9.2 | ❌ | 13.31 |
+
+## Notes 
+
+* Follow [this PR](https://github.com/huggingface/diffusers/pull/3313) for more details on the environment used for conducting the benchmarks. 
+* For the IF pipeline and batch sizes > 1, we only used a batch size of >1 in the first IF pipeline for text-to-image generation and NOT for upscaling. So, that means the two upscaling pipelines received a batch size of 1. 
+
+*Thanks to [Horace He](https://github.com/Chillee) from the PyTorch team for their support in improving our support of `torch.compile()` in Diffusers.*

docs/source/en/quicktour.mdx

@@ -33,7 +33,7 @@ The quicktour is a simplified version of the introductory 🧨 Diffusers [notebo
 Before you begin, make sure you have all the necessary libraries installed:
 
 ```bash
-pip install --upgrade diffusers accelerate transformers
+!pip install --upgrade diffusers accelerate transformers
 ```
 
 - [🤗 Accelerate](https://huggingface.co/docs/accelerate/index) speeds up model loading for inference and training.
@@ -121,9 +121,9 @@ Save the image by calling `save`:
 
 You can also use the pipeline locally. The only difference is you need to download the weights first:
 
-```
-git lfs install
-git clone https://huggingface.co/runwayml/stable-diffusion-v1-5
+```bash
+!git lfs install
+!git clone https://huggingface.co/runwayml/stable-diffusion-v1-5
 ```
 
 Then load the saved weights into the pipeline:

docs/source/en/stable_diffusion.mdx

@@ -1,333 +1,271 @@
-<!--Copyright 2023 The HuggingFace Team. All rights reserved.                                                                                                                                                                                 
-                                                                                                                                                                                                                                              
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with                                                                                                                           
-the License. You may obtain a copy of the License at                                                                                                                                                                                          
-                                                                                                                                                                                                                                              
-http://www.apache.org/licenses/LICENSE-2.0                                                                                                                                                                                                    
-                                                                                                                                                                                                                                              
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on                                                                                                                           
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the                                                                                                                            
-specific language governing permissions and limitations under the License.                                                                                                                                                                    
--->                                                                                                                                                                                                                                           
-                                                                                                                                                                                                                                              
-# The Stable Diffusion Guide 🎨                                                                                                                                                                                                           
-<a target="_blank" href="https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_101_guide.ipynb">                                                                                                                                                                                                                                                                                                                                                            
-    <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>                                                                                                                                                 
-</a>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    
-
-## Intro                                                                                                                                                                                                                                                                                                                                                                                                                                                                                
-
-Stable Diffusion is a [Latent Diffusion model](https://github.com/CompVis/latent-diffusion) developed by researchers from the Machine Vision and Learning group at LMU Munich, *a.k.a* CompVis.                                                                                                                                                                                                                                                                                             
-Model checkpoints were publicly released at the end of August 2022 by a collaboration of Stability AI, CompVis, and Runway with support from EleutherAI and LAION. For more information, you can check out [the official blog post](https://stability.ai/blog/stable-diffusion-public-release).                                                                                                                                                                                                  
-                                                                                                                                                                                                                                              
-Since its public release the community has done an incredible job at working together to make the stable diffusion checkpoints **faster**, **more memory efficient**, and **more performant**.                                                                                                                                                                                                                                                                                              
-                                                                                                                                                                                                                                              
-🧨 Diffusers offers a simple API to run stable diffusion with all memory, computing, and quality improvements.                                                                                                                                   
-                                                                                                                                                                                                                                              
-This notebook walks you through the improvements one-by-one so you can best leverage [`StableDiffusionPipeline`] for **inference**.                                                                                                          
-                                                                                                                                                                                                                                              
-## Prompt Engineering 🎨                                                                                                                                                                                                                      
-                                                                                                                                                                                                                                              
-When running *Stable Diffusion* in inference, we usually want to generate a certain type, or style of image and then improve upon it. Improving upon a previously generated image means running inference over and over again with a different prompt and potentially a different seed until we are happy with our generation.                                                                                                                                                                 
-
-So to begin with, it is most important to speed up stable diffusion as much as possible to generate as many pictures as possible in a given amount of time.                                                                                   
-
-This can be done by both improving the **computational efficiency** (speed) and the **memory efficiency** (GPU RAM).                                                                                                                          
-
-Let's start by looking into computational efficiency first.                                                                                                                                                                               
-
-Throughout the notebook, we will focus on [runwayml/stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5):                                                                                                           
-
-``` python                                                                                                                                                                                                                                    
-model_id = "runwayml/stable-diffusion-v1-5"                                                                                                                                                                                                   
-```                                                                                                                                                                                                                                           
-
-Let's load the pipeline.                                                                                                                                                                                                                      
-
-## Speed Optimization                                                                                                                                                                                                                                                                                                                                                                                                                                                                       
-
-``` python                                                                                                                                                                                                                                    
-from diffusers import DiffusionPipeline                                                                                                                                                                                                 
-                                                                                                                                                                                                                                              
-pipe = DiffusionPipeline.from_pretrained(model_id)                                                                                                                                                                                      
-```                                                                                                                                                                                                                                           
-                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            
-We aim at generating a beautiful photograph of an *old warrior chief* and will later try to find the best prompt to generate such a photograph. For now, let's keep the prompt simple:                                                                                                                                                                                                                                                                                                      
-                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            
-``` python                                                                                                                                                                                                                                    
-prompt = "portrait photo of a old warrior chief"                                                                                                                                                                                                                                                                                                                                                                                                                                            
-```                                                                                                                                                                                                                                           
-                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            
-To begin with, we should make sure we run inference on GPU, so let's move the pipeline to GPU, just like you would with any PyTorch module.                                                                                                   
-                                                                                                                                                                                                                                              
-``` python                                                                                                                                                                                                                                    
-pipe = pipe.to("cuda")                                                                                                                                                                                                                                                                                                                                                                                                                                                                      
-```                                                                                                                                                                                                                                           
-                                                                                                                                                                                                                                              
-To generate an image, you should use the [~`StableDiffusionPipeline.__call__`] method.                                                                                                                                                        
-                                                                                                                                                                                                                                              
-To make sure we can reproduce more or less the same image in every call, let's make use of the generator. See the documentation on reproducibility [here](./conceptual/reproducibility) for more information.                                                                                                                                                                                                                                                                                   
-
-``` python                                                                                                                                                                                                                                    
-generator = torch.Generator("cuda").manual_seed(0)                                                                                                                                                                                            
-```                                                                                                                                                                                                                                           
-                                                                                                                                                                                                                                              
-Now, let's take a spin on it.                                                                                                                                                                                                                 
-                                                                                                                                                                                                                                              
-``` python                                                                                                                                                                                                                                    
-image = pipe(prompt, generator=generator).images[0]                                                                                                                                                                                           
-image                                                                                                                                                                                                                                         
-```                                                                                                                                                                                                                                           
-
-![img](https://huggingface.co/datasets/diffusers/docs-images/resolve/main/stable_diffusion_101/sd_101_1.png)                                                                                                                                  
-                                                                                                                                                                                                                                              
-Cool, this now took roughly 30 seconds on a T4 GPU (you might see faster inference if your allocated GPU is better than a T4).                                                                                                              
-                                                                                                                                                                                                                                              
-The default run we did above used full float32 precision and ran the default number of inference steps (50). The easiest speed-ups come from switching to float16 (or half) precision and simply running fewer inference steps. Let's load the model now in float16 instead.                                                                                                                                                                                                                            
-                                                                                                                                                                                                                                              
-``` python                                                                                                                                                                                                                                    
-import torch                                                                                                                                                                                                                                  
-
-pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)                                                                                                                                                           
-pipe = pipe.to("cuda")                                                                                                                                                                                                                        
-```                                                                                                                                                                                                                                           
-
-And we can again call the pipeline to generate an image.                                                                                                                                                                                      
-
-``` python                                                                                                                                                                                                                                    
-generator = torch.Generator("cuda").manual_seed(0)                                                                                                                                                                                            
-
-image = pipe(prompt, generator=generator).images[0]                                                                                                                                                                                           
-image                                                                                                                                                                                                                                         
-```                                                                                                                                                                                                                                           
-![img](https://huggingface.co/datasets/diffusers/docs-images/resolve/main/stable_diffusion_101/sd_101_2.png)                                                                                                                                  
-
-Cool, this is almost three times as fast for arguably the same image quality.                                                                                                                                                           
-                                                                                                                                                                                                                                              
-We strongly suggest always running your pipelines in float16 as so far we have very rarely seen degradations in quality because of it.                                                                                                         
-
-Next, let's see if we need to use 50 inference steps or whether we could use significantly fewer. The number of inference steps is associated with the denoising scheduler we use. Choosing a more efficient scheduler could help us decrease the number of steps.
-
-Let's have a look at all the schedulers the stable diffusion pipeline is compatible with.                                                                                                                                                        
-                                                                                                                                                                                                                                              
-``` python                                                                                                                                                                                                                                    
-pipe.scheduler.compatibles                                                                                                                                                                                                                    
-```                                                                                                                                                                                                                                           
-                                                                                                                                                                                                                                              
-```                                                                                                                                                                                                                                           
-    [diffusers.schedulers.scheduling_dpmsolver_singlestep.DPMSolverSinglestepScheduler,                                                                                                                                                       
-     diffusers.schedulers.scheduling_lms_discrete.LMSDiscreteScheduler,                                                                                                                                                                       
-     diffusers.schedulers.scheduling_heun_discrete.HeunDiscreteScheduler,                                                                                                                                                                     
-     diffusers.schedulers.scheduling_pndm.PNDMScheduler,                                                                                                                                                                                      
-     diffusers.schedulers.scheduling_euler_discrete.EulerDiscreteScheduler,                                                                                                                                                                   
-     diffusers.schedulers.scheduling_euler_ancestral_discrete.EulerAncestralDiscreteScheduler,                                                                                                                                                
-     diffusers.schedulers.scheduling_dpmsolver_multistep.DPMSolverMultistepScheduler,                                                                                                                                                         
-     diffusers.schedulers.scheduling_ddpm.DDPMScheduler,                                                                                                                                                                                      
-     diffusers.schedulers.scheduling_ddim.DDIMScheduler]                                                                                                                                                                                      
-```                                                                                                                                                                                                                                           
-
-Cool, that's a lot of schedulers.                                                                                                                                                                                                                                                                                                                                                                                                                                                           
-
-🧨 Diffusers is constantly adding a bunch of novel schedulers/samplers that can be used with Stable Diffusion. For more information, we recommend taking a look at the official documentation [here](https://huggingface.co/docs/diffusers/main/en/api/schedulers/overview).                                                                                                                                                                                                              
-                                                                                                                                                                                                                                              
-Alright, right now Stable Diffusion is using the `PNDMScheduler` which usually requires around 50 inference steps. However, other schedulers such as `DPMSolverMultistepScheduler` or `DPMSolverSinglestepScheduler` seem to get away with just 20 to 25 inference steps. Let's try them out.                                                                                                                                                                                               
-                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            
-You can set a new scheduler by making use of the [from_config](https://huggingface.co/docs/diffusers/main/en/api/configuration#diffusers.ConfigMixin.from_config) function.                                                                                                                                                                                                                                                                                                                 
-                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            
-``` python                                                                                                                                                                                                                                    
-from diffusers import DPMSolverMultistepScheduler                                                                                                                                                                                             
-                                                                                                                                                                                                                                              
-pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)                                                                                                                                                               
-```                                                                                                                                                                                                                                           
-                                                                                                                                                                                                                                              
-Now, let's try to reduce the number of inference steps to just 20.                                                                                                                                                                            
-
-``` python                                                                                                                                                                                                                                    
-generator = torch.Generator("cuda").manual_seed(0)                                                                                                                                                                                            
-                                                                                                                                                                                                                                              
-image = pipe(prompt, generator=generator, num_inference_steps=20).images[0]                                                                                                                                                                   
-image                                                                                                                                                                                                                                         
-```                                                                                                                                                                                                                                           
-                                                                                                                                                                                                                                              
-![img](https://huggingface.co/datasets/diffusers/docs-images/resolve/main/stable_diffusion_101/sd_101_3.png)                                                                                                                                                                                                                                                                                                                                                                                
-                                                                                                                                                                                                                                              
-The image now does look a little different, but it's arguably still of equally high quality. We now cut inference time to just 4 seconds though 😍. 
-
-## Memory Optimization                                                                                                                                                                                                                        
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
-Less memory used in generation indirectly implies more speed, since we're often trying to maximize how many images we can generate per second. Usually, the more images per inference run, the more images per second too.                                                                                                                                              
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
 
-The easiest way to see how many images we can generate at once is to simply try it out, and see when we get a *"Out-of-memory (OOM)"* error.                                                                                                          
+http://www.apache.org/licenses/LICENSE-2.0
 
-We can run batched inference by simply passing a list of prompts and generators. Let's define a quick function that generates a batch for us.                                                                                                
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+                                                               
+# Effective and efficient diffusion
 
-``` python                                                                                                                                                                                                                                    
-def get_inputs(batch_size=1):                                                                                                                                                                                                                 
-  generator = [torch.Generator("cuda").manual_seed(i) for i in range(batch_size)]                                                                                                                                                             
-  prompts = batch_size * [prompt]                                                                                                                                                                                                             
-  num_inference_steps = 20                                                                                                                                                                                                                    
+[[open-in-colab]]
 
-  return {"prompt": prompts, "generator": generator, "num_inference_steps": num_inference_steps}                                                                                                                                              
-```                                                                                                                                                                                                                                           
-This function returns a list of prompts and a list of generators, so we can reuse the generator that produced a result we like.
+Getting the [`DiffusionPipeline`] to generate images in a certain style or include what you want can be tricky. Often times, you have to run the [`DiffusionPipeline`] several times before you end up with an image you're happy with. But generating something out of nothing is a computationally intensive process, especially if you're running inference over and over again. 
 
-We also need a method that allows us to easily display a batch of images.                                                                                                                                                                     
+This is why it's important to get the most *computational* (speed) and *memory* (GPU RAM) efficiency from the pipeline to reduce the time between inference cycles so you can iterate faster.
 
-``` python                                                                                                                                                                                                                                    
-from PIL import Image                                                                                                                                                                                                                         
+This tutorial walks you through how to generate faster and better with the [`DiffusionPipeline`].
 
-def image_grid(imgs, rows=2, cols=2):                                                                                                                                                                                                         
-    w, h = imgs[0].size                                                                                                                                                                                                                       
-    grid = Image.new('RGB', size=(cols*w, rows*h))                                                                                                                                                                                            
-                                                                                                                                                                                                                                              
-    for i, img in enumerate(imgs):                                                                                                                                                                                                            
-        grid.paste(img, box=(i%cols*w, i//cols*h))                                                                                                                                                                                            
-    return grid                                                                                                                                                                                                                               
-```                                                                                                                                                                                                                                           
+Begin by loading the [`runwayml/stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5) model:
 
-Cool, let's see how much memory we can use starting with `batch_size=4`.                                                                                                                                                                      
+```python
+from diffusers import DiffusionPipeline
 
-``` python                                                                                                                                                                                                                                    
-images = pipe(**get_inputs(batch_size=4)).images                                                                                                                                                                                              
-image_grid(images)                                                                                                                                                                                                                            
-```                                                                                                                                                                                                                                           
+model_id = "runwayml/stable-diffusion-v1-5"
+pipeline = DiffusionPipeline.from_pretrained(model_id)
+```
 
-![img](https://huggingface.co/datasets/diffusers/docs-images/resolve/main/stable_diffusion_101/sd_101_4.png)                                                                                                                                  
+The example prompt you'll use is a portrait of an old warrior chief, but feel free to use your own prompt:
 
-Going over a batch_size of 4 will error out in this notebook (assuming we are running it on a T4 GPU). Also, we can see we only generate slightly more images per second (3.75s/image) compared to 4s/image previously.                                                                                                                                                                                                                                                                                                                   
+```python
+prompt = "portrait photo of a old warrior chief"
+```
 
-However, the community has found some nice tricks to improve the memory constraints further. After stable diffusion was released, the community found improvements within days and shared them freely over GitHub - open-source at its finest! I believe the original idea came from [this](https://github.com/basujindal/stable-diffusion/pull/117) GitHub thread.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    
+## Speed
 
-By far most of the memory is taken up by the cross-attention layers. Instead of running this operation in batch, one can run it sequentially to save a significant amount of memory.                                                                                                                                                                                                                                                                                                         
+<Tip>
 
-It can easily be enabled by calling `enable_attention_slicing` as is documented [here](https://huggingface.co/docs/diffusers/main/en/api/pipelines/stable_diffusion/text2img#diffusers.StableDiffusionPipeline.enable_attention_slicing).                                                                                                                                                                                                                                                   
+💡 If you don't have access to a GPU, you can use one for free from a GPU provider like [Colab](https://colab.research.google.com/)!
 
-``` python                                                                                                                                                                                                                                    
-pipe.enable_attention_slicing()                                                                                                                                                                                                               
-```                                                                                                                                                                                                                                           
+</Tip>
 
-Great, now that attention slicing is enabled, let's try to double the batch size again, going for `batch_size=8`.                                                                                                                              
+One of the simplest ways to speed up inference is to place the pipeline on a GPU the same way you would with any PyTorch module:
 
-``` python                                                                                                                                                                                                                                    
-images = pipe(**get_inputs(batch_size=8)).images                                                                                                                                                                                              
-image_grid(images, rows=2, cols=4)                                                                                                                                                                                                            
-```                                                                                                                                                                                                                                           
+```python
+pipeline = pipeline.to("cuda")
+```
 
-![img](https://huggingface.co/datasets/diffusers/docs-images/resolve/main/stable_diffusion_101/sd_101_5.png)                                                                                                                                  
+To make sure you can use the same image and improve on it, use a [`Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) and set a seed for [reproducibility](./using-diffusers/reproducibility):
 
-Nice, it works. However, the speed gain is again not very big (it might however be much more significant on other GPUs).                                                                                                                      
+```python
+generator = torch.Generator("cuda").manual_seed(0)
+```
 
-We're at roughly 3.5 seconds per image 🔥 which is probably the fastest we can be with a simple T4 without sacrificing quality.                                                                                                               
+Now you can generate an image:
 
-Next, let's look into how to improve the quality!                                                                                                                                                                                             
+```python
+image = pipeline(prompt, generator=generator).images[0]
+image
+```
 
-## Quality Improvements                                                                                                                                                                                                                       
+<div class="flex justify-center">
+    <img src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/stable_diffusion_101/sd_101_1.png">
+</div>
 
-Now that our image generation pipeline is blazing fast, let's try to get maximum image quality.                                                                                                                                               
+This process took ~30 seconds on a T4 GPU (it might be faster if your allocated GPU is better than a T4). By default, the [`DiffusionPipeline`] runs inference with full `float32` precision for 50 inference steps. You can speed this up by switching to a lower precision like `float16` or running fewer inference steps. 
 
-First of all, image quality is extremely subjective, so it's difficult to make general claims here.                                                                                                                                           
+Let's start by loading the model in `float16` and generate an image:
 
-The most obvious step to take to improve quality is to use *better checkpoints*. Since the release of Stable Diffusion, many improved versions have been released, which are summarized here:                                                                                                                                                                                                                                                                                                
+```python
+import torch
 
--   *Official Release - 22 Aug 2022*: [Stable-Diffusion 1.4](https://huggingface.co/CompVis/stable-diffusion-v1-4)                                                                                                                            
--   *20 October 2022*: [Stable-Diffusion 1.5](https://huggingface.co/runwayml/stable-diffusion-v1-5)                                                                                                                                          
--   *24 Nov 2022*: [Stable-Diffusion 2.0](https://huggingface.co/stabilityai/stable-diffusion-2-0)                                                                                                                                            
--   *7 Dec 2022*: [Stable-Diffusion 2.1](https://huggingface.co/stabilityai/stable-diffusion-2-1)                                                                                                                                             
+pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+pipeline = pipeline.to("cuda")
+generator = torch.Generator("cuda").manual_seed(0)
+image = pipeline(prompt, generator=generator).images[0]
+image
+```
 
-Newer versions don't necessarily mean better image quality with the same parameters. People mentioned that *2.0* is slightly worse than *1.5* for certain prompts, but given the right prompt engineering *2.0* and *2.1* seem to be better.                                                                                                                                                                                                                                                 
+<div class="flex justify-center">
+    <img src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/stable_diffusion_101/sd_101_2.png">
+</div>
 
-Overall, we strongly recommend just trying the models out and reading up on advice online (e.g. it has been shown that using negative prompts is very important for 2.0 and 2.1 to get the highest possible quality. See for example [this nice blog post](https://minimaxir.com/2022/11/stable-diffusion-negative-prompt/).                                                                                                                                                                   
+This time, it only took ~11 seconds to generate the image, which is almost 3x faster than before!
 
-Additionally, the community has started fine-tuning many of the above versions on certain styles with some of them having an extremely high quality and gaining a lot of traction.                                                                                                                                                                                                                                                                                                          
+<Tip>
 
-We recommend having a look at all [diffusers checkpoints sorted by downloads and trying out the different checkpoints](https://huggingface.co/models?library=diffusers).                                                                                                                                                                                                                                                                                                               
+💡 We strongly suggest always running your pipelines in `float16`, and so far, we've rarely seen any degradation in output quality.
 
-For the following, we will stick to v1.5 for simplicity.                                                                                                                                                                                      
+</Tip>
 
-Next, we can also try to optimize single components of the pipeline, e.g. switching out the latent decoder. For more details on how the whole Stable Diffusion pipeline works, please have a look at [this blog post](https://huggingface.co/blog/stable_diffusion).                                                                                                                                                                                                                        
+Another option is to reduce the number of inference steps. Choosing a more efficient scheduler could help decrease the number of steps without sacrificing output quality. You can find which schedulers are compatible with the current model in the [`DiffusionPipeline`] by calling the `compatibles` method:
 
-Let's load [stabilityai's newest auto-decoder](https://huggingface.co/stabilityai/stable-diffusion-2-1).                                                                                                                                      
+```python
+pipeline.scheduler.compatibles
+[
+    diffusers.schedulers.scheduling_lms_discrete.LMSDiscreteScheduler,
+    diffusers.schedulers.scheduling_unipc_multistep.UniPCMultistepScheduler,
+    diffusers.schedulers.scheduling_k_dpm_2_discrete.KDPM2DiscreteScheduler,
+    diffusers.schedulers.scheduling_deis_multistep.DEISMultistepScheduler,
+    diffusers.schedulers.scheduling_euler_discrete.EulerDiscreteScheduler,
+    diffusers.schedulers.scheduling_dpmsolver_multistep.DPMSolverMultistepScheduler,
+    diffusers.schedulers.scheduling_ddpm.DDPMScheduler,
+    diffusers.schedulers.scheduling_dpmsolver_singlestep.DPMSolverSinglestepScheduler,
+    diffusers.schedulers.scheduling_k_dpm_2_ancestral_discrete.KDPM2AncestralDiscreteScheduler,
+    diffusers.schedulers.scheduling_heun_discrete.HeunDiscreteScheduler,
+    diffusers.schedulers.scheduling_pndm.PNDMScheduler,
+    diffusers.schedulers.scheduling_euler_ancestral_discrete.EulerAncestralDiscreteScheduler,
+    diffusers.schedulers.scheduling_ddim.DDIMScheduler,
+]
+```
 
-``` python                                                                                                                                                                                                                                    
-from diffusers import AutoencoderKL                                                                                                                                                                                                           
+The Stable Diffusion model uses the [`PNDMScheduler`] by default which usually requires ~50 inference steps, but more performant schedulers like [`DPMSolverMultistepScheduler`], require only ~20 or 25 inference steps. Use the [`ConfigMixin.from_config`] method to load a new scheduler:
 
-vae = AutoencoderKL.from_pretrained("stabilityai/sd-vae-ft-mse", torch_dtype=torch.float16).to("cuda")                                                                                                                                        
-```                                                                                                                                                                                                                                           
+```python
+from diffusers import DPMSolverMultistepScheduler
 
-Now we can set it to the vae of the pipeline to use it.                                                                                                                                                                                       
+pipeline.scheduler = DPMSolverMultistepScheduler.from_config(pipeline.scheduler.config)
+```
 
-``` python                                                                                                                                                                                                                                    
-pipe.vae = vae                                                                                                                                                                                                                                
-```                                                                                                                                                                                                                                           
+Now set the `num_inference_steps` to 20:
 
-Let's run the same prompt as before to compare quality.                                                                                                                                                                                       
+```python
+generator = torch.Generator("cuda").manual_seed(0)
+image = pipeline(prompt, generator=generator, num_inference_steps=20).images[0]
+image
+```
 
-``` python                                                                                                                                                                                                                                    
-images = pipe(**get_inputs(batch_size=8)).images                                                                                                                                                                                              
-image_grid(images, rows=2, cols=4)                                                                                                                                                                                                            
-```                                                                                                                                                                                                                                           
+<div class="flex justify-center">
+    <img src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/stable_diffusion_101/sd_101_3.png">
+</div>
 
-![img](https://huggingface.co/datasets/diffusers/docs-images/resolve/main/stable_diffusion_101/sd_101_6.png)                                                                                                                                  
+Great, you've managed to cut the inference time to just 4 seconds! ⚡️
 
-Seems like the difference is only very minor, but the new generations are arguably a bit *sharper*.                                                                                                                                           
+## Memory
 
-Cool, finally, let's look a bit into prompt engineering.                                                                                                                                                                                      
+The other key to improving pipeline performance is consuming less memory, which indirectly implies more speed, since you're often trying to maximize the number of images generated per second. The easiest way to see how many images you can generate at once is to try out different batch sizes until you get an `OutOfMemoryError` (OOM).
 
-Our goal was to generate a photo of an old warrior chief. Let's now try to bring a bit more color into the photos and make the look more impressive.                                                                                          
+Create a function that'll generate a batch of images from a list of prompts and `Generators`. Make sure to assign each `Generator` a seed so you can reuse it if it produces a good result.
 
-Originally our prompt was "*portrait photo of an old warrior chief*".                                                                                                                                                                          
+```python
+def get_inputs(batch_size=1):
+    generator = [torch.Generator("cuda").manual_seed(i) for i in range(batch_size)]
+    prompts = batch_size * [prompt]
+    num_inference_steps = 20
 
-To improve the prompt, it often helps to add cues that could have been used online to save high-quality photos, as well as add more details.                                                                                         
-Essentially, when doing prompt engineering, one has to think:                                                                                                                                                                                 
+    return {"prompt": prompts, "generator": generator, "num_inference_steps": num_inference_steps}
+```
 
--   How was the photo or similar photos of the one I want probably stored on the internet?                                                                                                                                                    
--   What additional detail can I give that steers the models into the style that I want?                                                                                                                                                      
+You'll also need a function that'll display each batch of images:
 
-Cool, let's add more details.                                                                                                                                                                                                                 
+```python
+from PIL import Image
 
-``` python                                                                                                                                                                                                                                    
-prompt += ", tribal panther make up, blue on red, side profile, looking away, serious eyes"                                                                                                                                                   
-```                                                                                                                                                                                                                                           
 
-and let's also add some cues that usually help to generate higher quality images.                                                                                                                                                             
+def image_grid(imgs, rows=2, cols=2):
+    w, h = imgs[0].size
+    grid = Image.new("RGB", size=(cols * w, rows * h))
 
-``` python                                                                                                                                                                                                                                    
-prompt += " 50mm portrait photography, hard rim lighting photography--beta --ar 2:3  --beta --upbeta"                                                                                                                                         
-prompt                                                                                                                                                                                                                                        
-```                                                                                                                                                                                                                                                                                                                                                                                                                                                                           
+    for i, img in enumerate(imgs):
+        grid.paste(img, box=(i % cols * w, i // cols * h))
+    return grid
+```
 
-Cool, let's now try this prompt.                                                                                                                                                                                                              
+Start with `batch_size=4` and see how much memory you've consumed:
 
-``` python                                                                                                                                                                                                                                    
-images = pipe(**get_inputs(batch_size=8)).images                                                                                                                                                                                              
-image_grid(images, rows=2, cols=4)                                                                                                                                                                                                            
-```                                                                                                                                                                                                                                           
+```python
+images = pipeline(**get_inputs(batch_size=4)).images
+image_grid(images)
+```
 
-![img](https://huggingface.co/datasets/diffusers/docs-images/resolve/main/stable_diffusion_101/sd_101_7.png)                                                                                                                                  
+Unless you have a GPU with more RAM, the code above probably returned an `OOM` error! Most of the memory is taken up by the cross-attention layers. Instead of running this operation in a batch, you can run it sequentially to save a significant amount of memory. All you have to do is configure the pipeline to use the [`~DiffusionPipeline.enable_attention_slicing`] function:
 
-Pretty impressive! We got some very high-quality image generations there. The 2nd image is my personal favorite, so I'll re-use this seed and see whether I can tweak the prompts slightly by using "oldest warrior", "old", "", and "young" instead of "old".                                                                                                                                                                                                                    
+```python
+pipeline.enable_attention_slicing()
+```
 
-``` python                                                                                                                                                                                                                                    
-prompts = [                                                                                                                                                                                                                                   
-    "portrait photo of the oldest warrior chief, tribal panther make up, blue on red, side profile, looking away, serious eyes 50mm portrait photography, hard rim lighting photography--beta --ar 2:3  --beta --upbeta",                                                                                                                                                                                                                                                                   
-    "portrait photo of a old warrior chief, tribal panther make up, blue on red, side profile, looking away, serious eyes 50mm portrait photography, hard rim lighting photography--beta --ar 2:3  --beta --upbeta",                                                                                                                                                                                                                                                                        
-    "portrait photo of a warrior chief, tribal panther make up, blue on red, side profile, looking away, serious eyes 50mm portrait photography, hard rim lighting photography--beta --ar 2:3  --beta --upbeta",                                                                                                                                                                                                                                                                            
-    "portrait photo of a young warrior chief, tribal panther make up, blue on red, side profile, looking away, serious eyes 50mm portrait photography, hard rim lighting photography--beta --ar 2:3  --beta --upbeta",                                                                                                                                                                                                                                                                      
-]                                                                                                                                                                                                                                             
+Now try increasing the `batch_size` to 8!
 
-generator = [torch.Generator("cuda").manual_seed(1) for _ in range(len(prompts))]  # 1 because we want the 2nd image                                                                                                                          
+```python
+images = pipeline(**get_inputs(batch_size=8)).images
+image_grid(images, rows=2, cols=4)
+```
 
-images = pipe(prompt=prompts, generator=generator, num_inference_steps=25).images                                                                                                                                                             
-image_grid(images)                                                                                                                                                                                                                            
-```                                                                                                                                                                                                                                           
+<div class="flex justify-center">
+    <img src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/stable_diffusion_101/sd_101_5.png">
+</div>
 
-![img](https://huggingface.co/datasets/diffusers/docs-images/resolve/main/stable_diffusion_101/sd_101_8.png)                                                                                                                                  
+Whereas before you couldn't even generate a batch of 4 images, now you can generate a batch of 8 images at ~3.5 seconds per image! This is probably the fastest you can go on a T4 GPU without sacrificing quality.
 
-The first picture looks nice! The eye movement slightly changed and looks nice. This finished up our 101-guide on how to use Stable Diffusion 🤗.                                                                                              
+## Quality
 
-For more information on optimization or other guides, I recommend taking a look at the following:                                                                                                                                            
+In the last two sections, you learned how to optimize the speed of your pipeline by using `fp16`, reducing the number of inference steps by using a more performant scheduler, and enabling attention slicing to reduce memory consumption. Now you're going to focus on how to improve the quality of generated images.
 
--   [Blog post about Stable Diffusion](https://huggingface.co/blog/stable_diffusion): In-detail blog post explaining Stable Diffusion.                                                                                                        
--   [FlashAttention](https://huggingface.co/docs/diffusers/optimization/xformers): XFormers flash attention can optimize your model even further with more speed and memory improvements.                                                                                                                                                                                                                                                                                                   
--   [Dreambooth](https://huggingface.co/docs/diffusers/training/dreambooth) - Quickly customize the model by fine-tuning it.                                                                                                                  
--   [General info on Stable Diffusion](https://huggingface.co/docs/diffusers/main/en/api/pipelines/stable_diffusion/overview) - Info on other tasks that are powered by Stable Diffusion.
+### Better checkpoints
+
+The most obvious step is to use better checkpoints. The Stable Diffusion model is a good starting point, and since its official launch, several improved versions have also been released. However, using a newer version doesn't automatically mean you'll get better results. You'll still have to experiment with different checkpoints yourself, and do a little research (such as using [negative prompts](https://minimaxir.com/2022/11/stable-diffusion-negative-prompt/)) to get the best results.
+
+As the field grows, there are more and more high-quality checkpoints finetuned to produce certain styles. Try exploring the [Hub](https://huggingface.co/models?library=diffusers&sort=downloads) and [Diffusers Gallery](https://huggingface.co/spaces/huggingface-projects/diffusers-gallery) to find one you're interested in!
+
+### Better pipeline components
+
+You can also try replacing the current pipeline components with a newer version. Let's try loading the latest [autodecoder](https://huggingface.co/stabilityai/stable-diffusion-2-1/tree/main/vae) from Stability AI into the pipeline, and generate some images:
+
+```python
+from diffusers import AutoencoderKL
+
+vae = AutoencoderKL.from_pretrained("stabilityai/sd-vae-ft-mse", torch_dtype=torch.float16).to("cuda")
+pipeline.vae = vae
+images = pipeline(**get_inputs(batch_size=8)).images
+image_grid(images, rows=2, cols=4)
+```
+
+<div class="flex justify-center">
+    <img src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/stable_diffusion_101/sd_101_6.png">
+</div>
+
+### Better prompt engineering
+
+The text prompt you use to generate an image is super important, so much so that it is called *prompt engineering*. Some considerations to keep during prompt engineering are:
+
+- How is the image or similar images of the one I want to generate stored on the internet?
+- What additional detail can I give that steers the model towards the style I want?
+
+With this in mind, let's improve the prompt to include color and higher quality details:
+
+```python
+prompt += ", tribal panther make up, blue on red, side profile, looking away, serious eyes"
+prompt += " 50mm portrait photography, hard rim lighting photography--beta --ar 2:3  --beta --upbeta"
+```
+
+Generate a batch of images with the new prompt:
+
+```python
+images = pipeline(**get_inputs(batch_size=8)).images
+image_grid(images, rows=2, cols=4)
+```
+
+<div class="flex justify-center">
+    <img src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/stable_diffusion_101/sd_101_7.png">
+</div>
+
+Pretty impressive! Let's tweak the second image - corresponding to the `Generator` with a seed of `1` - a bit more by adding some text about the age of the subject:
+
+```python
+prompts = [
+    "portrait photo of the oldest warrior chief, tribal panther make up, blue on red, side profile, looking away, serious eyes 50mm portrait photography, hard rim lighting photography--beta --ar 2:3  --beta --upbeta",
+    "portrait photo of a old warrior chief, tribal panther make up, blue on red, side profile, looking away, serious eyes 50mm portrait photography, hard rim lighting photography--beta --ar 2:3  --beta --upbeta",
+    "portrait photo of a warrior chief, tribal panther make up, blue on red, side profile, looking away, serious eyes 50mm portrait photography, hard rim lighting photography--beta --ar 2:3  --beta --upbeta",
+    "portrait photo of a young warrior chief, tribal panther make up, blue on red, side profile, looking away, serious eyes 50mm portrait photography, hard rim lighting photography--beta --ar 2:3  --beta --upbeta",
+]
+
+generator = [torch.Generator("cuda").manual_seed(1) for _ in range(len(prompts))]
+images = pipeline(prompt=prompts, generator=generator, num_inference_steps=25).images
+image_grid(images)
+```
+
+<div class="flex justify-center">
+    <img src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/stable_diffusion_101/sd_101_8.png">
+</div>
+
+## Next steps
+
+In this tutorial, you learned how to optimize a [`DiffusionPipeline`] for computational and memory efficiency as well as improving the quality of generated outputs. If you're interested in making your pipeline even faster, take a look at the following resources:
+
+- Learn how [PyTorch 2.0](./optimization/torch2.0) and [`torch.compile`](https://pytorch.org/docs/stable/generated/torch.compile.html) can yield 5 - 300% faster inference speed.
+- If you can't use PyTorch 2, we recommend you install [xFormers](./optimization/xformers). Its memory-efficient attention mechanism works great with PyTorch 1.13.1 for faster speed and reduced memory consumption.
+- Other optimization techniques, such as model offloading, are covered in [this guide](./optimization/fp16).

docs/source/en/training/adapt_a_model.mdx

@@ -0,0 +1,42 @@
+# Adapt a model to a new task
+
+Many diffusion systems share the same components, allowing you to adapt a pretrained model for one task to an entirely different task.
+
+This guide will show you how to adapt a pretrained text-to-image model for inpainting by initializing and modifying the architecture of a pretrained [`UNet2DConditionModel`].
+
+## Configure UNet2DConditionModel parameters
+
+A [`UNet2DConditionModel`] by default accepts 4 channels in the [input sample](https://huggingface.co/docs/diffusers/v0.16.0/en/api/models#diffusers.UNet2DConditionModel.in_channels). For example, load a pretrained text-to-image model like [`runwayml/stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5) and take a look at the number of `in_channels`:
+
+```py
+from diffusers import StableDiffusionPipeline
+
+pipeline = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")
+pipeline.unet.config["in_channels"]
+4
+```
+
+Inpainting requires 9 channels in the input sample. You can check this value in a pretrained inpainting model like [`runwayml/stable-diffusion-inpainting`](https://huggingface.co/runwayml/stable-diffusion-inpainting):
+
+```py
+from diffusers import StableDiffusionPipeline
+
+pipeline = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-inpainting")
+pipeline.unet.config["in_channels"]
+9
+```
+
+To adapt your text-to-image model for inpainting, you'll need to change the number of `in_channels` from 4 to 9. 
+
+Initialize a [`UNet2DConditionModel`] with the pretrained text-to-image model weights, and change `in_channels` to 9. Changing the number of `in_channels` means you need to set `ignore_mismatched_sizes=True` and `low_cpu_mem_usage=False` to avoid a size mismatch error because the shape is different now.
+
+```py
+from diffusers import UNet2DConditionModel
+
+model_id = "runwayml/stable-diffusion-v1-5"
+unet = UNet2DConditionModel.from_pretrained(
+    model_id, subfolder="unet", in_channels=9, low_cpu_mem_usage=False, ignore_mismatched_sizes=True
+)
+```
+
+The pretrained weights of the other components from the text-to-image model are initialized from their checkpoints, but the input channel weights (`conv_in.weight`) of the `unet` are randomly initialized. It is important to finetune the model for inpainting because otherwise the model returns noise.

docs/source/en/training/controlnet.mdx

@@ -33,7 +33,12 @@ cd diffusers
 pip install -e .
 ```
 
-Then navigate into the example folder and run:
+Then navigate into the [example folder](https://github.com/huggingface/diffusers/tree/main/examples/controlnet)
+```bash
+cd examples/controlnet
+```
+
+Now run:
 ```bash
 pip install -r requirements.txt
 ```
@@ -64,6 +69,8 @@ The original dataset is hosted in the ControlNet [repo](https://huggingface.co/l
 
 Our training examples use [`runwayml/stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5) because that is what the original set of ControlNet models was trained on. However, ControlNet can be trained to augment any compatible Stable Diffusion model (such as [`CompVis/stable-diffusion-v1-4`](https://huggingface.co/CompVis/stable-diffusion-v1-4)) or [`stabilityai/stable-diffusion-2-1`](https://huggingface.co/stabilityai/stable-diffusion-2-1).
 
+To use your own dataset, take a look at the [Create a dataset for training](create_dataset) guide.
+
 ## Training
 
 Download the following images to condition our training with:
@@ -74,6 +81,9 @@ wget https://huggingface.co/datasets/huggingface/documentation-images/resolve/ma
 wget https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/controlnet_training/conditioning_image_2.png
 ```
 
+Specify the `MODEL_NAME` environment variable (either a Hub model repository id or a path to the directory containing the model weights) and pass it to the [`pretrained_model_name_or_path`](https://huggingface.co/docs/diffusers/en/api/diffusion_pipeline#diffusers.DiffusionPipeline.from_pretrained.pretrained_model_name_or_path) argument.
+
+The training script creates and saves a `diffusion_pytorch_model.bin` file in your repository.
 
 ```bash
 export MODEL_DIR="runwayml/stable-diffusion-v1-5"
@@ -113,6 +123,29 @@ accelerate launch train_controlnet.py \
  --gradient_accumulation_steps=4
 ```
 
+## Training with multiple GPUs
+
+`accelerate` allows for seamless multi-GPU training. Follow the instructions [here](https://huggingface.co/docs/accelerate/basic_tutorials/launch)
+for running distributed training with `accelerate`. Here is an example command:
+
+```bash 
+export MODEL_DIR="runwayml/stable-diffusion-v1-5"
+export OUTPUT_DIR="path to save model"
+
+accelerate launch --mixed_precision="fp16" --multi_gpu train_controlnet.py \
+ --pretrained_model_name_or_path=$MODEL_DIR \
+ --output_dir=$OUTPUT_DIR \
+ --dataset_name=fusing/fill50k \
+ --resolution=512 \
+ --learning_rate=1e-5 \
+ --validation_image "./conditioning_image_1.png" "./conditioning_image_2.png" \
+ --validation_prompt "red circle with blue background" "cyan circle with brown floral background" \
+ --train_batch_size=4 \
+ --mixed_precision="fp16" \
+ --tracker_project_name="controlnet-demo" \
+ --report_to=wandb
+```
+
 ## Example results
 
 #### After 300 steps with batch size 8

docs/source/en/training/create_dataset.mdx

@@ -0,0 +1,90 @@
+# Create a dataset for training
+
+There are many datasets on the [Hub](https://huggingface.co/datasets?task_categories=task_categories:text-to-image&sort=downloads) to train a model on, but if you can't find one you're interested in or want to use your own, you can create a dataset with the 🤗 [Datasets](hf.co/docs/datasets) library. The dataset structure depends on the task you want to train your model on. The most basic dataset structure is a directory of images for tasks like unconditional image generation. Another dataset structure may be a directory of images and a text file containing their corresponding text captions for tasks like text-to-image generation.
+
+This guide will show you two ways to create a dataset to finetune on:
+
+- provide a folder of images to the `--train_data_dir` argument
+- upload a dataset to the Hub and pass the dataset repository id to the `--dataset_name` argument
+
+<Tip>
+
+💡 Learn more about how to create an image dataset for training in the [Create an image dataset](https://huggingface.co/docs/datasets/image_dataset) guide. 
+
+</Tip>
+
+## Provide a dataset as a folder
+
+For unconditional generation, you can provide your own dataset as a folder of images. The training script uses the [`ImageFolder`](https://huggingface.co/docs/datasets/en/image_dataset#imagefolder) builder from 🤗 Datasets to automatically build a dataset from the folder. Your directory structure should look like:
+
+```bash
+data_dir/xxx.png
+data_dir/xxy.png
+data_dir/[...]/xxz.png
+```
+
+Pass the path to the dataset directory to the `--train_data_dir` argument, and then you can start training:
+
+```bash
+accelerate launch train_unconditional.py \
+    --train_data_dir <path-to-train-directory> \
+    <other-arguments>
+```
+
+## Upload your data to the Hub
+
+<Tip>
+
+💡 For more details and context about creating and uploading a dataset to the Hub, take a look at the [Image search with 🤗 Datasets](https://huggingface.co/blog/image-search-datasets) post.
+
+</Tip>
+
+Start by creating a dataset with the [`ImageFolder`](https://huggingface.co/docs/datasets/image_load#imagefolder) feature, which creates an `image` column containing the PIL-encoded images. 
+
+You can use the `data_dir` or `data_files` parameters to specify the location of the dataset. The `data_files` parameter supports mapping specific files to dataset splits like `train` or `test`:
+
+```python
+from datasets import load_dataset
+
+# example 1: local folder
+dataset = load_dataset("imagefolder", data_dir="path_to_your_folder")
+
+# example 2: local files (supported formats are tar, gzip, zip, xz, rar, zstd)
+dataset = load_dataset("imagefolder", data_files="path_to_zip_file")
+
+# example 3: remote files (supported formats are tar, gzip, zip, xz, rar, zstd)
+dataset = load_dataset(
+    "imagefolder",
+    data_files="https://download.microsoft.com/download/3/E/1/3E1C3F21-ECDB-4869-8368-6DEBA77B919F/kagglecatsanddogs_3367a.zip",
+)
+
+# example 4: providing several splits
+dataset = load_dataset(
+    "imagefolder", data_files={"train": ["path/to/file1", "path/to/file2"], "test": ["path/to/file3", "path/to/file4"]}
+)
+```
+
+Then use the [`~datasets.Dataset.push_to_hub`] method to upload the dataset to the Hub:
+
+```python
+# assuming you have ran the huggingface-cli login command in a terminal
+dataset.push_to_hub("name_of_your_dataset")
+
+# if you want to push to a private repo, simply pass private=True:
+dataset.push_to_hub("name_of_your_dataset", private=True)
+```
+
+Now the dataset is available for training by passing the dataset name to the `--dataset_name` argument:
+
+```bash
+accelerate launch --mixed_precision="fp16"  train_text_to_image.py \
+  --pretrained_model_name_or_path="runwayml/stable-diffusion-v1-5" \
+  --dataset_name="name_of_your_dataset" \
+  <other-arguments>
+```
+
+## Next steps
+
+Now that you've created a dataset, you can plug it into the `train_data_dir` (if your dataset is local) or `dataset_name` (if your dataset is on the Hub) arguments of a training script.
+
+For your next steps, feel free to try and use your dataset to train a model for [unconditional generation](uncondtional_training) or [text-to-image generation](text2image)!

docs/source/en/training/custom_diffusion.mdx

@@ -0,0 +1,299 @@
+<!--Copyright 2023 Custom Diffusion authors The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# Custom Diffusion training example 
+
+[Custom Diffusion](https://arxiv.org/abs/2212.04488) is a method to customize text-to-image models like Stable Diffusion given just a few (4~5) images of a subject.
+The `train_custom_diffusion.py` script shows how to implement the training procedure and adapt it for stable diffusion.
+
+This training example was contributed by [Nupur Kumari](https://nupurkmr9.github.io/) (one of the authors of Custom Diffusion). 
+
+## Running locally with PyTorch
+
+### Installing the dependencies
+
+Before running the scripts, make sure to install the library's training dependencies:
+
+**Important**
+
+To make sure you can successfully run the latest versions of the example scripts, we highly recommend **installing from source** and keeping the install up to date as we update the example scripts frequently and install some example-specific requirements. To do this, execute the following steps in a new virtual environment:
+
+```bash
+git clone https://github.com/huggingface/diffusers
+cd diffusers
+pip install -e .
+```
+
+Then cd into the [example folder](https://github.com/huggingface/diffusers/tree/main/examples/custom_diffusion)
+
+```
+cd examples/custom_diffusion
+```
+
+Now run
+
+```bash
+pip install -r requirements.txt
+pip install clip-retrieval 
+```
+
+And initialize an [🤗Accelerate](https://github.com/huggingface/accelerate/) environment with:
+
+```bash
+accelerate config
+```
+
+Or for a default accelerate configuration without answering questions about your environment
+
+```bash
+accelerate config default
+```
+
+Or if your environment doesn't support an interactive shell e.g. a notebook
+
+```python
+from accelerate.utils import write_basic_config
+
+write_basic_config()
+```
+### Cat example 😺
+
+Now let's get our dataset. Download dataset from [here](https://www.cs.cmu.edu/~custom-diffusion/assets/data.zip) and unzip it. To use your own dataset, take a look at the [Create a dataset for training](create_dataset) guide.
+
+We also collect 200 real images using `clip-retrieval` which are combined with the target images in the training dataset as a regularization. This prevents overfitting to the the given target image. The following flags enable the regularization `with_prior_preservation`, `real_prior` with `prior_loss_weight=1.`. 
+The `class_prompt` should be the category name same as target image. The collected real images are with text captions similar to the `class_prompt`. The retrieved image are saved in `class_data_dir`. You can disable `real_prior` to use generated images as regularization. To collect the real images use this command first before training. 
+
+```bash
+pip install clip-retrieval
+python retrieve.py --class_prompt cat --class_data_dir real_reg/samples_cat --num_class_images 200
+```
+
+**___Note: Change the `resolution` to 768 if you are using the [stable-diffusion-2](https://huggingface.co/stabilityai/stable-diffusion-2) 768x768 model.___**
+
+The script creates and saves model checkpoints and a `pytorch_custom_diffusion_weights.bin` file in your repository.
+
+```bash
+export MODEL_NAME="CompVis/stable-diffusion-v1-4"
+export OUTPUT_DIR="path-to-save-model"
+export INSTANCE_DIR="./data/cat"
+
+accelerate launch train_custom_diffusion.py \
+  --pretrained_model_name_or_path=$MODEL_NAME  \
+  --instance_data_dir=$INSTANCE_DIR \
+  --output_dir=$OUTPUT_DIR \
+  --class_data_dir=./real_reg/samples_cat/ \
+  --with_prior_preservation --real_prior --prior_loss_weight=1.0 \
+  --class_prompt="cat" --num_class_images=200 \
+  --instance_prompt="photo of a <new1> cat"  \
+  --resolution=512  \
+  --train_batch_size=2  \
+  --learning_rate=1e-5  \
+  --lr_warmup_steps=0 \
+  --max_train_steps=250 \
+  --scale_lr --hflip  \
+  --modifier_token "<new1>" 
+```
+
+**Use `--enable_xformers_memory_efficient_attention` for faster training with lower VRAM requirement (16GB per GPU). Follow [this guide](https://github.com/facebookresearch/xformers) for installation instructions.**
+
+To track your experiments using Weights and Biases (`wandb`) and to save intermediate results (whcih we HIGHLY recommend), follow these steps:
+
+* Install `wandb`: `pip install wandb`.
+* Authorize: `wandb login`. 
+* Then specify a `validation_prompt` and set `report_to` to `wandb` while launching training. You can also configure the following related arguments:
+    * `num_validation_images`
+    * `validation_steps`
+
+Here is an example command:
+
+```bash
+accelerate launch train_custom_diffusion.py \
+  --pretrained_model_name_or_path=$MODEL_NAME  \
+  --instance_data_dir=$INSTANCE_DIR \
+  --output_dir=$OUTPUT_DIR \
+  --class_data_dir=./real_reg/samples_cat/ \
+  --with_prior_preservation --real_prior --prior_loss_weight=1.0 \
+  --class_prompt="cat" --num_class_images=200 \
+  --instance_prompt="photo of a <new1> cat"  \
+  --resolution=512  \
+  --train_batch_size=2  \
+  --learning_rate=1e-5  \
+  --lr_warmup_steps=0 \
+  --max_train_steps=250 \
+  --scale_lr --hflip  \
+  --modifier_token "<new1>" \
+  --validation_prompt="<new1> cat sitting in a bucket" \
+  --report_to="wandb"
+```
+
+Here is an example [Weights and Biases page](https://wandb.ai/sayakpaul/custom-diffusion/runs/26ghrcau) where you can check out the intermediate results along with other training details.  
+
+If you specify `--push_to_hub`, the learned parameters will be pushed to a repository on the Hugging Face Hub. Here is an [example repository](https://huggingface.co/sayakpaul/custom-diffusion-cat).
+
+### Training on multiple concepts 🐱🪵
+
+Provide a [json](https://github.com/adobe-research/custom-diffusion/blob/main/assets/concept_list.json) file with the info about each concept, similar to [this](https://github.com/ShivamShrirao/diffusers/blob/main/examples/dreambooth/train_dreambooth.py).
+
+To collect the real images run this command for each concept in the json file. 
+
+```bash
+pip install clip-retrieval
+python retrieve.py --class_prompt {} --class_data_dir {} --num_class_images 200
+```
+
+And then we're ready to start training!
+
+```bash
+export MODEL_NAME="CompVis/stable-diffusion-v1-4"
+export OUTPUT_DIR="path-to-save-model"
+
+accelerate launch train_custom_diffusion.py \
+  --pretrained_model_name_or_path=$MODEL_NAME  \
+  --output_dir=$OUTPUT_DIR \
+  --concepts_list=./concept_list.json \
+  --with_prior_preservation --real_prior --prior_loss_weight=1.0 \
+  --resolution=512  \
+  --train_batch_size=2  \
+  --learning_rate=1e-5  \
+  --lr_warmup_steps=0 \
+  --max_train_steps=500 \
+  --num_class_images=200 \
+  --scale_lr --hflip  \
+  --modifier_token "<new1>+<new2>" 
+```
+
+Here is an example [Weights and Biases page](https://wandb.ai/sayakpaul/custom-diffusion/runs/3990tzkg) where you can check out the intermediate results along with other training details.  
+
+### Training on human faces
+
+For fine-tuning on human faces we found the following configuration to work better: `learning_rate=5e-6`, `max_train_steps=1000 to 2000`, and `freeze_model=crossattn` with at least 15-20 images. 
+
+To collect the real images use this command first before training. 
+
+```bash
+pip install clip-retrieval
+python retrieve.py --class_prompt person --class_data_dir real_reg/samples_person --num_class_images 200
+```
+
+Then start training!
+
+```bash
+export MODEL_NAME="CompVis/stable-diffusion-v1-4"
+export OUTPUT_DIR="path-to-save-model"
+export INSTANCE_DIR="path-to-images"
+
+accelerate launch train_custom_diffusion.py \
+  --pretrained_model_name_or_path=$MODEL_NAME  \
+  --instance_data_dir=$INSTANCE_DIR \
+  --output_dir=$OUTPUT_DIR \
+  --class_data_dir=./real_reg/samples_person/ \
+  --with_prior_preservation --real_prior --prior_loss_weight=1.0 \
+  --class_prompt="person" --num_class_images=200 \
+  --instance_prompt="photo of a <new1> person"  \
+  --resolution=512  \
+  --train_batch_size=2  \
+  --learning_rate=5e-6  \
+  --lr_warmup_steps=0 \
+  --max_train_steps=1000 \
+  --scale_lr --hflip --noaug \
+  --freeze_model crossattn \
+  --modifier_token "<new1>" \
+  --enable_xformers_memory_efficient_attention 
+```
+
+## Inference
+
+Once you have trained a model using the above command, you can run inference using the below command. Make sure to include the `modifier token` (e.g. \<new1\> in above example) in your prompt.
+
+```python
+import torch
+from diffusers import DiffusionPipeline
+
+pipe = DiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", torch_dtype=torch.float16).to("cuda")
+pipe.unet.load_attn_procs("path-to-save-model", weight_name="pytorch_custom_diffusion_weights.bin")
+pipe.load_textual_inversion("path-to-save-model", weight_name="<new1>.bin")
+
+image = pipe(
+    "<new1> cat sitting in a bucket",
+    num_inference_steps=100,
+    guidance_scale=6.0,
+    eta=1.0,
+).images[0]
+image.save("cat.png")
+```
+
+It's possible to directly load these parameters from a Hub repository:
+
+```python
+import torch
+from huggingface_hub.repocard import RepoCard
+from diffusers import DiffusionPipeline
+
+model_id = "sayakpaul/custom-diffusion-cat"
+card = RepoCard.load(model_id)
+base_model_id = card.data.to_dict()["base_model"]
+
+pipe = DiffusionPipeline.from_pretrained(base_model_id, torch_dtype=torch.float16).to("cuda")
+pipe.unet.load_attn_procs(model_id, weight_name="pytorch_custom_diffusion_weights.bin")
+pipe.load_textual_inversion(model_id, weight_name="<new1>.bin")
+
+image = pipe(
+    "<new1> cat sitting in a bucket",
+    num_inference_steps=100,
+    guidance_scale=6.0,
+    eta=1.0,
+).images[0]
+image.save("cat.png")
+```
+
+Here is an example of performing inference with multiple concepts:
+
+```python
+import torch
+from huggingface_hub.repocard import RepoCard
+from diffusers import DiffusionPipeline
+
+model_id = "sayakpaul/custom-diffusion-cat-wooden-pot"
+card = RepoCard.load(model_id)
+base_model_id = card.data.to_dict()["base_model"]
+
+pipe = DiffusionPipeline.from_pretrained(base_model_id, torch_dtype=torch.float16).to("cuda")
+pipe.unet.load_attn_procs(model_id, weight_name="pytorch_custom_diffusion_weights.bin")
+pipe.load_textual_inversion(model_id, weight_name="<new1>.bin")
+pipe.load_textual_inversion(model_id, weight_name="<new2>.bin")
+
+image = pipe(
+    "the <new1> cat sculpture in the style of a <new2> wooden pot",
+    num_inference_steps=100,
+    guidance_scale=6.0,
+    eta=1.0,
+).images[0]
+image.save("multi-subject.png")
+```
+
+Here, `cat` and `wooden pot` refer to the multiple concepts.
+
+### Inference from a training checkpoint
+
+You can also perform inference from one of the complete checkpoint saved during the training process, if you used the `--checkpointing_steps` argument. 
+
+TODO.
+
+## Set grads to none
+
+To save even more memory, pass the `--set_grads_to_none` argument to the script. This will set grads to None instead of zero. However, be aware that it changes certain behaviors, so if you start experiencing any problems, remove this argument.
+
+More info: https://pytorch.org/docs/stable/generated/torch.optim.Optimizer.zero_grad.html
+
+## Experimental results
+
+You can refer to [our webpage](https://www.cs.cmu.edu/~custom-diffusion/) that discusses our experiments in detail. 

docs/source/en/training/distributed_inference.mdx

@@ -0,0 +1,91 @@
+# Distributed inference with multiple GPUs
+
+On distributed setups, you can run inference across multiple GPUs with 🤗 [Accelerate](https://huggingface.co/docs/accelerate/index) or [PyTorch Distributed](https://pytorch.org/tutorials/beginner/dist_overview.html), which is useful for generating with multiple prompts in parallel.
+
+This guide will show you how to use 🤗 Accelerate and PyTorch Distributed for distributed inference.
+
+## 🤗 Accelerate
+
+🤗 [Accelerate](https://huggingface.co/docs/accelerate/index) is a library designed to make it easy to train or run inference across distributed setups. It simplifies the process of setting up the distributed environment, allowing you to focus on your PyTorch code.
+
+To begin, create a Python file and initialize an [`accelerate.PartialState`] to create a distributed environment; your setup is automatically detected so you don't need to explicitly define the `rank` or `world_size`. Move the [`DiffusionPipeline`] to `distributed_state.device` to assign a GPU to each process.
+
+Now use the [`~accelerate.PartialState.split_between_processes`] utility as a context manager to automatically distribute the prompts between the number of processes.
+
+```py
+from accelerate import PartialState
+from diffusers import DiffusionPipeline
+
+pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
+distributed_state = PartialState()
+pipeline.to(distributed_state.device)
+
+with distributed_state.split_between_processes(["a dog", "a cat"]) as prompt:
+    result = pipeline(prompt).images[0]
+    result.save(f"result_{distributed_state.process_index}.png")
+```
+
+Use the `--num_processes` argument to specify the number of GPUs to use, and call `accelerate launch` to run the script:
+
+```bash
+accelerate launch run_distributed.py --num_processes=2
+```
+
+<Tip>
+
+To learn more, take a look at the [Distributed Inference with 🤗 Accelerate](https://huggingface.co/docs/accelerate/en/usage_guides/distributed_inference#distributed-inference-with-accelerate) guide.
+
+</Tip>
+
+## PyTorch Distributed
+
+PyTorch supports [`DistributedDataParallel`](https://pytorch.org/docs/stable/generated/torch.nn.parallel.DistributedDataParallel.html) which enables data parallelism.
+
+To start, create a Python file and import `torch.distributed` and `torch.multiprocessing` to set up the distributed process group and to spawn the processes for inference on each GPU. You should also initialize a [`DiffusionPipeline`]:
+
+```py
+import torch
+import torch.distributed as dist
+import torch.multiprocessing as mp
+
+from diffusers import DiffusionPipeline
+
+sd = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
+```
+
+You'll want to create a function to run inference; [`init_process_group`](https://pytorch.org/docs/stable/distributed.html?highlight=init_process_group#torch.distributed.init_process_group) handles creating a distributed environment with the type of backend to use, the `rank` of the current process, and the `world_size` or the number of processes participating. If you're running inference in parallel over 2 GPUs, then the `world_size` is 2.
+
+Move the [`DiffusionPipeline`] to `rank` and use `get_rank` to assign a GPU to each process, where each process handles a different prompt:
+
+```py
+def run_inference(rank, world_size):
+    dist.init_process_group("nccl", rank=rank, world_size=world_size)
+
+    sd.to(rank)
+
+    if torch.distributed.get_rank() == 0:
+        prompt = "a dog"
+    elif torch.distributed.get_rank() == 1:
+        prompt = "a cat"
+
+    image = sd(prompt).images[0]
+    image.save(f"./{'_'.join(prompt)}.png")
+```
+
+To run the distributed inference, call [`mp.spawn`](https://pytorch.org/docs/stable/multiprocessing.html#torch.multiprocessing.spawn) to run the `run_inference` function on the number of GPUs defined in `world_size`:
+
+```py
+def main():
+    world_size = 2
+    mp.spawn(run_inference, args=(world_size,), nprocs=world_size, join=True)
+
+
+if __name__ == "__main__":
+    main()
+```
+
+Once you've completed the inference script, use the `--nproc_per_node` argument to specify the number of GPUs to use and call `torchrun` to run the script:
+
+```bash
+torchrun run_distributed.py --nproc_per_node=2
+```

docs/source/en/training/dreambooth.mdx

@@ -50,6 +50,22 @@ from accelerate.utils import write_basic_config
 write_basic_config()
 ```
 
+Finally, download a [few images of a dog](https://huggingface.co/datasets/diffusers/dog-example) to DreamBooth with:
+
+```py
+from huggingface_hub import snapshot_download
+
+local_dir = "./dog"
+snapshot_download(
+    "diffusers/dog-example",
+    local_dir=local_dir,
+    repo_type="dataset",
+    ignore_patterns=".gitattributes",
+)
+```
+
+To use your own dataset, take a look at the [Create a dataset for training](create_dataset) guide.
+
 ## Finetuning
 
 <Tip warning={true}>
@@ -60,11 +76,13 @@ DreamBooth finetuning is very sensitive to hyperparameters and easy to overfit.
 
 <frameworkcontent>
 <pt>
-Let's try DreamBooth with a [few images of a dog](https://drive.google.com/drive/folders/1BO_dyz-p65qhBRRMRA4TbZ8qW4rB99JZ); download and save them to a directory and then set the `INSTANCE_DIR` environment variable to that path:
+Set the `INSTANCE_DIR` environment variable to the path of the directory containing the dog images.
+
+Specify the `MODEL_NAME` environment variable (either a Hub model repository id or a path to the directory containing the model weights) and pass it to the [`pretrained_model_name_or_path`] argument. The `instance_prompt` argument is a text prompt that contains a unique identifier, such as `sks`, and the class the image belongs to, which in this example is `a photo of a sks dog`.
 
 ```bash
 export MODEL_NAME="CompVis/stable-diffusion-v1-4"
-export INSTANCE_DIR="path_to_training_images"
+export INSTANCE_DIR="./dog"
 export OUTPUT_DIR="path_to_saved_model"
 ```
 
@@ -82,7 +100,8 @@ accelerate launch train_dreambooth.py \
   --learning_rate=5e-6 \
   --lr_scheduler="constant" \
   --lr_warmup_steps=0 \
-  --max_train_steps=400
+  --max_train_steps=400 \
+  --push_to_hub
 ```
 </pt>
 <jax>
@@ -94,11 +113,13 @@ Before running the script, make sure you have the requirements installed:
 pip install -U -r requirements.txt
 ```
 
+Specify the `MODEL_NAME` environment variable (either a Hub model repository id or a path to the directory containing the model weights) and pass it to the [`pretrained_model_name_or_path`] argument. The `instance_prompt` argument is a text prompt that contains a unique identifier, such as `sks`, and the class the image belongs to, which in this example is `a photo of a sks dog`.
+
 Now you can launch the training script with the following command:
 
 ```bash
 export MODEL_NAME="duongna/stable-diffusion-v1-4-flax"
-export INSTANCE_DIR="path-to-instance-images"
+export INSTANCE_DIR="./dog"
 export OUTPUT_DIR="path-to-save-model"
 
 python train_dreambooth_flax.py \
@@ -124,7 +145,7 @@ The authors recommend generating `num_epochs * num_samples` images for prior pre
 <pt>
 ```bash
 export MODEL_NAME="CompVis/stable-diffusion-v1-4"
-export INSTANCE_DIR="path_to_training_images"
+export INSTANCE_DIR="./dog"
 export CLASS_DIR="path_to_class_images"
 export OUTPUT_DIR="path_to_saved_model"
 
@@ -143,13 +164,14 @@ accelerate launch train_dreambooth.py \
   --lr_scheduler="constant" \
   --lr_warmup_steps=0 \
   --num_class_images=200 \
-  --max_train_steps=800
+  --max_train_steps=800 \
+  --push_to_hub
 ```
 </pt>
 <jax>
 ```bash
 export MODEL_NAME="duongna/stable-diffusion-v1-4-flax"
-export INSTANCE_DIR="path-to-instance-images"
+export INSTANCE_DIR="./dog"
 export CLASS_DIR="path-to-class-images"
 export OUTPUT_DIR="path-to-save-model"
 
@@ -186,7 +208,7 @@ Pass the `--train_text_encoder` argument to the training script to enable finetu
 <pt>
 ```bash
 export MODEL_NAME="CompVis/stable-diffusion-v1-4"
-export INSTANCE_DIR="path_to_training_images"
+export INSTANCE_DIR="./dog"
 export CLASS_DIR="path_to_class_images"
 export OUTPUT_DIR="path_to_saved_model"
 
@@ -207,13 +229,14 @@ accelerate launch train_dreambooth.py \
   --lr_scheduler="constant" \
   --lr_warmup_steps=0 \
   --num_class_images=200 \
-  --max_train_steps=800
+  --max_train_steps=800 \
+  --push_to_hub
 ```
 </pt>
 <jax>
 ```bash
 export MODEL_NAME="duongna/stable-diffusion-v1-4-flax"
-export INSTANCE_DIR="path-to-instance-images"
+export INSTANCE_DIR="./dog"
 export CLASS_DIR="path-to-class-images"
 export OUTPUT_DIR="path-to-save-model"
 
@@ -349,7 +372,7 @@ Then pass the `--use_8bit_adam` option to the training script:
 
 ```bash
 export MODEL_NAME="CompVis/stable-diffusion-v1-4"
-export INSTANCE_DIR="path_to_training_images"
+export INSTANCE_DIR="./dog"
 export CLASS_DIR="path_to_class_images"
 export OUTPUT_DIR="path_to_saved_model"
 
@@ -369,7 +392,8 @@ accelerate launch train_dreambooth.py \
   --lr_scheduler="constant" \
   --lr_warmup_steps=0 \
   --num_class_images=200 \
-  --max_train_steps=800
+  --max_train_steps=800 \
+  --push_to_hub
 ```
 
 ### 12GB GPU
@@ -378,7 +402,7 @@ To run DreamBooth on a 12GB GPU, you'll need to enable gradient checkpointing, t
 
 ```bash
 export MODEL_NAME="CompVis/stable-diffusion-v1-4"
-export INSTANCE_DIR="path-to-instance-images"
+export INSTANCE_DIR="./dog"
 export CLASS_DIR="path-to-class-images"
 export OUTPUT_DIR="path-to-save-model"
 
@@ -400,7 +424,8 @@ accelerate launch train_dreambooth.py \
   --lr_scheduler="constant" \
   --lr_warmup_steps=0 \
   --num_class_images=200 \
-  --max_train_steps=800
+  --max_train_steps=800 \
+  --push_to_hub
 ```
 
 ### 8 GB GPU
@@ -425,7 +450,7 @@ Launch training with the following command:
 
 ```bash
 export MODEL_NAME="CompVis/stable-diffusion-v1-4"
-export INSTANCE_DIR="path_to_training_images"
+export INSTANCE_DIR="./dog"
 export CLASS_DIR="path_to_class_images"
 export OUTPUT_DIR="path_to_saved_model"
 
@@ -446,7 +471,8 @@ accelerate launch train_dreambooth.py \
   --lr_warmup_steps=0 \
   --num_class_images=200 \
   --max_train_steps=800 \
-  --mixed_precision=fp16
+  --mixed_precision=fp16 \
+  --push_to_hub
 ```
 
 ## Inference
@@ -470,3 +496,67 @@ image.save("dog-bucket.png")
 ```
 
 You may also run inference from any of the [saved training checkpoints](#inference-from-a-saved-checkpoint).
+
+## IF
+
+You can use the lora and full dreambooth scripts to also train the text to image [IF model](https://huggingface.co/DeepFloyd/IF-I-XL-v1.0). A few alternative cli flags are needed due to the model size, the expected input resolution, and the text encoder conventions.
+
+### LoRA Dreambooth
+This training configuration requires ~28 GB VRAM.
+
+```sh
+export MODEL_NAME="DeepFloyd/IF-I-XL-v1.0"
+export INSTANCE_DIR="dog"
+export OUTPUT_DIR="dreambooth_dog_lora"
+
+accelerate launch train_dreambooth_lora.py \
+  --report_to wandb \
+  --pretrained_model_name_or_path=$MODEL_NAME  \
+  --instance_data_dir=$INSTANCE_DIR \
+  --output_dir=$OUTPUT_DIR \
+  --instance_prompt="a sks dog" \
+  --resolution=64 \ # The input resolution of the IF unet is 64x64
+  --train_batch_size=4 \
+  --gradient_accumulation_steps=1 \
+  --learning_rate=5e-6 \
+  --scale_lr \
+  --max_train_steps=1200 \
+  --validation_prompt="a sks dog" \
+  --validation_epochs=25 \
+  --checkpointing_steps=100 \
+  --pre_compute_text_embeddings \ # Pre compute text embeddings to that T5 doesn't have to be kept in memory
+  --tokenizer_max_length=77 \ # IF expects an override of the max token length
+  --text_encoder_use_attention_mask # IF expects attention mask for text embeddings
+```
+
+### Full Dreambooth
+Due to the size of the optimizer states, we recommend training the full XL IF model with 8bit adam. 
+Using 8bit adam and the rest of the following config, the model can be trained in ~48 GB VRAM.
+
+For full dreambooth, IF requires very low learning rates. With higher learning rates model quality will degrade.
+
+```sh
+export MODEL_NAME="DeepFloyd/IF-I-XL-v1.0"
+
+export INSTANCE_DIR="dog"
+export OUTPUT_DIR="dreambooth_if"
+
+accelerate launch train_dreambooth.py \
+  --pretrained_model_name_or_path=$MODEL_NAME  \
+  --instance_data_dir=$INSTANCE_DIR \
+  --output_dir=$OUTPUT_DIR \
+  --instance_prompt="a photo of sks dog" \
+  --resolution=64 \ # The input resolution of the IF unet is 64x64
+  --train_batch_size=4 \
+  --gradient_accumulation_steps=1 \
+  --learning_rate=1e-7 \
+  --max_train_steps=150 \
+  --validation_prompt "a photo of sks dog" \
+  --validation_steps 25 \
+  --text_encoder_use_attention_mask \ # IF expects attention mask for text embeddings
+  --tokenizer_max_length 77 \ # IF expects an override of the max token length
+  --pre_compute_text_embeddings \ # Pre compute text embeddings to that T5 doesn't have to be kept in memory
+  --use_8bit_adam \ # 
+  --set_grads_to_none \
+  --skip_save_text_encoder # do not save the full T5 text encoder with the model
+```

docs/source/en/training/instructpix2pix.mdx

@@ -24,7 +24,7 @@ The output is an "edited" image that reflects the edit instruction applied on th
     <img src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/output-gs%407-igs%401-steps%4050.png" alt="instructpix2pix-output" width=600/>
 </p>
 
-The `train_instruct_pix2pix.py` script shows how to implement the training procedure and adapt it for Stable Diffusion.
+The `train_instruct_pix2pix.py` script (you can find the it [here](https://github.com/huggingface/diffusers/blob/main/examples/instruct_pix2pix/train_instruct_pix2pix.py)) shows how to implement the training procedure and adapt it for Stable Diffusion.
 
 ***Disclaimer: Even though `train_instruct_pix2pix.py` implements the InstructPix2Pix
 training procedure while being faithful to the [original implementation](https://github.com/timothybrooks/instruct-pix2pix) we have only tested it on a [small-scale dataset](https://huggingface.co/datasets/fusing/instructpix2pix-1000-samples). This can impact the end results. For better results, we recommend longer training runs with a larger dataset. [Here](https://huggingface.co/datasets/timbrooks/instructpix2pix-clip-filtered) you can find a large dataset for InstructPix2Pix training.***
@@ -44,7 +44,12 @@ cd diffusers
 pip install -e .
 ```
 
-Then cd in the example folder and run
+Then cd in the example folder
+```bash
+cd examples/instruct_pix2pix
+```
+
+Now run
 ```bash
 pip install -r requirements.txt
 ```
@@ -72,17 +77,16 @@ write_basic_config()
 ### Toy example
 
 As mentioned before, we'll use a [small toy dataset](https://huggingface.co/datasets/fusing/instructpix2pix-1000-samples) for training. The dataset 
-is a smaller version of the [original dataset](https://huggingface.co/datasets/timbrooks/instructpix2pix-clip-filtered) used in the InstructPix2Pix paper.
+is a smaller version of the [original dataset](https://huggingface.co/datasets/timbrooks/instructpix2pix-clip-filtered) used in the InstructPix2Pix paper. To use your own dataset, take a look at the [Create a dataset for training](create_dataset) guide.
 
-Configure environment variables such as the dataset identifier and the Stable Diffusion
-checkpoint:
+Specify the `MODEL_NAME` environment variable (either a Hub model repository id or a path to the directory containing the model weights) and pass it to the [`pretrained_model_name_or_path`](https://huggingface.co/docs/diffusers/en/api/diffusion_pipeline#diffusers.DiffusionPipeline.from_pretrained.pretrained_model_name_or_path) argument. You'll also need to specify the dataset name in `DATASET_ID`:
 
 ```bash
 export MODEL_NAME="runwayml/stable-diffusion-v1-5"
 export DATASET_ID="fusing/instructpix2pix-1000-samples"
 ```
 
-Now, we can launch training:
+Now, we can launch training. The script saves all the components (`feature_extractor`, `scheduler`, `text_encoder`, `unet`, etc) in a subfolder in your repository.
 
 ```bash
 accelerate launch --mixed_precision="fp16" train_instruct_pix2pix.py \
@@ -126,6 +130,27 @@ accelerate launch --mixed_precision="fp16" train_instruct_pix2pix.py \
 
  ***Note: In the original paper, the authors observed that even when the model is trained with an image resolution of 256x256, it generalizes well to bigger resolutions such as 512x512. This is likely because of the larger dataset they used during training.***
 
+ ## Training with multiple GPUs
+
+`accelerate` allows for seamless multi-GPU training. Follow the instructions [here](https://huggingface.co/docs/accelerate/basic_tutorials/launch)
+for running distributed training with `accelerate`. Here is an example command:
+
+```bash 
+accelerate launch --mixed_precision="fp16" --multi_gpu train_instruct_pix2pix.py \
+ --pretrained_model_name_or_path=runwayml/stable-diffusion-v1-5 \
+ --dataset_name=sayakpaul/instructpix2pix-1000-samples \
+ --use_ema \
+ --enable_xformers_memory_efficient_attention \
+ --resolution=512 --random_flip \
+ --train_batch_size=4 --gradient_accumulation_steps=4 --gradient_checkpointing \
+ --max_train_steps=15000 \
+ --checkpointing_steps=5000 --checkpoints_total_limit=1 \
+ --learning_rate=5e-05 --lr_warmup_steps=0 \
+ --conditioning_dropout_prob=0.05 \
+ --mixed_precision=fp16 \
+ --seed=42 
+```
+
  ## Inference
 
  Once training is complete, we can perform inference:

docs/source/en/training/lora.mdx

@@ -16,7 +16,8 @@ specific language governing permissions and limitations under the License.
 
 <Tip warning={true}>
 
-Currently, LoRA is only supported for the attention layers of the [`UNet2DConditionalModel`].
+Currently, LoRA is only supported for the attention layers of the [`UNet2DConditionalModel`]. We also 
+support fine-tuning the text encoder for DreamBooth with LoRA in a limited capacity. Fine-tuning the text encoder for DreamBooth generally yields better results, but it can increase compute usage.
 
 </Tip>
 
@@ -50,7 +51,9 @@ Finetuning a model like Stable Diffusion, which has billions of parameters, can
 
 Let's finetune [`stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5) on the [Pokémon BLIP captions](https://huggingface.co/datasets/lambdalabs/pokemon-blip-captions) dataset to generate your own Pokémon.
 
-To start, make sure you have the `MODEL_NAME` and `DATASET_NAME` environment variables set. The `OUTPUT_DIR` and `HUB_MODEL_ID` variables are optional and specify where to save the model to on the Hub:
+Specify the `MODEL_NAME` environment variable (either a Hub model repository id or a path to the directory containing the model weights) and pass it to the [`pretrained_model_name_or_path`](https://huggingface.co/docs/diffusers/en/api/diffusion_pipeline#diffusers.DiffusionPipeline.from_pretrained.pretrained_model_name_or_path) argument. You'll also need to set the `DATASET_NAME` environment variable to the name of the dataset you want to train on. To use your own dataset, take a look at the [Create a dataset for training](create_dataset) guide.
+
+The `OUTPUT_DIR` and `HUB_MODEL_ID` variables are optional and specify where to save the model to on the Hub:
 
 ```bash
 export MODEL_NAME="runwayml/stable-diffusion-v1-5"
@@ -65,7 +68,7 @@ There are some flags to be aware of before you start training:
 * `--report_to=wandb` reports and logs the training results to your Weights & Biases dashboard (as an example, take a look at this [report](https://wandb.ai/pcuenq/text2image-fine-tune/runs/b4k1w0tn?workspace=user-pcuenq)).
 * `--learning_rate=1e-04`, you can afford to use a higher learning rate than you normally would with LoRA.
 
-Now you're ready to launch the training (you can find the full training script [here](https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image_lora.py)):
+Now you're ready to launch the training (you can find the full training script [here](https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image_lora.py)). Training takes about 5 hours on a 2080 Ti GPU with 11GB of RAM, and it'll create and save model checkpoints and the `pytorch_lora_weights` in your repository.
 
 ```bash
 accelerate launch --mixed_precision="fp16"  train_text_to_image_lora.py \
@@ -111,7 +114,7 @@ Load the LoRA weights from your finetuned model *on top of the base model weight
 </Tip>
 
 ```py
->>> pipe.unet.load_attn_procs(model_path)
+>>> pipe.unet.load_attn_procs(lora_model_path)
 >>> pipe.to("cuda")
 # use half the weights from the LoRA finetuned model and half the weights from the base model
 
@@ -124,6 +127,26 @@ Load the LoRA weights from your finetuned model *on top of the base model weight
 >>> image.save("blue_pokemon.png")
 ```
 
+<Tip>
+
+If you are loading the LoRA parameters from the Hub and if the Hub repository has
+a `base_model` tag (such as [this](https://huggingface.co/sayakpaul/sd-model-finetuned-lora-t4/blob/main/README.md?code=true#L4)), then
+you can do: 
+
+```py 
+from huggingface_hub.repocard import RepoCard
+
+lora_model_id = "sayakpaul/sd-model-finetuned-lora-t4"
+card = RepoCard.load(lora_model_id)
+base_model_id = card.data.to_dict()["base_model"]
+
+pipe = StableDiffusionPipeline.from_pretrained(base_model_id, torch_dtype=torch.float16)
+...
+```
+
+</Tip>
+
+
 ## DreamBooth
 
 [DreamBooth](https://arxiv.org/abs/2208.12242) is a finetuning technique for personalizing a text-to-image model like Stable Diffusion to generate photorealistic images of a subject in different contexts, given a few images of the subject. However, DreamBooth is very sensitive to hyperparameters and it is easy to overfit. Some important hyperparameters to consider include those that affect the training time (learning rate, number of training steps), and inference time (number of steps, scheduler type).
@@ -136,9 +159,11 @@ Load the LoRA weights from your finetuned model *on top of the base model weight
 
 ### Training[[dreambooth-training]]
 
-Let's finetune [`stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5) with DreamBooth and LoRA with some 🐶 [dog images](https://drive.google.com/drive/folders/1BO_dyz-p65qhBRRMRA4TbZ8qW4rB99JZ). Download and save these images to a directory.
+Let's finetune [`stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5) with DreamBooth and LoRA with some 🐶 [dog images](https://drive.google.com/drive/folders/1BO_dyz-p65qhBRRMRA4TbZ8qW4rB99JZ). Download and save these images to a directory. To use your own dataset, take a look at the [Create a dataset for training](create_dataset) guide.
 
-To start, make sure you have the `MODEL_NAME` and `INSTANCE_DIR` (path to directory containing images) environment variables set. The `OUTPUT_DIR` variables is optional and specifies where to save the model to on the Hub:
+To start, specify the `MODEL_NAME` environment variable (either a Hub model repository id or a path to the directory containing the model weights) and pass it to the [`pretrained_model_name_or_path`](https://huggingface.co/docs/diffusers/en/api/diffusion_pipeline#diffusers.DiffusionPipeline.from_pretrained.pretrained_model_name_or_path) argument. You'll also need to set `INSTANCE_DIR` to the path of the directory containing the images. 
+
+The `OUTPUT_DIR` variables is optional and specifies where to save the model to on the Hub:
 
 ```bash
 export MODEL_NAME="runwayml/stable-diffusion-v1-5"
@@ -152,7 +177,11 @@ There are some flags to be aware of before you start training:
 * `--report_to=wandb` reports and logs the training results to your Weights & Biases dashboard (as an example, take a look at this [report](https://wandb.ai/pcuenq/text2image-fine-tune/runs/b4k1w0tn?workspace=user-pcuenq)).
 * `--learning_rate=1e-04`, you can afford to use a higher learning rate than you normally would with LoRA.
 
-Now you're ready to launch the training (you can find the full training script [here](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/train_dreambooth_lora.py)):
+Now you're ready to launch the training (you can find the full training script [here](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/train_dreambooth_lora.py)). The script creates and saves model checkpoints and the `pytorch_lora_weights.bin` file in your repository.
+
+It's also possible to additionally fine-tune the text encoder with LoRA. This, in most cases, leads
+to better results with a slight increase in the compute. To allow fine-tuning the text encoder with LoRA,
+specify the `--train_text_encoder` while launching the `train_dreambooth_lora.py` script.
 
 ```bash
 accelerate launch train_dreambooth_lora.py \
@@ -173,7 +202,7 @@ accelerate launch train_dreambooth_lora.py \
   --validation_epochs=50 \
   --seed="0" \
   --push_to_hub
-```
+``` 
 
 ### Inference[[dreambooth-inference]]
 
@@ -197,7 +226,7 @@ Load the LoRA weights from your finetuned DreamBooth model *on top of the base m
 </Tip>
 
 ```py
->>> pipe.unet.load_attn_procs(model_path)
+>>> pipe.unet.load_attn_procs(lora_model_path)
 >>> pipe.to("cuda")
 # use half the weights from the LoRA finetuned model and half the weights from the base model
 
@@ -211,4 +240,36 @@ Load the LoRA weights from your finetuned DreamBooth model *on top of the base m
 
 >>> image = pipe("A picture of a sks dog in a bucket.", num_inference_steps=25, guidance_scale=7.5).images[0]
 >>> image.save("bucket-dog.png")
-```
+```
+
+If you used `--train_text_encoder` during training, then use `pipe.load_lora_weights()` to load the LoRA
+weights. For example:
+
+```python
+from huggingface_hub.repocard import RepoCard
+from diffusers import StableDiffusionPipeline
+import torch
+
+lora_model_id = "sayakpaul/dreambooth-text-encoder-test"
+card = RepoCard.load(lora_model_id)
+base_model_id = card.data.to_dict()["base_model"]
+
+pipe = StableDiffusionPipeline.from_pretrained(base_model_id, torch_dtype=torch.float16)
+pipe = pipe.to("cuda")
+pipe.load_lora_weights(lora_model_id)
+image = pipe("A picture of a sks dog in a bucket", num_inference_steps=25).images[0]
+```
+
+Note that the use of [`~diffusers.loaders.LoraLoaderMixin.load_lora_weights`] is preferred to [`~diffusers.loaders.UNet2DConditionLoadersMixin.load_attn_procs`] for loading LoRA parameters. This is because
+[`~diffusers.loaders.LoraLoaderMixin.load_lora_weights`] can handle the following situations:
+
+* LoRA parameters that don't have separate identifiers for the UNet and the text encoder (such as [`"patrickvonplaten/lora_dreambooth_dog_example"`](https://huggingface.co/patrickvonplaten/lora_dreambooth_dog_example)). So, you can just do:
+
+  ```py 
+  pipe.load_lora_weights(lora_model_path)
+  ```
+
+* LoRA parameters that have separate identifiers for the UNet and the text encoder such as: [`"sayakpaul/dreambooth"`](https://huggingface.co/sayakpaul/dreambooth).
+
+**Note** that it is possible to provide a local directory path to [`~diffusers.loaders.LoraLoaderMixin.load_lora_weights`] as well as [`~diffusers.loaders.UNet2DConditionLoadersMixin.load_attn_procs`]. To know about the supported inputs,
+refer to the respective docstrings.

docs/source/en/training/overview.mdx

@@ -39,6 +39,8 @@ Training examples show how to pretrain or fine-tune diffusion models for a varie
 - [Dreambooth](./dreambooth)
 - [LoRA Support](./lora)
 - [ControlNet](./controlnet)
+- [InstructPix2Pix](./instructpix2pix)
+- [Custom Diffusion](./custom_diffusion)
 
 If possible, please [install xFormers](../optimization/xformers) for memory efficient attention. This could help make your training faster and less memory intensive.
 
@@ -50,6 +52,8 @@ If possible, please [install xFormers](../optimization/xformers) for memory effi
 | [**Dreambooth**](./dreambooth) | ✅ | - | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_dreambooth_training.ipynb)
 | [**Training with LoRA**](./lora) | ✅ | - | - |
 | [**ControlNet**](./controlnet) | ✅ | ✅ | - |
+| [**InstructPix2Pix**](./instructpix2pix) | ✅ | ✅ | - |
+| [**Custom Diffusion**](./custom_diffusion) | ✅ | ✅ | - |
 
 ## Community
 

docs/source/en/training/text2image.mdx

@@ -72,7 +72,9 @@ To load a checkpoint to resume training, pass the argument `--resume_from_checkp
 
 <frameworkcontent>
 <pt>
-Launch the [PyTorch training script](https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image.py) for a fine-tuning run on the [Pokémon BLIP captions](https://huggingface.co/datasets/lambdalabs/pokemon-blip-captions) dataset like this:
+Launch the [PyTorch training script](https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image.py) for a fine-tuning run on the [Pokémon BLIP captions](https://huggingface.co/datasets/lambdalabs/pokemon-blip-captions) dataset like this.
+
+Specify the `MODEL_NAME` environment variable (either a Hub model repository id or a path to the directory containing the model weights) and pass it to the [`pretrained_model_name_or_path`](https://huggingface.co/docs/diffusers/en/api/diffusion_pipeline#diffusers.DiffusionPipeline.from_pretrained.pretrained_model_name_or_path) argument.
 
 <literalinclude>
 {"path": "../../../../examples/text_to_image/README.md",
@@ -106,6 +108,31 @@ accelerate launch train_text_to_image.py \
   --lr_scheduler="constant" --lr_warmup_steps=0 \
   --output_dir=${OUTPUT_DIR}
 ```
+
+#### Training with multiple GPUs
+
+`accelerate` allows for seamless multi-GPU training. Follow the instructions [here](https://huggingface.co/docs/accelerate/basic_tutorials/launch)
+for running distributed training with `accelerate`. Here is an example command:
+
+```bash
+export MODEL_NAME="CompVis/stable-diffusion-v1-4"
+export dataset_name="lambdalabs/pokemon-blip-captions"
+
+accelerate launch --mixed_precision="fp16" --multi_gpu  train_text_to_image.py \
+  --pretrained_model_name_or_path=$MODEL_NAME \
+  --dataset_name=$dataset_name \
+  --use_ema \
+  --resolution=512 --center_crop --random_flip \
+  --train_batch_size=1 \
+  --gradient_accumulation_steps=4 \
+  --gradient_checkpointing \
+  --max_train_steps=15000 \ 
+  --learning_rate=1e-05 \
+  --max_grad_norm=1 \
+  --lr_scheduler="constant" --lr_warmup_steps=0 \
+  --output_dir="sd-pokemon-model" 
+```
+
 </pt>
 <jax>
 With Flax, it's possible to train a Stable Diffusion model faster on TPUs and GPUs thanks to [@duongna211](https://github.com/duongna21). This is very efficient on TPU hardware but works great on GPUs too. The Flax training script doesn't support features like gradient checkpointing or gradient accumulation yet, so you'll need a GPU with at least 30GB of memory or a TPU v3.
@@ -116,6 +143,8 @@ Before running the script, make sure you have the requirements installed:
 pip install -U -r requirements_flax.txt
 ```
 
+Specify the `MODEL_NAME` environment variable (either a Hub model repository id or a path to the directory containing the model weights) and pass it to the [`pretrained_model_name_or_path`](https://huggingface.co/docs/diffusers/en/api/diffusion_pipeline#diffusers.DiffusionPipeline.from_pretrained.pretrained_model_name_or_path) argument.
+
 Now you can launch the [Flax training script](https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image_flax.py) like this:
 
 ```bash
@@ -155,6 +184,28 @@ python train_text_to_image_flax.py \
 </jax>
 </frameworkcontent>
 
+## Training with Min-SNR weighting
+
+We support training with the Min-SNR weighting strategy proposed in [Efficient Diffusion Training via Min-SNR Weighting Strategy](https://arxiv.org/abs/2303.09556) which helps to achieve faster convergence
+by rebalancing the loss. In order to use it, one needs to set the `--snr_gamma` argument. The recommended
+value when using it is 5.0. 
+
+You can find [this project on Weights and Biases](https://wandb.ai/sayakpaul/text2image-finetune-minsnr) that compares the loss surfaces of the following setups:
+
+* Training without the Min-SNR weighting strategy
+* Training with the Min-SNR weighting strategy (`snr_gamma` set to 5.0)
+* Training with the Min-SNR weighting strategy (`snr_gamma` set to 1.0)
+
+For our small Pokemons dataset, the effects of Min-SNR weighting strategy might not appear to be pronounced, but for larger datasets, we believe the effects will be more pronounced.
+
+Also, note that in this example, we either predict `epsilon` (i.e., the noise) or the `v_prediction`. For both of these cases, the formulation of the Min-SNR weighting strategy that we have used holds. 
+
+<Tip warning={true}>
+
+Training with Min-SNR weighting strategy is only supported in PyTorch.
+
+</Tip>
+
 ## LoRA
 
 You can also use Low-Rank Adaptation of Large Language Models (LoRA), a fine-tuning technique for accelerating training large models, for fine-tuning text-to-image models. For more details, take a look at the [LoRA training](lora#text-to-image) guide.

docs/source/en/training/text_inversion.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2023 The HuggingFace Team. All rights reserved.
+ <!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at
@@ -81,9 +81,20 @@ To resume training from a saved checkpoint, pass the following argument to the t
 
 ## Finetuning
 
-For your training dataset, download these [images of a cat statue](https://drive.google.com/drive/folders/1fmJMs25nxS_rSNqS5hTcRdLem_YQXbq5) and store them in a directory. 
+For your training dataset, download these [images of a cat toy](https://huggingface.co/datasets/diffusers/cat_toy_example) and store them in a directory. To use your own dataset, take a look at the [Create a dataset for training](create_dataset) guide.
 
-Set the `MODEL_NAME` environment variable to the model repository id, and the `DATA_DIR` environment variable to the path of the directory containing the images. Now you can launch the [training script](https://github.com/huggingface/diffusers/blob/main/examples/textual_inversion/textual_inversion.py):
+```py
+from huggingface_hub import snapshot_download
+
+local_dir = "./cat"
+snapshot_download(
+    "diffusers/cat_toy_example", local_dir=local_dir, repo_type="dataset", ignore_patterns=".gitattributes"
+)
+```
+
+Specify the `MODEL_NAME` environment variable (either a Hub model repository id or a path to the directory containing the model weights) and pass it to the [`pretrained_model_name_or_path`](https://huggingface.co/docs/diffusers/en/api/diffusion_pipeline#diffusers.DiffusionPipeline.from_pretrained.pretrained_model_name_or_path) argument, and the `DATA_DIR` environment variable to the path of the directory containing the images. 
+
+Now you can launch the [training script](https://github.com/huggingface/diffusers/blob/main/examples/textual_inversion/textual_inversion.py). The script creates and saves the following files to your repository: `learned_embeds.bin`, `token_identifier.txt`, and `type_of_concept.txt`.
 
 <Tip>
 
@@ -95,7 +106,7 @@ Set the `MODEL_NAME` environment variable to the model repository id, and the `D
 <pt>
 ```bash
 export MODEL_NAME="runwayml/stable-diffusion-v1-5"
-export DATA_DIR="path-to-dir-containing-images"
+export DATA_DIR="./cat"
 
 accelerate launch textual_inversion.py \
   --pretrained_model_name_or_path=$MODEL_NAME \
@@ -111,6 +122,18 @@ accelerate launch textual_inversion.py \
   --lr_warmup_steps=0 \
   --output_dir="textual_inversion_cat"
 ```
+
+<Tip>
+
+💡 If you want to increase the trainable capacity, you can associate your placeholder token, *e.g.* `<cat-toy>` to 
+multiple embedding vectors. This can help the model to better capture the style of more (complex) images. 
+To enable training multiple embedding vectors, simply pass:
+
+```bash
+--num_vectors=5
+```
+
+</Tip>
 </pt>
 <jax>
 If you have access to TPUs, try out the [Flax training script](https://github.com/huggingface/diffusers/blob/main/examples/textual_inversion/textual_inversion_flax.py) to train even faster (this'll also work for GPUs). With the same configuration settings, the Flax training script should be at least 70% faster than the PyTorch training script! ⚡️
@@ -121,11 +144,13 @@ Before you begin, make sure you install the Flax specific dependencies:
 pip install -U -r requirements_flax.txt
 ```
 
+Specify the `MODEL_NAME` environment variable (either a Hub model repository id or a path to the directory containing the model weights) and pass it to the [`pretrained_model_name_or_path`](https://huggingface.co/docs/diffusers/en/api/diffusion_pipeline#diffusers.DiffusionPipeline.from_pretrained.pretrained_model_name_or_path) argument.
+
 Then you can launch the [training script](https://github.com/huggingface/diffusers/blob/main/examples/textual_inversion/textual_inversion_flax.py):
 
 ```bash
 export MODEL_NAME="duongna/stable-diffusion-v1-4-flax"
-export DATA_DIR="path-to-dir-containing-images"
+export DATA_DIR="./cat"
 
 python textual_inversion_flax.py \
   --pretrained_model_name_or_path=$MODEL_NAME \
@@ -157,24 +182,61 @@ If you're interested in following along with your model training progress, you c
 
 ## Inference
 
-Once you have trained a model, you can use it for inference with the [`StableDiffusionPipeline`]. Make sure you include the `placeholder_token` in your prompt, in this case, it is `<cat-toy>`.
+Once you have trained a model, you can use it for inference with the [`StableDiffusionPipeline`].
+
+The textual inversion script will by default only save the textual inversion embedding vector(s) that have 
+been added to the text encoder embedding matrix and consequently been trained.
 
 <frameworkcontent>
 <pt>
+<Tip>
+
+💡 The community has created a large library of different textual inversion embedding vectors, called [sd-concepts-library](https://huggingface.co/sd-concepts-library).
+Instead of training textual inversion embeddings from scratch you can also see whether a fitting textual inversion embedding has already been added to the libary.
+
+</Tip>
+
+To load the textual inversion embeddings you first need to load the base model that was used when training 
+your textual inversion embedding vectors. Here we assume that [`runwayml/stable-diffusion-v1-5`](runwayml/stable-diffusion-v1-5)
+was used as a base model so we load it first:
 ```python
 from diffusers import StableDiffusionPipeline
+import torch
 
-model_id = "path-to-your-trained-model"
+model_id = "runwayml/stable-diffusion-v1-5"
 pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16).to("cuda")
+```
 
+Next, we need to load the textual inversion embedding vector which can be done via the [`TextualInversionLoaderMixin.load_textual_inversion`]
+function. Here we'll load the embeddings of the "<cat-toy>" example from before.
+```python
+pipe.load_textual_inversion("sd-concepts-library/cat-toy")
+```
+
+Now we can run the pipeline making sure that the placeholder token `<cat-toy>` is used in our prompt.
+
+```python
 prompt = "A <cat-toy> backpack"
 
-image = pipe(prompt, num_inference_steps=50, guidance_scale=7.5).images[0]
-
+image = pipe(prompt, num_inference_steps=50).images[0]
 image.save("cat-backpack.png")
 ```
+
+The function [`TextualInversionLoaderMixin.load_textual_inversion`] can not only 
+load textual embedding vectors saved in Diffusers' format, but also embedding vectors
+saved in [Automatic1111](https://github.com/AUTOMATIC1111/stable-diffusion-webui) format.
+To do so, you can first download an embedding vector from [civitAI](https://civitai.com/models/3036?modelVersionId=8387)
+and then load it locally:
+```python
+pipe.load_textual_inversion("./charturnerv2.pt")
+```
 </pt>
 <jax>
+Currently there is no `load_textual_inversion` function for Flax so one has to make sure the textual inversion
+embedding vector is saved as part of the model after training.
+
+The model can then be run just like any other Flax model:
+
 ```python
 import jax
 import numpy as np
@@ -183,7 +245,7 @@ from flax.training.common_utils import shard
 from diffusers import FlaxStableDiffusionPipeline
 
 model_path = "path-to-your-trained-model"
-pipe, params = FlaxStableDiffusionPipeline.from_pretrained(model_path, dtype=jax.numpy.bfloat16)
+pipeline, params = FlaxStableDiffusionPipeline.from_pretrained(model_path, dtype=jax.numpy.bfloat16)
 
 prompt = "A <cat-toy> backpack"
 prng_seed = jax.random.PRNGKey(0)

docs/source/en/training/unconditional_training.mdx

@@ -74,7 +74,9 @@ The full training state is saved in a subfolder in the `output_dir` every 500 st
 
 ## Finetuning
 
-You're ready to launch the [training script](https://github.com/huggingface/diffusers/blob/main/examples/unconditional_image_generation/train_unconditional.py) now! Specify the dataset name to finetune on with the `--dataset_name` argument and then save it to the path in `--output_dir`.
+You're ready to launch the [training script](https://github.com/huggingface/diffusers/blob/main/examples/unconditional_image_generation/train_unconditional.py) now! Specify the dataset name to finetune on with the `--dataset_name` argument and then save it to the path in `--output_dir`. To use your own dataset, take a look at the [Create a dataset for training](create_dataset) guide.
+
+The training script creates and saves a `diffusion_pytorch_model.bin` file in your repository.
 
 <Tip>
 
@@ -122,80 +124,22 @@ accelerate launch train_unconditional.py \
     <img src="https://user-images.githubusercontent.com/26864830/180248200-928953b4-db38-48db-b0c6-8b740fe6786f.png"/>
 </div>
 
-## Finetuning with your own data
+### Training with multiple GPUs
 
-There are two ways to finetune a model on your own dataset:
-
-- provide your own folder of images to the `--train_data_dir` argument
-- upload your dataset to the Hub and pass the dataset repository id to the `--dataset_name` argument.
-
-<Tip>
-
-💡 Learn more about how to create an image dataset for training in the [Create an image dataset](https://huggingface.co/docs/datasets/image_dataset) guide. 
-
-</Tip>
-
-Below, we explain both in more detail.
-
-### Provide the dataset as a folder
-
-If you provide your own dataset as a folder, the script expects the following directory structure:
+`accelerate` allows for seamless multi-GPU training. Follow the instructions [here](https://huggingface.co/docs/accelerate/basic_tutorials/launch)
+for running distributed training with `accelerate`. Here is an example command:
 
 ```bash
-data_dir/xxx.png
-data_dir/xxy.png
-data_dir/[...]/xxz.png
-```
-
-Pass the path to the folder containing the images to the `--train_data_dir` argument and launch the training:
-
-```bash
-accelerate launch train_unconditional.py \
-    --train_data_dir <path-to-train-directory> \
-    <other-arguments>
-```
-
-Internally, the script uses the [`ImageFolder`](https://huggingface.co/docs/datasets/image_load#imagefolder) to automatically build a dataset from the folder.
-
-### Upload your data to the Hub
-
-<Tip>
-
-💡 For more details and context about creating and uploading a dataset to the Hub, take a look at the [Image search with 🤗 Datasets](https://huggingface.co/blog/image-search-datasets) post.
-
-</Tip>
-
-To upload your dataset to the Hub, you can start by creating one with the [`ImageFolder`](https://huggingface.co/docs/datasets/image_load#imagefolder) feature, which creates an `image` column containing the PIL-encoded images, from 🤗 Datasets:
-
-```python
-from datasets import load_dataset
-
-# example 1: local folder
-dataset = load_dataset("imagefolder", data_dir="path_to_your_folder")
-
-# example 2: local files (supported formats are tar, gzip, zip, xz, rar, zstd)
-dataset = load_dataset("imagefolder", data_files="path_to_zip_file")
-
-# example 3: remote files (supported formats are tar, gzip, zip, xz, rar, zstd)
-dataset = load_dataset(
-    "imagefolder",
-    data_files="https://download.microsoft.com/download/3/E/1/3E1C3F21-ECDB-4869-8368-6DEBA77B919F/kagglecatsanddogs_3367a.zip",
-)
-
-# example 4: providing several splits
-dataset = load_dataset(
-    "imagefolder", data_files={"train": ["path/to/file1", "path/to/file2"], "test": ["path/to/file3", "path/to/file4"]}
-)
-```
-
-Then you can use the [`~datasets.Dataset.push_to_hub`] method to upload it to the Hub:
-
-```python
-# assuming you have ran the huggingface-cli login command in a terminal
-dataset.push_to_hub("name_of_your_dataset")
-
-# if you want to push to a private repo, simply pass private=True:
-dataset.push_to_hub("name_of_your_dataset", private=True)
-```
-
-Now train your model by simply setting the `--dataset_name` argument to the name of your dataset on the Hub.
+accelerate launch --mixed_precision="fp16" --multi_gpu train_unconditional.py \
+  --dataset_name="huggan/pokemon" \
+  --resolution=64 --center_crop --random_flip \
+  --output_dir="ddpm-ema-pokemon-64" \
+  --train_batch_size=16 \
+  --num_epochs=100 \
+  --gradient_accumulation_steps=1 \
+  --use_ema \
+  --learning_rate=1e-4 \
+  --lr_warmup_steps=500 \
+  --mixed_precision="fp16" \
+  --logger="wandb"
+```

docs/source/en/tutorials/basic_training.mdx

@@ -344,7 +344,7 @@ Now you can wrap all these components together in a training loop with 🤗 Acce
 
 ...             # Sample a random timestep for each image
 ...             timesteps = torch.randint(
-...                 0, noise_scheduler.num_train_timesteps, (bs,), device=clean_images.device
+...                 0, noise_scheduler.config.num_train_timesteps, (bs,), device=clean_images.device
 ...             ).long()
 
 ...             # Add noise to the clean images according to the noise magnitude at each timestep

docs/source/en/using-diffusers/contribute_pipeline.mdx

@@ -10,17 +10,21 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
 specific language governing permissions and limitations under the License.
 -->
 
-# How to build a community pipeline
+# How to contribute a community pipeline
 
-*Note*: this page was built from the GitHub Issue on Community Pipelines [#841](https://github.com/huggingface/diffusers/issues/841).
+<Tip>
 
-Let's make an example!
-Say you want to define a pipeline that just does a single forward pass to a U-Net and then calls a scheduler only once (Note, this doesn't make any sense from a scientific point of view, but only represents an example of how things work under the hood).
+💡 Take a look at GitHub Issue [#841](https://github.com/huggingface/diffusers/issues/841) for more context about why we're adding community pipelines to help everyone easily share their work without being slowed down.
 
-Cool! So you open your favorite IDE and start creating your pipeline 💻.
-First, what model weights and configurations do we need?
-We have a U-Net and a scheduler, so our pipeline should take a U-Net and a scheduler as an argument.
-Also, as stated above, you'd like to be able to load weights and the scheduler config for Hub and share your code with others, so we'll inherit from `DiffusionPipeline`:
+</Tip>
+
+Community pipelines allow you to add any additional features you'd like on top of the [`DiffusionPipeline`]. The main benefit of building on top of the `DiffusionPipeline` is anyone can load and use your pipeline by only adding one more argument, making it super easy for the community to access.
+
+This guide will show you how to create a community pipeline and explain how they work. To keep things simple, you'll create a "one-step" pipeline where the `UNet` does a single forward pass and calls the scheduler once.
+
+## Initialize the pipeline
+
+You should start by creating a `one_step_unet.py` file for your community pipeline. In this file, create a pipeline class that inherits from the [`DiffusionPipeline`] to be able to load model weights and the scheduler configuration from the Hub. The one-step pipeline needs a `UNet` and a scheduler, so you'll need to add these as arguments to the `__init__` function:
 
 ```python
 from diffusers import DiffusionPipeline
@@ -32,50 +36,52 @@ class UnetSchedulerOneForwardPipeline(DiffusionPipeline):
         super().__init__()
 ```
 
-Now, we must save the `unet` and `scheduler` in a config file so that you can save your pipeline with `save_pretrained`.
-Therefore, make sure you add every component that is save-able to the `register_modules` function:
+To ensure your pipeline and its components (`unet` and `scheduler`) can be saved with [`~DiffusionPipeline.save_pretrained`], add them to the `register_modules` function:
 
-```python
-from diffusers import DiffusionPipeline
-import torch
+```diff
+  from diffusers import DiffusionPipeline
+  import torch
 
+  class UnetSchedulerOneForwardPipeline(DiffusionPipeline):
+      def __init__(self, unet, scheduler):
+          super().__init__()
 
-class UnetSchedulerOneForwardPipeline(DiffusionPipeline):
-    def __init__(self, unet, scheduler):
-        super().__init__()
-
-        self.register_modules(unet=unet, scheduler=scheduler)
++         self.register_modules(unet=unet, scheduler=scheduler)
 ```
 
-Cool, the init is done! 🔥 Now, let's go into the forward pass, which we recommend defining as `__call__` . Here you're given all the creative freedom there is. For our amazing "one-step" pipeline, we simply create a random image and call the unet once and the scheduler once:
+Cool, the `__init__` step is done and you can move to the forward pass now! 🔥 
 
-```python
-from diffusers import DiffusionPipeline
-import torch
+## Define the forward pass
+
+In the forward pass, which we recommend defining as `__call__`, you have complete creative freedom to add whatever feature you'd like. For our amazing one-step pipeline, create a random image and only call the `unet` and `scheduler` once by setting `timestep=1`:
+
+```diff
+  from diffusers import DiffusionPipeline
+  import torch
 
 
-class UnetSchedulerOneForwardPipeline(DiffusionPipeline):
-    def __init__(self, unet, scheduler):
-        super().__init__()
+  class UnetSchedulerOneForwardPipeline(DiffusionPipeline):
+      def __init__(self, unet, scheduler):
+          super().__init__()
 
-        self.register_modules(unet=unet, scheduler=scheduler)
+          self.register_modules(unet=unet, scheduler=scheduler)
 
-    def __call__(self):
-        image = torch.randn(
-            (1, self.unet.in_channels, self.unet.sample_size, self.unet.sample_size),
-        )
-        timestep = 1
++     def __call__(self):
++         image = torch.randn(
++             (1, self.unet.config.in_channels, self.unet.config.sample_size, self.unet.config.sample_size),
++         )
++         timestep = 1
 
-        model_output = self.unet(image, timestep).sample
-        scheduler_output = self.scheduler.step(model_output, timestep, image).prev_sample
++         model_output = self.unet(image, timestep).sample
++         scheduler_output = self.scheduler.step(model_output, timestep, image).prev_sample
 
-        return scheduler_output
++         return scheduler_output
 ```
 
-Cool, that's it! 🚀 You can now run this pipeline by passing a `unet` and a `scheduler` to the init:
+That's it! 🚀 You can now run this pipeline by passing a `unet` and `scheduler` to it:
 
 ```python
-from diffusers import DDPMScheduler, Unet2DModel
+from diffusers import DDPMScheduler, UNet2DModel
 
 scheduler = DDPMScheduler()
 unet = UNet2DModel()
@@ -85,7 +91,7 @@ pipeline = UnetSchedulerOneForwardPipeline(unet=unet, scheduler=scheduler)
 output = pipeline()
 ```
 
-But what's even better is that you can load pre-existing weights into the pipeline if they match exactly your pipeline structure. This is e.g. the case for [https://huggingface.co/google/ddpm-cifar10-32](https://huggingface.co/google/ddpm-cifar10-32) so that we can do the following:
+But what's even better is you can load pre-existing weights into the pipeline if the pipeline structure is identical. For example, you can load the [`google/ddpm-cifar10-32`](https://huggingface.co/google/ddpm-cifar10-32) weights into the one-step pipeline:
 
 ```python
 pipeline = UnetSchedulerOneForwardPipeline.from_pretrained("google/ddpm-cifar10-32")
@@ -93,33 +99,11 @@ pipeline = UnetSchedulerOneForwardPipeline.from_pretrained("google/ddpm-cifar10-
 output = pipeline()
 ```
 
-We want to share this amazing pipeline with the community, so we would open a PR request to add the following code under `one_step_unet.py` to [https://github.com/huggingface/diffusers/tree/main/examples/community](https://github.com/huggingface/diffusers/tree/main/examples/community) .
+## Share your pipeline
 
-```python
-from diffusers import DiffusionPipeline
-import torch
+Open a Pull Request on the 🧨 Diffusers [repository](https://github.com/huggingface/diffusers) to add your awesome pipeline in `one_step_unet.py` to the [examples/community](https://github.com/huggingface/diffusers/tree/main/examples/community) subfolder.
 
-
-class UnetSchedulerOneForwardPipeline(DiffusionPipeline):
-    def __init__(self, unet, scheduler):
-        super().__init__()
-
-        self.register_modules(unet=unet, scheduler=scheduler)
-
-    def __call__(self):
-        image = torch.randn(
-            (1, self.unet.in_channels, self.unet.sample_size, self.unet.sample_size),
-        )
-        timestep = 1
-
-        model_output = self.unet(image, timestep).sample
-        scheduler_output = self.scheduler.step(model_output, timestep, image).prev_sample
-
-        return scheduler_output
-```
-
-Our amazing pipeline got merged here: [#840](https://github.com/huggingface/diffusers/pull/840).
-Now everybody that has `diffusers >= 0.4.0` installed can use our pipeline magically 🪄 as follows:
+Once it is merged, anyone with `diffusers >= 0.4.0` installed can use this pipeline magically 🪄 by specifying it in the `custom_pipeline` argument:
 
 ```python
 from diffusers import DiffusionPipeline
@@ -128,28 +112,59 @@ pipe = DiffusionPipeline.from_pretrained("google/ddpm-cifar10-32", custom_pipeli
 pipe()
 ```
 
-Another way to upload your custom_pipeline, besides sending a PR, is uploading the code that contains it to the Hugging Face Hub, [as exemplified here](https://huggingface.co/docs/diffusers/using-diffusers/custom_pipeline_overview#loading-custom-pipelines-from-the-hub).
+Another way to share your community pipeline is to upload the `one_step_unet.py` file directly to your preferred [model repository](https://huggingface.co/docs/hub/models-uploading) on the Hub. Instead of specifying the `one_step_unet.py` file, pass the model repository id to the `custom_pipeline` argument:
 
-**Try it out now - it works!**
+```python
+from diffusers import DiffusionPipeline
 
-In general, you will want to create much more sophisticated pipelines, so we recommend looking at existing pipelines here: [https://github.com/huggingface/diffusers/tree/main/examples/community](https://github.com/huggingface/diffusers/tree/main/examples/community).
+pipeline = DiffusionPipeline.from_pretrained("google/ddpm-cifar10-32", custom_pipeline="stevhliu/one_step_unet")
+```
 
-IMPORTANT:
-You can use whatever package you want in your community pipeline file - as long as the user has it installed, everything will work fine. Make sure you have one and only one pipeline class that inherits from `DiffusionPipeline` as this will be automatically detected.
+Take a look at the following table to compare the two sharing workflows to help you decide the best option for you:
+
+|                | GitHub community pipeline                                                                                        | HF Hub community pipeline                                                                 |
+|----------------|------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------|
+| usage          | same                                                                                                             | same                                                                                      |
+| review process | open a Pull Request on GitHub and undergo a review process from the Diffusers team before merging; may be slower | upload directly to a Hub repository without any review; this is the fastest workflow      |
+| visibility     | included in the official Diffusers repository and documentation                                                  | included on your HF Hub profile and relies on your own usage/promotion to gain visibility |
+
+<Tip>
+
+💡 You can use whatever package you want in your community pipeline file - as long as the user has it installed, everything will work fine. Make sure you have one and only one pipeline class that inherits from `DiffusionPipeline` because this is automatically detected.
+
+</Tip>
 
 ## How do community pipelines work?
-A community pipeline is a class that has to inherit from ['DiffusionPipeline']:
-and that has been added to `examples/community` [files](https://github.com/huggingface/diffusers/tree/main/examples/community).
-The community can load the pipeline code via the custom_pipeline argument from DiffusionPipeline. See docs [here](https://huggingface.co/docs/diffusers/api/diffusion_pipeline#diffusers.DiffusionPipeline.from_pretrained.custom_pipeline):
 
-This means:
-The model weights and configs of the pipeline should be loaded from the `pretrained_model_name_or_path` [argument](https://huggingface.co/docs/diffusers/api/diffusion_pipeline#diffusers.DiffusionPipeline.from_pretrained.pretrained_model_name_or_path):
-whereas the code that powers the community pipeline is defined in a file added in [`examples/community`](https://github.com/huggingface/diffusers/tree/main/examples/community).
+A community pipeline is a class that inherits from [`DiffusionPipeline`] which means:
 
-Now, it might very well be that only some of your pipeline components weights can be downloaded from an official repo.
-The other components should then be passed directly to init as is the case for the ClIP guidance notebook [here](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/CLIP_Guided_Stable_diffusion_with_diffusers.ipynb#scrollTo=z9Kglma6hjki).
+- It can be loaded with the [`custom_pipeline`] argument.
+- The model weights and scheduler configuration are loaded from [`pretrained_model_name_or_path`].
+- The code that implements a feature in the community pipeline is defined in a `pipeline.py` file.
 
-The magic behind all of this is that we load the code directly from GitHub. You can check it out in more detail if you follow the functionality defined here:
+Sometimes you can't load all the pipeline components weights from an official repository. In this case, the other components should be passed directly to the pipeline:
+
+```python
+from diffusers import DiffusionPipeline
+from transformers import CLIPFeatureExtractor, CLIPModel
+
+model_id = "CompVis/stable-diffusion-v1-4"
+clip_model_id = "laion/CLIP-ViT-B-32-laion2B-s34B-b79K"
+
+feature_extractor = CLIPFeatureExtractor.from_pretrained(clip_model_id)
+clip_model = CLIPModel.from_pretrained(clip_model_id, torch_dtype=torch.float16)
+
+pipeline = DiffusionPipeline.from_pretrained(
+    model_id,
+    custom_pipeline="clip_guided_stable_diffusion",
+    clip_model=clip_model,
+    feature_extractor=feature_extractor,
+    scheduler=scheduler,
+    torch_dtype=torch.float16,
+)
+```
+
+The magic behind community pipelines is contained in the following code. It allows the community pipeline to be loaded from GitHub or the Hub, and it'll be available to all 🧨 Diffusers packages.
 
 ```python
 # 2. Load the pipeline class, if using custom module then load it from the hub
@@ -164,6 +179,3 @@ else:
     diffusers_module = importlib.import_module(cls.__module__.split(".")[0])
     pipeline_class = getattr(diffusers_module, config_dict["_class_name"])
 ```
-
-This is why a community pipeline merged to GitHub will be directly available to all `diffusers` packages.
-

docs/source/en/using-diffusers/controlling_generation.mdx

@@ -37,6 +37,28 @@ Unless otherwise mentioned, these are techniques that work with existing models
 9. [Textual Inversion](#textual-inversion)
 10. [ControlNet](#controlnet)
 11. [Prompt Weighting](#prompt-weighting)
+12. [Custom Diffusion](#custom-diffusion)
+13. [Model Editing](#model-editing)
+14. [DiffEdit](#diffedit)
+
+For convenience, we provide a table to denote which methods are inference-only and which require fine-tuning/training. 
+
+| **Method** | **Inference only** | **Requires training /<br> fine-tuning** | **Comments** |
+|:---:|:---:|:---:|:---:|
+| [Instruct Pix2Pix](#instruct-pix2pix) | ✅ | ❌ | Can additionally be<br>fine-tuned for better <br>performance on specific <br>edit instructions. |
+| [Pix2Pix Zero](#pix2pixzero) | ✅ | ❌ |  |
+| [Attend and Excite](#attend-and-excite) | ✅ | ❌ |  |
+| [Semantic Guidance](#semantic-guidance) | ✅ | ❌ |  |
+| [Self-attention Guidance](#self-attention-guidance) | ✅ | ❌ |  |
+| [Depth2Image](#depth2image) | ✅ | ❌ |  |
+| [MultiDiffusion Panorama](#multidiffusion-panorama) | ✅ | ❌ |  |
+| [DreamBooth](#dreambooth) | ❌ | ✅ |  |
+| [Textual Inversion](#textual-inversion) | ❌ | ✅ |  |
+| [ControlNet](#controlnet) | ✅ | ❌ | A ControlNet can be <br>trained/fine-tuned on<br>a custom conditioning.  |
+| [Prompt Weighting](#prompt-weighting) | ✅ | ❌ |  |
+| [Custom Diffusion](#custom-diffusion) | ❌ | ✅ |  |
+| [Model Editing](#model-editing) | ✅ | ❌ |  |
+| [DiffEdit](#diffedit) | ✅ | ❌ |  |
 
 ## Instruct Pix2Pix
 
@@ -137,13 +159,13 @@ See [here](../api/pipelines/stable_diffusion/panorama) for more information on h
 
 In addition to pre-trained models, Diffusers has training scripts for fine-tuning models on user-provided data.
 
-### DreamBooth
+## DreamBooth
 
 [DreamBooth](../training/dreambooth) fine-tunes a model to teach it about a new subject. I.e. a few pictures of a person can be used to generate images of that person in different styles.
 
 See [here](../training/dreambooth) for more information on how to use it.
 
-### Textual Inversion
+## Textual Inversion
 
 [Textual Inversion](../training/text_inversion) fine-tunes a model to teach it about a new concept. I.e. a few pictures of a style of artwork can be used to generate images in that style.
 
@@ -165,3 +187,32 @@ Prompt weighting is a simple technique that puts more attention weight on certai
 input. 
 
 For a more in-detail explanation and examples, see [here](../using-diffusers/weighted_prompts).
+
+## Custom Diffusion 
+
+[Custom Diffusion](../training/custom_diffusion) only fine-tunes the cross-attention maps of a pre-trained 
+text-to-image diffusion model. It also allows for additionally performing textual inversion. It supports 
+multi-concept training by design. Like DreamBooth and Textual Inversion, Custom Diffusion is also used to
+teach a pre-trained text-to-image diffusion model about new concepts to generate outputs involving the 
+concept(s) of interest.
+ 
+For more details, check out our [official doc](../training/custom_diffusion). 
+
+## Model Editing 
+
+[Paper](https://arxiv.org/abs/2303.08084)
+
+The [text-to-image model editing pipeline](../api/pipelines/stable_diffusion/model_editing) helps you mitigate some of the incorrect implicit assumptions a pre-trained text-to-image
+diffusion model might make about the subjects present in the input prompt. For example, if you prompt Stable Diffusion to generate images for "A pack of roses", the roses in the generated images
+are more likely to be red. This pipeline helps you change that assumption. 
+
+To know more details, check out the [official doc](../api/pipelines/stable_diffusion/model_editing).
+
+## DiffEdit 
+
+[Paper](https://arxiv.org/abs/2210.11427)
+
+[DiffEdit](../api/pipelines/stable_diffusion/diffedit) allows for semantic editing of input images along with 
+input prompts while preserving the original input images as much as possible. 
+
+To know more details, check out the [official doc](../api/pipelines/stable_diffusion/model_editing).

docs/source/en/using-diffusers/custom_pipeline_examples.mdx

@@ -10,7 +10,7 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
 specific language governing permissions and limitations under the License.
 -->
 
-# Custom Pipelines
+# Community pipelines
 
 > **For more information about community pipelines, please have a look at [this issue](https://github.com/huggingface/diffusers/issues/841).**
 

docs/source/en/using-diffusers/custom_pipeline_overview.mdx

@@ -10,19 +10,21 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
 specific language governing permissions and limitations under the License.
 -->
 
-# Loading and Adding Custom Pipelines
+# Load community pipelines
 
-Diffusers allows you to conveniently load any custom pipeline from the Hugging Face Hub as well as any [official community pipeline](https://github.com/huggingface/diffusers/tree/main/examples/community) 
-via the [`DiffusionPipeline`] class.
+Community pipelines are any [`DiffusionPipeline`] class that are different from the original implementation as specified in their paper (for example, the [`StableDiffusionControlNetPipeline`] corresponds to the [Text-to-Image Generation with ControlNet Conditioning](https://arxiv.org/abs/2302.05543) paper). They provide additional functionality or extend the original implementation of a pipeline.
 
-## Loading custom pipelines from the Hub
+There are many cool community pipelines like [Speech to Image](https://github.com/huggingface/diffusers/tree/main/examples/community#speech-to-image) or [Composable Stable Diffusion](https://github.com/huggingface/diffusers/tree/main/examples/community#composable-stable-diffusion), and you can find all the official community pipelines [here](https://github.com/huggingface/diffusers/tree/main/examples/community).
 
-Custom pipelines can be easily loaded from any model repository on the Hub that defines a diffusion pipeline in a `pipeline.py` file.
-Let's load a dummy pipeline from [hf-internal-testing/diffusers-dummy-pipeline](https://huggingface.co/hf-internal-testing/diffusers-dummy-pipeline).
+To load any community pipeline on the Hub, pass the repository id of the community pipeline to the `custom_pipeline` argument and the model repository where you'd like to load the pipeline weights and components from. For example, the example below loads a dummy pipeline from [`hf-internal-testing/diffusers-dummy-pipeline`](https://huggingface.co/hf-internal-testing/diffusers-dummy-pipeline/blob/main/pipeline.py) and the pipeline weights and components from [`google/ddpm-cifar10-32`](https://huggingface.co/google/ddpm-cifar10-32):
 
-All you need to do is pass the custom pipeline repo id with the `custom_pipeline` argument alongside the repo from where you wish to load the pipeline modules.
+<Tip warning={true}>
 
-```python
+🔒 By loading a community pipeline from the Hugging Face Hub, you are trusting that the code you are loading is safe. Make sure to inspect the code online before loading and running it automatically!
+
+</Tip>
+
+```py
 from diffusers import DiffusionPipeline
 
 pipeline = DiffusionPipeline.from_pretrained(
@@ -30,25 +32,9 @@ pipeline = DiffusionPipeline.from_pretrained(
 )
 ```
 
-This will load the custom pipeline as defined in the [model repository](https://huggingface.co/hf-internal-testing/diffusers-dummy-pipeline/blob/main/pipeline.py).
+Loading an official community pipeline is similar, but you can mix loading weights from an official repository id and pass pipeline components directly. The example below loads the community [CLIP Guided Stable Diffusion](https://github.com/huggingface/diffusers/tree/main/examples/community#clip-guided-stable-diffusion) pipeline, and you can pass the CLIP model components directly to it:
 
-<Tip warning={true} >
-
-By loading a custom pipeline from the Hugging Face Hub, you are trusting that the code you are loading 
-is safe 🔒. Make sure to check out the code online before loading & running it automatically.
-
-</Tip>
-
-## Loading official community pipelines
-
-Community pipelines are summarized in the [community examples folder](https://github.com/huggingface/diffusers/tree/main/examples/community). 
-
-Similarly, you need to pass both the *repo id* from where you wish to load the weights as well as the `custom_pipeline` argument. Here the `custom_pipeline` argument should consist simply of the filename of the community pipeline excluding the `.py` suffix, *e.g.* `clip_guided_stable_diffusion`.
-
-Since community pipelines are often more complex, one can mix loading weights from an official *repo id*
-and passing pipeline modules directly.
-
-```python
+```py
 from diffusers import DiffusionPipeline
 from transformers import CLIPImageProcessor, CLIPModel
 
@@ -65,57 +51,4 @@ pipeline = DiffusionPipeline.from_pretrained(
 )
 ```
 
-## Adding custom pipelines to the Hub
-
-To add a custom pipeline to the Hub, all you need to do is to define a pipeline class that inherits 
-from [`DiffusionPipeline`] in a `pipeline.py` file.
-Make sure that the whole pipeline is encapsulated within a single class and that the `pipeline.py` file
-has only one such class.
-
-Let's quickly define an example pipeline.
-
-
-```python
-import torch
-from diffusers import DiffusionPipeline
-
-
-class MyPipeline(DiffusionPipeline):
-    def __init__(self, unet, scheduler):
-        super().__init__()
-
-    self.register_modules(unet=unet, scheduler=scheduler)
-
-    @torch.no_grad()
-    def __call__(self, batch_size: int = 1, num_inference_steps: int = 50):
-        # Sample gaussian noise to begin loop
-        image = torch.randn((batch_size, self.unet.in_channels, self.unet.sample_size, self.unet.sample_size))
-
-        image = image.to(self.device)
-
-        # set step values
-        self.scheduler.set_timesteps(num_inference_steps)
-
-        for t in self.progress_bar(self.scheduler.timesteps):
-            # 1. predict noise model_output
-            model_output = self.unet(image, t).sample
-
-            # 2. predict previous mean of image x_t-1 and add variance depending on eta
-            # eta corresponds to η in paper and should be between [0, 1]
-            # do x_t -> x_t-1
-            image = self.scheduler.step(model_output, t, image, eta).prev_sample
-
-        image = (image / 2 + 0.5).clamp(0, 1)
-        image = image.cpu().permute(0, 2, 3, 1).numpy()
-
-        return image
-```
-
-Now you can upload this short file under the name `pipeline.py` in your preferred [model repository](https://huggingface.co/docs/hub/models-uploading). For Stable Diffusion pipelines, you may also [join the community organisation for shared pipelines](https://huggingface.co/organizations/sd-diffusers-pipelines-library/share/BUPyDUuHcciGTOKaExlqtfFcyCZsVFdrjr) to upload yours.
-Finally, we can load the custom pipeline by passing the model repository name, *e.g.* `sd-diffusers-pipelines-library/my_custom_pipeline` alongside the model repository from where we want to load the `unet` and `scheduler` components.
-
-```python
-my_pipeline = DiffusionPipeline.from_pretrained(
-    "google/ddpm-cifar10-32", custom_pipeline="patrickvonplaten/my_custom_pipeline"
-)
-```
+For more information about community pipelines, take a look at the [Community pipelines](custom_pipeline_examples) guide for how to use them and if you're interested in adding a community pipeline check out the [How to contribute a community pipeline](contribute_pipeline) guide!

docs/source/en/using-diffusers/inpaint.mdx

@@ -52,7 +52,7 @@ Now you can create a prompt to replace the mask with something else:
 
 ```python
 prompt = "Face of a yellow cat, high resolution, sitting on a park bench"
-image = pipe(prompt=prompt, image=init_image, mask_image=mask_image).images[0]
+image = pipeline(prompt=prompt, image=init_image, mask_image=mask_image).images[0]
 ```
 
 `image`          | `mask_image` | `prompt` | output |

docs/source/en/using-diffusers/loading.mdx

@@ -10,20 +10,28 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
 specific language governing permissions and limitations under the License.
 -->
 
-# Loading
+# Load pipelines, models, and schedulers
 
-A core premise of the diffusers library is to make diffusion models **as accessible as possible**.
-Accessibility is therefore achieved by providing an API to load complete diffusion pipelines as well as individual components with a single line of code. 
+Having an easy way to use a diffusion system for inference is essential to 🧨 Diffusers. Diffusion systems often consist of multiple components like parameterized models, tokenizers, and schedulers that interact in complex ways. That is why we designed the [`DiffusionPipeline`] to wrap the complexity of the entire diffusion system into an easy-to-use API, while remaining flexible enough to be adapted for other use cases, such as loading each component individually as building blocks to assemble your own diffusion system.
 
-In the following we explain in-detail how to easily load:
+Everything you need for inference or training is accessible with the `from_pretrained()` method.
 
-- *Complete Diffusion Pipelines* via the [`DiffusionPipeline.from_pretrained`]
-- *Diffusion Models* via [`ModelMixin.from_pretrained`]
-- *Schedulers* via [`SchedulerMixin.from_pretrained`]
+This guide will show you how to load:
 
-## Loading pipelines
+- pipelines from the Hub and locally
+- different components into a pipeline
+- checkpoint variants such as different floating point types or non-exponential mean averaged (EMA) weights
+- models and schedulers
 
-The [`DiffusionPipeline`] class is the easiest way to access any diffusion model that is [available on the Hub](https://huggingface.co/models?library=diffusers). Let's look at an example on how to download [Runway's Stable Diffusion model](https://huggingface.co/runwayml/stable-diffusion-v1-5).
+## Diffusion Pipeline
+
+<Tip>
+
+💡 Skip to the [DiffusionPipeline explained](#diffusionpipeline-explained) section if you interested in learning in more detail about how the [`DiffusionPipeline`] class works.
+
+</Tip>
+
+The [`DiffusionPipeline`] class is the simplest and most generic way to load any diffusion model from the [Hub](https://huggingface.co/models?library=diffusers). The [`DiffusionPipeline.from_pretrained`] method automatically detects the correct pipeline class from the checkpoint, downloads and caches all the required configuration and weight files, and returns a pipeline instance ready for inference.
 
 ```python
 from diffusers import DiffusionPipeline
@@ -32,10 +40,7 @@ repo_id = "runwayml/stable-diffusion-v1-5"
 pipe = DiffusionPipeline.from_pretrained(repo_id)
 ```
 
-Here [`DiffusionPipeline`] automatically detects the correct pipeline (*i.e.* [`StableDiffusionPipeline`]), downloads and caches all required configuration and weight files (if not already done so), and finally returns a pipeline instance, called `pipe`.
-The pipeline instance can then be called using [`StableDiffusionPipeline.__call__`] (i.e., `pipe("image of a astronaut riding a horse")`) for text-to-image generation.
-
-Instead of using the generic [`DiffusionPipeline`] class for loading, you can also load the appropriate pipeline class directly. The code snippet above yields the same instance as when doing:
+You can also load a checkpoint with it's specific pipeline class. The example above loaded a Stable Diffusion model; to get the same result, use the [`StableDiffusionPipeline`] class:
 
 ```python
 from diffusers import StableDiffusionPipeline
@@ -44,10 +49,7 @@ repo_id = "runwayml/stable-diffusion-v1-5"
 pipe = StableDiffusionPipeline.from_pretrained(repo_id)
 ```
 
-<Tip>
-
-Many checkpoints, such as [CompVis/stable-diffusion-v1-4](https://huggingface.co/CompVis/stable-diffusion-v1-4) and [runwayml/stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5) can be used for multiple tasks, *e.g.* *text-to-image* or *image-to-image*.
-If you want to use those checkpoints for a task that is different from the default one, you have to load it directly from the corresponding task-specific pipeline class:
+A checkpoint (such as [`CompVis/stable-diffusion-v1-4`](https://huggingface.co/CompVis/stable-diffusion-v1-4) or [`runwayml/stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5)) may also be used for more than one task, like text-to-image or image-to-image. To differentiate what task you want to use the checkpoint for, you have to load it directly with it's corresponding task-specific pipeline class:
 
 ```python
 from diffusers import StableDiffusionImg2ImgPipeline
@@ -56,82 +58,16 @@ repo_id = "runwayml/stable-diffusion-v1-5"
 pipe = StableDiffusionImg2ImgPipeline.from_pretrained(repo_id)
 ```
 
-</Tip>
+### Local pipeline
 
+To load a diffusion pipeline locally, use [`git-lfs`](https://git-lfs.github.com/) to manually download the checkpoint (in this case, [`runwayml/stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5)) to your local disk. This creates a local folder, `./stable-diffusion-v1-5`, on your disk:
 
-Diffusion pipelines like `StableDiffusionPipeline` or `StableDiffusionImg2ImgPipeline` consist of multiple components. These components can be both parameterized models, such as `"unet"`, `"vae"` and `"text_encoder"`, tokenizers or schedulers. 
-These components often interact in complex ways with each other when using the pipeline in inference, *e.g.* for [`StableDiffusionPipeline`] the inference call is explained [here](https://huggingface.co/blog/stable_diffusion#how-does-stable-diffusion-work).
-The purpose of the [pipeline classes](./api/overview#diffusers-summary) is to wrap the complexity of these diffusion systems and give the user an easy-to-use API while staying flexible for customization, as will be shown later.
-
-<!---
-THE FOLLOWING CAN BE UNCOMMENTED ONCE WE HAVE NEW MODELS WITH ACCESS REQUIREMENT
-
-# Loading pipelines that require access request
-
-Due to the capabilities of diffusion models to generate extremely realistic images, there is a certain danger that such models might be misused for unwanted applications, *e.g.* generating pornography or violent images.
-In order to minimize the possibility of such unsolicited use cases, some of the most powerful diffusion models require users to acknowledge a license before being able to use the model. If the user does not agree to the license, the pipeline cannot be downloaded.
-If you try to load [`runwayml/stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5) the same way as done previously:
-
-```python
-from diffusers import DiffusionPipeline
-
-repo_id = "runwayml/stable-diffusion-v1-5"
-stable_diffusion = DiffusionPipeline.from_pretrained(repo_id)
-```
-
-it will only work if you have both *click-accepted* the license on [the model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) and are logged into the Hugging Face Hub. Otherwise you will get an error message
-such as the following:
-
-```
-OSError: runwayml/stable-diffusion-v1-5 is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models'
-If this is a private repository, make sure to pass a token having permission to this repo with `use_auth_token` or log in with `huggingface-cli login`
-```
-
-Therefore, we need to make sure to *click-accept* the license. You can do this by simply visiting 
-the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) and clicking on "Agree and access repository":
-
-<p align="center">
-    <br>
-    <img src="https://raw.githubusercontent.com/huggingface/diffusers/main/docs/source/imgs/access_request.png" width="400"/>
-    <br>
-</p>
-
-Second, you need to login with your access token:
-
-```
-huggingface-cli login
-```
-
-before trying to load the model. Or alternatively, you can pass [your access token](https://huggingface.co/docs/hub/security-tokens#user-access-tokens) directly via the flag `use_auth_token`. In this case you do **not** need 
-to run `huggingface-cli login` before:
-
-```python
-from diffusers import DiffusionPipeline
-
-repo_id = "runwayml/stable-diffusion-v1-5"
-stable_diffusion = DiffusionPipeline.from_pretrained(repo_id, use_auth_token="<your-access-token>")
-```
-
-The final option to use pipelines that require access without having to rely on the Hugging Face Hub is to load the pipeline locally as explained in the next section.
--->
-
-### Loading pipelines locally
-
-If you prefer to have complete control over the pipeline and its corresponding files or, as said before, if you want to use pipelines that require an access request without having to be connected to the Hugging Face Hub, 
-we recommend loading pipelines locally.
-
-To load a diffusion pipeline locally, you first need to manually download the whole folder structure on your local disk and then pass a local path to the [`DiffusionPipeline.from_pretrained`]. Let's again look at an example for 
-[Runway's Stable Diffusion Diffusion model](https://huggingface.co/runwayml/stable-diffusion-v1-5).
-
-First, you should make use of [`git-lfs`](https://git-lfs.github.com/) to download the whole folder structure that has been uploaded to the [model repository](https://huggingface.co/runwayml/stable-diffusion-v1-5/tree/main):
-
-```
+```bash
 git lfs install
 git clone https://huggingface.co/runwayml/stable-diffusion-v1-5
 ```
 
-The command above will create a local folder called `./stable-diffusion-v1-5` on your disk.
-Now, all you have to do is to simply pass the local folder path to `from_pretrained`:
+Then pass the local path to [`~DiffusionPipeline.from_pretrained`]:
 
 ```python
 from diffusers import DiffusionPipeline
@@ -140,17 +76,29 @@ repo_id = "./stable-diffusion-v1-5"
 stable_diffusion = DiffusionPipeline.from_pretrained(repo_id)
 ```
 
-If `repo_id` is a local path, as it is the case here, [`DiffusionPipeline.from_pretrained`] will automatically detect it and therefore not try to download any files from the Hub.
-While we usually recommend to load weights directly from the Hub to be certain to stay up to date with the newest changes, loading pipelines locally should be preferred if one 
-wants to stay anonymous, self-contained applications, etc...
+The [`~DiffusionPipeline.from_pretrained`] method won't download any files from the Hub when it detects a local path, but this also means it won't download and cache the latest changes to a checkpoint.
 
-### Loading customized pipelines
+### Swap components in a pipeline
 
-Advanced users that want to load customized versions of diffusion pipelines can do so by swapping any of the default components, *e.g.* the scheduler, with other scheduler classes.
-A classical use case of this functionality is to swap the scheduler. [Stable Diffusion v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5) uses the [`PNDMScheduler`] by default which is generally not the most performant scheduler. Since the release
-of stable diffusion, multiple improved schedulers have been published. To use those, the user has to manually load their preferred scheduler and pass it into [`DiffusionPipeline.from_pretrained`].
+You can customize the default components of any pipeline with another compatible component. Customization is important because:
 
-*E.g.* to use [`EulerDiscreteScheduler`] or [`DPMSolverMultistepScheduler`] to have a better quality vs. generation speed trade-off for inference, one could load them as follows:
+- Changing the scheduler is important for exploring the trade-off between generation speed and quality.
+- Different components of a model are typically trained independently and you can swap out a component with a better-performing one.
+- During finetuning, usually only some components - like the UNet or text encoder - are trained.
+
+To find out which schedulers are compatible for customization, you can use the `compatibles` method:
+
+```py
+from diffusers import DiffusionPipeline
+
+repo_id = "runwayml/stable-diffusion-v1-5"
+stable_diffusion = DiffusionPipeline.from_pretrained(repo_id)
+stable_diffusion.scheduler.compatibles
+```
+
+Let's use the [`SchedulerMixin.from_pretrained`] method to replace the default [`PNDMScheduler`] with a more performant scheduler, [`EulerDiscreteScheduler`]. The `subfolder="scheduler"` argument is required to load the scheduler configuration from the correct [subfolder](https://huggingface.co/runwayml/stable-diffusion-v1-5/tree/main/scheduler) of the pipeline repository.
+
+Then you can pass the new [`EulerDiscreteScheduler`] instance to the `scheduler` argument in [`DiffusionPipeline`]:
 
 ```python
 from diffusers import DiffusionPipeline, EulerDiscreteScheduler, DPMSolverMultistepScheduler
@@ -158,31 +106,24 @@ from diffusers import DiffusionPipeline, EulerDiscreteScheduler, DPMSolverMultis
 repo_id = "runwayml/stable-diffusion-v1-5"
 
 scheduler = EulerDiscreteScheduler.from_pretrained(repo_id, subfolder="scheduler")
-# or
-# scheduler = DPMSolverMultistepScheduler.from_pretrained(repo_id, subfolder="scheduler")
 
 stable_diffusion = DiffusionPipeline.from_pretrained(repo_id, scheduler=scheduler)
 ```
 
-Three things are worth paying attention to here.
-- First, the scheduler is loaded with [`SchedulerMixin.from_pretrained`]
-- Second, the scheduler is loaded with a function argument, called `subfolder="scheduler"` as the configuration of stable diffusion's scheduling is defined in a [subfolder of the official pipeline repository](https://huggingface.co/runwayml/stable-diffusion-v1-5/tree/main/scheduler)
-- Third, the scheduler instance can simply be passed with the `scheduler` keyword argument to [`DiffusionPipeline.from_pretrained`]. This works because the [`StableDiffusionPipeline`] defines its scheduler with the `scheduler` attribute. It's not possible to use a different name, such as `sampler=scheduler` since `sampler` is not a defined keyword for [`StableDiffusionPipeline.__init__`]
+### Safety checker
 
-Not only the scheduler components can be customized for diffusion pipelines; in theory, all components of a pipeline can be customized. In practice, however, it often only makes sense to switch out a component that has **compatible** alternatives to what the pipeline expects.
-Many scheduler classes are compatible with each other as can be seen [here](https://github.com/huggingface/diffusers/blob/0dd8c6b4dbab4069de9ed1cafb53cbd495873879/src/diffusers/schedulers/scheduling_ddim.py#L112). This is not always the case for other components, such as the `"unet"`.
-
-One special case that can also be customized is the `"safety_checker"` of stable diffusion. If you believe the safety checker doesn't serve you any good, you can simply disable it by passing `None`:
+Diffusion models like Stable Diffusion can generate harmful content, which is why 🧨 Diffusers has a [safety checker](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/safety_checker.py) to check generated outputs against known hardcoded NSFW content. If you'd like to disable the safety checker for whatever reason, pass `None` to the `safety_checker` argument:
 
 ```python
-from diffusers import DiffusionPipeline, EulerDiscreteScheduler, DPMSolverMultistepScheduler
+from diffusers import DiffusionPipeline
 
+repo_id = "runwayml/stable-diffusion-v1-5"
 stable_diffusion = DiffusionPipeline.from_pretrained(repo_id, safety_checker=None)
 ```
 
-Another common use case is to reuse the same components in multiple pipelines, *e.g.* the weights and configurations of [`"runwayml/stable-diffusion-v1-5"`](https://huggingface.co/runwayml/stable-diffusion-v1-5) can be used for both [`StableDiffusionPipeline`] and [`StableDiffusionImg2ImgPipeline`] and we might not want to 
-use the exact same weights into RAM twice. In this case, customizing all the input instances would help us 
-to only load the weights into RAM once:
+### Reuse components across pipelines
+
+You can also reuse the same components in multiple pipelines to avoid loading the weights into RAM twice. Use the [`~DiffusionPipeline.components`] method to save the components:
 
 ```python
 from diffusers import StableDiffusionPipeline, StableDiffusionImg2ImgPipeline
@@ -191,227 +132,212 @@ model_id = "runwayml/stable-diffusion-v1-5"
 stable_diffusion_txt2img = StableDiffusionPipeline.from_pretrained(model_id)
 
 components = stable_diffusion_txt2img.components
+```
 
-# weights are not reloaded into RAM
+Then you can pass the `components` to another pipeline without reloading the weights into RAM:
+
+```py
 stable_diffusion_img2img = StableDiffusionImg2ImgPipeline(**components)
 ```
 
-Note how the above code snippet makes use of [`DiffusionPipeline.components`].
-
-### Loading variants
-
-Diffusion Pipeline checkpoints can offer variants of the "main" diffusion pipeline checkpoint.
-Such checkpoint variants are usually variations of the checkpoint that have advantages for specific use-cases and that are so similar to the "main" checkpoint that they **should not** be put in a new checkpoint.
-A variation of a checkpoint has to have **exactly** the same serialization format and **exactly** the same model structure, including all weights having the same tensor shapes.
-
-Examples of variations are different floating point types and non-ema weights. I.e. "fp16", "bf16", and "no_ema" are common variations.
-
-#### Let's first talk about whats **not** checkpoint variant,
-
-Checkpoint variants do **not** include different serialization formats (such as [safetensors](https://huggingface.co/docs/diffusers/main/en/using-diffusers/using_safetensors)) as weights in different serialization formats are 
-identical to the weights of the "main" checkpoint, just loaded in a different framework.
-
-Also variants do not correspond to different model structures, *e.g.* [stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5) is not a variant of [stable-diffusion-2-0](https://huggingface.co/stabilityai/stable-diffusion-2) since the model structure is different (Stable Diffusion 1-5 uses a different `CLIPTextModel` compared to Stable Diffusion 2.0).
-
-Pipeline checkpoints that are identical in model structure, but have been trained on different datasets, trained with vastly different training setups and thus correspond to different official releases (such as [Stable Diffusion v1-4](https://huggingface.co/CompVis/stable-diffusion-v1-4) and [Stable Diffusion v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5)) should probably be stored in individual repositories instead of as variations of each other.
-
-#### So what are checkpoint variants then? 
-
-Checkpoint variants usually consist of the checkpoint stored in "*low-precision, low-storage*" dtype so that less bandwith is required to download them, or of *non-exponential-averaged* weights that shall be used when continuing fine-tuning from the checkpoint.
-Both use cases have clear advantages when their weights are considered variants: they share the same serialization format as the reference weights, and they correspond to a specialization of the "main" checkpoint which does not warrant a new model repository. 
-A checkpoint stored in [torch's half-precision / float16 format](https://pytorch.org/blog/accelerating-training-on-nvidia-gpus-with-pytorch-automatic-mixed-precision/) requires only half the bandwith and storage when downloading the checkpoint,
-**but** cannot be used when continuing training or when running the checkpoint on CPU.
-Similarly the *non-exponential-averaged* (or non-EMA) version of the checkpoint should be used when continuing fine-tuning of the model checkpoint, **but** should not be used when using the checkpoint for inference. 
-
-#### How to save and load variants
-
-Saving a diffusion pipeline as a variant can be done by providing [`DiffusionPipeline.save_pretrained`] with the `variant` argument. 
-The `variant` extends the weight name by the provided variation, by changing the default weight name from `diffusion_pytorch_model.bin` to `diffusion_pytorch_model.{variant}.bin` or from `diffusion_pytorch_model.safetensors` to `diffusion_pytorch_model.{variant}.safetensors`. By doing so, one creates a variant of the pipeline checkpoint that can be loaded **instead** of the "main" pipeline checkpoint.
-
-Let's have a look at how we could create a float16 variant of a pipeline. First, we load 
-the "main" variant of a checkpoint (stored in `float32` precision) into mixed precision format, using `torch_dtype=torch.float16`.
+You can also pass the components individually to the pipeline if you want more flexibility over which components to reuse or disable. For example, to reuse the same components in the text-to-image pipeline, except for the safety checker and feature extractor, in the image-to-image pipeline:
 
 ```py
-from diffusers import DiffusionPipeline
-import torch
+from diffusers import StableDiffusionPipeline, StableDiffusionImg2ImgPipeline
 
-pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
+model_id = "runwayml/stable-diffusion-v1-5"
+stable_diffusion_txt2img = StableDiffusionPipeline.from_pretrained(model_id)
+stable_diffusion_img2img = StableDiffusionImg2ImgPipeline(
+    vae=stable_diffusion_txt2img.vae,
+    text_encoder=stable_diffusion_txt2img.text_encoder,
+    tokenizer=stable_diffusion_txt2img.tokenizer,
+    unet=stable_diffusion_txt2img.unet,
+    scheduler=stable_diffusion_txt2img.scheduler,
+    safety_checker=None,
+    feature_extractor=None,
+    requires_safety_checker=False,
+)
 ```
 
-Now all model components of the pipeline are stored in half-precision dtype. We can now save the 
-pipeline under a `"fp16"` variant as follows:
+## Checkpoint variants
 
-```py
-pipe.save_pretrained("./stable-diffusion-v1-5", variant="fp16")
-```
+A checkpoint variant is usually a checkpoint where it's weights are:
 
-If we don't save into an existing `stable-diffusion-v1-5` folder the new folder would look as follows:
-
-```
-stable-diffusion-v1-5
-├── feature_extractor
-│   └── preprocessor_config.json
-├── model_index.json
-├── safety_checker
-│   ├── config.json
-│   └── pytorch_model.fp16.bin
-├── scheduler
-│   └── scheduler_config.json
-├── text_encoder
-│   ├── config.json
-│   └── pytorch_model.fp16.bin
-├── tokenizer
-│   ├── merges.txt
-│   ├── special_tokens_map.json
-│   ├── tokenizer_config.json
-│   └── vocab.json
-├── unet
-│   ├── config.json
-│   └── diffusion_pytorch_model.fp16.bin
-└── vae
-    ├── config.json
-    └── diffusion_pytorch_model.fp16.bin
-```
-
-As one can see, all model files now have a `.fp16.bin` extension instead of just `.bin`.
-The variant now has to be loaded by also passing a `variant="fp16"` to [`DiffusionPipeline.from_pretrained`], e.g.:
-
-
-```py
-DiffusionPipeline.from_pretrained("./stable-diffusion-v1-5", variant="fp16", torch_dtype=torch.float16)
-```
-
-works just fine, while:
-
-```py
-DiffusionPipeline.from_pretrained("./stable-diffusion-v1-5", torch_dtype=torch.float16)
-```
-
-throws an Exception:
-```
-OSError: Error no file named diffusion_pytorch_model.bin found in directory ./stable-diffusion-v1-45/vae since we **only** stored the model 
-```
-
-This is expected as we don't have any "non-variant" checkpoint files saved locally.
-However, the whole idea of pipeline variants is that they can co-exist with the "main" variant, 
-so one would typically also save the "main" variant in the same folder. Let's do this:
-
-```py
-pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")
-pipe.save_pretrained("./stable-diffusion-v1-5")
-```
-
-and upload the pipeline to the Hub under [diffusers/stable-diffusion-variants](https://huggingface.co/diffusers/stable-diffusion-variants).
-The file structure [on the Hub](https://huggingface.co/diffusers/stable-diffusion-variants/tree/main) now looks as follows:
-
-```
-├── feature_extractor
-│   └── preprocessor_config.json
-├── model_index.json
-├── safety_checker
-│   ├── config.json
-│   ├── pytorch_model.bin
-│   └── pytorch_model.fp16.bin
-├── scheduler
-│   └── scheduler_config.json
-├── text_encoder
-│   ├── config.json
-│   ├── pytorch_model.bin
-│   └── pytorch_model.fp16.bin
-├── tokenizer
-│   ├── merges.txt
-│   ├── special_tokens_map.json
-│   ├── tokenizer_config.json
-│   └── vocab.json
-├── unet
-│   ├── config.json
-│   ├── diffusion_pytorch_model.bin
-│   ├── diffusion_pytorch_model.fp16.bin
-└── vae
-    ├── config.json
-    ├── diffusion_pytorch_model.bin
-    └── diffusion_pytorch_model.fp16.bin
-```
-
-We can now both download the "main" and the "fp16" variant from the Hub. Both:
-
-```py
-pipe = DiffusionPipeline.from_pretrained("diffusers/stable-diffusion-variants")
-```
-
-and 
-
-```py
-pipe = DiffusionPipeline.from_pretrained("diffusers/stable-diffusion-variants", variant="fp16")
-```
-
-work.
+- Stored in a different floating point type for lower precision and lower storage, such as [`torch.float16`](https://pytorch.org/docs/stable/tensors.html#data-types), because it only requires half the bandwidth and storage to download. You can't use this variant if you're continuing training or using a CPU.
+- Non-exponential mean averaged (EMA) weights which shouldn't be used for inference. You should use these to continue finetuning a model.
 
 <Tip>
 
-Note that Diffusers never downloads more checkpoints than needed. E.g. when downloading 
-the "main" variant, none of the "fp16.bin" files are downloaded and cached.
-Only when the user specifies `variant="fp16"` are those files downloaded and cached.
+💡 When the checkpoints have identical model structures, but they were trained on different datasets and with a different training setup, they should be stored in separate repositories instead of variations (for example, [`stable-diffusion-v1-4`] and [`stable-diffusion-v1-5`]).
 
 </Tip>
 
-Finally, there are cases where only some of the checkpoint files of the pipeline are of a certain 
-variation. E.g. it's usually only the UNet checkpoint that has both a *exponential-mean-averaged* (EMA) and a *non-exponential-mean-averaged* (non-EMA) version. All other model components, e.g. the text encoder, safety checker or variational auto-encoder usually don't have such a variation.
-In such a case, one would upload just the UNet's checkpoint file with a `non_ema` version format (as done [here](https://huggingface.co/diffusers/stable-diffusion-variants/blob/main/unet/diffusion_pytorch_model.non_ema.bin)) and upon calling:
+Otherwise, a variant is **identical** to the original checkpoint. They have exactly the same serialization format (like [Safetensors](./using-diffusers/using_safetensors)), model structure, and weights have identical tensor shapes.
+
+| **checkpoint type** | **weight name**                     | **argument for loading weights** |
+|---------------------|-------------------------------------|----------------------------------|
+| original            | diffusion_pytorch_model.bin         |                                  |
+| floating point      | diffusion_pytorch_model.fp16.bin    | `variant`, `torch_dtype`         |
+| non-EMA             | diffusion_pytorch_model.non_ema.bin | `variant`                        |
+
+There are two important arguments to know for loading variants:
+
+- `torch_dtype` defines the floating point precision of the loaded checkpoints. For example, if you want to save bandwidth by loading a `fp16` variant, you should specify `torch_dtype=torch.float16` to *convert the weights* to `fp16`. Otherwise, the `fp16` weights are converted to the default `fp32` precision. You can also load the original checkpoint without defining the `variant` argument, and convert it to `fp16` with `torch_dtype=torch.float16`. In this case, the default `fp32` weights are downloaded first, and then they're converted to `fp16` after loading.
+
+- `variant` defines which files should be loaded from the repository. For example, if you want to load a `non_ema` variant from the [`diffusers/stable-diffusion-variants`](https://huggingface.co/diffusers/stable-diffusion-variants/tree/main/unet) repository, you should specify `variant="non_ema"` to download the `non_ema` files.
 
 ```python
-pipe = DiffusionPipeline.from_pretrained("diffusers/stable-diffusion-variants", variant="non_ema")
+from diffusers import DiffusionPipeline
+
+# load fp16 variant
+stable_diffusion = DiffusionPipeline.from_pretrained(
+    "runwayml/stable-diffusion-v1-5", variant="fp16", torch_dtype=torch.float16
+)
+# load non_ema variant
+stable_diffusion = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", variant="non_ema")
 ```
 
-the model will use only the "non_ema" checkpoint variant if it is available - otherwise it'll load the 
-"main" variation. In the above example, `variant="non_ema"` would therefore download the following file structure:
+To save a checkpoint stored in a different floating point type or as a non-EMA variant, use the [`DiffusionPipeline.save_pretrained`] method and specify the `variant` argument. You should try and save a variant to the same folder as the original checkpoint, so you can load both from the same folder:
 
-```
-├── feature_extractor
-│   └── preprocessor_config.json
-├── model_index.json
-├── safety_checker
-│   ├── config.json
-│   ├── pytorch_model.bin
-├── scheduler
-│   └── scheduler_config.json
-├── text_encoder
-│   ├── config.json
-│   ├── pytorch_model.bin
-├── tokenizer
-│   ├── merges.txt
-│   ├── special_tokens_map.json
-│   ├── tokenizer_config.json
-│   └── vocab.json
-├── unet
-│   ├── config.json
-│   └── diffusion_pytorch_model.non_ema.bin
-└── vae
-    ├── config.json
-    ├── diffusion_pytorch_model.bin
+```python
+from diffusers import DiffusionPipeline
+
+# save as fp16 variant
+stable_diffusion.save_pretrained("runwayml/stable-diffusion-v1-5", variant="fp16")
+# save as non-ema variant
+stable_diffusion.save_pretrained("runwayml/stable-diffusion-v1-5", variant="non_ema")
 ```
 
-In a nutshell, using `variant="{variant}"` will download all files that match the `{variant}` and if for a model component such a file variant is not present it will download the "main" variant. If neither a "main" or `{variant}` variant is available, an error will the thrown.
+If you don't save the variant to an existing folder, you must specify the `variant` argument otherwise it'll throw an `Exception` because it can't find the original checkpoint:
 
-### How does loading work?
+```python
+# 👎 this won't work
+stable_diffusion = DiffusionPipeline.from_pretrained("./stable-diffusion-v1-5", torch_dtype=torch.float16)
+# 👍 this works
+stable_diffusion = DiffusionPipeline.from_pretrained(
+    "./stable-diffusion-v1-5", variant="fp16", torch_dtype=torch.float16
+)
+```
+
+<!--
+TODO(Patrick) - Make sure to uncomment this part as soon as things are deprecated.
+
+#### Using `revision` to load pipeline variants is deprecated
+
+Previously the `revision` argument of [`DiffusionPipeline.from_pretrained`] was heavily used to 
+load model variants, e.g.:
+
+```python
+from diffusers import DiffusionPipeline
+
+pipe = DiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", revision="fp16")
+```
+
+However, this behavior is now deprecated since the "revision" argument should (just as it's done in GitHub) better be used to load model checkpoints from a specific commit or branch in development.
+
+The above example is therefore deprecated and won't be supported anymore for `diffusers >= 1.0.0`.
+
+<Tip warning={true}>
+
+If you load diffusers pipelines or models with `revision="fp16"` or `revision="non_ema"`, 
+please make sure to update to code and use `variant="fp16"` or `variation="non_ema"` respectively
+instead.
+
+</Tip>
+-->
+
+## Models
+
+Models are loaded from the [`ModelMixin.from_pretrained`] method, which downloads and caches the latest version of the model weights and configurations. If the latest files are available in the local cache, [`~ModelMixin.from_pretrained`] reuses files in the cache instead of redownloading them.
+
+Models can be loaded from a subfolder with the `subfolder` argument. For example, the model weights for `runwayml/stable-diffusion-v1-5` are stored in the [`unet`](https://huggingface.co/runwayml/stable-diffusion-v1-5/tree/main/unet) subfolder:
+
+```python
+from diffusers import UNet2DConditionModel
+
+repo_id = "runwayml/stable-diffusion-v1-5"
+model = UNet2DConditionModel.from_pretrained(repo_id, subfolder="unet")
+```
+
+Or directly from a repository's [directory](https://huggingface.co/google/ddpm-cifar10-32/tree/main):
+
+```python
+from diffusers import UNet2DModel
+
+repo_id = "google/ddpm-cifar10-32"
+model = UNet2DModel.from_pretrained(repo_id)
+```
+
+You can also load and save model variants by specifying the `variant` argument in [`ModelMixin.from_pretrained`] and [`ModelMixin.save_pretrained`]:
+
+```python
+from diffusers import UNet2DConditionModel
+
+model = UNet2DConditionModel.from_pretrained("runwayml/stable-diffusion-v1-5", subfolder="unet", variant="non-ema")
+model.save_pretrained("./local-unet", variant="non-ema")
+```
+
+## Schedulers
+
+Schedulers are loaded from the [`SchedulerMixin.from_pretrained`] method, and unlike models, schedulers are **not parameterized** or **trained**; they are defined by a configuration file.
+
+Loading schedulers does not consume any significant amount of memory and the same configuration file can be used for a variety of different schedulers.
+For example, the following schedulers are compatible with [`StableDiffusionPipeline`] which means you can load the same scheduler configuration file in any of these classes:
+
+```python
+from diffusers import StableDiffusionPipeline
+from diffusers import (
+    DDPMScheduler,
+    DDIMScheduler,
+    PNDMScheduler,
+    LMSDiscreteScheduler,
+    EulerDiscreteScheduler,
+    EulerAncestralDiscreteScheduler,
+    DPMSolverMultistepScheduler,
+)
+
+repo_id = "runwayml/stable-diffusion-v1-5"
+
+ddpm = DDPMScheduler.from_pretrained(repo_id, subfolder="scheduler")
+ddim = DDIMScheduler.from_pretrained(repo_id, subfolder="scheduler")
+pndm = PNDMScheduler.from_pretrained(repo_id, subfolder="scheduler")
+lms = LMSDiscreteScheduler.from_pretrained(repo_id, subfolder="scheduler")
+euler_anc = EulerAncestralDiscreteScheduler.from_pretrained(repo_id, subfolder="scheduler")
+euler = EulerDiscreteScheduler.from_pretrained(repo_id, subfolder="scheduler")
+dpm = DPMSolverMultistepScheduler.from_pretrained(repo_id, subfolder="scheduler")
+
+# replace `dpm` with any of `ddpm`, `ddim`, `pndm`, `lms`, `euler_anc`, `euler`
+pipeline = StableDiffusionPipeline.from_pretrained(repo_id, scheduler=dpm)
+```
+
+## DiffusionPipeline explained
 
 As a class method, [`DiffusionPipeline.from_pretrained`] is responsible for two things:
-- Download the latest version of the folder structure required to run the `repo_id` with `diffusers` and cache them. If the latest folder structure is available in the local cache, [`DiffusionPipeline.from_pretrained`] will simply reuse the cache and **not** re-download the files.
-- Load the cached weights into the _correct_ pipeline class – one of the [officially supported pipeline classes](./api/overview#diffusers-summary) - and return an instance of the class. The _correct_ pipeline class is thereby retrieved from the `model_index.json` file.
 
-The underlying folder structure of diffusion pipelines corresponds 1-to-1 to their corresponding class instances, *e.g.* [`StableDiffusionPipeline`] for [`runwayml/stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5).
-This can be better understood by looking at an example. Let's load a pipeline class instance `pipe` and print it:
+- Download the latest version of the folder structure required for inference and cache it. If the latest folder structure is available in the local cache, [`DiffusionPipeline.from_pretrained`] reuses the cache and won't redownload the files.
+- Load the cached weights into the correct pipeline [class](./api/pipelines/overview#diffusers-summary) - retrieved from the `model_index.json` file - and return an instance of it.
+
+The pipelines underlying folder structure corresponds directly with their class instances. For example, the [`StableDiffusionPipeline`] corresponds to the folder structure in [`runwayml/stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5).
 
 ```python
 from diffusers import DiffusionPipeline
 
 repo_id = "runwayml/stable-diffusion-v1-5"
-pipe = DiffusionPipeline.from_pretrained(repo_id)
-print(pipe)
+pipeline = DiffusionPipeline.from_pretrained(repo_id)
+print(pipeline)
 ```
 
-*Output*:
-```
+You'll see pipeline is an instance of [`StableDiffusionPipeline`], which consists of seven components:
+
+- `"feature_extractor"`: a [`~transformers.CLIPFeatureExtractor`] from 🤗 Transformers.
+- `"safety_checker"`: a [component](https://github.com/huggingface/diffusers/blob/e55687e1e15407f60f32242027b7bb8170e58266/src/diffusers/pipelines/stable_diffusion/safety_checker.py#L32) for screening against harmful content.
+- `"scheduler"`: an instance of [`PNDMScheduler`].
+- `"text_encoder"`: a [`~transformers.CLIPTextModel`] from 🤗 Transformers.
+- `"tokenizer"`: a [`~transformers.CLIPTokenizer`] from 🤗 Transformers.
+- `"unet"`: an instance of [`UNet2DConditionModel`].
+- `"vae"` an instance of [`AutoencoderKL`].
+
+```json
 StableDiffusionPipeline {
   "feature_extractor": [
     "transformers",
@@ -444,16 +370,7 @@ StableDiffusionPipeline {
 }
 ```
 
-First, we see that the official pipeline is the [`StableDiffusionPipeline`], and second we see that the `StableDiffusionPipeline` consists of 7 components:
-- `"feature_extractor"` of class `CLIPImageProcessor` as defined [in `transformers`](https://huggingface.co/docs/transformers/main/en/model_doc/clip#transformers.CLIPImageProcessor).
-- `"safety_checker"` as defined [here](https://github.com/huggingface/diffusers/blob/e55687e1e15407f60f32242027b7bb8170e58266/src/diffusers/pipelines/stable_diffusion/safety_checker.py#L32).
-- `"scheduler"` of class [`PNDMScheduler`].
-- `"text_encoder"` of class `CLIPTextModel` as defined [in `transformers`](https://huggingface.co/docs/transformers/main/en/model_doc/clip#transformers.CLIPTextModel).
-- `"tokenizer"` of class `CLIPTokenizer` as defined [in `transformers`](https://huggingface.co/docs/transformers/main/en/model_doc/clip#transformers.CLIPTokenizer).
-- `"unet"` of class [`UNet2DConditionModel`].
-- `"vae"` of class [`AutoencoderKL`].
-
-Let's now compare the pipeline instance to the folder structure of the model repository `runwayml/stable-diffusion-v1-5`. Looking at the folder structure of [`runwayml/stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5/tree/main) on the Hub and  excluding model and saving format variants, we can see it matches 1-to-1 the printed out instance of `StableDiffusionPipeline` above:
+Compare the components of the pipeline instance to the [`runwayml/stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5) folder structure, and you'll see there is a separate folder for each of the components in the repository:
 
 ```
 .
@@ -481,13 +398,33 @@ Let's now compare the pipeline instance to the folder structure of the model rep
     ├── diffusion_pytorch_model.bin
 ```
 
-Each attribute of the instance of `StableDiffusionPipeline` has its configuration and possibly weights defined in a subfolder that is called **exactly** like the class attribute (`"feature_extractor"`, `"safety_checker"`, `"scheduler"`, `"text_encoder"`, `"tokenizer"`, `"unet"`, `"vae"`). Importantly, every pipeline expects a `model_index.json` file that tells the `DiffusionPipeline` both:
-- which pipeline class should be loaded, and
-- what sub-classes from which library are stored in which subfolders
-
-In the case of `runwayml/stable-diffusion-v1-5` the `model_index.json` is therefore defined as follows:
+You can access each of the components of the pipeline as an attribute to view its configuration:
 
+```py
+pipeline.tokenizer
+CLIPTokenizer(
+    name_or_path="/root/.cache/huggingface/hub/models--runwayml--stable-diffusion-v1-5/snapshots/39593d5650112b4cc580433f6b0435385882d819/tokenizer",
+    vocab_size=49408,
+    model_max_length=77,
+    is_fast=False,
+    padding_side="right",
+    truncation_side="right",
+    special_tokens={
+        "bos_token": AddedToken("<|startoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=True),
+        "eos_token": AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=True),
+        "unk_token": AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=True),
+        "pad_token": "<|endoftext|>",
+    },
+)
 ```
+
+Every pipeline expects a `model_index.json` file that tells the [`DiffusionPipeline`]:
+
+- which pipeline class to load from `_class_name`
+- which version of 🧨 Diffusers was used to create the model in `_diffusers_version`
+- what components from which library are stored in the subfolders (`name` corresponds to the component and subfolder name, `library` corresponds to the name of the library to load the class from, and `class` corresponds to the class name)
+
+```json
 {
   "_class_name": "StableDiffusionPipeline",
   "_diffusers_version": "0.6.0",
@@ -520,138 +457,4 @@ In the case of `runwayml/stable-diffusion-v1-5` the `model_index.json` is theref
     "AutoencoderKL"
   ]
 }
-```
-
-- `_class_name` tells `DiffusionPipeline` which pipeline class should be loaded. 
-- `_diffusers_version` can be useful to know under which `diffusers` version this model was created.
-- Every component of the pipeline is then defined under the form:
-```
-"name" : [
-  "library",
-  "class"
-]
-```
-	- The `"name"` field corresponds both to the name of the subfolder in which the configuration and weights are stored as well as the attribute name of the pipeline class (as can be seen [here](https://huggingface.co/runwayml/stable-diffusion-v1-5/tree/main/bert) and [here](https://github.com/huggingface/diffusers/blob/cd502b25cf0debac6f98d27a6638ef95208d1ea2/src/diffusers/pipelines/latent_diffusion/pipeline_latent_diffusion.py#L42))
-	- The `"library"` field corresponds to the name of the library, *e.g.* `diffusers` or `transformers` from which the `"class"` should be loaded
-	- The `"class"` field corresponds to the name of the class, *e.g.* [`CLIPTokenizer`](https://huggingface.co/docs/transformers/main/en/model_doc/clip#transformers.CLIPTokenizer) or [`UNet2DConditionModel`]
-
-<!--
-TODO(Patrick) - Make sure to uncomment this part as soon as things are deprecated.
-
-#### Using `revision` to load pipeline variants is deprecated
-
-Previously the `revision` argument of [`DiffusionPipeline.from_pretrained`] was heavily used to 
-load model variants, e.g.:
-
-```python
-from diffusers import DiffusionPipeline
-
-pipe = DiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", revision="fp16")
-```
-
-However, this behavior is now deprecated since the "revision" argument should (just as it's done in GitHub) better be used to load model checkpoints from a specific commit or branch in development.
-
-The above example is therefore deprecated and won't be supported anymore for `diffusers >= 1.0.0`.
-
-<Tip warning={true}>
-
-If you load diffusers pipelines or models with `revision="fp16"` or `revision="non_ema"`, 
-please make sure to update to code and use `variant="fp16"` or `variation="non_ema"` respectively
-instead.
-
-</Tip>
--->
-
-## Loading models
-
-Models as defined under [src/diffusers/models](https://github.com/huggingface/diffusers/tree/main/src/diffusers/models) can be loaded via the [`ModelMixin.from_pretrained`] function. The API is very similar the [`DiffusionPipeline.from_pretrained`] and works in the same way:
-- Download the latest version of the model weights and configuration with `diffusers` and cache them. If the latest files are available in the local cache, [`ModelMixin.from_pretrained`] will simply reuse the cache and **not** re-download the files.
-- Load the cached weights into the _defined_ model class - one of [the existing model classes](./api/models) - and return an instance of the class.
-
-In constrast to [`DiffusionPipeline.from_pretrained`], models rely on fewer files that usually don't require a folder structure, but just a `diffusion_pytorch_model.bin` and `config.json` file.
-
-Let's look at an example:
-
-```python
-from diffusers import UNet2DConditionModel
-
-repo_id = "runwayml/stable-diffusion-v1-5"
-model = UNet2DConditionModel.from_pretrained(repo_id, subfolder="unet")
-```
-
-Note how we have to define the `subfolder="unet"` argument to tell [`ModelMixin.from_pretrained`] that the model weights are located in a [subfolder of the repository](https://huggingface.co/runwayml/stable-diffusion-v1-5/tree/main/unet).
-
-As explained in [Loading customized pipelines]("./using-diffusers/loading#loading-customized-pipelines"), one can pass a loaded model to a diffusion pipeline, via [`DiffusionPipeline.from_pretrained`]:
-
-```python
-from diffusers import DiffusionPipeline
-
-repo_id = "runwayml/stable-diffusion-v1-5"
-pipe = DiffusionPipeline.from_pretrained(repo_id, unet=model)
-```
-
-If the model files can be found directly at the root level, which is usually only the case for some very simple diffusion models, such as [`google/ddpm-cifar10-32`](https://huggingface.co/google/ddpm-cifar10-32), we don't 
-need to pass a `subfolder` argument:
-
-```python
-from diffusers import UNet2DModel
-
-repo_id = "google/ddpm-cifar10-32"
-model = UNet2DModel.from_pretrained(repo_id)
-```
-
-As motivated in [How to save and load variants?](#how-to-save-and-load-variants), models can load and 
-save variants. To load a model variant, one should pass the `variant` function argument to [`ModelMixin.from_pretrained`]. Analogous, to save a model variant, one should pass the `variant` function argument to [`ModelMixin.save_pretrained`]:
-
-```python
-from diffusers import UNet2DConditionModel
-
-model = UNet2DConditionModel.from_pretrained(
-    "diffusers/stable-diffusion-variants", subfolder="unet", variant="non_ema"
-)
-model.save_pretrained("./local-unet", variant="non_ema")
-```
-
-## Loading schedulers
-
-Schedulers rely on [`SchedulerMixin.from_pretrained`]. Schedulers are **not parameterized** or **trained**, but instead purely defined by a configuration file.
-For consistency, we use the same method name as we do for models or pipelines, but no weights are loaded in this case.
-
-In constrast to pipelines or models, loading schedulers does not consume any significant amount of memory and the same configuration file can often be used for a variety of different schedulers.
-For example, all of:
-
-- [`DDPMScheduler`]
-- [`DDIMScheduler`]
-- [`PNDMScheduler`]
-- [`LMSDiscreteScheduler`]
-- [`EulerDiscreteScheduler`]
-- [`EulerAncestralDiscreteScheduler`]
-- [`DPMSolverMultistepScheduler`]
-
-are compatible with [`StableDiffusionPipeline`] and therefore the same scheduler configuration file can be loaded in any of those classes:
-
-```python
-from diffusers import StableDiffusionPipeline
-from diffusers import (
-    DDPMScheduler,
-    DDIMScheduler,
-    PNDMScheduler,
-    LMSDiscreteScheduler,
-    EulerDiscreteScheduler,
-    EulerAncestralDiscreteScheduler,
-    DPMSolverMultistepScheduler,
-)
-
-repo_id = "runwayml/stable-diffusion-v1-5"
-
-ddpm = DDPMScheduler.from_pretrained(repo_id, subfolder="scheduler")
-ddim = DDIMScheduler.from_pretrained(repo_id, subfolder="scheduler")
-pndm = PNDMScheduler.from_pretrained(repo_id, subfolder="scheduler")
-lms = LMSDiscreteScheduler.from_pretrained(repo_id, subfolder="scheduler")
-euler_anc = EulerAncestralDiscreteScheduler.from_pretrained(repo_id, subfolder="scheduler")
-euler = EulerDiscreteScheduler.from_pretrained(repo_id, subfolder="scheduler")
-dpm = DPMSolverMultistepScheduler.from_pretrained(repo_id, subfolder="scheduler")
-
-# replace `dpm` with any of `ddpm`, `ddim`, `pndm`, `lms`, `euler_anc`, `euler`
-pipeline = StableDiffusionPipeline.from_pretrained(repo_id, scheduler=dpm)
-```
+```

docs/source/en/using-diffusers/reproducibility.mdx

@@ -14,7 +14,7 @@ specific language governing permissions and limitations under the License.
 
 Reproducibility is important for testing, replicating results, and can even be used to [improve image quality](reusing_seeds). However, the randomness in diffusion models is a desired property because it allows the pipeline to generate different images every time it is run. While you can't expect to get the exact same results across platforms, you can expect results to be reproducible across releases and platforms within a certain tolerance range. Even then, tolerance varies depending on the diffusion pipeline and checkpoint.
 
-This is why it's important to understand how to control sources of randomness in diffusion models.
+This is why it's important to understand how to control sources of randomness in diffusion models or use deterministic algorithms.
 
 <Tip>
 
@@ -24,7 +24,7 @@ This is why it's important to understand how to control sources of randomness in
 
 </Tip>
 
-## Inference
+## Control randomness
 
 During inference, pipelines rely heavily on random sampling operations which include creating the 
 Gaussian noise tensors to denoise and adding noise to the scheduling step.
@@ -147,5 +147,46 @@ susceptible to precision error propagation. Don't expect similar results across
 different GPU hardware or PyTorch versions. In this case, you'll need to run 
 exactly the same hardware and PyTorch version for full reproducibility.
 
-## randn_tensor
+### randn_tensor
 [[autodoc]] diffusers.utils.randn_tensor
+
+## Deterministic algorithms
+
+You can also configure PyTorch to use deterministic algorithms to create a reproducible pipeline. However, you should be aware that deterministic algorithms may be slower than nondeterministic ones and you may observe a decrease in performance. But if reproducibility is important to you, then this is the way to go!
+
+Nondeterministic behavior occurs when operations are launched in more than one CUDA stream. To avoid this, set the environment varibale [`CUBLAS_WORKSPACE_CONFIG`](https://docs.nvidia.com/cuda/cublas/index.html#results-reproducibility) to `:16:8` to only use one buffer size during runtime.
+
+PyTorch typically benchmarks multiple algorithms to select the fastest one, but if you want reproducibility, you should disable this feature because the benchmark may select different algorithms each time. Lastly, pass `True` to [`torch.use_deterministic_algorithms`](https://pytorch.org/docs/stable/generated/torch.use_deterministic_algorithms.html) to enable deterministic algorithms.
+
+```py
+import os
+
+os.environ["CUBLAS_WORKSPACE_CONFIG"] = ":16:8"
+
+torch.backends.cudnn.benchmark = False
+torch.use_deterministic_algorithms(True)
+```
+
+Now when you run the same pipeline twice, you'll get identical results.
+
+```py
+import torch
+from diffusers import DDIMScheduler, StableDiffusionPipeline
+import numpy as np
+
+model_id = "runwayml/stable-diffusion-v1-5"
+pipe = StableDiffusionPipeline.from_pretrained(model_id).to("cuda")
+pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config)
+g = torch.Generator(device="cuda")
+
+prompt = "A bear is playing a guitar on Times Square"
+
+g.manual_seed(0)
+result1 = pipe(prompt=prompt, num_inference_steps=50, generator=g, output_type="latent").images
+
+g.manual_seed(0)
+result2 = pipe(prompt=prompt, num_inference_steps=50, generator=g, output_type="latent").images
+
+print("L_inf dist = ", abs(result1 - result2).max())
+"L_inf dist =  tensor(0., device='cuda:0')"
+```

docs/source/en/using-diffusers/stable_diffusion_jax_how_to.mdx

@@ -0,0 +1,250 @@
+# 🧨 Stable Diffusion in JAX / Flax !
+
+[[open-in-colab]]
+
+🤗 Hugging Face [Diffusers](https://github.com/huggingface/diffusers) supports Flax since version `0.5.1`! This allows for super fast inference on Google TPUs, such as those available in Colab, Kaggle or Google Cloud Platform.
+
+This notebook shows how to run inference using JAX / Flax. If you want more details about how Stable Diffusion works or want to run it in GPU, please refer to [this notebook](https://huggingface.co/docs/diffusers/stable_diffusion).
+
+First, make sure you are using a TPU backend. If you are running this notebook in Colab, select `Runtime` in the menu above, then select the option "Change runtime type" and then select `TPU` under the `Hardware accelerator` setting.
+
+Note that JAX is not exclusive to TPUs, but it shines on that hardware because each TPU server has 8 TPU accelerators working in parallel.
+
+## Setup
+
+First make sure diffusers is installed.
+
+```bash
+!pip install jax==0.3.25 jaxlib==0.3.25 flax transformers ftfy
+!pip install diffusers
+```
+
+```python
+import jax.tools.colab_tpu
+
+jax.tools.colab_tpu.setup_tpu()
+import jax
+```
+
+```python
+num_devices = jax.device_count()
+device_type = jax.devices()[0].device_kind
+
+print(f"Found {num_devices} JAX devices of type {device_type}.")
+assert (
+    "TPU" in device_type
+), "Available device is not a TPU, please select TPU from Edit > Notebook settings > Hardware accelerator"
+```
+
+```python out
+Found 8 JAX devices of type Cloud TPU.
+```
+
+Then we import all the dependencies.
+
+```python
+import numpy as np
+import jax
+import jax.numpy as jnp
+
+from pathlib import Path
+from jax import pmap
+from flax.jax_utils import replicate
+from flax.training.common_utils import shard
+from PIL import Image
+
+from huggingface_hub import notebook_login
+from diffusers import FlaxStableDiffusionPipeline
+```
+
+## Model Loading
+
+TPU devices support `bfloat16`, an efficient half-float type. We'll use it for our tests, but you can also use `float32` to use full precision instead.
+
+```python
+dtype = jnp.bfloat16
+```
+
+Flax is a functional framework, so models are stateless and parameters are stored outside them. Loading the pre-trained Flax pipeline will return both the pipeline itself and the model weights (or parameters). We are using a `bf16` version of the weights, which leads to type warnings that you can safely ignore.
+
+```python
+pipeline, params = FlaxStableDiffusionPipeline.from_pretrained(
+    "CompVis/stable-diffusion-v1-4",
+    revision="bf16",
+    dtype=dtype,
+)
+```
+
+## Inference
+
+Since TPUs usually have 8 devices working in parallel, we'll replicate our prompt as many times as devices we have. Then we'll perform inference on the 8 devices at once, each responsible for generating one image. Thus, we'll get 8 images in the same amount of time it takes for one chip to generate a single one.
+
+After replicating the prompt, we obtain the tokenized text ids by invoking the `prepare_inputs` function of the pipeline. The length of the tokenized text is set to 77 tokens, as required by the configuration of the underlying CLIP Text model.
+
+```python
+prompt = "A cinematic film still of Morgan Freeman starring as Jimi Hendrix, portrait, 40mm lens, shallow depth of field, close up, split lighting, cinematic"
+prompt = [prompt] * jax.device_count()
+prompt_ids = pipeline.prepare_inputs(prompt)
+prompt_ids.shape
+```
+
+```python out
+(8, 77)
+```
+
+### Replication and parallelization
+
+Model parameters and inputs have to be replicated across the 8 parallel devices we have. The parameters dictionary is replicated using `flax.jax_utils.replicate`, which traverses the dictionary and changes the shape of the weights so they are repeated 8 times. Arrays are replicated using `shard`.
+
+```python
+p_params = replicate(params)
+```
+
+```python
+prompt_ids = shard(prompt_ids)
+prompt_ids.shape
+```
+
+```python out
+(8, 1, 77)
+```
+
+That shape means that each one of the `8` devices will receive as an input a `jnp` array with shape `(1, 77)`. `1` is therefore the batch size per device. In TPUs with sufficient memory, it could be larger than `1` if we wanted to generate multiple images (per chip) at once.
+
+We are almost ready to generate images! We just need to create a random number generator to pass to the generation function. This is the standard procedure in Flax, which is very serious and opinionated about random numbers – all functions that deal with random numbers are expected to receive a generator. This ensures reproducibility, even when we are training across multiple distributed devices.
+
+The helper function below uses a seed to initialize a random number generator. As long as we use the same seed, we'll get the exact same results. Feel free to use different seeds when exploring results later in the notebook.
+
+```python
+def create_key(seed=0):
+    return jax.random.PRNGKey(seed)
+```
+
+We obtain a rng and then "split" it 8 times so each device receives a different generator. Therefore, each device will create a different image, and the full process is reproducible.
+
+```python
+rng = create_key(0)
+rng = jax.random.split(rng, jax.device_count())
+```
+
+JAX code can be compiled to an efficient representation that runs very fast. However, we need to ensure that all inputs have the same shape in subsequent calls; otherwise, JAX will have to recompile the code, and we wouldn't be able to take advantage of the optimized speed.
+
+The Flax pipeline can compile the code for us if we pass `jit = True` as an argument. It will also ensure that the model runs in parallel in the 8 available devices.
+
+The first time we run the following cell it will take a long time to compile, but subequent calls (even with different inputs) will be much faster. For example, it took more than a minute to compile in a TPU v2-8 when I tested, but then it takes about **`7s`** for future inference runs.
+
+```
+%%time
+images = pipeline(prompt_ids, p_params, rng, jit=True)[0]
+```
+
+```python out
+CPU times: user 56.2 s, sys: 42.5 s, total: 1min 38s
+Wall time: 1min 29s
+```
+
+The returned array has shape `(8, 1, 512, 512, 3)`. We reshape it to get rid of the second dimension and obtain 8 images of `512 × 512 × 3` and then convert them to PIL.
+
+```python
+images = images.reshape((images.shape[0] * images.shape[1],) + images.shape[-3:])
+images = pipeline.numpy_to_pil(images)
+```
+
+### Visualization
+
+Let's create a helper function to display images in a grid.
+
+```python
+def image_grid(imgs, rows, cols):
+    w, h = imgs[0].size
+    grid = Image.new("RGB", size=(cols * w, rows * h))
+    for i, img in enumerate(imgs):
+        grid.paste(img, box=(i % cols * w, i // cols * h))
+    return grid
+```
+
+```python
+image_grid(images, 2, 4)
+```
+
+![img](https://huggingface.co/datasets/YiYiXu/test-doc-assets/resolve/main/stable_diffusion_jax_how_to_cell_38_output_0.jpeg)
+
+
+## Using different prompts
+
+We don't have to replicate the _same_ prompt in all the devices. We can do whatever we want: generate 2 prompts 4 times each, or even generate 8 different prompts at once. Let's do that!
+
+First, we'll refactor the input preparation code into a handy function:
+
+```python
+prompts = [
+    "Labrador in the style of Hokusai",
+    "Painting of a squirrel skating in New York",
+    "HAL-9000 in the style of Van Gogh",
+    "Times Square under water, with fish and a dolphin swimming around",
+    "Ancient Roman fresco showing a man working on his laptop",
+    "Close-up photograph of young black woman against urban background, high quality, bokeh",
+    "Armchair in the shape of an avocado",
+    "Clown astronaut in space, with Earth in the background",
+]
+```
+
+```python
+prompt_ids = pipeline.prepare_inputs(prompts)
+prompt_ids = shard(prompt_ids)
+
+images = pipeline(prompt_ids, p_params, rng, jit=True).images
+images = images.reshape((images.shape[0] * images.shape[1],) + images.shape[-3:])
+images = pipeline.numpy_to_pil(images)
+
+image_grid(images, 2, 4)
+```
+
+![img](https://huggingface.co/datasets/YiYiXu/test-doc-assets/resolve/main/stable_diffusion_jax_how_to_cell_43_output_0.jpeg)
+
+
+## How does parallelization work?
+
+We said before that the `diffusers` Flax pipeline automatically compiles the model and runs it in parallel on all available devices. We'll now briefly look inside that process to show how it works.
+
+JAX parallelization can be done in multiple ways. The easiest one revolves around using the `jax.pmap` function to achieve single-program, multiple-data (SPMD) parallelization. It means we'll run several copies of the same code, each on different data inputs. More sophisticated approaches are possible, we invite you to go over the [JAX documentation](https://jax.readthedocs.io/en/latest/index.html) and the [`pjit` pages](https://jax.readthedocs.io/en/latest/jax-101/08-pjit.html?highlight=pjit) to explore this topic if you are interested!
+
+`jax.pmap` does two things for us:
+- Compiles (or `jit`s) the code, as if we had invoked `jax.jit()`. This does not happen when we call `pmap`, but the first time the pmapped function is invoked.
+- Ensures the compiled code runs in parallel in all the available devices.
+
+To show how it works we `pmap` the `_generate` method of the pipeline, which is the private method that runs generates images. Please, note that this method may be renamed or removed in future releases of `diffusers`.
+
+```python
+p_generate = pmap(pipeline._generate)
+```
+
+After we use `pmap`, the prepared function `p_generate` will conceptually do the following:
+* Invoke a copy of the underlying function `pipeline._generate` in each device.
+* Send each device a different portion of the input arguments. That's what sharding is used for. In our case, `prompt_ids` has shape `(8, 1, 77, 768)`. This array will be split in `8` and each copy of `_generate` will receive an input with shape `(1, 77, 768)`.
+
+We can code `_generate` completely ignoring the fact that it will be invoked in parallel. We just care about our batch size (`1` in this example) and the dimensions that make sense for our code, and don't have to change anything to make it work in parallel.
+
+The same way as when we used the pipeline call, the first time we run the following cell it will take a while, but then it will be much faster.
+
+```
+%%time
+images = p_generate(prompt_ids, p_params, rng)
+images = images.block_until_ready()
+images.shape
+```
+
+```python out
+CPU times: user 1min 15s, sys: 18.2 s, total: 1min 34s
+Wall time: 1min 15s
+```
+
+```python
+images.shape
+```
+
+```python out
+(8, 1, 512, 512, 3)
+```
+
+We use `block_until_ready()` to correctly measure inference time, because JAX uses asynchronous dispatch and returns control to the Python loop as soon as it can. You don't need to use that in your code; blocking will occur automatically when you want to use the result of a computation that has not yet been materialized.

docs/source/en/using-diffusers/textual_inversion_inference.mdx

@@ -0,0 +1,80 @@
+# Textual inversion
+
+[[open-in-colab]]
+
+The [`StableDiffusionPipeline`] supports textual inversion, a technique that enables a model like Stable Diffusion to learn a new concept from just a few sample images. This gives you more control over the generated images and allows you to tailor the model towards specific concepts. You can get started quickly with a collection of community created concepts in the [Stable Diffusion Conceptualizer](https://huggingface.co/spaces/sd-concepts-library/stable-diffusion-conceptualizer).
+
+This guide will show you how to run inference with textual inversion using a pre-learned concept from the Stable Diffusion Conceptualizer. If you're interested in teaching a model new concepts with textual inversion, take a look at the [Textual Inversion](./training/text_inversion) training guide.
+
+Login to your Hugging Face account:
+
+```py
+from huggingface_hub import notebook_login
+
+notebook_login()
+```
+
+Import the necessary libraries, and create a helper function to visualize the generated images:
+
+```py
+import os
+import torch
+
+import PIL
+from PIL import Image
+
+from diffusers import StableDiffusionPipeline
+from transformers import CLIPFeatureExtractor, CLIPTextModel, CLIPTokenizer
+
+
+def image_grid(imgs, rows, cols):
+    assert len(imgs) == rows * cols
+
+    w, h = imgs[0].size
+    grid = Image.new("RGB", size=(cols * w, rows * h))
+    grid_w, grid_h = grid.size
+
+    for i, img in enumerate(imgs):
+        grid.paste(img, box=(i % cols * w, i // cols * h))
+    return grid
+```
+
+Pick a Stable Diffusion checkpoint and a pre-learned concept from the [Stable Diffusion Conceptualizer](https://huggingface.co/spaces/sd-concepts-library/stable-diffusion-conceptualizer):
+
+```py
+pretrained_model_name_or_path = "runwayml/stable-diffusion-v1-5"
+repo_id_embeds = "sd-concepts-library/cat-toy"
+```
+
+Now you can load a pipeline, and pass the pre-learned concept to it:
+
+```py
+pipeline = StableDiffusionPipeline.from_pretrained(pretrained_model_name_or_path, torch_dtype=torch.float16).to("cuda")
+
+pipeline.load_textual_inversion(repo_id_embeds)
+```
+
+Create a prompt with the pre-learned concept by using the special placeholder token `<cat-toy>`, and choose the number of samples and rows of images you'd like to generate:
+
+```py
+prompt = "a grafitti in a favela wall with a <cat-toy> on it"
+
+num_samples = 2
+num_rows = 2
+```
+
+Then run the pipeline (feel free to adjust the parameters like `num_inference_steps` and `guidance_scale` to see how they affect image quality), save the generated images and visualize them with the helper function you created at the beginning:
+
+```py
+all_images = []
+for _ in range(num_rows):
+    images = pipe(prompt, num_images_per_prompt=num_samples, num_inference_steps=50, guidance_scale=7.5).images
+    all_images.extend(images)
+
+grid = image_grid(all_images, num_samples, num_rows)
+grid
+```
+
+<div class="flex justify-center">
+    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/textual_inversion_inference.png">
+</div>

docs/source/en/using-diffusers/using_safetensors.mdx

@@ -1,87 +1,74 @@
-# What is safetensors ? 
+# Load safetensors
 
-[safetensors](https://github.com/huggingface/safetensors) is a different format
-from the classic `.bin` which uses Pytorch which uses pickle. It contains the
-exact same data, which is just the model weights (or tensors).
+[safetensors](https://github.com/huggingface/safetensors) is a safe and fast file format for storing and loading tensors. Typically, PyTorch model weights are saved or *pickled* into a `.bin` file with Python's [`pickle`](https://docs.python.org/3/library/pickle.html) utility. However, `pickle` is not secure and pickled files may contain malicious code that can be executed. safetensors is a secure alternative to `pickle`, making it ideal for sharing model weights.
 
-Pickle is notoriously unsafe which allow any malicious file to execute arbitrary code.
-The hub itself tries to prevent issues from it, but it's not a silver bullet.
+This guide will show you how you load `.safetensor` files, and how to convert Stable Diffusion model weights stored in other formats to `.safetensor`. Before you start, make sure you have safetensors installed:
 
-`safetensors` first and foremost goal is to make loading machine learning models *safe*
-in the sense that no takeover of your computer can be done.
-
-Hence the name.
-
-# Why use safetensors ?
-
-**Safety** can be one reason, if you're attempting to use a not well known model and
-you're not sure about the source of the file.
-
-And a secondary reason, is **the speed of loading**. Safetensors can load models much faster
-than regular pickle files. If you spend a lot of times switching models, this can be
-a huge timesave.
-
-Numbers taken AMD EPYC 7742 64-Core Processor 
-```
-from diffusers import StableDiffusionPipeline
-
-pipe = StableDiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-2-1")
-
-# Loaded in safetensors 0:00:02.033658
-# Loaded in Pytorch 0:00:02.663379
+```bash
+!pip install safetensors
 ```
 
-This is for the entire loading time, the actual weights loading time to load 500MB:
+If you look at the [`runwayml/stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5/tree/main) repository, you'll see weights inside the `text_encoder`, `unet` and `vae` subfolders are stored in the `.safetensors` format. By default, 🤗 Diffusers automatically loads these `.safetensors` files from their subfolders if they're available in the model repository.
 
-```
-Safetensors: 3.4873ms
-PyTorch: 172.7537ms
-```
+For more explicit control, you can optionally set `use_safetensors=True` (if `safetensors` is not installed, you'll get an error message asking you to install it):
 
-Performance in general is a tricky business, and there are a few things to understand:
-
-- If you're using the model for the first time from the hub, you will have to download the weights.
-  That's extremely likely to be much slower than any loading method, therefore you will not see any difference
-- If you're loading the model for the first time (let's say after a reboot) then your machine will have to 
-  actually read the disk. It's likely to be as slow in both cases. Again the speed difference may not be as visible (this depends on hardware and the actual model).
-- The best performance benefit is when the model was already loaded previously on your computer and you're switching from one model to another. Your OS, is trying really hard not to read from disk, since this is slow, so it will keep the files around in RAM, making it loading again much faster. Since safetensors is doing zero-copy of the tensors, reloading will be faster than pytorch since it has at least once extra copy to do.
-
-# How to use safetensors ?
-
-If you have `safetensors` installed, and all the weights are available in `safetensors` format, \
-then by default it will use that instead of the pytorch weights.
-
-If you are really paranoid about this, the ultimate weapon would be disabling `torch.load`:
-```python
-import torch
-
-
-def _raise():
-    raise RuntimeError("I don't want to use pickle")
-
-
-torch.load = lambda *args, **kwargs: _raise()
-```
-
-# I want to use model X but it doesn't have safetensors weights.
-
-Just go to this [space](https://huggingface.co/spaces/diffusers/convert).
-This will create a new PR with the weights, let's say `refs/pr/22`.
-
-This space will download the pickled version, convert it, and upload it on the hub as a PR.
-If anything bad is contained in the file, it's Huggingface hub that will get issues, not your own computer.
-And we're equipped with dealing with it.
-
-Then in order to use the model, even before the branch gets accepted by the original author you can do:
-
-```python
+```py
 from diffusers import DiffusionPipeline
 
-pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-2-1", revision="refs/pr/22")
+pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", use_safetensors=True)
 ```
 
-or you can test it directly online with this [space](https://huggingface.co/spaces/diffusers/check_pr).
+However, model weights are not necessarily stored in separate subfolders like in the example above. Sometimes, all the weights are stored in a single `.safetensors` file. In this case, if the weights are Stable Diffusion weights, you can load the file directly with the [`~diffusers.loaders.FromCkptMixin.from_ckpt`] method:
 
-And that's it !
+```py
+from diffusers import StableDiffusionPipeline
 
-Anything unclear, concerns, or found a bugs ? [Open an issue](https://github.com/huggingface/diffusers/issues/new/choose)
+pipeline = StableDiffusionPipeline.from_ckpt(
+    "https://huggingface.co/WarriorMama777/OrangeMixs/blob/main/Models/AbyssOrangeMix/AbyssOrangeMix.safetensors"
+)
+```
+
+## Convert to safetensors
+
+Not all weights on the Hub are available in the `.safetensors` format, and you may encounter weights stored as `.bin`. In this case, use the Space below to convert the weights to `.safetensors`. The Convert Space downloads the pickled weights, converts them, and opens a Pull Request to upload the newly converted `.safetensors` file on the Hub. This way, if there is any malicious code contained in the pickled files, they're uploaded to the Hub - which has a [security scanner](https://huggingface.co/docs/hub/security-pickle#hubs-security-scanner) to detect unsafe files and suspicious pickle imports - instead of your computer.
+
+<iframe
+	src="https://safetensors-convert.hf.space"
+	frameborder="0"
+	width="850"
+	height="450"
+></iframe>
+
+You can use the model with the new `.safetensors` weights by specifying the reference to the Pull Request in the `revision` parameter (you can also test it in this [Check PR](https://huggingface.co/spaces/diffusers/check_pr) Space on the Hub), for example `refs/pr/22`:
+
+```py
+from diffusers import DiffusionPipeline
+
+pipeline = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-2-1", revision="refs/pr/22")
+```
+
+## Why use safetensors?
+
+There are several reasons for using safetensors:
+
+- Safety is the number one reason for using safetensors. As open-source and model distribution grows, it is important to be able to trust the model weights you downloaded don't contain any malicious code. The current size of the header in safetensors prevents parsing extremely large JSON files.
+- Loading speed between switching models is another reason to use safetensors, which performs zero-copy of the tensors. It is especially fast compared to `pickle` if you're loading the weights to CPU (the default case), and just as fast if not faster when directly loading the weights to GPU. You'll only notice the performance difference if the model is already loaded, and not if you're downloading the weights or loading the model for the first time.
+
+	The time it takes to load the entire pipeline:
+
+	```py
+ from diffusers import StableDiffusionPipeline
+
+ pipeline = StableDiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-2-1")
+ "Loaded in safetensors 0:00:02.033658"
+ "Loaded in PyTorch 0:00:02.663379"
+	```
+
+	But the actual time it takes to load 500MB of the model weights is only:
+
+	```bash
+	safetensors: 3.4873ms
+	PyTorch: 172.7537ms
+	```
+
+- Lazy loading is also supported in safetensors, which is useful in distributed settings to only load some of the tensors. This format allowed the [BLOOM](https://huggingface.co/bigscience/bloom) model to be loaded in 45 seconds on 8 GPUs instead of 10 minutes with regular PyTorch weights.

docs/source/en/using-diffusers/write_own_pipeline.mdx

@@ -82,8 +82,8 @@ To recreate the pipeline with the model and scheduler separately, let's write ou
     >>> for t in scheduler.timesteps:
     ...     with torch.no_grad():
     ...         noisy_residual = model(input, t).sample
-    >>> previous_noisy_sample = scheduler.step(noisy_residual, t, input).prev_sample
-    >>> input = previous_noisy_sample
+    ...     previous_noisy_sample = scheduler.step(noisy_residual, t, input).prev_sample
+    ...     input = previous_noisy_sample
     ```
 
     This is the entire denoising process, and you can use this same pattern to write any diffusion system.
@@ -96,7 +96,7 @@ To recreate the pipeline with the model and scheduler separately, let's write ou
 
     >>> image = (input / 2 + 0.5).clamp(0, 1)
     >>> image = image.cpu().permute(0, 2, 3, 1).numpy()[0]
-    >>> image = Image.fromarray((image * 255)).round().astype("uint8")
+    >>> image = Image.fromarray((image * 255).round().astype("uint8"))
     >>> image
     ```
 
@@ -287,4 +287,4 @@ This is really what 🧨 Diffusers is designed for: to make it intuitive and eas
 For your next steps, feel free to:
 
 * Learn how to [build and contribute a pipeline](using-diffusers/#contribute_pipeline) to 🧨 Diffusers. We can't wait and see what you'll come up with!
-* Explore [existing pipelines](./api/pipelines/overview) in the library, and see if you can deconstruct and build a pipeline from scratch using the models and schedulers separately.
+* Explore [existing pipelines](./api/pipelines/overview) in the library, and see if you can deconstruct and build a pipeline from scratch using the models and schedulers separately.

docs/source/ko/_toctree.yml

@@ -3,191 +3,46 @@
     title: "🧨 Diffusers"
   - local: quicktour
     title: "훑어보기"
+  - local: in_translation
+    title: Stable Diffusion
   - local: installation
     title: "설치"
   title: "시작하기"
+
 - sections:
   - sections:
     - local: in_translation
-      title: "Loading Pipelines, Models, and Schedulers"
+      title: 개요
     - local: in_translation
-      title: "Using different Schedulers"
+      title: Unconditional 이미지 생성
     - local: in_translation
-      title: "Configuring Pipelines, Models, and Schedulers"
+      title: Textual Inversion
+    - local: training/dreambooth
+      title: DreamBooth
+    - local: training/text2image
+      title: Text-to-image
+    - local: training/lora
+      title: Low-Rank Adaptation of Large Language Models (LoRA)
     - local: in_translation
-      title: "Loading and Adding Custom Pipelines"
-    title: "불러오기 & 허브 (번역 예정)"
-  - sections:
+      title: ControlNet
     - local: in_translation
-      title: "Unconditional Image Generation"
-    - local: in_translation
-      title: "Text-to-Image Generation"
-    - local: in_translation
-      title: "Text-Guided Image-to-Image"
-    - local: in_translation
-      title: "Text-Guided Image-Inpainting"
-    - local: in_translation
-      title: "Text-Guided Depth-to-Image"
-    - local: in_translation
-      title: "Reusing seeds for deterministic generation"
-    - local: in_translation
-      title: "Community Pipelines"
-    - local: in_translation
-      title: "How to contribute a Pipeline"
-    title: "추론을 위한 파이프라인 (번역 예정)"
-  - sections:
-    - local: in_translation
-      title: "Reinforcement Learning"
-    - local: in_translation
-      title: "Audio"
-    - local: in_translation
-      title: "Other Modalities"
-    title: "Taking Diffusers Beyond Images"
-  title: "Diffusers 사용법 (번역 예정)"
+      title: InstructPix2Pix 학습
+    title: 학습
 - sections:
   - local: in_translation
-    title: "Memory and Speed"
+    title: 개요
+  - local: optimization/fp16
+    title: 메모리와 속도
   - local: in_translation
-    title: "xFormers"
-  - local: in_translation
-    title: "ONNX"
-  - local: in_translation
-    title: "OpenVINO"
-  - local: in_translation
-    title: "MPS"
-  - local: in_translation
-    title: "Habana Gaudi"
-  title: "최적화/특수 하드웨어 (번역 예정)"
-- sections:
-  - local: in_translation
-    title: "Overview"
-  - local: in_translation
-    title: "Unconditional Image Generation"
-  - local: in_translation
-    title: "Textual Inversion"
-  - local: in_translation
-    title: "Dreambooth"
-  - local: in_translation
-    title: "Text-to-image fine-tuning"
-  title: "학습 (번역 예정)"
-- sections:
-  - local: in_translation
-    title: "Stable Diffusion"
-  - local: in_translation
-    title: "Philosophy"
-  - local: in_translation
-    title: "How to contribute?"
-  title: "개념 설명 (번역 예정)"
-- sections:
-  - sections:
-    - local: in_translation
-      title: "Models"
-    - local: in_translation
-      title: "Diffusion Pipeline"
-    - local: in_translation
-      title: "Logging"
-    - local: in_translation
-      title: "Configuration"
-    - local: in_translation
-      title: "Outputs"
-    title: "Main Classes"
-    
-  - sections:
-    - local: in_translation
-      title: "Overview"
-    - local: in_translation
-      title: "AltDiffusion"
-    - local: in_translation
-      title: "Cycle Diffusion"
-    - local: in_translation
-      title: "DDIM"
-    - local: in_translation
-      title: "DDPM"
-    - local: in_translation
-      title: "Latent Diffusion"
-    - local: in_translation
-      title: "Unconditional Latent Diffusion"
-    - local: in_translation
-      title: "PaintByExample"
-    - local: in_translation
-      title: "PNDM"
-    - local: in_translation
-      title: "Score SDE VE"
-    - sections:
-      - local: in_translation
-        title: "Overview"
-      - local: in_translation
-        title: "Text-to-Image"
-      - local: in_translation
-        title: "Image-to-Image"
-      - local: in_translation
-        title: "Inpaint"
-      - local: in_translation
-        title: "Depth-to-Image"
-      - local: in_translation
-        title: "Image-Variation"  
-      - local: in_translation
-        title: "Super-Resolution"  
-      title: "Stable Diffusion"
-    - local: in_translation
-      title: "Stable Diffusion 2"
-    - local: in_translation
-      title: "Safe Stable Diffusion"
-    - local: in_translation
-      title: "Stochastic Karras VE"
-    - local: in_translation
-      title: "Dance Diffusion"
-    - local: in_translation
-      title: "UnCLIP"
-    - local: in_translation
-      title: "Versatile Diffusion"
-    - local: in_translation
-      title: "VQ Diffusion"
-    - local: in_translation
-      title: "RePaint"
-    - local: in_translation
-      title: "Audio Diffusion"
-    title: "파이프라인 (번역 예정)"
-  - sections:
-    - local: in_translation
-      title: "Overview"
-    - local: in_translation
-      title: "DDIM"
-    - local: in_translation
-      title: "DDPM"
-    - local: in_translation
-      title: "Singlestep DPM-Solver"
-    - local: in_translation
-      title: "Multistep DPM-Solver"
-    - local: in_translation
-      title: "Heun Scheduler"
-    - local: in_translation
-      title: "DPM Discrete Scheduler"
-    - local: in_translation
-      title: "DPM Discrete Scheduler with ancestral sampling"
-    - local: in_translation
-      title: "Stochastic Kerras VE"
-    - local: in_translation
-      title: "Linear Multistep"
-    - local: in_translation
-      title: "PNDM"
-    - local: in_translation
-      title: "VE-SDE"
-    - local: in_translation
-      title: "IPNDM"
-    - local: in_translation
-      title: "VP-SDE"
-    - local: in_translation
-      title: "Euler scheduler"
-    - local: in_translation
-      title: "Euler Ancestral Scheduler"
-    - local: in_translation
-      title: "VQDiffusionScheduler"
-    - local: in_translation
-      title: "RePaint Scheduler"      
-    title: "스케줄러 (번역 예정)"
-  - sections:
-    - local: in_translation
-      title: "RL Planning"
-    title: "Experimental Features"
-  title: "API (번역 예정)"
+    title: Torch2.0 지원
+  - local: optimization/xformers
+    title: xFormers
+  - local: optimization/onnx
+    title: ONNX
+  - local: optimization/open_vino
+    title: OpenVINO
+  - local: optimization/mps
+    title: MPS
+  - local: optimization/habana
+    title: Habana Gaudi
+  title: 최적화/특수 하드웨어

docs/source/ko/optimization/fp16.mdx

@@ -0,0 +1,410 @@
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# 메모리와 속도
+
+메모리 또는 속도에 대해 🤗 Diffusers *추론*을 최적화하기 위한 몇 가지 기술과 아이디어를 제시합니다. 
+일반적으로, memory-efficient attention을 위해 [xFormers](https://github.com/facebookresearch/xformers) 사용을 추천하기 때문에, 추천하는 [설치 방법](xformers)을 보고 설치해 보세요.
+
+다음 설정이 성능과 메모리에 미치는 영향에 대해 설명합니다.
+
+|                  | 지연시간  | 속도 향상 |
+| ---------------- | ------- | ------- |
+| 별도 설정 없음      | 9.50s   | x1      |
+| cuDNN auto-tuner | 9.37s   | x1.01   |
+| fp16             | 3.61s   | x2.63   |
+| Channels Last 메모리 형식     | 3.30s   | x2.88   |
+| traced UNet      | 3.21s   | x2.96   |
+| memory-efficient attention | 2.63s  | x3.61   |
+
+<em>
+   NVIDIA TITAN RTX에서 50 DDIM 스텝의 "a photo of an astronaut riding a horse on mars" 프롬프트로 512x512 크기의 단일 이미지를 생성하였습니다. 
+</em>
+
+## cuDNN auto-tuner 활성화하기
+
+[NVIDIA cuDNN](https://developer.nvidia.com/cudnn)은 컨볼루션을 계산하는 많은 알고리즘을 지원합니다. Autotuner는 짧은 벤치마크를 실행하고 주어진 입력 크기에 대해 주어진 하드웨어에서 최고의 성능을 가진 커널을 선택합니다.
+
+**컨볼루션 네트워크**를 활용하고 있기 때문에 (다른 유형들은 현재 지원되지 않음), 다음 설정을 통해 추론 전에 cuDNN autotuner를 활성화할 수 있습니다:
+
+```python
+import torch
+
+torch.backends.cudnn.benchmark = True
+```
+
+### fp32 대신 tf32 사용하기  (Ampere 및 이후 CUDA 장치들에서)
+
+Ampere 및 이후 CUDA 장치에서 행렬곱 및 컨볼루션은 TensorFloat32(TF32) 모드를 사용하여 더 빠르지만 약간 덜 정확할 수 있습니다. 
+기본적으로 PyTorch는 컨볼루션에 대해 TF32 모드를 활성화하지만 행렬 곱셈은 활성화하지 않습니다. 
+네트워크에 완전한 float32 정밀도가 필요한 경우가 아니면 행렬 곱셈에 대해서도 이 설정을 활성화하는 것이 좋습니다. 
+이는 일반적으로 무시할 수 있는 수치의 정확도 손실이 있지만, 계산 속도를 크게 높일 수 있습니다. 
+그것에 대해 [여기](https://huggingface.co/docs/transformers/v4.18.0/en/performance#tf32)서 더 읽을 수 있습니다. 
+추론하기 전에 다음을 추가하기만 하면 됩니다:
+
+```python
+import torch
+
+torch.backends.cuda.matmul.allow_tf32 = True
+```
+
+## 반정밀도 가중치
+
+더 많은 GPU 메모리를 절약하고 더 빠른 속도를 얻기 위해 모델 가중치를 반정밀도(half precision)로 직접 로드하고 실행할 수 있습니다. 
+여기에는 `fp16`이라는 브랜치에 저장된 float16 버전의 가중치를 불러오고, 그 때 `float16` 유형을 사용하도록 PyTorch에 지시하는 작업이 포함됩니다.
+
+```Python
+pipe = StableDiffusionPipeline.from_pretrained(
+    "runwayml/stable-diffusion-v1-5",
+    
+    torch_dtype=torch.float16,
+)
+pipe = pipe.to("cuda")
+
+prompt = "a photo of an astronaut riding a horse on mars"
+image = pipe(prompt).images[0]
+```
+
+<Tip warning={true}>
+  어떤 파이프라인에서도 [`torch.autocast`](https://pytorch.org/docs/stable/amp.html#torch.autocast) 를 사용하는 것은 검은색 이미지를 생성할 수 있고, 순수한 float16 정밀도를 사용하는 것보다 항상 느리기 때문에 사용하지 않는 것이 좋습니다. 
+</Tip>
+
+## 추가 메모리 절약을 위한 슬라이스 어텐션
+
+추가 메모리 절약을 위해, 한 번에 모두 계산하는 대신 단계적으로 계산을 수행하는 슬라이스 버전의 어텐션(attention)을 사용할 수 있습니다.
+
+<Tip>
+  Attention slicing은 모델이 하나 이상의 어텐션 헤드를 사용하는 한, 배치 크기가 1인 경우에도 유용합니다.
+  하나 이상의 어텐션 헤드가 있는 경우 *QK^T* 어텐션 매트릭스는 상당한 양의 메모리를 절약할 수 있는 각 헤드에 대해 순차적으로 계산될 수 있습니다.
+</Tip>
+
+각 헤드에 대해 순차적으로 어텐션 계산을 수행하려면, 다음과 같이 추론 전에 파이프라인에서 [`~StableDiffusionPipeline.enable_attention_slicing`]를 호출하면 됩니다:
+
+```Python
+import torch
+from diffusers import StableDiffusionPipeline
+
+pipe = StableDiffusionPipeline.from_pretrained(
+    "runwayml/stable-diffusion-v1-5",
+    
+    torch_dtype=torch.float16,
+)
+pipe = pipe.to("cuda")
+
+prompt = "a photo of an astronaut riding a horse on mars"
+pipe.enable_attention_slicing()
+image = pipe(prompt).images[0]
+```
+
+추론 시간이 약 10% 느려지는 약간의 성능 저하가 있지만 이 방법을 사용하면 3.2GB 정도의 작은 VRAM으로도 Stable Diffusion을 사용할 수 있습니다!
+
+
+## 더 큰 배치를 위한 sliced VAE 디코드
+
+제한된 VRAM에서 대규모 이미지 배치를 디코딩하거나 32개 이상의 이미지가 포함된 배치를 활성화하기 위해, 배치의 latent 이미지를 한 번에 하나씩 디코딩하는 슬라이스 VAE 디코드를 사용할 수 있습니다.
+
+이를 [`~StableDiffusionPipeline.enable_attention_slicing`] 또는 [`~StableDiffusionPipeline.enable_xformers_memory_efficient_attention`]과 결합하여 메모리 사용을 추가로 최소화할 수 있습니다.
+
+VAE 디코드를 한 번에 하나씩 수행하려면 추론 전에 파이프라인에서 [`~StableDiffusionPipeline.enable_vae_slicing`]을 호출합니다. 예를 들어:
+
+```Python
+import torch
+from diffusers import StableDiffusionPipeline
+
+pipe = StableDiffusionPipeline.from_pretrained(
+    "runwayml/stable-diffusion-v1-5",
+    
+    torch_dtype=torch.float16,
+)
+pipe = pipe.to("cuda")
+
+prompt = "a photo of an astronaut riding a horse on mars"
+pipe.enable_vae_slicing()
+images = pipe([prompt] * 32).images
+```
+
+다중 이미지 배치에서 VAE 디코드가 약간의 성능 향상이 이루어집니다. 단일 이미지 배치에서는 성능 영향은 없습니다.
+
+
+<a name="sequential_offloading"></a>
+## 메모리 절약을 위해 가속 기능을 사용하여 CPU로 오프로딩
+
+추가 메모리 절약을 위해 가중치를 CPU로 오프로드하고 순방향 전달을 수행할 때만 GPU로 로드할 수 있습니다.
+
+CPU 오프로딩을 수행하려면 [`~StableDiffusionPipeline.enable_sequential_cpu_offload`]를 호출하기만 하면 됩니다:
+
+```Python
+import torch
+from diffusers import StableDiffusionPipeline
+
+pipe = StableDiffusionPipeline.from_pretrained(
+    "runwayml/stable-diffusion-v1-5",
+    
+    torch_dtype=torch.float16,
+)
+
+prompt = "a photo of an astronaut riding a horse on mars"
+pipe.enable_sequential_cpu_offload()
+image = pipe(prompt).images[0]
+```
+
+그러면 메모리 소비를 3GB 미만으로 줄일 수 있습니다.
+
+참고로 이 방법은 전체 모델이 아닌 서브모듈 수준에서 작동합니다. 이는 메모리 소비를 최소화하는 가장 좋은 방법이지만 프로세스의 반복적 특성으로 인해 추론 속도가 훨씬 느립니다. 파이프라인의 UNet 구성 요소는 여러 번 실행됩니다('num_inference_steps' 만큼). 매번 UNet의 서로 다른 서브모듈이 순차적으로 온로드된 다음 필요에 따라 오프로드되므로 메모리 이동 횟수가 많습니다.
+
+<Tip>
+또 다른 최적화 방법인 <a href="#model_offloading">모델 오프로딩</a>을 사용하는 것을 고려하십시오. 이는 훨씬 빠르지만 메모리 절약이 크지는 않습니다.
+</Tip>
+
+또한 ttention slicing과 연결해서 최소 메모리(< 2GB)로도 동작할 수 있습니다. 
+
+
+```Python
+import torch
+from diffusers import StableDiffusionPipeline
+
+pipe = StableDiffusionPipeline.from_pretrained(
+    "runwayml/stable-diffusion-v1-5",
+    
+    torch_dtype=torch.float16,
+)
+
+prompt = "a photo of an astronaut riding a horse on mars"
+pipe.enable_sequential_cpu_offload()
+pipe.enable_attention_slicing(1)
+
+image = pipe(prompt).images[0]
+```
+
+**참고**: 'enable_sequential_cpu_offload()'를 사용할 때, 미리 파이프라인을 CUDA로 이동하지 **않는** 것이 중요합니다.그렇지 않으면 메모리 소비의 이득이 최소화됩니다. 더 많은 정보를 위해 [이 이슈](https://github.com/huggingface/diffusers/issues/1934)를 보세요.
+
+<a name="model_offloading"></a>
+## 빠른 추론과 메모리 메모리 절약을 위한 모델 오프로딩
+
+[순차적 CPU 오프로딩](#sequential_offloading)은 이전 섹션에서 설명한 것처럼 많은 메모리를 보존하지만 필요에 따라 서브모듈을 GPU로 이동하고 새 모듈이 실행될 때 즉시 CPU로 반환되기 때문에 추론 속도가 느려집니다.
+
+전체 모델 오프로딩은 각 모델의 구성 요소인 _modules_을 처리하는 대신, 전체 모델을 GPU로 이동하는 대안입니다. 이로 인해 추론 시간에 미치는 영향은 미미하지만(파이프라인을 'cuda'로 이동하는 것과 비교하여) 여전히 약간의 메모리를 절약할 수 있습니다.
+
+이 시나리오에서는 파이프라인의 주요 구성 요소 중 하나만(일반적으로 텍스트 인코더, unet 및 vae) GPU에 있고, 나머지는 CPU에서 대기할 것입니다.
+여러 반복을 위해 실행되는 UNet과 같은 구성 요소는 더 이상 필요하지 않을 때까지 GPU에 남아 있습니다.
+
+이 기능은 아래와 같이 파이프라인에서 `enable_model_cpu_offload()`를 호출하여 활성화할 수 있습니다.
+
+```Python
+import torch
+from diffusers import StableDiffusionPipeline
+
+pipe = StableDiffusionPipeline.from_pretrained(
+    "runwayml/stable-diffusion-v1-5",  
+    torch_dtype=torch.float16,
+)
+
+prompt = "a photo of an astronaut riding a horse on mars"
+pipe.enable_model_cpu_offload()
+image = pipe(prompt).images[0]
+```
+
+이는 추가적인 메모리 절약을 위한 attention slicing과도 호환됩니다.
+
+```Python
+import torch
+from diffusers import StableDiffusionPipeline
+
+pipe = StableDiffusionPipeline.from_pretrained(
+    "runwayml/stable-diffusion-v1-5",
+    torch_dtype=torch.float16,
+)
+
+prompt = "a photo of an astronaut riding a horse on mars"
+pipe.enable_model_cpu_offload()
+pipe.enable_attention_slicing(1)
+
+image = pipe(prompt).images[0]
+```
+
+<Tip>
+이 기능을 사용하려면 'accelerate' 버전 0.17.0 이상이 필요합니다.
+</Tip>
+
+## Channels Last 메모리 형식 사용하기
+
+Channels Last 메모리 형식은 차원 순서를 보존하는 메모리에서 NCHW 텐서 배열을 대체하는 방법입니다.
+Channels Last 텐서는 채널이 가장 조밀한 차원이 되는 방식으로 정렬됩니다(일명 픽셀당 이미지를 저장).
+현재 모든 연산자 Channels Last 형식을 지원하는 것은 아니라 성능이 저하될 수 있으므로, 사용해보고 모델에 잘 작동하는지 확인하는 것이 좋습니다.
+
+
+예를 들어 파이프라인의 UNet 모델이 channels Last 형식을 사용하도록 설정하려면 다음을 사용할 수 있습니다:
+
+```python
+print(pipe.unet.conv_out.state_dict()["weight"].stride())  # (2880, 9, 3, 1)
+pipe.unet.to(memory_format=torch.channels_last)  # in-place 연산
+# 2번째 차원에서 스트라이드 1을 가지는 (2880, 1, 960, 320)로, 연산이 작동함을 증명합니다.
+print(pipe.unet.conv_out.state_dict()["weight"].stride())
+```
+
+## 추적(tracing)
+
+추적은 모델을 통해 예제 입력 텐서를 통해 실행되는데, 해당 입력이 모델의 레이어를 통과할 때 호출되는 작업을 캡처하여 실행 파일 또는 'ScriptFunction'이 반환되도록 하고, 이는 just-in-time 컴파일로 최적화됩니다.
+
+UNet 모델을 추적하기 위해 다음을 사용할 수 있습니다:
+
+```python
+import time
+import torch
+from diffusers import StableDiffusionPipeline
+import functools
+
+# torch 기울기 비활성화
+torch.set_grad_enabled(False)
+
+# 변수 설정
+n_experiments = 2
+unet_runs_per_experiment = 50
+
+
+# 입력 불러오기
+def generate_inputs():
+    sample = torch.randn(2, 4, 64, 64).half().cuda()
+    timestep = torch.rand(1).half().cuda() * 999
+    encoder_hidden_states = torch.randn(2, 77, 768).half().cuda()
+    return sample, timestep, encoder_hidden_states
+
+
+pipe = StableDiffusionPipeline.from_pretrained(
+    "runwayml/stable-diffusion-v1-5",
+    torch_dtype=torch.float16,
+).to("cuda")
+unet = pipe.unet
+unet.eval()
+unet.to(memory_format=torch.channels_last)  # Channels Last 메모리 형식 사용
+unet.forward = functools.partial(unet.forward, return_dict=False)  # return_dict=False을 기본값으로 설정
+
+# 워밍업
+for _ in range(3):
+    with torch.inference_mode():
+        inputs = generate_inputs()
+        orig_output = unet(*inputs)
+
+# 추적
+print("tracing..")
+unet_traced = torch.jit.trace(unet, inputs)
+unet_traced.eval()
+print("done tracing")
+
+
+# 워밍업 및 그래프 최적화
+for _ in range(5):
+    with torch.inference_mode():
+        inputs = generate_inputs()
+        orig_output = unet_traced(*inputs)
+
+
+# 벤치마킹
+with torch.inference_mode():
+    for _ in range(n_experiments):
+        torch.cuda.synchronize()
+        start_time = time.time()
+        for _ in range(unet_runs_per_experiment):
+            orig_output = unet_traced(*inputs)
+        torch.cuda.synchronize()
+        print(f"unet traced inference took {time.time() - start_time:.2f} seconds")
+    for _ in range(n_experiments):
+        torch.cuda.synchronize()
+        start_time = time.time()
+        for _ in range(unet_runs_per_experiment):
+            orig_output = unet(*inputs)
+        torch.cuda.synchronize()
+        print(f"unet inference took {time.time() - start_time:.2f} seconds")
+
+# 모델 저장
+unet_traced.save("unet_traced.pt")
+```
+
+그 다음, 파이프라인의 `unet` 특성을 다음과 같이 추적된 모델로 바꿀 수 있습니다.
+
+```python
+from diffusers import StableDiffusionPipeline
+import torch
+from dataclasses import dataclass
+
+
+@dataclass
+class UNet2DConditionOutput:
+    sample: torch.FloatTensor
+
+
+pipe = StableDiffusionPipeline.from_pretrained(
+    "runwayml/stable-diffusion-v1-5",
+    torch_dtype=torch.float16,
+).to("cuda")
+
+# jitted unet 사용
+unet_traced = torch.jit.load("unet_traced.pt")
+
+
+# pipe.unet 삭제
+class TracedUNet(torch.nn.Module):
+    def __init__(self):
+        super().__init__()
+        self.in_channels = pipe.unet.in_channels
+        self.device = pipe.unet.device
+
+    def forward(self, latent_model_input, t, encoder_hidden_states):
+        sample = unet_traced(latent_model_input, t, encoder_hidden_states)[0]
+        return UNet2DConditionOutput(sample=sample)
+
+
+pipe.unet = TracedUNet()
+
+with torch.inference_mode():
+    image = pipe([prompt] * 1, num_inference_steps=50).images[0]
+```
+
+
+## Memory-efficient attention
+
+어텐션 블록의 대역폭을 최적화하는 최근 작업으로 GPU 메모리 사용량이 크게 향상되고 향상되었습니다.
+@tridao의 가장 최근의 플래시 어텐션: [code](https://github.com/HazyResearch/flash-attention), [paper](https://arxiv.org/pdf/2205.14135.pdf).
+
+배치 크기 1(프롬프트 1개)의 512x512 크기로 추론을 실행할 때 몇 가지 Nvidia GPU에서 얻은 속도 향상은 다음과 같습니다:
+
+| GPU              	| 기준 어텐션 FP16 	       | 메모리 효율적인 어텐션 FP16 	|
+|------------------	|---------------------	|---------------------------------	|
+| NVIDIA Tesla T4  	| 3.5it/s             	| 5.5it/s                         	|
+| NVIDIA 3060 RTX  	| 4.6it/s             	| 7.8it/s                         	|
+| NVIDIA A10G      	| 8.88it/s            	| 15.6it/s                        	|
+| NVIDIA RTX A6000 	| 11.7it/s            	| 21.09it/s                       	|
+| NVIDIA TITAN RTX  | 12.51it/s         	| 18.22it/s                       	|
+| A100-SXM4-40GB    	| 18.6it/s            	| 29.it/s                        	|
+| A100-SXM-80GB    	| 18.7it/s            	| 29.5it/s                        	|
+
+이를 활용하려면 다음을 만족해야 합니다: 
+ - PyTorch > 1.12
+ - Cuda 사용 가능
+ - [xformers 라이브러리를 설치함](xformers)
+```python
+from diffusers import StableDiffusionPipeline
+import torch
+
+pipe = StableDiffusionPipeline.from_pretrained(
+    "runwayml/stable-diffusion-v1-5",
+    torch_dtype=torch.float16,
+).to("cuda")
+
+pipe.enable_xformers_memory_efficient_attention()
+
+with torch.inference_mode():
+    sample = pipe("a small cat")
+
+# 선택: 이를 비활성화 하기 위해 다음을 사용할 수 있습니다.
+# pipe.disable_xformers_memory_efficient_attention()
+```

docs/source/ko/optimization/habana.mdx

@@ -0,0 +1,71 @@
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# Habana Gaudi에서 Stable Diffusion을 사용하는 방법
+
+🤗 Diffusers는 🤗 [Optimum Habana](https://huggingface.co/docs/optimum/habana/usage_guides/stable_diffusion)를 통해서 Habana Gaudi와 호환됩니다.
+
+## 요구 사항
+
+- Optimum Habana 1.4 또는 이후, [여기](https://huggingface.co/docs/optimum/habana/installation)에 설치하는 방법이 있습니다.
+- SynapseAI 1.8.
+
+
+## 추론 파이프라인
+
+Gaudi에서 Stable Diffusion 1 및 2로 이미지를 생성하려면 두 인스턴스를 인스턴스화해야 합니다:
+- [`GaudiStableDiffusionPipeline`](https://huggingface.co/docs/optimum/habana/package_reference/stable_diffusion_pipeline)이 포함된 파이프라인. 이 파이프라인은 *텍스트-이미지 생성*을 지원합니다.
+- [`GaudiDDIMScheduler`](https://huggingface.co/docs/optimum/habana/package_reference/stable_diffusion_pipeline#optimum.habana.diffusers.GaudiDDIMScheduler)이 포함된 스케줄러. 이 스케줄러는 Habana Gaudi에 최적화되어 있습니다.
+
+파이프라인을 초기화할 때, HPU에 배포하기 위해 `use_habana=True`를 지정해야 합니다.
+또한 가능한 가장 빠른 생성을 위해 `use_hpu_graphs=True`로 **HPU 그래프**를 활성화해야 합니다.
+마지막으로, [Hugging Face Hub](https://huggingface.co/Habana)에서 다운로드할 수 있는 [Gaudi configuration](https://huggingface.co/docs/optimum/habana/package_reference/gaudi_config)을 지정해야 합니다.
+
+```python
+from optimum.habana import GaudiConfig
+from optimum.habana.diffusers import GaudiDDIMScheduler, GaudiStableDiffusionPipeline
+
+model_name = "stabilityai/stable-diffusion-2-base"
+scheduler = GaudiDDIMScheduler.from_pretrained(model_name, subfolder="scheduler")
+pipeline = GaudiStableDiffusionPipeline.from_pretrained(
+    model_name,
+    scheduler=scheduler,
+    use_habana=True,
+    use_hpu_graphs=True,
+    gaudi_config="Habana/stable-diffusion",
+)
+```
+
+파이프라인을 호출하여 하나 이상의 프롬프트에서 배치별로 이미지를 생성할 수 있습니다.
+
+```python
+outputs = pipeline(
+    prompt=[
+        "High quality photo of an astronaut riding a horse in space",
+        "Face of a yellow cat, high resolution, sitting on a park bench",
+    ],
+    num_images_per_prompt=10,
+    batch_size=4,
+)
+```
+
+더 많은 정보를 얻기 위해, Optimum Habana의 [문서](https://huggingface.co/docs/optimum/habana/usage_guides/stable_diffusion)와 공식 Github 저장소에 제공된 [예시](https://github.com/huggingface/optimum-habana/tree/main/examples/stable-diffusion)를 확인하세요.
+
+
+## 벤치마크
+
+다음은 [Habana/stable-diffusion](https://huggingface.co/Habana/stable-diffusion) Gaudi 구성(혼합 정밀도 bf16/fp32)을 사용하는 Habana first-generation Gaudi 및 Gaudi2의 지연 시간입니다:
+
+|                        | Latency (배치 크기 = 1) | Throughput (배치 크기 = 8) |
+| ---------------------- |:------------------------:|:---------------------------:|
+| first-generation Gaudi | 4.29s                    | 0.283 images/s              |
+| Gaudi2                 | 1.54s                    | 0.904 images/s              |

docs/source/ko/optimization/mps.mdx

@@ -0,0 +1,71 @@
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# Apple Silicon (M1/M2)에서 Stable Diffusion을 사용하는 방법
+
+Diffusers는 Stable Diffusion 추론을 위해 PyTorch `mps`를 사용해 Apple 실리콘과 호환됩니다. 다음은 Stable Diffusion이 있는 M1 또는 M2 컴퓨터를 사용하기 위해 따라야 하는 단계입니다.
+
+## 요구 사항
+
+- Apple silicon (M1/M2) 하드웨어의 Mac 컴퓨터.
+- macOS 12.6 또는 이후 (13.0 또는 이후 추천).
+- Python arm64 버전
+- PyTorch 2.0(추천) 또는 1.13(`mps`를 지원하는 최소 버전). Yhttps://pytorch.org/get-started/locally/의 지침에 따라 `pip` 또는 `conda`로 설치할 수 있습니다.
+
+
+## 추론 파이프라인
+
+아래 코도는 익숙한 `to()` 인터페이스를 사용하여 `mps` 백엔드로 Stable Diffusion 파이프라인을 M1 또는 M2 장치로 이동하는 방법을 보여줍니다.
+
+
+<Tip warning={true}>
+
+**PyTorch 1.13을 사용 중일 때 ** 추가 일회성 전달을 사용하여 파이프라인을 "프라이밍"하는 것을 추천합니다. 이것은 발견한 이상한 문제에 대한 임시 해결 방법입니다. 첫 번째 추론 전달은 후속 전달와 약간 다른 결과를 생성합니다. 이 전달은 한 번만 수행하면 되며 추론 단계를 한 번만 사용하고 결과를 폐기해도 됩니다.
+
+</Tip>
+
+이전 팁에서 설명한 것들을 포함한 여러 문제를 해결하므로 PyTorch 2 이상을 사용하는 것이 좋습니다.
+
+
+```python
+# `huggingface-cli login`에 로그인되어 있음을 확인
+from diffusers import DiffusionPipeline
+
+pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")
+pipe = pipe.to("mps")
+
+# 컴퓨터가 64GB 이하의 RAM 램일 때 추천
+pipe.enable_attention_slicing()
+
+prompt = "a photo of an astronaut riding a horse on mars"
+
+# 처음 "워밍업" 전달 (위 설명을 보세요)
+_ = pipe(prompt, num_inference_steps=1)
+
+# 결과는 워밍업 전달 후의 CPU 장치의 결과와 일치합니다.
+image = pipe(prompt).images[0]
+```
+
+## 성능 추천
+
+M1/M2 성능은 메모리 압력에 매우 민감합니다. 시스템은 필요한 경우 자동으로 스왑되지만 스왑할 때 성능이 크게 저하됩니다.
+
+
+특히 컴퓨터의 시스템 RAM이 64GB 미만이거나 512 × 512픽셀보다 큰 비표준 해상도에서 이미지를 생성하는 경우, 추론 중에 메모리 압력을 줄이고 스와핑을 방지하기 위해 *어텐션 슬라이싱*을 사용하는 것이 좋습니다. 어텐션 슬라이싱은 비용이 많이 드는 어텐션 작업을 한 번에 모두 수행하는 대신 여러 단계로 수행합니다. 일반적으로 범용 메모리가 없는 컴퓨터에서 ~20%의 성능 영향을 미치지만 64GB 이상이 아닌 경우 대부분의 Apple Silicon 컴퓨터에서 *더 나은 성능*이 관찰되었습니다.
+
+```python
+pipeline.enable_attention_slicing()
+```
+
+## Known Issues
+
+- 여러 프롬프트를 배치로 생성하는 것은 [충돌이 발생하거나 안정적으로 작동하지 않습니다](https://github.com/huggingface/diffusers/issues/363). 우리는 이것이 [PyTorch의 `mps` 백엔드](https://github.com/pytorch/pytorch/issues/84039)와 관련이 있다고 생각합니다. 이 문제는 해결되고 있지만 지금은 배치 대신 반복 방법을 사용하는 것이 좋습니다.

docs/source/ko/optimization/onnx.mdx

@@ -0,0 +1,65 @@
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+
+# 추론을 위해 ONNX 런타임을 사용하는 방법
+
+🤗 Diffusers는 ONNX Runtime과 호환되는 Stable Diffusion 파이프라인을 제공합니다. 이를 통해 ONNX(CPU 포함)를 지원하고 PyTorch의 가속 버전을 사용할 수 없는 모든 하드웨어에서 Stable Diffusion을 실행할 수 있습니다.
+
+## 설치
+
+다음 명령어로 ONNX Runtime를 지원하는 🤗 Optimum를 설치합니다:
+
+```
+pip install optimum["onnxruntime"]
+```
+
+## Stable Diffusion 추론
+
+아래 코드는 ONNX 런타임을 사용하는 방법을 보여줍니다. `StableDiffusionPipeline` 대신 `OnnxStableDiffusionPipeline`을 사용해야 합니다. 
+PyTorch 모델을 불러오고 즉시 ONNX 형식으로 변환하려는 경우 `export=True`로 설정합니다.
+
+```python
+from optimum.onnxruntime import ORTStableDiffusionPipeline
+
+model_id = "runwayml/stable-diffusion-v1-5"
+pipe = ORTStableDiffusionPipeline.from_pretrained(model_id, export=True)
+prompt = "a photo of an astronaut riding a horse on mars"
+images = pipe(prompt).images[0]
+pipe.save_pretrained("./onnx-stable-diffusion-v1-5")
+```
+
+파이프라인을 ONNX 형식으로 오프라인으로 내보내고 나중에 추론에 사용하려는 경우, 
+[`optimum-cli export`](https://huggingface.co/docs/optimum/main/en/exporters/onnx/usage_guides/export_a_model#exporting-a-model-to-onnx-using-the-cli) 명령어를 사용할 수 있습니다:
+
+```bash
+optimum-cli export onnx --model runwayml/stable-diffusion-v1-5 sd_v15_onnx/
+```
+
+그 다음 추론을 수행합니다:
+
+```python 
+from optimum.onnxruntime import ORTStableDiffusionPipeline
+
+model_id = "sd_v15_onnx"
+pipe = ORTStableDiffusionPipeline.from_pretrained(model_id)
+prompt = "a photo of an astronaut riding a horse on mars"
+images = pipe(prompt).images[0]
+```
+
+Notice that we didn't have to specify `export=True` above.
+
+[Optimum 문서](https://huggingface.co/docs/optimum/)에서 더 많은 예시를 찾을 수 있습니다.
+
+## 알려진 이슈들
+
+- 여러 프롬프트를 배치로 생성하면 너무 많은 메모리가 사용되는 것 같습니다. 이를 조사하는 동안, 배치 대신 반복 방법이 필요할 수도 있습니다.

docs/source/ko/optimization/open_vino.mdx

@@ -0,0 +1,39 @@
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# 추론을 위한 OpenVINO 사용 방법
+
+🤗 [Optimum](https://github.com/huggingface/optimum-intel)은 OpenVINO와 호환되는 Stable Diffusion 파이프라인을 제공합니다.
+이제 다양한 Intel 프로세서에서 OpenVINO Runtime으로 쉽게 추론을 수행할 수 있습니다. ([여기](https://docs.openvino.ai/latest/openvino_docs_OV_UG_supported_plugins_Supported_Devices.html)서 지원되는 전 기기 목록을 확인하세요).
+
+## 설치
+
+다음 명령어로 🤗 Optimum을 설치합니다:
+
+```
+pip install optimum["openvino"]
+```
+
+## Stable Diffusion 추론
+
+OpenVINO 모델을 불러오고 OpenVINO 런타임으로 추론을 실행하려면 `StableDiffusionPipeline`을 `OVStableDiffusionPipeline`으로 교체해야 합니다. PyTorch 모델을 불러오고 즉시 OpenVINO 형식으로 변환하려는 경우 `export=True`로 설정합니다.
+
+```python
+from optimum.intel.openvino import OVStableDiffusionPipeline
+
+model_id = "runwayml/stable-diffusion-v1-5"
+pipe = OVStableDiffusionPipeline.from_pretrained(model_id, export=True)
+prompt = "a photo of an astronaut riding a horse on mars"
+images = pipe(prompt).images[0]
+```
+
+[Optimum 문서](https://huggingface.co/docs/optimum/intel/inference#export-and-inference-of-stable-diffusion-models)에서 (정적 reshaping과 모델 컴파일 등의) 더 많은 예시들을 찾을 수 있습니다.

docs/source/ko/optimization/xformers.mdx

@@ -0,0 +1,36 @@
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# xFormers 설치하기
+
+추론과 학습 모두에 [xFormers](https://github.com/facebookresearch/xformers)를 사용하는 것이 좋습니다.
+자체 테스트로 어텐션 블록에서 수행된 최적화가 더 빠른 속도와 적은 메모리 소비를 확인했습니다.
+
+2023년 1월에 출시된 xFormers 버전 '0.0.16'부터 사전 빌드된 pip wheel을 사용하여 쉽게 설치할 수 있습니다:
+
+```bash
+pip install xformers
+```
+
+<Tip>
+
+xFormers PIP 패키지에는 최신 버전의 PyTorch(xFormers 0.0.16에 1.13.1)가 필요합니다. 이전 버전의 PyTorch를 사용해야 하는 경우 [프로젝트 지침](https://github.com/facebookresearch/xformers#installing-xformers)의 소스를 사용해 xFormers를 설치하는 것이 좋습니다.
+
+</Tip>
+
+xFormers를 설치하면, [여기](fp16#memory-efficient-attention)서 설명한 것처럼 'enable_xformers_memory_efficient_attention()'을 사용하여 추론 속도를 높이고 메모리 소비를 줄일 수 있습니다.
+
+<Tip warning={true}>
+
+[이 이슈](https://github.com/huggingface/diffusers/issues/2234#issuecomment-1416931212)에 따르면 xFormers `v0.0.16`에서 GPU를 사용한 학습(파인 튜닝 또는 Dreambooth)을 할 수 없습니다. 해당 문제가 발견되면. 해당 코멘트를 참고해 development 버전을 설치하세요.
+
+</Tip>

docs/source/ko/training/dreambooth.mdx

@@ -0,0 +1,475 @@
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# DreamBooth
+
+[DreamBooth](https://arxiv.org/abs/2208.12242)는 한 주제에 대한 적은 이미지(3~5개)만으로도 stable diffusion과 같이 text-to-image 모델을 개인화할 수 있는 방법입니다. 이를 통해 모델은 다양한 장면, 포즈 및 장면(뷰)에서 피사체에 대해 맥락화(contextualized)된 이미지를 생성할 수 있습니다.
+
+![프로젝트 블로그에서의 DreamBooth 예시](https://dreambooth.github.io/DreamBooth_files/teaser_static.jpg)
+<a href="https://dreambooth.github.io">project's blog.</a></small>
+<small><a href="https://dreambooth.github.io">프로젝트 블로그</a>에서의 Dreambooth 예시</small>
+
+
+이 가이드는 다양한 GPU, Flax 사양에 대해 [`CompVis/stable-diffusion-v1-4`](https://huggingface.co/CompVis/stable-diffusion-v1-4) 모델로 DreamBooth를 파인튜닝하는 방법을 보여줍니다. 더 깊이 파고들어 작동 방식을 확인하는 데 관심이 있는 경우, 이 가이드에 사용된 DreamBooth의 모든 학습 스크립트를 [여기](https://github.com/huggingface/diffusers/tree/main/examples/dreambooth)에서 찾을 수 있습니다.
+
+스크립트를 실행하기 전에 라이브러리의 학습에 필요한 dependencies를 설치해야 합니다. 또한 `main` GitHub 브랜치에서 🧨 Diffusers를 설치하는 것이 좋습니다.
+
+```bash
+pip install git+https://github.com/huggingface/diffusers
+pip install -U -r diffusers/examples/dreambooth/requirements.txt
+```
+
+xFormers는 학습에 필요한 요구 사항은 아니지만, 가능하면 [설치](../optimization/xformers)하는 것이 좋습니다. 학습 속도를 높이고 메모리 사용량을 줄일 수 있기 때문입니다.
+
+모든 dependencies을 설정한 후 다음을 사용하여 [🤗 Accelerate](https://github.com/huggingface/accelerate/) 환경을 다음과 같이 초기화합니다:
+
+```bash
+accelerate config
+```
+
+별도 설정 없이 기본 🤗 Accelerate 환경을 설치하려면 다음을 실행합니다:
+
+```bash
+accelerate config default
+```
+
+또는 현재 환경이 노트북과 같은 대화형 셸을 지원하지 않는 경우 다음을 사용할 수 있습니다:
+
+```py
+from accelerate.utils import write_basic_config
+
+write_basic_config()
+```
+
+## 파인튜닝
+
+<Tip warning={true}>
+
+DreamBooth 파인튜닝은 하이퍼파라미터에 매우 민감하고 과적합되기 쉽습니다. 적절한 하이퍼파라미터를 선택하는 데 도움이 되도록 다양한 권장 설정이 포함된 [심층 분석](https://huggingface.co/blog/dreambooth)을 살펴보는 것이 좋습니다.
+
+</Tip>
+
+<frameworkcontent>
+<pt>
+[몇 장의 강아지 이미지들](https://drive.google.com/drive/folders/1BO_dyz-p65qhBRRMRA4TbZ8qW4rB99JZ)로 DreamBooth를 시도해봅시다. 
+이를 다운로드해 디렉터리에 저장한 다음 `INSTANCE_DIR` 환경 변수를 해당 경로로 설정합니다:
+
+
+```bash
+export MODEL_NAME="CompVis/stable-diffusion-v1-4"
+export INSTANCE_DIR="path_to_training_images"
+export OUTPUT_DIR="path_to_saved_model"
+```
+
+그런 다음, 다음 명령을 사용하여 학습 스크립트를 실행할 수 있습니다 (전체 학습 스크립트는 [여기](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/train_dreambooth.py)에서 찾을 수 있습니다):
+
+```bash
+accelerate launch train_dreambooth.py \
+  --pretrained_model_name_or_path=$MODEL_NAME  \
+  --instance_data_dir=$INSTANCE_DIR \
+  --output_dir=$OUTPUT_DIR \
+  --instance_prompt="a photo of sks dog" \
+  --resolution=512 \
+  --train_batch_size=1 \
+  --gradient_accumulation_steps=1 \
+  --learning_rate=5e-6 \
+  --lr_scheduler="constant" \
+  --lr_warmup_steps=0 \
+  --max_train_steps=400
+```
+</pt>
+<jax>
+
+TPU에 액세스할 수 있거나 더 빠르게 훈련하고 싶다면 [Flax 학습 스크립트](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/train_dreambooth_flax.py)를 사용해 볼 수 있습니다. Flax 학습 스크립트는 gradient checkpointing 또는 gradient accumulation을 지원하지 않으므로, 메모리가 30GB 이상인 GPU가 필요합니다.
+
+스크립트를 실행하기 전에 요구 사항이 설치되어 있는지 확인하십시오.
+
+```bash
+pip install -U -r requirements.txt
+```
+
+그러면 다음 명령어로 학습 스크립트를 실행시킬 수 있습니다:
+
+```bash
+export MODEL_NAME="duongna/stable-diffusion-v1-4-flax"
+export INSTANCE_DIR="path-to-instance-images"
+export OUTPUT_DIR="path-to-save-model"
+
+python train_dreambooth_flax.py \
+  --pretrained_model_name_or_path=$MODEL_NAME  \
+  --instance_data_dir=$INSTANCE_DIR \
+  --output_dir=$OUTPUT_DIR \
+  --instance_prompt="a photo of sks dog" \
+  --resolution=512 \
+  --train_batch_size=1 \
+  --learning_rate=5e-6 \
+  --max_train_steps=400
+```
+</jax>
+</frameworkcontent>
+
+### Prior-preserving(사전 보존) loss를 사용한 파인튜닝
+
+과적합과 language drift를 방지하기 위해 사전 보존이 사용됩니다(관심이 있는 경우 [논문](https://arxiv.org/abs/2208.12242)을 참조하세요).  사전 보존을 위해 동일한 클래스의 다른 이미지를 학습 프로세스의 일부로 사용합니다. 좋은 점은 Stable Diffusion 모델 자체를 사용하여 이러한 이미지를 생성할 수 있다는 것입니다! 학습 스크립트는 생성된 이미지를 우리가 지정한 로컬 경로에 저장합니다.
+
+저자들에 따르면 사전 보존을 위해 `num_epochs * num_samples`개의 이미지를 생성하는 것이 좋습니다. 200-300개에서 대부분 잘 작동합니다.
+
+<frameworkcontent>
+<pt>
+```bash
+export MODEL_NAME="CompVis/stable-diffusion-v1-4"
+export INSTANCE_DIR="path_to_training_images"
+export CLASS_DIR="path_to_class_images"
+export OUTPUT_DIR="path_to_saved_model"
+
+accelerate launch train_dreambooth.py \
+  --pretrained_model_name_or_path=$MODEL_NAME  \
+  --instance_data_dir=$INSTANCE_DIR \
+  --class_data_dir=$CLASS_DIR \
+  --output_dir=$OUTPUT_DIR \
+  --with_prior_preservation --prior_loss_weight=1.0 \
+  --instance_prompt="a photo of sks dog" \
+  --class_prompt="a photo of dog" \
+  --resolution=512 \
+  --train_batch_size=1 \
+  --gradient_accumulation_steps=1 \
+  --learning_rate=5e-6 \
+  --lr_scheduler="constant" \
+  --lr_warmup_steps=0 \
+  --num_class_images=200 \
+  --max_train_steps=800
+```
+</pt>
+<jax>
+```bash
+export MODEL_NAME="duongna/stable-diffusion-v1-4-flax"
+export INSTANCE_DIR="path-to-instance-images"
+export CLASS_DIR="path-to-class-images"
+export OUTPUT_DIR="path-to-save-model"
+
+python train_dreambooth_flax.py \
+  --pretrained_model_name_or_path=$MODEL_NAME  \
+  --instance_data_dir=$INSTANCE_DIR \
+  --class_data_dir=$CLASS_DIR \
+  --output_dir=$OUTPUT_DIR \
+  --with_prior_preservation --prior_loss_weight=1.0 \
+  --instance_prompt="a photo of sks dog" \
+  --class_prompt="a photo of dog" \
+  --resolution=512 \
+  --train_batch_size=1 \
+  --learning_rate=5e-6 \
+  --num_class_images=200 \
+  --max_train_steps=800
+```
+</jax>
+</frameworkcontent>
+
+## 텍스트 인코더와 and UNet로 파인튜닝하기
+
+해당 스크립트를 사용하면 `unet`과 함께 `text_encoder`를 파인튜닝할 수 있습니다. 실험에서(자세한 내용은 [🧨 Diffusers를 사용해 DreamBooth로 Stable Diffusion 학습하기](https://huggingface.co/blog/dreambooth) 게시물을 확인하세요), 특히 얼굴 이미지를 생성할 때 훨씬 더 나은 결과를 얻을 수 있습니다.
+
+<Tip warning={true}>
+
+텍스트 인코더를 학습시키려면 추가 메모리가 필요해 16GB GPU로는 동작하지 않습니다. 이 옵션을 사용하려면 최소 24GB VRAM이 필요합니다.
+
+</Tip>
+
+`--train_text_encoder` 인수를 학습 스크립트에 전달하여 `text_encoder` 및 `unet`을 파인튜닝할 수 있습니다:
+
+<frameworkcontent>
+<pt>
+```bash
+export MODEL_NAME="CompVis/stable-diffusion-v1-4"
+export INSTANCE_DIR="path_to_training_images"
+export CLASS_DIR="path_to_class_images"
+export OUTPUT_DIR="path_to_saved_model"
+
+accelerate launch train_dreambooth.py \
+  --pretrained_model_name_or_path=$MODEL_NAME  \
+  --train_text_encoder \
+  --instance_data_dir=$INSTANCE_DIR \
+  --class_data_dir=$CLASS_DIR \
+  --output_dir=$OUTPUT_DIR \
+  --with_prior_preservation --prior_loss_weight=1.0 \
+  --instance_prompt="a photo of sks dog" \
+  --class_prompt="a photo of dog" \
+  --resolution=512 \
+  --train_batch_size=1 \
+  --use_8bit_adam
+  --gradient_checkpointing \
+  --learning_rate=2e-6 \
+  --lr_scheduler="constant" \
+  --lr_warmup_steps=0 \
+  --num_class_images=200 \
+  --max_train_steps=800
+```
+</pt>
+<jax>
+```bash
+export MODEL_NAME="duongna/stable-diffusion-v1-4-flax"
+export INSTANCE_DIR="path-to-instance-images"
+export CLASS_DIR="path-to-class-images"
+export OUTPUT_DIR="path-to-save-model"
+
+python train_dreambooth_flax.py \
+  --pretrained_model_name_or_path=$MODEL_NAME  \
+  --train_text_encoder \
+  --instance_data_dir=$INSTANCE_DIR \
+  --class_data_dir=$CLASS_DIR \
+  --output_dir=$OUTPUT_DIR \
+  --with_prior_preservation --prior_loss_weight=1.0 \
+  --instance_prompt="a photo of sks dog" \
+  --class_prompt="a photo of dog" \
+  --resolution=512 \
+  --train_batch_size=1 \
+  --learning_rate=2e-6 \
+  --num_class_images=200 \
+  --max_train_steps=800
+```
+</jax>
+</frameworkcontent>
+
+## LoRA로 파인튜닝하기
+
+DreamBooth에서 대규모 모델의 학습을 가속화하기 위한 파인튜닝 기술인 LoRA(Low-Rank Adaptation of Large Language Models)를 사용할 수 있습니다. 자세한 내용은 [LoRA 학습](training/lora#dreambooth) 가이드를 참조하세요.
+
+### 학습 중 체크포인트 저장하기
+
+Dreambooth로 훈련하는 동안 과적합하기 쉬우므로, 때때로 학습 중에 정기적인 체크포인트를 저장하는 것이 유용합니다. 중간 체크포인트 중 하나가 최종 모델보다 더 잘 작동할 수 있습니다! 체크포인트 저장 기능을 활성화하려면 학습 스크립트에 다음 인수를 전달해야 합니다:
+
+```bash
+  --checkpointing_steps=500
+```
+
+이렇게 하면 `output_dir`의 하위 폴더에 전체 학습 상태가 저장됩니다. 하위 폴더 이름은 접두사 `checkpoint-`로 시작하고 지금까지 수행된 step 수입니다. 예시로 `checkpoint-1500`은 1500 학습 step 후에 저장된 체크포인트입니다.
+
+#### 저장된 체크포인트에서 훈련 재개하기
+
+저장된 체크포인트에서 훈련을 재개하려면, `--resume_from_checkpoint` 인수를 전달한 다음 사용할 체크포인트의 이름을 지정하면 됩니다. 특수 문자열 `"latest"`를 사용하여 저장된 마지막 체크포인트(즉, step 수가 가장 많은 체크포인트)에서 재개할 수도 있습니다. 예를 들어 다음은 1500 step 후에 저장된 체크포인트에서부터 학습을 재개합니다:
+
+```bash
+  --resume_from_checkpoint="checkpoint-1500"
+```
+
+원하는 경우 일부 하이퍼파라미터를 조정할 수 있습니다.
+
+#### 저장된 체크포인트를 사용하여 추론 수행하기
+
+저장된 체크포인트는 훈련 재개에 적합한 형식으로 저장됩니다. 여기에는 모델 가중치뿐만 아니라 옵티마이저, 데이터 로더 및 학습률의 상태도 포함됩니다.
+
+**`"accelerate>=0.16.0"`**이 설치된 경우 다음 코드를 사용하여 중간 체크포인트에서 추론을 실행합니다.
+
+```python
+from diffusers import DiffusionPipeline, UNet2DConditionModel
+from transformers import CLIPTextModel
+import torch
+
+# 학습에 사용된 것과 동일한 인수(model, revision)로 파이프라인을 로드합니다.
+model_id = "CompVis/stable-diffusion-v1-4"
+
+unet = UNet2DConditionModel.from_pretrained("/sddata/dreambooth/daruma-v2-1/checkpoint-100/unet")
+
+# `args.train_text_encoder`로 학습한 경우면 텍스트 인코더를 꼭 불러오세요
+text_encoder = CLIPTextModel.from_pretrained("/sddata/dreambooth/daruma-v2-1/checkpoint-100/text_encoder")
+
+pipeline = DiffusionPipeline.from_pretrained(model_id, unet=unet, text_encoder=text_encoder, dtype=torch.float16)
+pipeline.to("cuda")
+
+# 추론을 수행하거나 저장하거나, 허브에 푸시합니다.
+pipeline.save_pretrained("dreambooth-pipeline")
+```
+
+If you have **`"accelerate<0.16.0"`** installed, you need to convert it to an inference pipeline first:
+
+```python
+from accelerate import Accelerator
+from diffusers import DiffusionPipeline
+
+# 학습에 사용된 것과 동일한 인수(model, revision)로 파이프라인을 로드합니다.
+model_id = "CompVis/stable-diffusion-v1-4"
+pipeline = DiffusionPipeline.from_pretrained(model_id)
+
+accelerator = Accelerator()
+
+# 초기 학습에 `--train_text_encoder`가 사용된 경우 text_encoder를 사용합니다.
+unet, text_encoder = accelerator.prepare(pipeline.unet, pipeline.text_encoder)
+
+# 체크포인트 경로로부터 상태를 복원합니다. 여기서는 절대 경로를 사용해야 합니다.
+accelerator.load_state("/sddata/dreambooth/daruma-v2-1/checkpoint-100")
+
+# unwrapped 모델로 파이프라인을 다시 빌드합니다.(.unet and .text_encoder로의 할당도 작동해야 합니다)
+pipeline = DiffusionPipeline.from_pretrained(
+    model_id,
+    unet=accelerator.unwrap_model(unet),
+    text_encoder=accelerator.unwrap_model(text_encoder),
+)
+
+# 추론을 수행하거나 저장하거나, 허브에 푸시합니다.
+pipeline.save_pretrained("dreambooth-pipeline")
+```
+
+## 각 GPU 용량에서의 최적화
+
+하드웨어에 따라 16GB에서 8GB까지 GPU에서 DreamBooth를 최적화하는 몇 가지 방법이 있습니다!
+
+### xFormers
+
+[xFormers](https://github.com/facebookresearch/xformers)는 Transformers를 최적화하기 위한 toolbox이며, 🧨 Diffusers에서 사용되는[memory-efficient attention](https://facebookresearch.github.io/xformers/components/ops.html#module-xformers.ops)  메커니즘을 포함하고 있습니다. [xFormers를 설치](./optimization/xformers)한 다음 학습 스크립트에 다음 인수를 추가합니다:
+
+```bash
+  --enable_xformers_memory_efficient_attention
+```
+
+xFormers는 Flax에서 사용할 수 없습니다.
+
+### 그래디언트 없음으로 설정
+
+메모리 사용량을 줄일 수 있는 또 다른 방법은 [기울기 설정](https://pytorch.org/docs/stable/generated/torch.optim.Optimizer.zero_grad.html)을 0 대신 `None`으로 하는 것입니다. 그러나 이로 인해 특정 동작이 변경될 수 있으므로 문제가 발생하면 이 인수를 제거해 보십시오. 학습 스크립트에 다음 인수를 추가하여 그래디언트를 `None`으로 설정합니다.
+
+```bash
+  --set_grads_to_none
+```
+
+### 16GB GPU
+
+Gradient checkpointing과 [bitsandbytes](https://github.com/TimDettmers/bitsandbytes)의 8비트 옵티마이저의 도움으로, 16GB GPU에서 dreambooth를 훈련할 수 있습니다. bitsandbytes가 설치되어 있는지 확인하세요:
+
+```bash
+pip install bitsandbytes
+```
+
+그 다음, 학습 스크립트에 `--use_8bit_adam` 옵션을 명시합니다:
+
+```bash
+export MODEL_NAME="CompVis/stable-diffusion-v1-4"
+export INSTANCE_DIR="path_to_training_images"
+export CLASS_DIR="path_to_class_images"
+export OUTPUT_DIR="path_to_saved_model"
+
+accelerate launch train_dreambooth.py \
+  --pretrained_model_name_or_path=$MODEL_NAME  \
+  --instance_data_dir=$INSTANCE_DIR \
+  --class_data_dir=$CLASS_DIR \
+  --output_dir=$OUTPUT_DIR \
+  --with_prior_preservation --prior_loss_weight=1.0 \
+  --instance_prompt="a photo of sks dog" \
+  --class_prompt="a photo of dog" \
+  --resolution=512 \
+  --train_batch_size=1 \
+  --gradient_accumulation_steps=2 --gradient_checkpointing \
+  --use_8bit_adam \
+  --learning_rate=5e-6 \
+  --lr_scheduler="constant" \
+  --lr_warmup_steps=0 \
+  --num_class_images=200 \
+  --max_train_steps=800
+```
+
+### 12GB GPU
+
+12GB GPU에서 DreamBooth를 실행하려면 gradient checkpointing, 8비트 옵티마이저, xFormers를 활성화하고 그래디언트를 `None`으로 설정해야 합니다.
+
+```bash
+export MODEL_NAME="CompVis/stable-diffusion-v1-4"
+export INSTANCE_DIR="path-to-instance-images"
+export CLASS_DIR="path-to-class-images"
+export OUTPUT_DIR="path-to-save-model"
+
+accelerate launch train_dreambooth.py \
+  --pretrained_model_name_or_path=$MODEL_NAME  \
+  --instance_data_dir=$INSTANCE_DIR \
+  --class_data_dir=$CLASS_DIR \
+  --output_dir=$OUTPUT_DIR \
+  --with_prior_preservation --prior_loss_weight=1.0 \
+  --instance_prompt="a photo of sks dog" \
+  --class_prompt="a photo of dog" \
+  --resolution=512 \
+  --train_batch_size=1 \
+  --gradient_accumulation_steps=1 --gradient_checkpointing \
+  --use_8bit_adam \
+  --enable_xformers_memory_efficient_attention \
+  --set_grads_to_none \
+  --learning_rate=2e-6 \
+  --lr_scheduler="constant" \
+  --lr_warmup_steps=0 \
+  --num_class_images=200 \
+  --max_train_steps=800
+```
+
+### 8GB GPU에서 학습하기
+
+8GB GPU에 대해서는 [DeepSpeed](https://www.deepspeed.ai/)를 사용해 일부 텐서를 VRAM에서 CPU 또는 NVME로 오프로드하여 더 적은 GPU 메모리로 학습할 수도 있습니다.
+
+🤗 Accelerate 환경을 구성하려면 다음 명령을 실행하세요:
+
+```bash
+accelerate config
+```
+
+환경 구성 중에 DeepSpeed를 사용할 것을 확인하세요.
+그러면 DeepSpeed stage 2, fp16 혼합 정밀도를 결합하고 모델 매개변수와 옵티마이저 상태를 모두 CPU로 오프로드하면 8GB VRAM 미만에서 학습할 수 있습니다. 
+단점은 더 많은 시스템 RAM(약 25GB)이 필요하다는 것입니다. 추가 구성 옵션은 [DeepSpeed 문서](https://huggingface.co/docs/accelerate/usage_guides/deepspeed)를 참조하세요.
+
+또한 기본 Adam 옵티마이저를 DeepSpeed의 최적화된 Adam 버전으로 변경해야 합니다.
+이는 상당한 속도 향상을 위한 Adam인 [`deepspeed.ops.adam.DeepSpeedCPUAdam`](https://deepspeed.readthedocs.io/en/latest/optimizers.html#adam-cpu)입니다. 
+`DeepSpeedCPUAdam`을 활성화하려면 시스템의 CUDA toolchain 버전이 PyTorch와 함께 설치된 것과 동일해야 합니다.
+
+8비트 옵티마이저는 현재 DeepSpeed와 호환되지 않는 것 같습니다.
+
+다음 명령으로 학습을 시작합니다:
+
+```bash
+export MODEL_NAME="CompVis/stable-diffusion-v1-4"
+export INSTANCE_DIR="path_to_training_images"
+export CLASS_DIR="path_to_class_images"
+export OUTPUT_DIR="path_to_saved_model"
+
+accelerate launch train_dreambooth.py \
+  --pretrained_model_name_or_path=$MODEL_NAME \
+  --instance_data_dir=$INSTANCE_DIR \
+  --class_data_dir=$CLASS_DIR \
+  --output_dir=$OUTPUT_DIR \
+  --with_prior_preservation --prior_loss_weight=1.0 \
+  --instance_prompt="a photo of sks dog" \
+  --class_prompt="a photo of dog" \
+  --resolution=512 \
+  --train_batch_size=1 \
+  --sample_batch_size=1 \
+  --gradient_accumulation_steps=1 --gradient_checkpointing \
+  --learning_rate=5e-6 \
+  --lr_scheduler="constant" \
+  --lr_warmup_steps=0 \
+  --num_class_images=200 \
+  --max_train_steps=800 \
+  --mixed_precision=fp16
+```
+
+## 추론
+
+모델을 학습한 후에는, 모델이 저장된 경로를 지정해 [`StableDiffusionPipeline`]로 추론을 수행할 수 있습니다. 프롬프트에 학습에 사용된 특수 `식별자`(이전 예시의 `sks`)가 포함되어 있는지 확인하세요.
+
+**`"accelerate>=0.16.0"`**이 설치되어 있는 경우 다음 코드를 사용하여 중간 체크포인트에서 추론을 실행할 수 있습니다:
+
+```python
+from diffusers import StableDiffusionPipeline
+import torch
+
+model_id = "path_to_saved_model"
+pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16).to("cuda")
+
+prompt = "A photo of sks dog in a bucket"
+image = pipe(prompt, num_inference_steps=50, guidance_scale=7.5).images[0]
+
+image.save("dog-bucket.png")
+```
+
+[저장된 학습 체크포인트](#inference-from-a-saved-checkpoint)에서도 추론을 실행할 수도 있습니다.

docs/source/ko/training/lora.mdx

@@ -0,0 +1,128 @@
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# Low-Rank Adaptation of Large Language Models (LoRA)
+
+[[open-in-colab]]
+
+<Tip warning={true}>
+
+현재 LoRA는 [`UNet2DConditionalModel`]의 어텐션 레이어에서만 지원됩니다.
+
+</Tip>
+
+[LoRA(Low-Rank Adaptation of Large Language Models)](https://arxiv.org/abs/2106.09685)는 메모리를 적게 사용하면서 대규모 모델의 학습을 가속화하는 학습 방법입니다. 이는 rank-decomposition weight 행렬 쌍(**업데이트 행렬**이라고 함)을 추가하고 새로 추가된 가중치**만** 학습합니다. 여기에는 몇 가지 장점이 있습니다.
+
+- 이전에 미리 학습된 가중치는 고정된 상태로 유지되므로 모델이 [치명적인 망각](https://www.pnas.org/doi/10.1073/pnas.1611835114) 경향이 없습니다.
+- Rank-decomposition 행렬은 원래 모델보다 파라메터 수가 훨씬 적으므로 학습된 LoRA 가중치를 쉽게 끼워넣을 수 있습니다.
+- LoRA 매트릭스는 일반적으로 원본 모델의 어텐션 레이어에 추가됩니다. 🧨 Diffusers는 [`~diffusers.loaders.UNet2DConditionLoadersMixin.load_attn_procs`] 메서드를 제공하여 LoRA 가중치를 모델의 어텐션 레이어로 불러옵니다. `scale` 매개변수를 통해 모델이 새로운 학습 이미지에 맞게 조정되는 범위를 제어할 수 있습니다.
+- 메모리 효율성이 향상되어 Tesla T4, RTX 3080 또는 RTX 2080 Ti와 같은 소비자용 GPU에서 파인튜닝을 실행할 수 있습니다! T4와 같은 GPU는 무료이며 Kaggle 또는 Google Colab 노트북에서 쉽게 액세스할 수 있습니다.
+
+
+<Tip>
+
+💡 LoRA는 어텐션 레이어에만 한정되지는 않습니다. 저자는 언어 모델의 어텐션 레이어를 수정하는 것이 매우 효율적으로 죻은 성능을 얻기에 충분하다는 것을 발견했습니다. 이것이 LoRA 가중치를 모델의 어텐션 레이어에 추가하는 것이 일반적인 이유입니다. LoRA 작동 방식에 대한 자세한 내용은 [Using LoRA for effective Stable Diffusion fine-tuning](https://huggingface.co/blog/lora) 블로그를 확인하세요!
+
+</Tip>
+
+[cloneofsimo](https://github.com/cloneofsimo)는 인기 있는 [lora](https://github.com/cloneofsimo/lora) GitHub 리포지토리에서 Stable Diffusion을 위한 LoRA 학습을 최초로 시도했습니다. 🧨 Diffusers는 [text-to-image 생성](https://github.com/huggingface/diffusers/tree/main/examples/text_to_image#training-with-lora) 및 [DreamBooth](https://github.com/huggingface/diffusers/tree/main/examples/dreambooth#training-with-low-rank-adaptation-of-large-language-models-lora)을 지원합니다. 이 가이드는 두 가지를 모두 수행하는 방법을 보여줍니다.
+
+모델을 저장하거나 커뮤니티와 공유하려면 Hugging Face 계정에 로그인하세요(아직 계정이 없는 경우 [생성](hf.co/join)하세요):
+
+```bash
+huggingface-cli login
+```
+
+## Text-to-image
+
+수십억 개의 파라메터들이 있는 Stable Diffusion과 같은 모델을 파인튜닝하는 것은 느리고 어려울 수 있습니다. LoRA를 사용하면 diffusion 모델을 파인튜닝하는 것이 훨씬 쉽고 빠릅니다. 8비트 옵티마이저와 같은 트릭에 의존하지 않고도 11GB의 GPU RAM으로 하드웨어에서 실행할 수 있습니다.
+
+
+### 학습 [[text-to-image 학습]]
+
+[Pokémon BLIP 캡션](https://huggingface.co/datasets/lambdalabs/pokemon-blip-captions) 데이터셋으로 [`stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5)를 파인튜닝해 나만의 포켓몬을 생성해 보겠습니다.
+
+시작하려면 `MODEL_NAME` 및 `DATASET_NAME` 환경 변수가 설정되어 있는지 확인하십시오. `OUTPUT_DIR` 및 `HUB_MODEL_ID` 변수는 선택 사항이며 허브에서 모델을 저장할 위치를 지정합니다.
+
+```bash
+export MODEL_NAME="runwayml/stable-diffusion-v1-5"
+export OUTPUT_DIR="/sddata/finetune/lora/pokemon"
+export HUB_MODEL_ID="pokemon-lora"
+export DATASET_NAME="lambdalabs/pokemon-blip-captions"
+```
+
+학습을 시작하기 전에 알아야 할 몇 가지 플래그가 있습니다.
+
+* `--push_to_hub`를 명시하면 학습된 LoRA 임베딩을 허브에 저장합니다.
+* `--report_to=wandb`는 학습 결과를 가중치 및 편향 대시보드에 보고하고 기록합니다(예를 들어, 이 [보고서](https://wandb.ai/pcuenq/text2image-fine-tune/run/b4k1w0tn?workspace=user-pcuenq)를 참조하세요).
+* `--learning_rate=1e-04`, 일반적으로 LoRA에서 사용하는 것보다 더 높은 학습률을 사용할 수 있습니다.
+
+이제 학습을 시작할 준비가 되었습니다 (전체 학습 스크립트는 [여기](https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image_lora.py)에서 찾을 수 있습니다).
+
+```bash
+accelerate launch train_dreambooth_lora.py \
+  --pretrained_model_name_or_path=$MODEL_NAME  \
+  --instance_data_dir=$INSTANCE_DIR \
+  --output_dir=$OUTPUT_DIR \
+  --instance_prompt="a photo of sks dog" \
+  --resolution=512 \
+  --train_batch_size=1 \
+  --gradient_accumulation_steps=1 \
+  --checkpointing_steps=100 \
+  --learning_rate=1e-4 \
+  --report_to="wandb" \
+  --lr_scheduler="constant" \
+  --lr_warmup_steps=0 \
+  --max_train_steps=500 \
+  --validation_prompt="A photo of sks dog in a bucket" \
+  --validation_epochs=50 \
+  --seed="0" \
+  --push_to_hub
+```
+
+### 추론 [[dreambooth 추론]]
+
+이제 [`StableDiffusionPipeline`]에서 기본 모델을 불러와 추론을 위해 모델을 사용할 수 있습니다:
+
+```py
+>>> import torch
+>>> from diffusers import StableDiffusionPipeline
+
+>>> model_base = "runwayml/stable-diffusion-v1-5"
+
+>>> pipe = StableDiffusionPipeline.from_pretrained(model_base, torch_dtype=torch.float16)
+```
+
+*기본 모델의 가중치 위에* 파인튜닝된 DreamBooth 모델에서 LoRA 가중치를 로드한 다음, 더 빠른 추론을 위해 파이프라인을 GPU로 이동합니다. LoRA 가중치를 프리징된 사전 훈련된 모델 가중치와 병합할 때, 선택적으로 'scale' 매개변수로 어느 정도의 가중치를 병합할 지 조절할 수 있습니다:
+
+<Tip>
+
+💡 `0`의 `scale` 값은 LoRA 가중치를 사용하지 않아 원래 모델의 가중치만 사용한 것과 같고, `1`의 `scale` 값은 파인튜닝된 LoRA 가중치만 사용함을 의미합니다. 0과 1 사이의 값들은 두 결과들 사이로 보간됩니다.
+
+</Tip>
+
+```py
+>>> pipe.unet.load_attn_procs(model_path)
+>>> pipe.to("cuda")
+# LoRA 파인튜닝된 모델의 가중치 절반과 기본 모델의 가중치 절반 사용
+
+>>> image = pipe(
+...     "A picture of a sks dog in a bucket.",
+...     num_inference_steps=25,
+...     guidance_scale=7.5,
+...     cross_attention_kwargs={"scale": 0.5},
+... ).images[0]
+# 완전히 파인튜닝된 LoRA 모델의 가중치 사용
+
+>>> image = pipe("A picture of a sks dog in a bucket.", num_inference_steps=25, guidance_scale=7.5).images[0]
+>>> image.save("bucket-dog.png")
+```

docs/source/ko/training/text2image.mdx

@@ -0,0 +1,224 @@
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+
+# Text-to-image
+
+<Tip warning={true}>
+
+text-to-image 파인튜닝 스크립트는 experimental 상태입니다. 과적합하기 쉽고 치명적인 망각과 같은 문제에 부딪히기 쉽습니다. 자체 데이터셋에서 최상의 결과를 얻으려면 다양한 하이퍼파라미터를 탐색하는 것이 좋습니다.
+
+</Tip>
+
+Stable Diffusion과 같은 text-to-image 모델은 텍스트 프롬프트에서 이미지를 생성합니다. 이 가이드는 PyTorch 및 Flax를 사용하여 자체 데이터셋에서 [`CompVis/stable-diffusion-v1-4`](https://huggingface.co/CompVis/stable-diffusion-v1-4) 모델로 파인튜닝하는 방법을 보여줍니다. 이 가이드에 사용된 text-to-image 파인튜닝을 위한 모든 학습 스크립트에 관심이 있는 경우 이 [리포지토리](https://github.com/huggingface/diffusers/tree/main/examples/text_to_image)에서 자세히 찾을 수 있습니다.
+
+스크립트를 실행하기 전에, 라이브러리의 학습 dependency들을 설치해야 합니다:
+
+```bash
+pip install git+https://github.com/huggingface/diffusers.git
+pip install -U -r requirements.txt
+```
+
+그리고 [🤗Accelerate](https://github.com/huggingface/accelerate/) 환경을 초기화합니다:
+
+```bash
+accelerate config
+```
+
+리포지토리를 이미 복제한 경우, 이 단계를 수행할 필요가 없습니다. 대신, 로컬 체크아웃 경로를 학습 스크립트에 명시할 수 있으며 거기에서 로드됩니다.
+
+### 하드웨어 요구 사항
+
+`gradient_checkpointing` 및 `mixed_precision`을 사용하면 단일 24GB GPU에서 모델을 파인튜닝할 수 있습니다. 더 높은 `batch_size`와 더 빠른 훈련을 위해서는 GPU 메모리가 30GB 이상인 GPU를 사용하는 것이 좋습니다. TPU 또는 GPU에서 파인튜닝을 위해 JAX나 Flax를 사용할 수도 있습니다. 자세한 내용은 [아래](#flax-jax-finetuning)를 참조하세요.
+
+xFormers로 memory efficient attention을 활성화하여 메모리 사용량 훨씬 더 줄일 수 있습니다. [xFormers가 설치](./optimization/xformers)되어 있는지 확인하고 `--enable_xformers_memory_efficient_attention`를 학습 스크립트에 명시합니다.
+
+xFormers는 Flax에 사용할 수 없습니다.
+
+## Hub에 모델 업로드하기
+
+학습 스크립트에 다음 인수를 추가하여 모델을 허브에 저장합니다:
+
+```bash
+  --push_to_hub
+```
+
+
+## 체크포인트 저장 및 불러오기
+
+학습 중 발생할 수 있는 일에 대비하여 정기적으로 체크포인트를 저장해 두는 것이 좋습니다. 체크포인트를 저장하려면 학습 스크립트에 다음 인수를 명시합니다.
+
+```bash
+  --checkpointing_steps=500
+```
+
+500스텝마다 전체 학습 state가 'output_dir'의 하위 폴더에 저장됩니다. 체크포인트는 'checkpoint-'에 지금까지 학습된 step 수입니다. 예를 들어 'checkpoint-1500'은 1500 학습 step 후에 저장된 체크포인트입니다.
+
+학습을 재개하기 위해 체크포인트를 불러오려면 '--resume_from_checkpoint' 인수를 학습 스크립트에 명시하고 재개할 체크포인트를 지정하십시오. 예를 들어 다음 인수는 1500개의 학습 step 후에 저장된 체크포인트에서부터 훈련을 재개합니다.
+
+```bash
+  --resume_from_checkpoint="checkpoint-1500"
+```
+
+## 파인튜닝
+
+<frameworkcontent>
+<pt>
+다음과 같이 [Pokémon BLIP 캡션](https://huggingface.co/datasets/lambdalabs/pokemon-blip-captions) 데이터셋에서 파인튜닝 실행을 위해 [PyTorch 학습 스크립트](https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image.py)를 실행합니다:
+
+
+```bash
+export MODEL_NAME="CompVis/stable-diffusion-v1-4"
+export dataset_name="lambdalabs/pokemon-blip-captions"
+
+accelerate launch train_text_to_image.py \
+  --pretrained_model_name_or_path=$MODEL_NAME \
+  --dataset_name=$dataset_name \
+  --use_ema \
+  --resolution=512 --center_crop --random_flip \
+  --train_batch_size=1 \
+  --gradient_accumulation_steps=4 \
+  --gradient_checkpointing \
+  --mixed_precision="fp16" \
+  --max_train_steps=15000 \
+  --learning_rate=1e-05 \
+  --max_grad_norm=1 \
+  --lr_scheduler="constant" --lr_warmup_steps=0 \
+  --output_dir="sd-pokemon-model" 
+```
+
+자체 데이터셋으로 파인튜닝하려면 🤗 [Datasets](https://huggingface.co/docs/datasets/index)에서 요구하는 형식에 따라 데이터셋을 준비하세요. [데이터셋을 허브에 업로드](https://huggingface.co/docs/datasets/image_dataset#upload-dataset-to-the-hub)하거나 [파일들이 있는 로컬 폴더를 준비](https ://huggingface.co/docs/datasets/image_dataset#imagefolder)할 수 있습니다.
+
+사용자 커스텀 loading logic을 사용하려면 스크립트를 수정하십시오. 도움이 되도록 코드의 적절한 위치에 포인터를 남겼습니다. 🤗 아래 예제 스크립트는 `TRAIN_DIR`의 로컬 데이터셋으로를 파인튜닝하는 방법과 `OUTPUT_DIR`에서 모델을 저장할 위치를 보여줍니다:
+
+
+```bash
+export MODEL_NAME="CompVis/stable-diffusion-v1-4"
+export TRAIN_DIR="path_to_your_dataset"
+export OUTPUT_DIR="path_to_save_model"
+
+accelerate launch train_text_to_image.py \
+  --pretrained_model_name_or_path=$MODEL_NAME \
+  --train_data_dir=$TRAIN_DIR \
+  --use_ema \
+  --resolution=512 --center_crop --random_flip \
+  --train_batch_size=1 \
+  --gradient_accumulation_steps=4 \
+  --gradient_checkpointing \
+  --mixed_precision="fp16" \
+  --max_train_steps=15000 \
+  --learning_rate=1e-05 \
+  --max_grad_norm=1 \
+  --lr_scheduler="constant" --lr_warmup_steps=0 \
+  --output_dir=${OUTPUT_DIR}
+```
+
+</pt>
+<jax>
+[@duongna211](https://github.com/duongna21)의 기여로, Flax를 사용해 TPU 및 GPU에서 Stable Diffusion 모델을 더 빠르게 학습할 수 있습니다. 이는 TPU 하드웨어에서 매우 효율적이지만 GPU에서도 훌륭하게 작동합니다. Flax 학습 스크립트는 gradient checkpointing나 gradient accumulation과 같은 기능을 아직 지원하지 않으므로 메모리가 30GB 이상인 GPU 또는 TPU v3가 필요합니다.
+
+스크립트를 실행하기 전에 요구 사항이 설치되어 있는지 확인하십시오:
+
+```bash
+pip install -U -r requirements_flax.txt
+```
+
+그러면 다음과 같이 [Flax 학습 스크립트](https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image_flax.py)를 실행할 수 있습니다.
+
+```bash
+export MODEL_NAME="runwayml/stable-diffusion-v1-5"
+export dataset_name="lambdalabs/pokemon-blip-captions"
+
+python train_text_to_image_flax.py \
+  --pretrained_model_name_or_path=$MODEL_NAME \
+  --dataset_name=$dataset_name \
+  --resolution=512 --center_crop --random_flip \
+  --train_batch_size=1 \
+  --max_train_steps=15000 \
+  --learning_rate=1e-05 \
+  --max_grad_norm=1 \
+  --output_dir="sd-pokemon-model" 
+```
+
+자체 데이터셋으로 파인튜닝하려면 🤗 [Datasets](https://huggingface.co/docs/datasets/index)에서 요구하는 형식에 따라 데이터셋을 준비하세요. [데이터셋을 허브에 업로드](https://huggingface.co/docs/datasets/image_dataset#upload-dataset-to-the-hub)하거나 [파일들이 있는 로컬 폴더를 준비](https ://huggingface.co/docs/datasets/image_dataset#imagefolder)할 수 있습니다.
+
+사용자 커스텀 loading logic을 사용하려면 스크립트를 수정하십시오. 도움이 되도록 코드의 적절한 위치에 포인터를 남겼습니다. 🤗 아래 예제 스크립트는 `TRAIN_DIR`의 로컬 데이터셋으로를 파인튜닝하는 방법을 보여줍니다:
+
+```bash
+export MODEL_NAME="duongna/stable-diffusion-v1-4-flax"
+export TRAIN_DIR="path_to_your_dataset"
+
+python train_text_to_image_flax.py \
+  --pretrained_model_name_or_path=$MODEL_NAME \
+  --train_data_dir=$TRAIN_DIR \
+  --resolution=512 --center_crop --random_flip \
+  --train_batch_size=1 \
+  --mixed_precision="fp16" \
+  --max_train_steps=15000 \
+  --learning_rate=1e-05 \
+  --max_grad_norm=1 \
+  --output_dir="sd-pokemon-model"
+```
+</jax>
+</frameworkcontent>
+
+## LoRA
+
+Text-to-image 모델 파인튜닝을 위해, 대규모 모델 학습을 가속화하기 위한 파인튜닝 기술인 LoRA(Low-Rank Adaptation of Large Language Models)를 사용할 수 있습니다. 자세한 내용은 [LoRA 학습](lora#text-to-image) 가이드를 참조하세요.
+
+## 추론
+
+허브의 모델 경로 또는 모델 이름을 [`StableDiffusionPipeline`]에 전달하여 추론을 위해 파인 튜닝된 모델을 불러올 수 있습니다:
+
+<frameworkcontent>
+<pt>
+```python
+from diffusers import StableDiffusionPipeline
+
+model_path = "path_to_saved_model"
+pipe = StableDiffusionPipeline.from_pretrained(model_path, torch_dtype=torch.float16)
+pipe.to("cuda")
+
+image = pipe(prompt="yoda").images[0]
+image.save("yoda-pokemon.png")
+```
+</pt>
+<jax>
+```python
+import jax
+import numpy as np
+from flax.jax_utils import replicate
+from flax.training.common_utils import shard
+from diffusers import FlaxStableDiffusionPipeline
+
+model_path = "path_to_saved_model"
+pipe, params = FlaxStableDiffusionPipeline.from_pretrained(model_path, dtype=jax.numpy.bfloat16)
+
+prompt = "yoda pokemon"
+prng_seed = jax.random.PRNGKey(0)
+num_inference_steps = 50
+
+num_samples = jax.device_count()
+prompt = num_samples * [prompt]
+prompt_ids = pipeline.prepare_inputs(prompt)
+
+# shard inputs and rng
+params = replicate(params)
+prng_seed = jax.random.split(prng_seed, jax.device_count())
+prompt_ids = shard(prompt_ids)
+
+images = pipeline(prompt_ids, params, prng_seed, num_inference_steps, jit=True).images
+images = pipeline.numpy_to_pil(np.asarray(images.reshape((num_samples,) + images.shape[-3:])))
+image.save("yoda-pokemon.png")
+```
+</jax>
+</frameworkcontent>

docs/source/zh/_toctree.yml

@@ -4,51 +4,79 @@
   - local: quicktour
     title: 快速入门
   - local: stable_diffusion
-    title: Stable Diffusion
+    title: Effective and efficient diffusion
   - local: installation
     title: 安装
   title: 开始
 - sections:
+  - local: tutorials/tutorial_overview
+    title: Overview
+  - local: using-diffusers/write_own_pipeline
+    title: Understanding models and schedulers
   - local: tutorials/basic_training
     title: Train a diffusion model
   title: Tutorials
 - sections:
   - sections:
+    - local: using-diffusers/loading_overview
+      title: Overview
     - local: using-diffusers/loading
-      title: Loading Pipelines, Models, and Schedulers
+      title: Load pipelines, models, and schedulers
     - local: using-diffusers/schedulers
-      title: Using different Schedulers
-    - local: using-diffusers/configuration
-      title: Configuring Pipelines, Models, and Schedulers
+      title: Load and compare different schedulers
     - local: using-diffusers/custom_pipeline_overview
-      title: Loading and Adding Custom Pipelines
+      title: Load community pipelines
     - local: using-diffusers/kerascv
-      title: Using KerasCV Stable Diffusion Checkpoints in Diffusers
+      title: Load KerasCV Stable Diffusion checkpoints
     title: Loading & Hub
   - sections:
+    - local: using-diffusers/pipeline_overview
+      title: Overview
     - local: using-diffusers/unconditional_image_generation
-      title: Unconditional Image Generation
+      title: Unconditional image generation
     - local: using-diffusers/conditional_image_generation
-      title: Text-to-Image Generation
+      title: Text-to-image generation
     - local: using-diffusers/img2img
-      title: Text-Guided Image-to-Image
+      title: Text-guided image-to-image
     - local: using-diffusers/inpaint
-      title: Text-Guided Image-Inpainting
+      title: Text-guided image-inpainting
     - local: using-diffusers/depth2img
-      title: Text-Guided Depth-to-Image
-    - local: using-diffusers/controlling_generation
-      title: Controlling generation
+      title: Text-guided depth-to-image
     - local: using-diffusers/reusing_seeds
-      title: Reusing seeds for deterministic generation
+      title: Improve image quality with deterministic generation
     - local: using-diffusers/reproducibility
-      title: Reproducibility
+      title: Create reproducible pipelines
     - local: using-diffusers/custom_pipeline_examples
-      title: Community Pipelines
+      title: Community pipelines
     - local: using-diffusers/contribute_pipeline
-      title: How to contribute a Pipeline
+      title: How to contribute a community pipeline
     - local: using-diffusers/using_safetensors
       title: Using safetensors
+    - local: using-diffusers/stable_diffusion_jax_how_to
+      title: Stable Diffusion in JAX/Flax
+    - local: using-diffusers/weighted_prompts
+      title: Weighting Prompts
     title: Pipelines for Inference
+  - sections:
+    - local: training/overview
+      title: Overview
+    - local: training/unconditional_training
+      title: Unconditional image generation
+    - local: training/text_inversion
+      title: Textual Inversion
+    - local: training/dreambooth
+      title: DreamBooth
+    - local: training/text2image
+      title: Text-to-image
+    - local: training/lora
+      title: Low-Rank Adaptation of Large Language Models (LoRA)
+    - local: training/controlnet
+      title: ControlNet
+    - local: training/instructpix2pix
+      title: InstructPix2Pix Training
+    - local: training/custom_diffusion
+      title: Custom Diffusion
+    title: Training
   - sections:
     - local: using-diffusers/rl
       title: Reinforcement Learning
@@ -59,6 +87,8 @@
     title: Taking Diffusers Beyond Images
   title: Using Diffusers
 - sections:
+  - local: optimization/opt_overview
+    title: Overview
   - local: optimization/fp16
     title: Memory and Speed
   - local: optimization/torch2.0
@@ -69,32 +99,26 @@
     title: ONNX
   - local: optimization/open_vino
     title: OpenVINO
+  - local: optimization/coreml
+    title: Core ML
   - local: optimization/mps
     title: MPS
   - local: optimization/habana
     title: Habana Gaudi
+  - local: optimization/tome
+    title: Token Merging
   title: Optimization/Special Hardware
-- sections:
-  - local: training/overview
-    title: Overview
-  - local: training/unconditional_training
-    title: Unconditional Image Generation
-  - local: training/text_inversion
-    title: Textual Inversion
-  - local: training/dreambooth
-    title: DreamBooth
-  - local: training/text2image
-    title: Text-to-image
-  - local: training/lora
-    title: Low-Rank Adaptation of Large Language Models (LoRA)
-  title: Training
 - sections:
   - local: conceptual/philosophy
     title: Philosophy
+  - local: using-diffusers/controlling_generation
+    title: Controlled generation
   - local: conceptual/contribution
     title: How to contribute?
   - local: conceptual/ethical_guidelines
     title: Diffusers' Ethical Guidelines
+  - local: conceptual/evaluation
+    title: Evaluating Diffusion Models
   title: Conceptual Guides
 - sections:
   - sections:
@@ -118,6 +142,8 @@
       title: AltDiffusion
     - local: api/pipelines/audio_diffusion
       title: Audio Diffusion
+    - local: api/pipelines/audioldm
+      title: AudioLDM
     - local: api/pipelines/cycle_diffusion
       title: Cycle Diffusion
     - local: api/pipelines/dance_diffusion
@@ -128,6 +154,8 @@
       title: DDPM
     - local: api/pipelines/dit
       title: DiT
+    - local: api/pipelines/if
+      title: IF
     - local: api/pipelines/latent_diffusion
       title: Latent Diffusion
     - local: api/pipelines/paint_by_example
@@ -142,6 +170,8 @@
       title: Score SDE VE
     - local: api/pipelines/semantic_stable_diffusion
       title: Semantic Guidance
+    - local: api/pipelines/spectrogram_diffusion
+      title: "Spectrogram Diffusion"
     - sections:
       - local: api/pipelines/stable_diffusion/overview
         title: Overview
@@ -171,6 +201,8 @@
         title: MultiDiffusion Panorama
       - local: api/pipelines/stable_diffusion/controlnet
         title: Text-to-Image Generation with ControlNet Conditioning
+      - local: api/pipelines/stable_diffusion/model_editing
+        title: Text-to-Image Model Editing
       title: Stable Diffusion
     - local: api/pipelines/stable_diffusion_2
       title: Stable Diffusion 2
@@ -178,6 +210,10 @@
       title: Stable unCLIP
     - local: api/pipelines/stochastic_karras_ve
       title: Stochastic Karras VE
+    - local: api/pipelines/text_to_video
+      title: Text-to-Video
+    - local: api/pipelines/text_to_video_zero
+      title: Text-to-Video Zero
     - local: api/pipelines/unclip
       title: UnCLIP
     - local: api/pipelines/latent_diffusion_uncond
@@ -235,4 +271,4 @@
     - local: api/experimental/rl
       title: RL Planning
     title: Experimental Features
-  title: API
+  title: API

docs/source/zh/index.mdx

@@ -18,61 +18,84 @@ specific language governing permissions and limitations under the License.
 
 # 🧨 Diffusers
 
-🤗Diffusers提供了预训练好的视觉和音频扩散模型，并可以作为推理和训练的模块化工具箱。
+🤗 Diffusers 是一个值得首选用于生成图像、音频甚至 3D 分子结构的，最先进的预训练扩散模型库。
+无论您是在寻找简单的推理解决方案，还是想训练自己的扩散模型，🤗 Diffusers 这一模块化工具箱都能对其提供支持。
+本库的设计更偏重于[可用而非高性能](conceptual/philosophy#usability-over-performance)、[简明而非简单](conceptual/philosophy#simple-over-easy)以及[易用而非抽象](conceptual/philosophy#tweakable-contributorfriendly-over-abstraction)。
 
-更准确地说，🤗Diffusers提供了：
 
-- 最先进的扩散管道，可以在推理中仅用几行代码运行(详情看[**Using Diffusers**](./using-diffusers/conditional_image_generation))或看[**管道**](#pipelines) 以获取所有支持的管道及其对应的论文的概述。
-- 可以在推理中交替使用的各种噪声调度程序，以便在推理过程中权衡如何选择速度和质量。有关更多信息，可以看[**Schedulers**](./api/schedulers/overview)。
-- 多种类型的模型，如U-Net，可用作端到端扩散系统中的构建模块。有关更多详细信息，可以看 [**Models**](./api/models) 。
-- 训练示例，展示如何训练最流行的扩散模型任务。更多相关信息，可以看[**Training**](./training/overview)。
+本库包含三个主要组件：
 
+- 最先进的扩散管道 [diffusion pipelines](api/pipelines/overview)，只需几行代码即可进行推理。
+- 可交替使用的各种噪声调度器 [noise schedulers](api/schedulers/overview)，用于平衡生成速度和质量。
+- 预训练模型 [models](api/models)，可作为构建模块，并与调度程序结合使用，来创建您自己的端到端扩散系统。
+
+<div class="mt-10">
+  <div class="w-full flex flex-col space-y-4 md:space-y-0 md:grid md:grid-cols-2 md:gap-y-4 md:gap-x-5">
+    <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="./tutorials/tutorial_overview"
+      ><div class="w-full text-center bg-gradient-to-br from-blue-400 to-blue-500 rounded-lg py-1.5 font-semibold mb-5 text-white text-lg leading-relaxed">Tutorials</div>
+      <p class="text-gray-700">Learn the fundamental skills you need to start generating outputs, build your own diffusion system, and train a diffusion model. We recommend starting here if you're using 🤗 Diffusers for the first time!</p>
+    </a>
+    <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="./using-diffusers/loading_overview"
+      ><div class="w-full text-center bg-gradient-to-br from-indigo-400 to-indigo-500 rounded-lg py-1.5 font-semibold mb-5 text-white text-lg leading-relaxed">How-to guides</div>
+      <p class="text-gray-700">Practical guides for helping you load pipelines, models, and schedulers. You'll also learn how to use pipelines for specific tasks, control how outputs are generated, optimize for inference speed, and different training techniques.</p>
+    </a>
+    <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="./conceptual/philosophy"
+      ><div class="w-full text-center bg-gradient-to-br from-pink-400 to-pink-500 rounded-lg py-1.5 font-semibold mb-5 text-white text-lg leading-relaxed">Conceptual guides</div>
+      <p class="text-gray-700">Understand why the library was designed the way it was, and learn more about the ethical guidelines and safety implementations for using the library.</p>
+   </a>
+    <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="./api/models"
+      ><div class="w-full text-center bg-gradient-to-br from-purple-400 to-purple-500 rounded-lg py-1.5 font-semibold mb-5 text-white text-lg leading-relaxed">Reference</div>
+      <p class="text-gray-700">Technical descriptions of how 🤗 Diffusers classes and methods work.</p>
+    </a>
+  </div>
+</div>
 
 ## 🧨 Diffusers pipelines
 
-下表总结了所有官方支持的pipelines及其对应的论文，部分提供了colab，可以直接尝试一下。
+下表汇总了当前所有官方支持的pipelines及其对应的论文.
 
-
-| 管道 | 论文 | 任务 | Colab
-|---|---|:---:|:---:|
-| [alt_diffusion](./api/pipelines/alt_diffusion) | [**AltDiffusion**](https://arxiv.org/abs/2211.06679) | Image-to-Image Text-Guided Generation |
-| [audio_diffusion](./api/pipelines/audio_diffusion) | [**Audio Diffusion**](https://github.com/teticio/audio-diffusion.git) | Unconditional Audio Generation | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/teticio/audio-diffusion/blob/master/notebooks/audio_diffusion_pipeline.ipynb)
-| [controlnet](./api/pipelines/stable_diffusion/controlnet) | [**ControlNet with Stable Diffusion**](https://arxiv.org/abs/2302.05543) | Image-to-Image Text-Guided Generation | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/controlnet.ipynb)
-| [cycle_diffusion](./api/pipelines/cycle_diffusion) | [**Cycle Diffusion**](https://arxiv.org/abs/2210.05559) | Image-to-Image Text-Guided Generation |
-| [dance_diffusion](./api/pipelines/dance_diffusion) | [**Dance Diffusion**](https://github.com/williamberman/diffusers.git) | Unconditional Audio Generation |
-| [ddpm](./api/pipelines/ddpm) | [**Denoising Diffusion Probabilistic Models**](https://arxiv.org/abs/2006.11239) | Unconditional Image Generation |
-| [ddim](./api/pipelines/ddim) | [**Denoising Diffusion Implicit Models**](https://arxiv.org/abs/2010.02502) | Unconditional Image Generation |
-| [latent_diffusion](./api/pipelines/latent_diffusion) | [**High-Resolution Image Synthesis with Latent Diffusion Models**](https://arxiv.org/abs/2112.10752)| Text-to-Image Generation | 
-| [latent_diffusion](./api/pipelines/latent_diffusion) | [**High-Resolution Image Synthesis with Latent Diffusion Models**](https://arxiv.org/abs/2112.10752)| Super Resolution Image-to-Image | 
-| [latent_diffusion_uncond](./api/pipelines/latent_diffusion_uncond) | [**High-Resolution Image Synthesis with Latent Diffusion Models**](https://arxiv.org/abs/2112.10752) | Unconditional Image Generation | 
-| [paint_by_example](./api/pipelines/paint_by_example) | [**Paint by Example: Exemplar-based Image Editing with Diffusion Models**](https://arxiv.org/abs/2211.13227) | Image-Guided Image Inpainting | 
-| [pndm](./api/pipelines/pndm) | [**Pseudo Numerical Methods for Diffusion Models on Manifolds**](https://arxiv.org/abs/2202.09778) | Unconditional Image Generation | 
-| [score_sde_ve](./api/pipelines/score_sde_ve) | [**Score-Based Generative Modeling through Stochastic Differential Equations**](https://openreview.net/forum?id=PxTIG12RRHS) | Unconditional Image Generation | 
-| [score_sde_vp](./api/pipelines/score_sde_vp) | [**Score-Based Generative Modeling through Stochastic Differential Equations**](https://openreview.net/forum?id=PxTIG12RRHS) | Unconditional Image Generation | 
-| [semantic_stable_diffusion](./api/pipelines/semantic_stable_diffusion) | [**Semantic Guidance**](https://arxiv.org/abs/2301.12247) | Text-Guided Generation | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/ml-research/semantic-image-editing/blob/main/examples/SemanticGuidance.ipynb)
-| [stable_diffusion_text2img](./api/pipelines/stable_diffusion/text2img) | [**Stable Diffusion**](https://stability.ai/blog/stable-diffusion-public-release) | Text-to-Image Generation | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/training_example.ipynb)
-| [stable_diffusion_img2img](./api/pipelines/stable_diffusion/img2img) | [**Stable Diffusion**](https://stability.ai/blog/stable-diffusion-public-release) | Image-to-Image Text-Guided Generation | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/image_2_image_using_diffusers.ipynb)
-| [stable_diffusion_inpaint](./api/pipelines/stable_diffusion/inpaint) | [**Stable Diffusion**](https://stability.ai/blog/stable-diffusion-public-release) | Text-Guided Image Inpainting | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/in_painting_with_stable_diffusion_using_diffusers.ipynb)
-| [stable_diffusion_panorama](./api/pipelines/stable_diffusion/panorama) | [**MultiDiffusion**](https://multidiffusion.github.io/) | Text-to-Panorama Generation |
-| [stable_diffusion_pix2pix](./api/pipelines/stable_diffusion/pix2pix) | [**InstructPix2Pix**](https://github.com/timothybrooks/instruct-pix2pix) | Text-Guided Image Editing| 
-| [stable_diffusion_pix2pix_zero](./api/pipelines/stable_diffusion/pix2pix_zero) | [**Zero-shot Image-to-Image Translation**](https://pix2pixzero.github.io/) | Text-Guided Image Editing | 
-| [stable_diffusion_attend_and_excite](./api/pipelines/stable_diffusion/attend_and_excite) | [**Attend and Excite for Stable Diffusion**](https://attendandexcite.github.io/Attend-and-Excite/) | Text-to-Image Generation | 
-| [stable_diffusion_self_attention_guidance](./api/pipelines/stable_diffusion/self_attention_guidance) | [**Self-Attention Guidance**](https://ku-cvlab.github.io/Self-Attention-Guidance) | Text-to-Image Generation | 
-| [stable_diffusion_image_variation](./stable_diffusion/image_variation) | [**Stable Diffusion Image Variations**](https://github.com/LambdaLabsML/lambda-diffusers#stable-diffusion-image-variations) | Image-to-Image Generation |
-| [stable_diffusion_latent_upscale](./stable_diffusion/latent_upscale) | [**Stable Diffusion Latent Upscaler**](https://twitter.com/StabilityAI/status/1590531958815064065) | Text-Guided Super Resolution Image-to-Image |
-| [stable_diffusion_2](./api/pipelines/stable_diffusion_2) | [**Stable Diffusion 2**](https://stability.ai/blog/stable-diffusion-v2-release) | Text-to-Image Generation |
-| [stable_diffusion_2](./api/pipelines/stable_diffusion_2) | [**Stable Diffusion 2**](https://stability.ai/blog/stable-diffusion-v2-release) | Text-Guided Image Inpainting | 
-| [stable_diffusion_2](./api/pipelines/stable_diffusion_2) | [**Depth-Conditional Stable Diffusion**](https://github.com/Stability-AI/stablediffusion#depth-conditional-stable-diffusion) | Depth-to-Image Generation | 
-| [stable_diffusion_2](./api/pipelines/stable_diffusion_2) | [**Stable Diffusion 2**](https://stability.ai/blog/stable-diffusion-v2-release) | Text-Guided Super Resolution Image-to-Image |
-| [stable_diffusion_safe](./api/pipelines/stable_diffusion_safe) | [**Safe Stable Diffusion**](https://arxiv.org/abs/2211.05105) | Text-Guided Generation | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/ml-research/safe-latent-diffusion/blob/main/examples/Safe%20Latent%20Diffusion.ipynb)
-| [stable_unclip](./stable_unclip) | **Stable unCLIP** | Text-to-Image Generation |
-| [stable_unclip](./stable_unclip) | **Stable unCLIP** | Image-to-Image Text-Guided Generation |
-| [stochastic_karras_ve](./api/pipelines/stochastic_karras_ve) | [**Elucidating the Design Space of Diffusion-Based Generative Models**](https://arxiv.org/abs/2206.00364) | Unconditional Image Generation | 
-| [unclip](./api/pipelines/unclip) | [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://arxiv.org/abs/2204.06125) | Text-to-Image Generation |
-| [versatile_diffusion](./api/pipelines/versatile_diffusion) | [Versatile Diffusion: Text, Images and Variations All in One Diffusion Model](https://arxiv.org/abs/2211.08332) | Text-to-Image Generation | 
-| [versatile_diffusion](./api/pipelines/versatile_diffusion) | [Versatile Diffusion: Text, Images and Variations All in One Diffusion Model](https://arxiv.org/abs/2211.08332) | Image Variations Generation | 
-| [versatile_diffusion](./api/pipelines/versatile_diffusion) | [Versatile Diffusion: Text, Images and Variations All in One Diffusion Model](https://arxiv.org/abs/2211.08332) | Dual Image and Text Guided Generation | 
-| [vq_diffusion](./api/pipelines/vq_diffusion) | [Vector Quantized Diffusion Model for Text-to-Image Synthesis](https://arxiv.org/abs/2111.14822) | Text-to-Image Generation | 
-
-
-**注意**: 管道是如何使用相应论文中提出的扩散模型的简单示例。
+| 管道 | 论文/仓库 | 任务 |
+|---|---|:---:|
+| [alt_diffusion](./api/pipelines/alt_diffusion) | [AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities](https://arxiv.org/abs/2211.06679) | Image-to-Image Text-Guided Generation |
+| [audio_diffusion](./api/pipelines/audio_diffusion) | [Audio Diffusion](https://github.com/teticio/audio-diffusion.git) | Unconditional Audio Generation |
+| [controlnet](./api/pipelines/stable_diffusion/controlnet) | [Adding Conditional Control to Text-to-Image Diffusion Models](https://arxiv.org/abs/2302.05543) | Image-to-Image Text-Guided Generation |
+| [cycle_diffusion](./api/pipelines/cycle_diffusion) | [Unifying Diffusion Models' Latent Space, with Applications to CycleDiffusion and Guidance](https://arxiv.org/abs/2210.05559) | Image-to-Image Text-Guided Generation |
+| [dance_diffusion](./api/pipelines/dance_diffusion) | [Dance Diffusion](https://github.com/williamberman/diffusers.git) | Unconditional Audio Generation |
+| [ddpm](./api/pipelines/ddpm) | [Denoising Diffusion Probabilistic Models](https://arxiv.org/abs/2006.11239) | Unconditional Image Generation |
+| [ddim](./api/pipelines/ddim) | [Denoising Diffusion Implicit Models](https://arxiv.org/abs/2010.02502) | Unconditional Image Generation |
+| [if](./if) | [**IF**](./api/pipelines/if) | Image Generation |
+| [if_img2img](./if) | [**IF**](./api/pipelines/if) | Image-to-Image Generation |
+| [if_inpainting](./if) | [**IF**](./api/pipelines/if) | Image-to-Image Generation |
+| [latent_diffusion](./api/pipelines/latent_diffusion) | [High-Resolution Image Synthesis with Latent Diffusion Models](https://arxiv.org/abs/2112.10752)| Text-to-Image Generation |
+| [latent_diffusion](./api/pipelines/latent_diffusion) | [High-Resolution Image Synthesis with Latent Diffusion Models](https://arxiv.org/abs/2112.10752)| Super Resolution Image-to-Image |
+| [latent_diffusion_uncond](./api/pipelines/latent_diffusion_uncond) | [High-Resolution Image Synthesis with Latent Diffusion Models](https://arxiv.org/abs/2112.10752) | Unconditional Image Generation |
+| [paint_by_example](./api/pipelines/paint_by_example) | [Paint by Example: Exemplar-based Image Editing with Diffusion Models](https://arxiv.org/abs/2211.13227) | Image-Guided Image Inpainting |
+| [pndm](./api/pipelines/pndm) | [Pseudo Numerical Methods for Diffusion Models on Manifolds](https://arxiv.org/abs/2202.09778) | Unconditional Image Generation |
+| [score_sde_ve](./api/pipelines/score_sde_ve) | [Score-Based Generative Modeling through Stochastic Differential Equations](https://openreview.net/forum?id=PxTIG12RRHS) | Unconditional Image Generation |
+| [score_sde_vp](./api/pipelines/score_sde_vp) | [Score-Based Generative Modeling through Stochastic Differential Equations](https://openreview.net/forum?id=PxTIG12RRHS) | Unconditional Image Generation |
+| [semantic_stable_diffusion](./api/pipelines/semantic_stable_diffusion) | [Semantic Guidance](https://arxiv.org/abs/2301.12247) | Text-Guided Generation |
+| [stable_diffusion_text2img](./api/pipelines/stable_diffusion/text2img) | [Stable Diffusion](https://stability.ai/blog/stable-diffusion-public-release) | Text-to-Image Generation |
+| [stable_diffusion_img2img](./api/pipelines/stable_diffusion/img2img) | [Stable Diffusion](https://stability.ai/blog/stable-diffusion-public-release) | Image-to-Image Text-Guided Generation |
+| [stable_diffusion_inpaint](./api/pipelines/stable_diffusion/inpaint) | [Stable Diffusion](https://stability.ai/blog/stable-diffusion-public-release) | Text-Guided Image Inpainting |
+| [stable_diffusion_panorama](./api/pipelines/stable_diffusion/panorama) | [MultiDiffusion](https://multidiffusion.github.io/) | Text-to-Panorama Generation |
+| [stable_diffusion_pix2pix](./api/pipelines/stable_diffusion/pix2pix) | [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://arxiv.org/abs/2211.09800)  | Text-Guided Image Editing|
+| [stable_diffusion_pix2pix_zero](./api/pipelines/stable_diffusion/pix2pix_zero) | [Zero-shot Image-to-Image Translation](https://pix2pixzero.github.io/) | Text-Guided Image Editing |
+| [stable_diffusion_attend_and_excite](./api/pipelines/stable_diffusion/attend_and_excite) | [Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models](https://arxiv.org/abs/2301.13826) | Text-to-Image Generation |
+| [stable_diffusion_self_attention_guidance](./api/pipelines/stable_diffusion/self_attention_guidance) | [Improving Sample Quality of Diffusion Models Using Self-Attention Guidance](https://arxiv.org/abs/2210.00939) | Text-to-Image Generation Unconditional Image Generation |
+| [stable_diffusion_image_variation](./stable_diffusion/image_variation) | [Stable Diffusion Image Variations](https://github.com/LambdaLabsML/lambda-diffusers#stable-diffusion-image-variations) | Image-to-Image Generation |
+| [stable_diffusion_latent_upscale](./stable_diffusion/latent_upscale) | [Stable Diffusion Latent Upscaler](https://twitter.com/StabilityAI/status/1590531958815064065) | Text-Guided Super Resolution Image-to-Image |
+| [stable_diffusion_model_editing](./api/pipelines/stable_diffusion/model_editing) | [Editing Implicit Assumptions in Text-to-Image Diffusion Models](https://time-diffusion.github.io/) | Text-to-Image Model Editing |
+| [stable_diffusion_2](./api/pipelines/stable_diffusion_2) | [Stable Diffusion 2](https://stability.ai/blog/stable-diffusion-v2-release) | Text-to-Image Generation |
+| [stable_diffusion_2](./api/pipelines/stable_diffusion_2) | [Stable Diffusion 2](https://stability.ai/blog/stable-diffusion-v2-release) | Text-Guided Image Inpainting |
+| [stable_diffusion_2](./api/pipelines/stable_diffusion_2) | [Depth-Conditional Stable Diffusion](https://github.com/Stability-AI/stablediffusion#depth-conditional-stable-diffusion) | Depth-to-Image Generation |
+| [stable_diffusion_2](./api/pipelines/stable_diffusion_2) | [Stable Diffusion 2](https://stability.ai/blog/stable-diffusion-v2-release) | Text-Guided Super Resolution Image-to-Image |
+| [stable_diffusion_safe](./api/pipelines/stable_diffusion_safe) | [Safe Stable Diffusion](https://arxiv.org/abs/2211.05105) | Text-Guided Generation |
+| [stable_unclip](./stable_unclip) | Stable unCLIP | Text-to-Image Generation |
+| [stable_unclip](./stable_unclip) | Stable unCLIP | Image-to-Image Text-Guided Generation |
+| [stochastic_karras_ve](./api/pipelines/stochastic_karras_ve) | [Elucidating the Design Space of Diffusion-Based Generative Models](https://arxiv.org/abs/2206.00364) | Unconditional Image Generation |
+| [text_to_video_sd](./api/pipelines/text_to_video) | [Modelscope's Text-to-video-synthesis Model in Open Domain](https://modelscope.cn/models/damo/text-to-video-synthesis/summary) | Text-to-Video Generation |
+| [unclip](./api/pipelines/unclip) | [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://arxiv.org/abs/2204.06125)(implementation by [kakaobrain](https://github.com/kakaobrain/karlo)) | Text-to-Image Generation |
+| [versatile_diffusion](./api/pipelines/versatile_diffusion) | [Versatile Diffusion: Text, Images and Variations All in One Diffusion Model](https://arxiv.org/abs/2211.08332) | Text-to-Image Generation |
+| [versatile_diffusion](./api/pipelines/versatile_diffusion) | [Versatile Diffusion: Text, Images and Variations All in One Diffusion Model](https://arxiv.org/abs/2211.08332) | Image Variations Generation |
+| [versatile_diffusion](./api/pipelines/versatile_diffusion) | [Versatile Diffusion: Text, Images and Variations All in One Diffusion Model](https://arxiv.org/abs/2211.08332) | Dual Image and Text Guided Generation |
+| [vq_diffusion](./api/pipelines/vq_diffusion) | [Vector Quantized Diffusion Model for Text-to-Image Synthesis](https://arxiv.org/abs/2111.14822) | Text-to-Image Generation |

docs/source/zh/installation.mdx

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # 安装
 
-安装🤗 Diffusers 到你正在使用的任何深度学习框架中。
+在你正在使用的任意深度学习框架中安装 🤗 Diffusers 。
 
 🤗 Diffusers已在Python 3.7+、PyTorch 1.7.0+和Flax上进行了测试。按照下面的安装说明，针对你正在使用的深度学习框架进行安装：
 
@@ -21,11 +21,11 @@ specific language governing permissions and limitations under the License.
 
 ## 使用pip安装
 
-你需要在[虚拟环境](https://docs.python.org/3/library/venv.html)中安装🤗 Diffusers 。
+你需要在[虚拟环境](https://docs.python.org/3/library/venv.html)中安装 🤗 Diffusers 。
 
 如果你对 Python 虚拟环境不熟悉，可以看看这个[教程](https://packaging.python.org/guides/installing-using-pip-and-virtual-environments/).
 
-使用虚拟环境你可以轻松管理不同的项目，避免了依赖项之间的兼容性问题。
+在虚拟环境中，你可以轻松管理不同的项目，避免依赖项之间的兼容性问题。
 
 首先，在你的项目目录下创建一个虚拟环境：
 
@@ -39,7 +39,7 @@ python -m venv .env
 source .env/bin/activate
 ```
 
-现在你就可以安装 🤗 Diffusers了！使用下边这个命令：
+现在，你就可以安装 🤗 Diffusers了！使用下边这个命令：
 
 **PyTorch**
 
@@ -55,7 +55,7 @@ pip install diffusers["flax"]
 
 ## 从源代码安装
 
-在从源代码安装 `diffusers` 之前，你先确定你已经安装了 `torch` 和 `accelerate`。
+在从源代码安装 `diffusers` 之前，确保你已经安装了 `torch` 和 `accelerate`。
 
 `torch`的安装教程可以看 `torch` [文档](https://pytorch.org/get-started/locally/#start-locally).
 
@@ -65,17 +65,17 @@ pip install diffusers["flax"]
 pip install accelerate
 ```
 
-从源码安装 🤗 Diffusers 使用以下命令:
+从源码安装 🤗 Diffusers 需要使用以下命令:
 
 ```bash
 pip install git+https://github.com/huggingface/diffusers
 ```
 
 这个命令安装的是最新的 `main`版本，而不是最近的`stable`版。
-`main`是一直和最新进展保持一致的。比如，上次正式版发布了，有bug，新的正式版还没推出，但是`main`中可以看到这个bug被修复了。
-但是这也意味着 `main`版本并不总是稳定的。
+`main`是一直和最新进展保持一致的。比如，上次发布的正式版中有bug，在`main`中可以看到这个bug被修复了，但是新的正式版此时尚未推出。
+但是这也意味着 `main`版本不保证是稳定的。
 
-我们努力保持`main`版本正常运行,大多数问题都能在几个小时或一天之内解决
+我们努力保持`main`版本正常运行，大多数问题都能在几个小时或一天之内解决
 
 如果你遇到了问题，可以提 [Issue](https://github.com/huggingface/transformers/issues)，这样我们就能更快修复问题了。
 
@@ -105,8 +105,8 @@ pip install -e ".[torch]"
 pip install -e ".[flax]"
 ```
 
-这些命令将连接你克隆的版本库和你的 Python 库路径。
-现在，除了正常的库路径外，Python 还会在你克隆的文件夹内寻找。
+这些命令将连接到你克隆的版本库和你的 Python 库路径。
+现在，不只是在通常的库路径，Python 还会在你克隆的文件夹内寻找包。
 例如，如果你的 Python 包通常安装在 `~/anaconda3/envs/main/lib/python3.7/Site-packages/`，Python 也会搜索你克隆到的文件夹。`~/diffusers/`。
 
 <Tip warning={true}>
@@ -116,32 +116,31 @@ pip install -e ".[flax]"
 </Tip>
 
 
-现在你可以用下面的命令轻松地将你克隆的🤗Diffusers仓库更新到最新版本。
+现在你可以用下面的命令轻松地将你克隆的 🤗 Diffusers 库更新到最新版本。
 
 ```bash
 cd ~/diffusers/
 git pull
 ```
 
-你的Python环境将在下次运行时找到`main`版本的🤗 Diffusers。
+你的Python环境将在下次运行时找到`main`版本的 🤗 Diffusers。
 
-## 注意遥测日志
+## 注意 Telemetry 日志
 
-我们的库会在使用`from_pretrained()`请求期间收集信息。这些数据包括Diffusers和PyTorch/Flax的版本，请求的模型或管道，以及预训练检查点的路径（如果它被托管在Hub上）。
+我们的库会在使用`from_pretrained()`请求期间收集 telemetry 信息。这些数据包括Diffusers和PyTorch/Flax的版本，请求的模型或管道类，以及预训练检查点的路径（如果它被托管在Hub上的话）。
+这些使用数据有助于我们调试问题并确定新功能的开发优先级。
+Telemetry 数据仅在从 HuggingFace Hub 中加载模型和管道时发送，而不会在本地使用期间收集。
 
-这些使用数据有助于我们调试问题并优先考虑新功能。
-当从HuggingFace Hub加载模型和管道时才会发送遥测数据，并且在本地使用时不会收集数据。
-
-我们知道并不是每个人都想分享这些的信息，我们尊重您的隐私，
-因此您可以通过在终端中设置“DISABLE_TELEMETRY”环境变量来禁用遥测数据的收集：
+我们知道，并不是每个人都想分享这些的信息，我们尊重您的隐私，
+因此您可以通过在终端中设置 `DISABLE_TELEMETRY` 环境变量从而禁用 Telemetry 数据收集：
 
 
-在Linux/MacOS中:
+Linux/MacOS :
 ```bash
 export DISABLE_TELEMETRY=YES
 ```
 
-在Windows中:
+Windows :
 ```bash
 set DISABLE_TELEMETRY=YES
 ```

examples/community/README.md

@@ -6,33 +6,36 @@
 Please have a look at the following table to get an overview of all community examples. Click on the **Code Example** to get a copy-and-paste ready code example that you can try out.
 If a community doesn't work as expected, please open an issue and ping the author on it.
 
-| Example                                | Description                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              | Code Example                                                      | Colab                                                                                                                                                                                                              |                                                     Author |
-|:---------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------:|
-| CLIP Guided Stable Diffusion           | Doing CLIP guidance for text to image generation with Stable Diffusion                                                                                                                                                                                                                                                                                                                                                                                                                                   | [CLIP Guided Stable Diffusion](#clip-guided-stable-diffusion)     | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/CLIP_Guided_Stable_diffusion_with_diffusers.ipynb) |             [Suraj Patil](https://github.com/patil-suraj/) | 
-| One Step U-Net (Dummy)                 | Example showcasing of how to use Community Pipelines (see https://github.com/huggingface/diffusers/issues/841)                                                                                                                                                                                                                                                                                                                                                                                           | [One Step U-Net](#one-step-unet)                                  | -                                                                                                                                                                                                                  | [Patrick von Platen](https://github.com/patrickvonplaten/) |
-| Stable Diffusion Interpolation         | Interpolate the latent space of Stable Diffusion between different prompts/seeds                                                                                                                                                                                                                                                                                                                                                                                                                         | [Stable Diffusion Interpolation](#stable-diffusion-interpolation) | -                                                                                                                                                                                                                  |                    [Nate Raw](https://github.com/nateraw/) |
-| Stable Diffusion Mega                  | **One** Stable Diffusion Pipeline with all functionalities of [Text2Image](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py), [Image2Image](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py) and [Inpainting](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_inpaint.py) | [Stable Diffusion Mega](#stable-diffusion-mega)                   | -                                                                                                                                                                                                                  | [Patrick von Platen](https://github.com/patrickvonplaten/) |
-| Long Prompt Weighting Stable Diffusion | **One** Stable Diffusion Pipeline without tokens length limit, and support parsing weighting in prompt.                                                                                                                                                                                                                                                                                                                                                                                                  | [Long Prompt Weighting Stable Diffusion](#long-prompt-weighting-stable-diffusion)                                                                 | -                                                                                                                                                                                                                  |                        [SkyTNT](https://github.com/SkyTNT) |
-| Speech to Image                        | Using automatic-speech-recognition to transcribe text and Stable Diffusion to generate images                                                                                                                                                                                                                                                                                                                                                                                                            | [Speech to Image](#speech-to-image)                               | -                                                                                                                                                                                                                  | [Mikail Duzenli](https://github.com/MikailINTech)
-| Wild Card Stable Diffusion | Stable Diffusion Pipeline that supports prompts that contain wildcard terms (indicated by surrounding double underscores), with values instantiated randomly from a corresponding txt file or a dictionary of possible values                                                                                                                                                                                                                                                                                                     | [Wildcard Stable Diffusion](#wildcard-stable-diffusion)                                                                 | -                                                                                                                                                                                                                  |                        [Shyam Sudhakaran](https://github.com/shyamsn97) |
-| [Composable Stable Diffusion](https://energy-based-model.github.io/Compositional-Visual-Generation-with-Composable-Diffusion-Models/) | Stable Diffusion Pipeline that supports prompts that contain "|" in prompts (as an AND condition) and weights (separated by "|" as well) to positively / negatively weight prompts.                                                                                                                                                                                                                                                                                                     | [Composable Stable Diffusion](#composable-stable-diffusion)                                                                 | -                                                                                                                                                                                                                  |                        [Mark Rich](https://github.com/MarkRich) |
-| Seed Resizing Stable Diffusion| Stable Diffusion Pipeline that supports resizing an image and retaining the concepts of the 512 by 512 generation.                                                                                                                                                                                                                                                                                                     | [Seed Resizing](#seed-resizing)                                                                 | -                                                                                                                                                                                                                  |                        [Mark Rich](https://github.com/MarkRich) |
-| Imagic Stable Diffusion | Stable Diffusion Pipeline that enables writing a text prompt to edit an existing image| [Imagic Stable Diffusion](#imagic-stable-diffusion)                                                                 | -                                                                                                                                                                                                                  |                        [Mark Rich](https://github.com/MarkRich) |
-| Multilingual Stable Diffusion| Stable Diffusion Pipeline that supports prompts in 50 different languages.                                                                                                                                                                                                                                                                                                     | [Multilingual Stable Diffusion](#multilingual-stable-diffusion-pipeline)                                                                 | -                                                                                                                                                                                                                  |                        [Juan Carlos Piñeros](https://github.com/juancopi81) |
-| Image to Image Inpainting Stable Diffusion | Stable Diffusion Pipeline that enables the overlaying of two images and subsequent inpainting| [Image to Image Inpainting Stable Diffusion](#image-to-image-inpainting-stable-diffusion)                                                                 | -                                                                                                                                                                                                                  |                        [Alex McKinney](https://github.com/vvvm23) |
-| Text Based Inpainting Stable Diffusion | Stable Diffusion Inpainting Pipeline that enables passing a text prompt to generate the mask for inpainting| [Text Based Inpainting Stable Diffusion](#image-to-image-inpainting-stable-diffusion)                                                                 | -                                                                                                                                                                                                                  |                        [Dhruv Karan](https://github.com/unography) |
-| Bit Diffusion | Diffusion on discrete data | [Bit Diffusion](#bit-diffusion) | -  |[Stuti R.](https://github.com/kingstut) |
-| K-Diffusion Stable Diffusion | Run Stable Diffusion with any of [K-Diffusion's samplers](https://github.com/crowsonkb/k-diffusion/blob/master/k_diffusion/sampling.py) | [Stable Diffusion with K Diffusion](#stable-diffusion-with-k-diffusion) | -  | [Patrick von Platen](https://github.com/patrickvonplaten/) |
-| Checkpoint Merger Pipeline | Diffusion Pipeline that enables merging of saved model checkpoints | [Checkpoint Merger Pipeline](#checkpoint-merger-pipeline)                   | -                                                                                                                                                                                                                  | [Naga Sai Abhinay Devarinti](https://github.com/Abhinay1997/) | 
-Stable Diffusion v1.1-1.4 Comparison | Run all 4 model checkpoints for Stable Diffusion and compare their results together | [Stable Diffusion Comparison](#stable-diffusion-comparisons) | - | [Suvaditya Mukherjee](https://github.com/suvadityamuk) |
-MagicMix | Diffusion Pipeline for semantic mixing of an image and a text prompt | [MagicMix](#magic-mix) | - | [Partho Das](https://github.com/daspartho) |
-| Stable UnCLIP | Diffusion Pipeline for combining prior model (generate clip image embedding from text, UnCLIPPipeline `"kakaobrain/karlo-v1-alpha"`) and decoder pipeline (decode clip image embedding to image, StableDiffusionImageVariationPipeline `"lambdalabs/sd-image-variations-diffusers"` ). | [Stable UnCLIP](#stable-unclip) | -  |[Ray Wang](https://wrong.wang) |
-| UnCLIP Text Interpolation Pipeline | Diffusion Pipeline that allows passing two prompts and produces images while interpolating between the text-embeddings of the two prompts | [UnCLIP Text Interpolation Pipeline](#unclip-text-interpolation-pipeline)                   | -                                                                                                                                                                                                                  | [Naga Sai Abhinay Devarinti](https://github.com/Abhinay1997/) | 
-| UnCLIP Image Interpolation Pipeline | Diffusion Pipeline that allows passing two images/image_embeddings and produces images while interpolating between their image-embeddings | [UnCLIP Image Interpolation Pipeline](#unclip-image-interpolation-pipeline)                   | -                                                                                                                                                                                                                  | [Naga Sai Abhinay Devarinti](https://github.com/Abhinay1997/) | 
-| DDIM Noise Comparative Analysis Pipeline | Investigating how the diffusion models learn visual concepts from each noise level (which is a contribution of [P2 weighting (CVPR 2022)](https://arxiv.org/abs/2204.00227)) | [DDIM Noise Comparative Analysis Pipeline](#ddim-noise-comparative-analysis-pipeline) | - |[Aengus (Duc-Anh)](https://github.com/aengusng8) |
-| CLIP Guided Img2Img Stable Diffusion Pipeline | Doing CLIP guidance for image to image generation with Stable Diffusion | [CLIP Guided Img2Img Stable Diffusion](#clip-guided-img2img-stable-diffusion) | - | [Nipun Jindal](https://github.com/nipunjindal/) | 
-
-
+| Example                                                                                                                               | Description                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              | Code Example                                                                              | Colab                                                                                                                                                                                                              |                                                        Author |
+|:--------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------:|
+| CLIP Guided Stable Diffusion                                                                                                          | Doing CLIP guidance for text to image generation with Stable Diffusion                                                                                                                                                                                                                                                                                                                                                                                                                                   | [CLIP Guided Stable Diffusion](#clip-guided-stable-diffusion)                             | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/CLIP_Guided_Stable_diffusion_with_diffusers.ipynb) |                [Suraj Patil](https://github.com/patil-suraj/) | 
+| One Step U-Net (Dummy)                                                                                                                | Example showcasing of how to use Community Pipelines (see https://github.com/huggingface/diffusers/issues/841)                                                                                                                                                                                                                                                                                                                                                                                           | [One Step U-Net](#one-step-unet)                                                          | -                                                                                                                                                                                                                  |    [Patrick von Platen](https://github.com/patrickvonplaten/) |
+| Stable Diffusion Interpolation                                                                                                        | Interpolate the latent space of Stable Diffusion between different prompts/seeds                                                                                                                                                                                                                                                                                                                                                                                                                         | [Stable Diffusion Interpolation](#stable-diffusion-interpolation)                         | -                                                                                                                                                                                                                  |                       [Nate Raw](https://github.com/nateraw/) |
+| Stable Diffusion Mega                                                                                                                 | **One** Stable Diffusion Pipeline with all functionalities of [Text2Image](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py), [Image2Image](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py) and [Inpainting](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_inpaint.py) | [Stable Diffusion Mega](#stable-diffusion-mega)                                           | -                                                                                                                                                                                                                  |    [Patrick von Platen](https://github.com/patrickvonplaten/) |
+| Long Prompt Weighting Stable Diffusion                                                                                                | **One** Stable Diffusion Pipeline without tokens length limit, and support parsing weighting in prompt.                                                                                                                                                                                                                                                                                                                                                                                                  | [Long Prompt Weighting Stable Diffusion](#long-prompt-weighting-stable-diffusion)         | -                                                                                                                                                                                                                  |                           [SkyTNT](https://github.com/SkyTNT) |
+| Speech to Image                                                                                                                       | Using automatic-speech-recognition to transcribe text and Stable Diffusion to generate images                                                                                                                                                                                                                                                                                                                                                                                                            | [Speech to Image](#speech-to-image)                                                       | -                                                                                                                                                                                                                  |             [Mikail Duzenli](https://github.com/MikailINTech) 
+| Wild Card Stable Diffusion                                                                                                            | Stable Diffusion Pipeline that supports prompts that contain wildcard terms (indicated by surrounding double underscores), with values instantiated randomly from a corresponding txt file or a dictionary of possible values                                                                                                                                                                                                                                                                            | [Wildcard Stable Diffusion](#wildcard-stable-diffusion)                                   | -                                                                                                                                                                                                                  |              [Shyam Sudhakaran](https://github.com/shyamsn97) |
+| [Composable Stable Diffusion](https://energy-based-model.github.io/Compositional-Visual-Generation-with-Composable-Diffusion-Models/) | Stable Diffusion Pipeline that supports prompts that contain "|" in prompts (as an AND condition) and weights (separated by "|" as well) to positively / negatively weight prompts.                                                                                                                                                                                                                                                                                                            | [Composable Stable Diffusion](#composable-stable-diffusion)                               | -                                                                                                                                                                                                                  |                      [Mark Rich](https://github.com/MarkRich) |
+| Seed Resizing Stable Diffusion                                                                                                        | Stable Diffusion Pipeline that supports resizing an image and retaining the concepts of the 512 by 512 generation.                                                                                                                                                                                                                                                                                                                                                                                       | [Seed Resizing](#seed-resizing)                                                           | -                                                                                                                                                                                                                  |                      [Mark Rich](https://github.com/MarkRich) |
+| Imagic Stable Diffusion                                                                                                               | Stable Diffusion Pipeline that enables writing a text prompt to edit an existing image                                                                                                                                                                                                                                                                                                                                                                                                                   | [Imagic Stable Diffusion](#imagic-stable-diffusion)                                       | -                                                                                                                                                                                                                  |                      [Mark Rich](https://github.com/MarkRich) |
+| Multilingual Stable Diffusion                                                                                                         | Stable Diffusion Pipeline that supports prompts in 50 different languages.                                                                                                                                                                                                                                                                                                                                                                                                                               | [Multilingual Stable Diffusion](#multilingual-stable-diffusion-pipeline)                  | -                                                                                                                                                                                                                  |          [Juan Carlos Piñeros](https://github.com/juancopi81) |
+| Image to Image Inpainting Stable Diffusion                                                                                            | Stable Diffusion Pipeline that enables the overlaying of two images and subsequent inpainting                                                                                                                                                                                                                                                                                                                                                                                                            | [Image to Image Inpainting Stable Diffusion](#image-to-image-inpainting-stable-diffusion) | -                                                                                                                                                                                                                  |                    [Alex McKinney](https://github.com/vvvm23) |
+| Text Based Inpainting Stable Diffusion                                                                                                | Stable Diffusion Inpainting Pipeline that enables passing a text prompt to generate the mask for inpainting                                                                                                                                                                                                                                                                                                                                                                                              | [Text Based Inpainting Stable Diffusion](#image-to-image-inpainting-stable-diffusion)     | -                                                                                                                                                                                                                  |                   [Dhruv Karan](https://github.com/unography) |
+| Bit Diffusion                                                                                                                         | Diffusion on discrete data                                                                                                                                                                                                                                                                                                                                                                                                                                                                               | [Bit Diffusion](#bit-diffusion)                                                           | -  |                       [Stuti R.](https://github.com/kingstut) |
+| K-Diffusion Stable Diffusion                                                                                                          | Run Stable Diffusion with any of [K-Diffusion's samplers](https://github.com/crowsonkb/k-diffusion/blob/master/k_diffusion/sampling.py)                                                                                                                                                                                                                                                                                                                                                                  | [Stable Diffusion with K Diffusion](#stable-diffusion-with-k-diffusion)                   | -  |    [Patrick von Platen](https://github.com/patrickvonplaten/) |
+| Checkpoint Merger Pipeline                                                                                                            | Diffusion Pipeline that enables merging of saved model checkpoints                                                                                                                                                                                                                                                                                                                                                                                                                                       | [Checkpoint Merger Pipeline](#checkpoint-merger-pipeline)                                 | -                                                                                                                                                                                                                  | [Naga Sai Abhinay Devarinti](https://github.com/Abhinay1997/) | 
+ Stable Diffusion v1.1-1.4 Comparison                                                                                                  | Run all 4 model checkpoints for Stable Diffusion and compare their results together                                                                                                                                                                                                                                                                                                                                                                                                                      | [Stable Diffusion Comparison](#stable-diffusion-comparisons)                              | - |        [Suvaditya Mukherjee](https://github.com/suvadityamuk) |
+ MagicMix                                                                                                                              | Diffusion Pipeline for semantic mixing of an image and a text prompt                                                                                                                                                                                                                                                                                                                                                                                                                                     | [MagicMix](#magic-mix)                                                                    | - |                    [Partho Das](https://github.com/daspartho) |
+| Stable UnCLIP                                                                                                                         | Diffusion Pipeline for combining prior model (generate clip image embedding from text, UnCLIPPipeline `"kakaobrain/karlo-v1-alpha"`) and decoder pipeline (decode clip image embedding to image, StableDiffusionImageVariationPipeline `"lambdalabs/sd-image-variations-diffusers"` ).                                                                                                                                                                                                                   | [Stable UnCLIP](#stable-unclip)                                                           | -  |                                [Ray Wang](https://wrong.wang) |
+| UnCLIP Text Interpolation Pipeline                                                                                                    | Diffusion Pipeline that allows passing two prompts and produces images while interpolating between the text-embeddings of the two prompts                                                                                                                                                                                                                                                                                                                                                                | [UnCLIP Text Interpolation Pipeline](#unclip-text-interpolation-pipeline)                 | -                                                                                                                                                                                                                  | [Naga Sai Abhinay Devarinti](https://github.com/Abhinay1997/) | 
+| UnCLIP Image Interpolation Pipeline                                                                                                   | Diffusion Pipeline that allows passing two images/image_embeddings and produces images while interpolating between their image-embeddings                                                                                                                                                                                                                                                                                                                                                                | [UnCLIP Image Interpolation Pipeline](#unclip-image-interpolation-pipeline)               | -                                                                                                                                                                                                                  | [Naga Sai Abhinay Devarinti](https://github.com/Abhinay1997/) | 
+| DDIM Noise Comparative Analysis Pipeline                                                                                              | Investigating how the diffusion models learn visual concepts from each noise level (which is a contribution of [P2 weighting (CVPR 2022)](https://arxiv.org/abs/2204.00227))                                                                                                                                                                                                                                                                                                                             | [DDIM Noise Comparative Analysis Pipeline](#ddim-noise-comparative-analysis-pipeline)     | - |              [Aengus (Duc-Anh)](https://github.com/aengusng8) |
+| CLIP Guided Img2Img Stable Diffusion Pipeline                                                                                         | Doing CLIP guidance for image to image generation with Stable Diffusion                                                                                                                                                                                                                                                                                                                                                                                                                                  | [CLIP Guided Img2Img Stable Diffusion](#clip-guided-img2img-stable-diffusion)             | - |               [Nipun Jindal](https://github.com/nipunjindal/) | 
+| TensorRT Stable Diffusion Text to Image Pipeline                                                                                                    | Accelerates the Stable Diffusion Text2Image Pipeline using TensorRT                                                                                                                                                                                                                                                                                                                                                                                                                                      | [TensorRT Stable Diffusion Text to Image Pipeline](#tensorrt-text2image-stable-diffusion-pipeline)      | - |              [Asfiya Baig](https://github.com/asfiyab-nvidia) |
+| EDICT Image Editing Pipeline                                                                                                          | Diffusion pipeline for text-guided image editing                                                                                                                                                                                                                                                                                                                                                                                                                                                         | [EDICT Image Editing Pipeline](#edict-image-editing-pipeline)                             | - |                    [Joqsan Azocar](https://github.com/Joqsan) | 
+| Stable Diffusion RePaint                                                                                                              | Stable Diffusion pipeline using [RePaint](https://arxiv.org/abs/2201.0986) for inpainting.                                                                                                                                                                                                                                                                                                                                                                                                               | [Stable Diffusion RePaint](#stable-diffusion-repaint )                                    | - |                  [Markus Pobitzer](https://github.com/Markus-Pobitzer) | 
+| TensorRT Stable Diffusion Image to Image Pipeline                                                                                                    | Accelerates the Stable Diffusion Image2Image Pipeline using TensorRT                                                                                                                                                                                                                                                                                                                                                                                                                                      | [TensorRT Stable Diffusion Image to Image Pipeline](#tensorrt-image2image-stable-diffusion-pipeline)      | - |              [Asfiya Baig](https://github.com/asfiyab-nvidia) |
+| Stable Diffusion IPEX Pipeline | Accelerate Stable Diffusion inference pipeline with BF16/FP32 precision on Intel Xeon CPUs with [IPEX](https://github.com/intel/intel-extension-for-pytorch) | [Stable Diffusion on IPEX](#stable-diffusion-on-ipex) | - | [Yingjie Han](https://github.com/yingjie-han/) | 
 
 To load a custom pipeline you just need to pass the `custom_pipeline` argument to `DiffusionPipeline`, as one of the files in `diffusers/examples/community`. Feel free to send a PR with your own pipelines, we will merge them quickly.
 ```py
@@ -1130,3 +1133,380 @@ Init Image
 Output Image
 
 ![img2img_clip_guidance](https://huggingface.co/datasets/njindal/images/resolve/main/clip_guided_img2img.jpg)
+
+### TensorRT Text2Image Stable Diffusion Pipeline
+
+The TensorRT Pipeline can be used to accelerate the Text2Image Stable Diffusion Inference run.
+
+NOTE: The ONNX conversions and TensorRT engine build may take up to 30 minutes.
+
+```python
+import torch
+from diffusers import DDIMScheduler
+from diffusers.pipelines.stable_diffusion import StableDiffusionPipeline
+
+# Use the DDIMScheduler scheduler here instead
+scheduler = DDIMScheduler.from_pretrained("stabilityai/stable-diffusion-2-1",
+                                            subfolder="scheduler")
+
+pipe = StableDiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-2-1",
+                                                custom_pipeline="stable_diffusion_tensorrt_txt2img",
+                                                revision='fp16',
+                                                torch_dtype=torch.float16,
+                                                scheduler=scheduler,)
+
+# re-use cached folder to save ONNX models and TensorRT Engines
+pipe.set_cached_folder("stabilityai/stable-diffusion-2-1", revision='fp16',)
+
+pipe = pipe.to("cuda")
+
+prompt = "a beautiful photograph of Mt. Fuji during cherry blossom"
+image = pipe(prompt).images[0]
+image.save('tensorrt_mt_fuji.png')
+```
+
+### EDICT Image Editing Pipeline
+
+This pipeline implements the text-guided image editing approach from the paper [EDICT: Exact Diffusion Inversion via Coupled Transformations](https://arxiv.org/abs/2211.12446). You have to pass:
+- (`PIL`) `image` you want to edit.
+- `base_prompt`: the text prompt describing the current image (before editing).
+- `target_prompt`: the text prompt describing with the edits.
+
+```python
+from diffusers import DiffusionPipeline, DDIMScheduler
+from transformers import CLIPTextModel
+import torch, PIL, requests
+from io import BytesIO
+from IPython.display import display
+
+def center_crop_and_resize(im):
+
+    width, height = im.size
+    d = min(width, height)
+    left = (width - d) / 2
+    upper = (height - d) / 2
+    right = (width + d) / 2
+    lower = (height + d) / 2
+
+    return im.crop((left, upper, right, lower)).resize((512, 512))
+
+torch_dtype = torch.float16
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+
+# scheduler and text_encoder param values as in the paper
+scheduler = DDIMScheduler(
+        num_train_timesteps=1000,
+        beta_start=0.00085,
+        beta_end=0.012,
+        beta_schedule="scaled_linear",
+        set_alpha_to_one=False,
+        clip_sample=False,
+)
+
+text_encoder = CLIPTextModel.from_pretrained(
+    pretrained_model_name_or_path="openai/clip-vit-large-patch14",
+    torch_dtype=torch_dtype,
+)
+
+# initialize pipeline
+pipeline = DiffusionPipeline.from_pretrained(
+    pretrained_model_name_or_path="CompVis/stable-diffusion-v1-4",
+    custom_pipeline="edict_pipeline",
+    revision="fp16",
+    scheduler=scheduler,
+    text_encoder=text_encoder,
+    leapfrog_steps=True,
+    torch_dtype=torch_dtype,
+).to(device)
+
+# download image
+image_url = "https://huggingface.co/datasets/Joqsan/images/resolve/main/imagenet_dog_1.jpeg"
+response = requests.get(image_url)
+image = PIL.Image.open(BytesIO(response.content))
+
+# preprocess it
+cropped_image = center_crop_and_resize(image)
+
+# define the prompts
+base_prompt = "A dog"
+target_prompt = "A golden retriever"
+
+# run the pipeline
+result_image = pipeline(
+      base_prompt=base_prompt, 
+      target_prompt=target_prompt, 
+      image=cropped_image,
+)
+
+display(result_image)
+```
+
+Init Image
+
+![img2img_init_edict_text_editing](https://huggingface.co/datasets/Joqsan/images/resolve/main/imagenet_dog_1.jpeg)
+
+Output Image
+
+![img2img_edict_text_editing](https://huggingface.co/datasets/Joqsan/images/resolve/main/imagenet_dog_1_cropped_generated.png)
+
+### Stable Diffusion RePaint
+
+This pipeline uses the [RePaint](https://arxiv.org/abs/2201.09865) logic on the latent space of stable diffusion. It can
+be used similarly to other image inpainting pipelines but does not rely on a specific inpainting model. This means you can use
+models that are not specifically created for inpainting.
+
+Make sure to use the ```RePaintScheduler``` as shown in the example below.
+
+Disclaimer: The mask gets transferred into latent space, this may lead to unexpected changes on the edge of the masked part.
+The inference time is a lot slower.
+
+```py
+import PIL
+import requests
+import torch
+from io import BytesIO
+from diffusers import StableDiffusionPipeline, RePaintScheduler
+def download_image(url):
+    response = requests.get(url)
+    return PIL.Image.open(BytesIO(response.content)).convert("RGB")
+img_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png"
+mask_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png"
+init_image = download_image(img_url).resize((512, 512))
+mask_image = download_image(mask_url).resize((512, 512))
+mask_image = PIL.ImageOps.invert(mask_image)
+pipe = StableDiffusionPipeline.from_pretrained(
+    "CompVis/stable-diffusion-v1-4", torch_dtype=torch.float16, custom_pipeline="stable_diffusion_repaint",
+)
+pipe.scheduler = RePaintScheduler.from_config(pipe.scheduler.config)
+pipe = pipe.to("cuda")
+prompt = "Face of a yellow cat, high resolution, sitting on a park bench"
+image = pipe(prompt=prompt, image=init_image, mask_image=mask_image).images[0]
+```
+
+### TensorRT Image2Image Stable Diffusion Pipeline
+
+The TensorRT Pipeline can be used to accelerate the Image2Image Stable Diffusion Inference run.
+
+NOTE: The ONNX conversions and TensorRT engine build may take up to 30 minutes.
+
+```python
+import requests
+from io import BytesIO
+from PIL import Image
+import torch
+from diffusers import DDIMScheduler
+from diffusers.pipelines.stable_diffusion import StableDiffusionImg2ImgPipeline
+
+# Use the DDIMScheduler scheduler here instead
+scheduler = DDIMScheduler.from_pretrained("stabilityai/stable-diffusion-2-1",
+                                            subfolder="scheduler")
+
+
+pipe = StableDiffusionImg2ImgPipeline.from_pretrained("stabilityai/stable-diffusion-2-1",
+                                                custom_pipeline="stable_diffusion_tensorrt_img2img",
+                                                revision='fp16',
+                                                torch_dtype=torch.float16,
+                                                scheduler=scheduler,)
+
+# re-use cached folder to save ONNX models and TensorRT Engines
+pipe.set_cached_folder("stabilityai/stable-diffusion-2-1", revision='fp16',)
+
+pipe = pipe.to("cuda")
+
+url = "https://pajoca.com/wp-content/uploads/2022/09/tekito-yamakawa-1.png"
+response = requests.get(url)
+input_image = Image.open(BytesIO(response.content)).convert("RGB")
+
+prompt = "photorealistic new zealand hills"
+image = pipe(prompt, image=input_image, strength=0.75,).images[0]
+image.save('tensorrt_img2img_new_zealand_hills.png')
+```
+
+### Stable Diffusion Reference
+
+This pipeline uses the Reference Control. Refer to the [sd-webui-controlnet discussion: Reference-only Control](https://github.com/Mikubill/sd-webui-controlnet/discussions/1236)[sd-webui-controlnet discussion: Reference-adain Control](https://github.com/Mikubill/sd-webui-controlnet/discussions/1280).
+
+
+```py
+import torch
+from diffusers import UniPCMultistepScheduler
+from diffusers.utils import load_image
+
+input_image = load_image("https://hf.co/datasets/huggingface/documentation-images/resolve/main/diffusers/input_image_vermeer.png")
+
+pipe = StableDiffusionReferencePipeline.from_pretrained(
+       "runwayml/stable-diffusion-v1-5",
+       safety_checker=None,
+       torch_dtype=torch.float16
+       ).to('cuda:0')
+
+pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
+
+result_img = pipe(ref_image=input_image,
+      prompt="1girl",
+      num_inference_steps=20,
+      reference_attn=True,
+      reference_adain=True).images[0]
+```
+
+Reference Image
+
+![reference_image](https://hf.co/datasets/huggingface/documentation-images/resolve/main/diffusers/input_image_vermeer.png)
+
+Output Image of `reference_attn=True` and `reference_adain=False`
+
+![output_image](https://github.com/huggingface/diffusers/assets/24734142/813b5c6a-6d89-46ba-b7a4-2624e240eea5)
+
+Output Image of `reference_attn=False` and `reference_adain=True`
+
+![output_image](https://github.com/huggingface/diffusers/assets/24734142/ffc90339-9ef0-4c4d-a544-135c3e5644da)
+
+Output Image of `reference_attn=True` and `reference_adain=True`
+
+![output_image](https://github.com/huggingface/diffusers/assets/24734142/3c5255d6-867d-4d35-b202-8dfd30cc6827)
+
+### Stable Diffusion ControlNet Reference
+
+This pipeline uses the Reference Control with ControlNet. Refer to the [sd-webui-controlnet discussion: Reference-only Control](https://github.com/Mikubill/sd-webui-controlnet/discussions/1236)[sd-webui-controlnet discussion: Reference-adain Control](https://github.com/Mikubill/sd-webui-controlnet/discussions/1280).
+
+
+```py
+import cv2
+import torch
+import numpy as np
+from PIL import Image
+from diffusers import UniPCMultistepScheduler
+from diffusers.utils import load_image
+
+input_image = load_image("https://hf.co/datasets/huggingface/documentation-images/resolve/main/diffusers/input_image_vermeer.png")
+
+# get canny image
+image = cv2.Canny(np.array(input_image), 100, 200)
+image = image[:, :, None]
+image = np.concatenate([image, image, image], axis=2)
+canny_image = Image.fromarray(image)
+
+controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", torch_dtype=torch.float16)
+pipe = StableDiffusionControlNetReferencePipeline.from_pretrained(
+       "runwayml/stable-diffusion-v1-5",
+       controlnet=controlnet,
+       safety_checker=None,
+       torch_dtype=torch.float16
+       ).to('cuda:0')
+
+pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
+
+result_img = pipe(ref_image=input_image,
+      prompt="1girl",
+      image=canny_image,
+      num_inference_steps=20,
+      reference_attn=True,
+      reference_adain=True).images[0]
+```
+
+Reference Image
+
+![reference_image](https://hf.co/datasets/huggingface/documentation-images/resolve/main/diffusers/input_image_vermeer.png)
+
+Output Image
+
+![output_image](https://github.com/huggingface/diffusers/assets/24734142/7b9a5830-f173-4b92-b0cf-73d0e9c01d60)
+
+
+### Stable Diffusion on IPEX
+
+This diffusion pipeline aims to accelarate the inference of Stable-Diffusion on Intel Xeon CPUs with BF16/FP32 precision using [IPEX](https://github.com/intel/intel-extension-for-pytorch).
+
+To use this pipeline, you need to:
+1. Install [IPEX](https://github.com/intel/intel-extension-for-pytorch)
+
+**Note:** For each PyTorch release, there is a corresponding release of the IPEX. Here is the mapping relationship. It is recommended to install Pytorch/IPEX2.0 to get the best performance.
+
+|PyTorch Version|IPEX Version|
+|--|--|
+|[v2.0.\*](https://github.com/pytorch/pytorch/tree/v2.0.1 "v2.0.1")|[v2.0.\*](https://github.com/intel/intel-extension-for-pytorch/tree/v2.0.100+cpu)|
+|[v1.13.\*](https://github.com/pytorch/pytorch/tree/v1.13.0 "v1.13.0")|[v1.13.\*](https://github.com/intel/intel-extension-for-pytorch/tree/v1.13.100+cpu)|
+
+You can simply use pip to install IPEX with the latest version.
+```python
+python -m pip install intel_extension_for_pytorch
+```
+**Note:** To install a specific version, run with the following command:
+```
+python -m pip install intel_extension_for_pytorch==<version_name> -f https://developer.intel.com/ipex-whl-stable-cpu
+```
+
+2. After pipeline initialization, `prepare_for_ipex()` should be called to enable IPEX accelaration. Supported inference datatypes are Float32 and BFloat16.
+
+**Note:** The setting of generated image height/width for `prepare_for_ipex()` should be same as the setting of pipeline inference.
+```python
+pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", custom_pipeline="stable_diffusion_ipex")
+# For Float32
+pipe.prepare_for_ipex(prompt, dtype=torch.float32, height=512, width=512) #value of image height/width should be consistent with the pipeline inference
+# For BFloat16 
+pipe.prepare_for_ipex(prompt, dtype=torch.bfloat16, height=512, width=512) #value of image height/width should be consistent with the pipeline inference
+```
+
+Then you can use the ipex pipeline in a similar way to the default stable diffusion pipeline.
+```python
+# For Float32
+image = pipe(prompt, num_inference_steps=20, height=512, width=512).images[0] #value of image height/width should be consistent with 'prepare_for_ipex()'
+# For BFloat16 
+with torch.cpu.amp.autocast(enabled=True, dtype=torch.bfloat16):
+    image = pipe(prompt, num_inference_steps=20, height=512, width=512).images[0] #value of image height/width should be consistent with 'prepare_for_ipex()'
+```
+
+The following code compares the performance of the original stable diffusion pipeline with the ipex-optimized pipeline.
+
+```python
+import torch
+import intel_extension_for_pytorch as ipex
+from diffusers import StableDiffusionPipeline
+import time
+
+prompt = "sailing ship in storm by Rembrandt"
+model_id = "runwayml/stable-diffusion-v1-5"
+# Helper function for time evaluation
+def elapsed_time(pipeline, nb_pass=3, num_inference_steps=20):
+    # warmup
+    for _ in range(2):
+        images = pipeline(prompt, num_inference_steps=num_inference_steps, height=512, width=512).images
+    #time evaluation
+    start = time.time()
+    for _ in range(nb_pass):
+        pipeline(prompt, num_inference_steps=num_inference_steps, height=512, width=512)
+    end = time.time()
+    return (end - start) / nb_pass
+
+##############     bf16 inference performance    ###############
+
+# 1. IPEX Pipeline initialization
+pipe = DiffusionPipeline.from_pretrained(model_id, custom_pipeline="stable_diffusion_ipex")
+pipe.prepare_for_ipex(prompt, dtype=torch.bfloat16, height=512, width=512)
+
+# 2. Original Pipeline initialization
+pipe2 = StableDiffusionPipeline.from_pretrained(model_id)
+
+# 3. Compare performance between Original Pipeline and IPEX Pipeline
+with torch.cpu.amp.autocast(enabled=True, dtype=torch.bfloat16):
+    latency = elapsed_time(pipe)
+    print("Latency of StableDiffusionIPEXPipeline--bf16", latency)
+    latency = elapsed_time(pipe2)
+    print("Latency of StableDiffusionPipeline--bf16",latency)
+
+##############     fp32 inference performance    ###############
+
+# 1. IPEX Pipeline initialization
+pipe3 = DiffusionPipeline.from_pretrained(model_id, custom_pipeline="stable_diffusion_ipex")
+pipe3.prepare_for_ipex(prompt, dtype=torch.float32, height=512, width=512)
+
+# 2. Original Pipeline initialization
+pipe4 = StableDiffusionPipeline.from_pretrained(model_id)
+
+# 3. Compare performance between Original Pipeline and IPEX Pipeline
+latency = elapsed_time(pipe3)
+print("Latency of StableDiffusionIPEXPipeline--fp32", latency)
+latency = elapsed_time(pipe4)
+print("Latency of StableDiffusionPipeline--fp32",latency)
+
+```

examples/community/bit_diffusion.py

@@ -238,7 +238,7 @@ class BitDiffusion(DiffusionPipeline):
         **kwargs,
     ) -> Union[Tuple, ImagePipelineOutput]:
         latents = torch.randn(
-            (batch_size, self.unet.in_channels, height, width),
+            (batch_size, self.unet.config.in_channels, height, width),
             generator=generator,
         )
         latents = decimal_to_bits(latents) * self.bit_scale

examples/community/clip_guided_stable_diffusion.py

@@ -254,7 +254,7 @@ class CLIPGuidedStableDiffusion(DiffusionPipeline):
         # Unlike in other pipelines, latents need to be generated in the target device
         # for 1-to-1 results reproducibility with the CompVis implementation.
         # However this currently doesn't work in `mps`.
-        latents_shape = (batch_size * num_images_per_prompt, self.unet.in_channels, height // 8, width // 8)
+        latents_shape = (batch_size * num_images_per_prompt, self.unet.config.in_channels, height // 8, width // 8)
         latents_dtype = text_embeddings.dtype
         if latents is None:
             if self.device.type == "mps":

examples/community/clip_guided_stable_diffusion_img2img.py

@@ -414,7 +414,7 @@ class CLIPGuidedStableDiffusion(DiffusionPipeline):
         # Unlike in other pipelines, latents need to be generated in the target device
         # for 1-to-1 results reproducibility with the CompVis implementation.
         # However this currently doesn't work in `mps`.
-        latents_shape = (batch_size * num_images_per_prompt, self.unet.in_channels, height // 8, width // 8)
+        latents_shape = (batch_size * num_images_per_prompt, self.unet.config.in_channels, height // 8, width // 8)
         latents_dtype = text_embeddings.dtype
         if latents is None:
             if self.device.type == "mps":

examples/community/composable_stable_diffusion.py

@@ -22,6 +22,8 @@ from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer
 from diffusers import DiffusionPipeline
 from diffusers.configuration_utils import FrozenDict
 from diffusers.models import AutoencoderKL, UNet2DConditionModel
+from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion import StableDiffusionPipelineOutput
+from diffusers.pipelines.stable_diffusion.safety_checker import StableDiffusionSafetyChecker
 from diffusers.schedulers import (
     DDIMScheduler,
     DPMSolverMultistepScheduler,
@@ -30,11 +32,7 @@ from diffusers.schedulers import (
     LMSDiscreteScheduler,
     PNDMScheduler,
 )
-from diffusers.utils import is_accelerate_available
-
-from ...utils import deprecate, logging
-from . import StableDiffusionPipelineOutput
-from .safety_checker import StableDiffusionSafetyChecker
+from diffusers.utils import deprecate, is_accelerate_available, logging
 
 
 logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
@@ -513,7 +511,7 @@ class ComposableStableDiffusionPipeline(DiffusionPipeline):
         timesteps = self.scheduler.timesteps
 
         # 5. Prepare latent variables
-        num_channels_latents = self.unet.in_channels
+        num_channels_latents = self.unet.config.in_channels
         latents = self.prepare_latents(
             batch_size * num_images_per_prompt,
             num_channels_latents,

examples/community/edict_pipeline.py

@@ -0,0 +1,264 @@
+from typing import Optional
+
+import torch
+from PIL import Image
+from tqdm.auto import tqdm
+from transformers import CLIPTextModel, CLIPTokenizer
+
+from diffusers import AutoencoderKL, DDIMScheduler, DiffusionPipeline, UNet2DConditionModel
+from diffusers.image_processor import VaeImageProcessor
+from diffusers.utils import (
+    deprecate,
+)
+
+
+class EDICTPipeline(DiffusionPipeline):
+    def __init__(
+        self,
+        vae: AutoencoderKL,
+        text_encoder: CLIPTextModel,
+        tokenizer: CLIPTokenizer,
+        unet: UNet2DConditionModel,
+        scheduler: DDIMScheduler,
+        mixing_coeff: float = 0.93,
+        leapfrog_steps: bool = True,
+    ):
+        self.mixing_coeff = mixing_coeff
+        self.leapfrog_steps = leapfrog_steps
+
+        super().__init__()
+        self.register_modules(
+            vae=vae,
+            text_encoder=text_encoder,
+            tokenizer=tokenizer,
+            unet=unet,
+            scheduler=scheduler,
+        )
+
+        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
+        self.image_processor = VaeImageProcessor(vae_scale_factor=self.vae_scale_factor)
+
+    def _encode_prompt(
+        self, prompt: str, negative_prompt: Optional[str] = None, do_classifier_free_guidance: bool = False
+    ):
+        text_inputs = self.tokenizer(
+            prompt,
+            padding="max_length",
+            max_length=self.tokenizer.model_max_length,
+            truncation=True,
+            return_tensors="pt",
+        )
+
+        prompt_embeds = self.text_encoder(text_inputs.input_ids.to(self.device)).last_hidden_state
+
+        prompt_embeds = prompt_embeds.to(dtype=self.text_encoder.dtype, device=self.device)
+
+        if do_classifier_free_guidance:
+            uncond_tokens = "" if negative_prompt is None else negative_prompt
+
+            uncond_input = self.tokenizer(
+                uncond_tokens,
+                padding="max_length",
+                max_length=self.tokenizer.model_max_length,
+                truncation=True,
+                return_tensors="pt",
+            )
+
+            negative_prompt_embeds = self.text_encoder(uncond_input.input_ids.to(self.device)).last_hidden_state
+
+            prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds])
+
+        return prompt_embeds
+
+    def denoise_mixing_layer(self, x: torch.Tensor, y: torch.Tensor):
+        x = self.mixing_coeff * x + (1 - self.mixing_coeff) * y
+        y = self.mixing_coeff * y + (1 - self.mixing_coeff) * x
+
+        return [x, y]
+
+    def noise_mixing_layer(self, x: torch.Tensor, y: torch.Tensor):
+        y = (y - (1 - self.mixing_coeff) * x) / self.mixing_coeff
+        x = (x - (1 - self.mixing_coeff) * y) / self.mixing_coeff
+
+        return [x, y]
+
+    def _get_alpha_and_beta(self, t: torch.Tensor):
+        # as self.alphas_cumprod is always in cpu
+        t = int(t)
+
+        alpha_prod = self.scheduler.alphas_cumprod[t] if t >= 0 else self.scheduler.final_alpha_cumprod
+
+        return alpha_prod, 1 - alpha_prod
+
+    def noise_step(
+        self,
+        base: torch.Tensor,
+        model_input: torch.Tensor,
+        model_output: torch.Tensor,
+        timestep: torch.Tensor,
+    ):
+        prev_timestep = timestep - self.scheduler.config.num_train_timesteps / self.scheduler.num_inference_steps
+
+        alpha_prod_t, beta_prod_t = self._get_alpha_and_beta(timestep)
+        alpha_prod_t_prev, beta_prod_t_prev = self._get_alpha_and_beta(prev_timestep)
+
+        a_t = (alpha_prod_t_prev / alpha_prod_t) ** 0.5
+        b_t = -a_t * (beta_prod_t**0.5) + beta_prod_t_prev**0.5
+
+        next_model_input = (base - b_t * model_output) / a_t
+
+        return model_input, next_model_input.to(base.dtype)
+
+    def denoise_step(
+        self,
+        base: torch.Tensor,
+        model_input: torch.Tensor,
+        model_output: torch.Tensor,
+        timestep: torch.Tensor,
+    ):
+        prev_timestep = timestep - self.scheduler.config.num_train_timesteps / self.scheduler.num_inference_steps
+
+        alpha_prod_t, beta_prod_t = self._get_alpha_and_beta(timestep)
+        alpha_prod_t_prev, beta_prod_t_prev = self._get_alpha_and_beta(prev_timestep)
+
+        a_t = (alpha_prod_t_prev / alpha_prod_t) ** 0.5
+        b_t = -a_t * (beta_prod_t**0.5) + beta_prod_t_prev**0.5
+        next_model_input = a_t * base + b_t * model_output
+
+        return model_input, next_model_input.to(base.dtype)
+
+    @torch.no_grad()
+    def decode_latents(self, latents: torch.Tensor):
+        latents = 1 / self.vae.config.scaling_factor * latents
+        image = self.vae.decode(latents).sample
+        image = (image / 2 + 0.5).clamp(0, 1)
+        return image
+
+    @torch.no_grad()
+    def prepare_latents(
+        self,
+        image: Image.Image,
+        text_embeds: torch.Tensor,
+        timesteps: torch.Tensor,
+        guidance_scale: float,
+        generator: Optional[torch.Generator] = None,
+    ):
+        do_classifier_free_guidance = guidance_scale > 1.0
+
+        image = image.to(device=self.device, dtype=text_embeds.dtype)
+        latent = self.vae.encode(image).latent_dist.sample(generator)
+
+        latent = self.vae.config.scaling_factor * latent
+
+        coupled_latents = [latent.clone(), latent.clone()]
+
+        for i, t in tqdm(enumerate(timesteps), total=len(timesteps)):
+            coupled_latents = self.noise_mixing_layer(x=coupled_latents[0], y=coupled_latents[1])
+
+            # j - model_input index, k - base index
+            for j in range(2):
+                k = j ^ 1
+
+                if self.leapfrog_steps:
+                    if i % 2 == 0:
+                        k, j = j, k
+
+                model_input = coupled_latents[j]
+                base = coupled_latents[k]
+
+                latent_model_input = torch.cat([model_input] * 2) if do_classifier_free_guidance else model_input
+
+                noise_pred = self.unet(latent_model_input, t, encoder_hidden_states=text_embeds).sample
+
+                if do_classifier_free_guidance:
+                    noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
+                    noise_pred = noise_pred_uncond + guidance_scale * (noise_pred_text - noise_pred_uncond)
+
+                base, model_input = self.noise_step(
+                    base=base,
+                    model_input=model_input,
+                    model_output=noise_pred,
+                    timestep=t,
+                )
+
+                coupled_latents[k] = model_input
+
+        return coupled_latents
+
+    @torch.no_grad()
+    def __call__(
+        self,
+        base_prompt: str,
+        target_prompt: str,
+        image: Image.Image,
+        guidance_scale: float = 3.0,
+        num_inference_steps: int = 50,
+        strength: float = 0.8,
+        negative_prompt: Optional[str] = None,
+        generator: Optional[torch.Generator] = None,
+        output_type: Optional[str] = "pil",
+    ):
+        do_classifier_free_guidance = guidance_scale > 1.0
+
+        image = self.image_processor.preprocess(image)
+
+        base_embeds = self._encode_prompt(base_prompt, negative_prompt, do_classifier_free_guidance)
+        target_embeds = self._encode_prompt(target_prompt, negative_prompt, do_classifier_free_guidance)
+
+        self.scheduler.set_timesteps(num_inference_steps, self.device)
+
+        t_limit = num_inference_steps - int(num_inference_steps * strength)
+        fwd_timesteps = self.scheduler.timesteps[t_limit:]
+        bwd_timesteps = fwd_timesteps.flip(0)
+
+        coupled_latents = self.prepare_latents(image, base_embeds, bwd_timesteps, guidance_scale, generator)
+
+        for i, t in tqdm(enumerate(fwd_timesteps), total=len(fwd_timesteps)):
+            # j - model_input index, k - base index
+            for k in range(2):
+                j = k ^ 1
+
+                if self.leapfrog_steps:
+                    if i % 2 == 1:
+                        k, j = j, k
+
+                model_input = coupled_latents[j]
+                base = coupled_latents[k]
+
+                latent_model_input = torch.cat([model_input] * 2) if do_classifier_free_guidance else model_input
+
+                noise_pred = self.unet(latent_model_input, t, encoder_hidden_states=target_embeds).sample
+
+                if do_classifier_free_guidance:
+                    noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
+                    noise_pred = noise_pred_uncond + guidance_scale * (noise_pred_text - noise_pred_uncond)
+
+                base, model_input = self.denoise_step(
+                    base=base,
+                    model_input=model_input,
+                    model_output=noise_pred,
+                    timestep=t,
+                )
+
+                coupled_latents[k] = model_input
+
+            coupled_latents = self.denoise_mixing_layer(x=coupled_latents[0], y=coupled_latents[1])
+
+        # either one is fine
+        final_latent = coupled_latents[0]
+
+        if output_type not in ["latent", "pt", "np", "pil"]:
+            deprecation_message = (
+                f"the output_type {output_type} is outdated. Please make sure to set it to one of these instead: "
+                "`pil`, `np`, `pt`, `latent`"
+            )
+            deprecate("Unsupported output_type", "1.0.0", deprecation_message, standard_warn=False)
+            output_type = "np"
+
+        if output_type == "latent":
+            image = final_latent
+        else:
+            image = self.decode_latents(final_latent)
+            image = self.image_processor.postprocess(image, output_type=output_type)
+
+        return image

examples/community/imagic_stable_diffusion.py

@@ -424,7 +424,7 @@ class ImagicStableDiffusionPipeline(DiffusionPipeline):
         # Unlike in other pipelines, latents need to be generated in the target device
         # for 1-to-1 results reproducibility with the CompVis implementation.
         # However this currently doesn't work in `mps`.
-        latents_shape = (1, self.unet.in_channels, height // 8, width // 8)
+        latents_shape = (1, self.unet.config.in_channels, height // 8, width // 8)
         latents_dtype = text_embeddings.dtype
         if self.device.type == "mps":
             # randn does not exist on mps

examples/community/interpolate_stable_diffusion.py

@@ -320,7 +320,7 @@ class StableDiffusionWalkPipeline(DiffusionPipeline):
         # Unlike in other pipelines, latents need to be generated in the target device
         # for 1-to-1 results reproducibility with the CompVis implementation.
         # However this currently doesn't work in `mps`.
-        latents_shape = (batch_size * num_images_per_prompt, self.unet.in_channels, height // 8, width // 8)
+        latents_shape = (batch_size * num_images_per_prompt, self.unet.config.in_channels, height // 8, width // 8)
         latents_dtype = text_embeddings.dtype
         if latents is None:
             if self.device.type == "mps":
@@ -416,7 +416,7 @@ class StableDiffusionWalkPipeline(DiffusionPipeline):
     def get_noise(self, seed, dtype=torch.float32, height=512, width=512):
         """Takes in random seed and returns corresponding noise vector"""
         return torch.randn(
-            (1, self.unet.in_channels, height // 8, width // 8),
+            (1, self.unet.config.in_channels, height // 8, width // 8),
             generator=torch.Generator(device=self.device).manual_seed(seed),
             device=self.device,
             dtype=dtype,

examples/community/lpw_stable_diffusion_onnx.py

@@ -486,7 +486,7 @@ class OnnxStableDiffusionLongPromptWeightingPipeline(OnnxStableDiffusionPipeline
             self.__init__additional__()
 
     def __init__additional__(self):
-        self.unet_in_channels = 4
+        self.unet.config.in_channels = 4
         self.vae_scale_factor = 8
 
     def _encode_prompt(
@@ -621,7 +621,7 @@ class OnnxStableDiffusionLongPromptWeightingPipeline(OnnxStableDiffusionPipeline
         if image is None:
             shape = (
                 batch_size,
-                self.unet_in_channels,
+                self.unet.config.in_channels,
                 height // self.vae_scale_factor,
                 width // self.vae_scale_factor,
             )

examples/community/magic_mix.py

@@ -93,7 +93,7 @@ class MagicMixPipeline(DiffusionPipeline):
 
         torch.manual_seed(seed)
         noise = torch.randn(
-            (1, self.unet.in_channels, height // 8, width // 8),
+            (1, self.unet.config.in_channels, height // 8, width // 8),
         ).to(self.device)
 
         latents = self.scheduler.add_noise(

examples/community/multilingual_stable_diffusion.py

@@ -355,7 +355,7 @@ class MultilingualStableDiffusion(DiffusionPipeline):
         # Unlike in other pipelines, latents need to be generated in the target device
         # for 1-to-1 results reproducibility with the CompVis implementation.
         # However this currently doesn't work in `mps`.
-        latents_shape = (batch_size * num_images_per_prompt, self.unet.in_channels, height // 8, width // 8)
+        latents_shape = (batch_size * num_images_per_prompt, self.unet.config.in_channels, height // 8, width // 8)
         latents_dtype = text_embeddings.dtype
         if latents is None:
             if self.device.type == "mps":