update

.github/workflows/build_docker_images.yml

@@ -34,7 +34,7 @@ jobs:
         id: file_changes
         uses: jitterbit/get-changed-files@v1
         with:
-          format: "space-delimited"
+          format: 'space-delimited'
           token: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Build Changed Docker Images
@@ -67,7 +67,6 @@ jobs:
           - diffusers-pytorch-cuda
           - diffusers-pytorch-compile-cuda
           - diffusers-pytorch-xformers-cuda
-          - diffusers-pytorch-minimum-cuda
           - diffusers-flax-cpu
           - diffusers-flax-tpu
           - diffusers-onnxruntime-cpu

.github/workflows/nightly_tests.yml

@@ -235,64 +235,7 @@ jobs:
         run: |
           pip install slack_sdk tabulate
           python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
-          
-  torch_minimum_version_cuda_tests:
-    name: Torch Minimum Version CUDA Tests
-    runs-on:
-      group: aws-g4dn-2xlarge
-    container:
-      image: diffusers/diffusers-pytorch-minimum-cuda
-      options: --shm-size "16gb" --ipc host --gpus 0
-    defaults:
-      run:
-        shell: bash
-    steps:
-      - name: Checkout diffusers
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 2
 
-      - name: Install dependencies
-        run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          python -m uv pip install -e [quality,test]
-          python -m uv pip install peft@git+https://github.com/huggingface/peft.git
-          pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-
-      - name: Environment
-        run: |
-          python utils/print_env.py
-
-      - name: Run PyTorch CUDA tests
-        env:
-          HF_TOKEN: ${{ secrets.HF_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" \
-            --make-reports=tests_torch_minimum_version_cuda \
-            tests/models/test_modelling_common.py \
-            tests/pipelines/test_pipelines_common.py \
-            tests/pipelines/test_pipeline_utils.py \
-            tests/pipelines/test_pipelines.py \
-            tests/pipelines/test_pipelines_auto.py \
-            tests/schedulers/test_schedulers.py \
-            tests/others
-
-      - name: Failure short reports
-        if: ${{ failure() }}
-        run: |
-          cat reports/tests_torch_minimum_version_cuda_stats.txt
-          cat reports/tests_torch_minimum_version_cuda_failures_short.txt
-
-      - name: Test suite reports artifacts
-        if: ${{ always() }}
-        uses: actions/upload-artifact@v4
-        with:
-          name: torch_minimum_version_cuda_test_reports
-          path: reports
- 
   run_flax_tpu_tests:
     name: Nightly Flax TPU Tests
     runs-on:

.github/workflows/release_tests_fast.yml

@@ -157,63 +157,6 @@ jobs:
         name: torch_cuda_${{ matrix.module }}_test_reports
         path: reports
 
-  torch_minimum_version_cuda_tests:
-    name: Torch Minimum Version CUDA Tests
-    runs-on:
-      group: aws-g4dn-2xlarge
-    container:
-      image: diffusers/diffusers-pytorch-minimum-cuda
-      options: --shm-size "16gb" --ipc host --gpus 0
-    defaults:
-      run:
-        shell: bash
-    steps:
-      - name: Checkout diffusers
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 2
-
-      - name: Install dependencies
-        run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          python -m uv pip install -e [quality,test]
-          python -m uv pip install peft@git+https://github.com/huggingface/peft.git
-          pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-
-      - name: Environment
-        run: |
-          python utils/print_env.py
-
-      - name: Run PyTorch CUDA tests
-        env:
-          HF_TOKEN: ${{ secrets.HF_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" \
-            --make-reports=tests_torch_minimum_cuda \
-            tests/models/test_modelling_common.py \
-            tests/pipelines/test_pipelines_common.py \
-            tests/pipelines/test_pipeline_utils.py \
-            tests/pipelines/test_pipelines.py \
-            tests/pipelines/test_pipelines_auto.py \
-            tests/schedulers/test_schedulers.py \
-            tests/others
-
-      - name: Failure short reports
-        if: ${{ failure() }}
-        run: |
-          cat reports/tests_torch_minimum_version_cuda_stats.txt
-          cat reports/tests_torch_minimum_version_cuda_failures_short.txt
-
-      - name: Test suite reports artifacts
-        if: ${{ always() }}
-        uses: actions/upload-artifact@v4
-        with:
-          name: torch_minimum_version_cuda_test_reports
-          path: reports
-          
   flax_tpu_tests:
     name: Flax TPU Tests
     runs-on: docker-tpu

docker/diffusers-pytorch-minimum-cuda/Dockerfile

@@ -1,53 +0,0 @@
-FROM nvidia/cuda:12.1.0-runtime-ubuntu20.04
-LABEL maintainer="Hugging Face"
-LABEL repository="diffusers"
-
-ENV DEBIAN_FRONTEND=noninteractive
-ENV MINIMUM_SUPPORTED_TORCH_VERSION="2.1.0"
-ENV MINIMUM_SUPPORTED_TORCHVISION_VERSION="0.16.0"
-ENV MINIMUM_SUPPORTED_TORCHAUDIO_VERSION="2.1.0"
-
-RUN apt-get -y update \
-    && apt-get install -y software-properties-common \
-    && add-apt-repository ppa:deadsnakes/ppa
-
-RUN apt install -y bash \
-    build-essential \
-    git \
-    git-lfs \
-    curl \
-    ca-certificates \
-    libsndfile1-dev \
-    libgl1 \
-    python3.10 \
-    python3.10-dev \
-    python3-pip \
-    python3.10-venv && \
-    rm -rf /var/lib/apt/lists
-
-# make sure to use venv
-RUN python3.10 -m venv /opt/venv
-ENV PATH="/opt/venv/bin:$PATH"
-
-# pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
-RUN python3.10 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
-    python3.10 -m uv pip install --no-cache-dir \
-    torch==$MINIMUM_SUPPORTED_TORCH_VERSION \
-    torchvision==$MINIMUM_SUPPORTED_TORCHVISION_VERSION \
-    torchaudio==$MINIMUM_SUPPORTED_TORCHAUDIO_VERSION \
-    invisible_watermark && \
-    python3.10 -m pip install --no-cache-dir \
-    accelerate \
-    datasets \
-    hf-doc-builder \
-    huggingface-hub \
-    hf_transfer \
-    Jinja2 \
-    librosa \
-    numpy==1.26.4 \
-    scipy \
-    tensorboard \
-    transformers \
-    hf_transfer
-
-CMD ["/bin/bash"]

docs/source/en/api/models/allegro_transformer3d.md

@@ -18,7 +18,7 @@ The model can be loaded with the following code snippet.
 ```python
 from diffusers import AllegroTransformer3DModel
 
-transformer = AllegroTransformer3DModel.from_pretrained("rhymes-ai/Allegro", subfolder="transformer", torch_dtype=torch.bfloat16).to("cuda")
+vae = AllegroTransformer3DModel.from_pretrained("rhymes-ai/Allegro", subfolder="transformer", torch_dtype=torch.bfloat16).to("cuda")
 ```
 
 ## AllegroTransformer3DModel

docs/source/en/api/models/cogvideox_transformer3d.md

@@ -18,7 +18,7 @@ The model can be loaded with the following code snippet.
 ```python
 from diffusers import CogVideoXTransformer3DModel
 
-transformer = CogVideoXTransformer3DModel.from_pretrained("THUDM/CogVideoX-2b", subfolder="transformer", torch_dtype=torch.float16).to("cuda")
+vae = CogVideoXTransformer3DModel.from_pretrained("THUDM/CogVideoX-2b", subfolder="transformer", torch_dtype=torch.float16).to("cuda")
 ```
 
 ## CogVideoXTransformer3DModel

docs/source/en/api/models/cogview3plus_transformer2d.md

@@ -18,7 +18,7 @@ The model can be loaded with the following code snippet.
 ```python
 from diffusers import CogView3PlusTransformer2DModel
 
-transformer = CogView3PlusTransformer2DModel.from_pretrained("THUDM/CogView3Plus-3b", subfolder="transformer", torch_dtype=torch.bfloat16).to("cuda")
+vae = CogView3PlusTransformer2DModel.from_pretrained("THUDM/CogView3Plus-3b", subfolder="transformer", torch_dtype=torch.bfloat16).to("cuda")
 ```
 
 ## CogView3PlusTransformer2DModel

docs/source/en/api/models/mochi_transformer3d.md

@@ -18,7 +18,7 @@ The model can be loaded with the following code snippet.
 ```python
 from diffusers import MochiTransformer3DModel
 
-transformer = MochiTransformer3DModel.from_pretrained("genmo/mochi-1-preview", subfolder="transformer", torch_dtype=torch.float16).to("cuda")
+vae = MochiTransformer3DModel.from_pretrained("genmo/mochi-1-preview", subfolder="transformer", torch_dtype=torch.float16).to("cuda")
 ```
 
 ## MochiTransformer3DModel

docs/source/en/api/pipelines/allegro.md

@@ -19,7 +19,7 @@ The abstract from the paper is:
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading.md#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/animatediff.md

@@ -803,7 +803,7 @@ FreeInit is not really free - the improved quality comes at the cost of extra co
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/attend_and_excite.md

@@ -22,7 +22,7 @@ You can find additional information about Attend-and-Excite on the [project page
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

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

@@ -37,7 +37,7 @@ During inference:
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/audioldm2.md

@@ -60,7 +60,7 @@ The following example demonstrates how to construct good music and speech genera
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/blip_diffusion.md

@@ -25,7 +25,7 @@ The original codebase can be found at [salesforce/LAVIS](https://github.com/sale
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/cogvideox.md

@@ -23,7 +23,7 @@ The abstract from the paper is:
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading.md#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/cogview3.md

@@ -23,7 +23,7 @@ The abstract from the paper is:
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading.md#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

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

@@ -26,7 +26,7 @@ The original codebase can be found at [lllyasviel/ControlNet](https://github.com
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/controlnet_flux.md

@@ -42,7 +42,7 @@ XLabs ControlNets are also supported, which was contributed by the [XLabs team](
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/controlnet_hunyuandit.md

@@ -26,7 +26,7 @@ This code is implemented by Tencent Hunyuan Team. You can find pre-trained check
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/controlnet_sd3.md

@@ -36,7 +36,7 @@ This controlnet code is mainly implemented by [The InstantX Team](https://huggin
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/controlnet_sdxl.md

@@ -32,7 +32,7 @@ If you don't see a checkpoint you're interested in, you can train your own SDXL
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/controlnetxs.md

@@ -26,7 +26,7 @@ This model was contributed by [UmerHA](https://twitter.com/UmerHAdil). ❤️
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/controlnetxs_sdxl.md

@@ -32,7 +32,7 @@ This model was contributed by [UmerHA](https://twitter.com/UmerHAdil). ❤️
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/dance_diffusion.md

@@ -19,7 +19,7 @@ Dance Diffusion is the first in a suite of generative audio tools for producers
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/ddpm.md

@@ -22,7 +22,7 @@ The original codebase can be found at [hohonathanho/diffusion](https://github.co
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/dit.md

@@ -22,7 +22,7 @@ The original codebase can be found at [facebookresearch/dit](https://github.com/
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/flux.md

@@ -305,10 +305,6 @@ image = control_pipe(
 image.save("output.png")
 ```
 
-## Note about `unload_lora_weights()` when using Flux LoRAs
-
-When unloading the Control LoRA weights, call `pipe.unload_lora_weights(reset_to_overwritten_params=True)` to reset the `pipe.transformer` completely back to its original form. The resultant pipeline can then be used with methods like [`DiffusionPipeline.from_pipe`]. More details about this argument are available in [this PR](https://github.com/huggingface/diffusers/pull/10397).
-
 ## Running FP16 inference
 
 Flux can generate high-quality images with FP16 (i.e. to accelerate inference on Turing/Volta GPUs) but produces different outputs compared to FP32/BF16. The issue is that some activations in the text encoders have to be clipped when running in FP16, which affects the overall image. Forcing text encoders to run with FP32 inference thus removes this output difference. See [here](https://github.com/huggingface/diffusers/pull/9097#issuecomment-2272292516) for details.

docs/source/en/api/pipelines/hunyuan_video.md

@@ -20,7 +20,7 @@
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](https://huggingface.co/docs/diffusers/main/en/using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/hunyuandit.md

@@ -30,7 +30,7 @@ HunyuanDiT has the following components:
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](https://huggingface.co/docs/diffusers/main/en/using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/i2vgenxl.md

@@ -22,7 +22,7 @@ The original codebase can be found [here](https://github.com/ali-vilab/i2vgen-xl
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines. Also, to know more about reducing the memory usage of this pipeline, refer to the ["Reduce memory usage"] section [here](../../using-diffusers/svd#reduce-memory-usage).
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines. Also, to know more about reducing the memory usage of this pipeline, refer to the ["Reduce memory usage"] section [here](../../using-diffusers/svd#reduce-memory-usage).
 
 </Tip>
 

docs/source/en/api/pipelines/kandinsky.md

@@ -25,7 +25,7 @@ Check out the [Kandinsky Community](https://huggingface.co/kandinsky-community)
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/kandinsky3.md

@@ -32,7 +32,7 @@ Check out the [Kandinsky Community](https://huggingface.co/kandinsky-community)
 
 <Tip>
 
-Make sure to check out the schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/kandinsky_v22.md

@@ -25,7 +25,7 @@ Check out the [Kandinsky Community](https://huggingface.co/kandinsky-community)
 
 <Tip>
 
-Make sure to check out the schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/latent_diffusion.md

@@ -22,7 +22,7 @@ The original codebase can be found at [CompVis/latent-diffusion](https://github.
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/latte.md

@@ -28,7 +28,7 @@ This pipeline was contributed by [maxin-cn](https://github.com/maxin-cn). The or
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading.md#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/ltx_video.md

@@ -18,7 +18,7 @@
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading.md#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/lumina.md

@@ -47,7 +47,7 @@ This pipeline was contributed by [PommesPeter](https://github.com/PommesPeter).
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading.md#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/marigold.md

@@ -43,7 +43,7 @@ The original checkpoints can be found under the [PRS-ETH](https://huggingface.co
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines. Also, to know more about reducing the memory usage of this pipeline, refer to the ["Reduce memory usage"] section [here](../../using-diffusers/svd#reduce-memory-usage).
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines. Also, to know more about reducing the memory usage of this pipeline, refer to the ["Reduce memory usage"] section [here](../../using-diffusers/svd#reduce-memory-usage).
 
 </Tip>
 

docs/source/en/api/pipelines/musicldm.md

@@ -42,7 +42,7 @@ During inference:
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/paint_by_example.md

@@ -26,7 +26,7 @@ Paint by Example is supported by the official [Fantasy-Studio/Paint-by-Example](
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/panorama.md

@@ -37,7 +37,7 @@ But with circular padding, the right and the left parts are matching (`circular_
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/pix2pix.md

@@ -22,7 +22,7 @@ You can find additional information about InstructPix2Pix on the [project page](
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/pixart.md

@@ -31,7 +31,7 @@ Some notes about this pipeline:
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading.md#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/sana.md

@@ -22,7 +22,7 @@ The abstract from the paper is:
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading.md#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/self_attention_guidance.md

@@ -22,7 +22,7 @@ You can find additional information about Self-Attention Guidance on the [projec
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

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

@@ -21,7 +21,7 @@ The abstract from the paper is:
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/shap_e.md

@@ -19,7 +19,7 @@ The original codebase can be found at [openai/shap-e](https://github.com/openai/
 
 <Tip>
 
-See the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+See the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

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

@@ -97,7 +97,7 @@ image
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/text_to_video.md

@@ -175,7 +175,7 @@ Check out the [Text or image-to-video](text-img2vid) guide for more details abou
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

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

@@ -284,7 +284,7 @@ You can filter out some available DreamBooth-trained models with [this link](htt
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/unclip.md

@@ -19,7 +19,7 @@ You can find lucidrains' DALL-E 2 recreation at [lucidrains/DALLE2-pytorch](http
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/unidiffuser.md

@@ -192,7 +192,7 @@ print(final_prompt)
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/value_guided_sampling.md

@@ -30,7 +30,7 @@ The script to run the model is available [here](https://github.com/huggingface/d
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/tutorials/using_peft_for_inference.md

@@ -56,7 +56,7 @@ image
 
 With the `adapter_name` parameter, it is really easy to use another adapter for inference! Load the [nerijs/pixel-art-xl](https://huggingface.co/nerijs/pixel-art-xl) adapter that has been fine-tuned to generate pixel art images and call it `"pixel"`.
 
-The pipeline automatically sets the first loaded adapter (`"toy"`) as the active adapter, but you can activate the `"pixel"` adapter with the [`~loaders.peft.PeftAdapterMixin.set_adapters`] method:
+The pipeline automatically sets the first loaded adapter (`"toy"`) as the active adapter, but you can activate the `"pixel"` adapter with the [`~PeftAdapterMixin.set_adapters`] method:
 
 ```python
 pipe.load_lora_weights("nerijs/pixel-art-xl", weight_name="pixel-art-xl.safetensors", adapter_name="pixel")
@@ -85,7 +85,7 @@ By default, if the most up-to-date versions of PEFT and Transformers are detecte
 
 You can also merge different adapter checkpoints for inference to blend their styles together.
 
-Once again, use the [`~loaders.peft.PeftAdapterMixin.set_adapters`] method to activate the `pixel` and `toy` adapters and specify the weights for how they should be merged.
+Once again, use the [`~PeftAdapterMixin.set_adapters`] method to activate the `pixel` and `toy` adapters and specify the weights for how they should be merged.
 
 ```python
 pipe.set_adapters(["pixel", "toy"], adapter_weights=[0.5, 1.0])
@@ -114,7 +114,7 @@ Impressive! As you can see, the model generated an image that mixed the characte
 > [!TIP]
 > Through its PEFT integration, Diffusers also offers more efficient merging methods which you can learn about in the [Merge LoRAs](../using-diffusers/merge_loras) guide!
 
-To return to only using one adapter, use the [`~loaders.peft.PeftAdapterMixin.set_adapters`] method to activate the `"toy"` adapter:
+To return to only using one adapter, use the [`~PeftAdapterMixin.set_adapters`] method to activate the `"toy"` adapter:
 
 ```python
 pipe.set_adapters("toy")
@@ -127,7 +127,7 @@ image = pipe(
 image
 ```
 
-Or to disable all adapters entirely, use the [`~loaders.peft.PeftAdapterMixin.disable_lora`] method to return the base model.
+Or to disable all adapters entirely, use the [`~PeftAdapterMixin.disable_lora`] method to return the base model.
 
 ```python
 pipe.disable_lora()
@@ -141,7 +141,7 @@ image
 
 ### Customize adapters strength
 
-For even more customization, you can control how strongly the adapter affects each part of the pipeline. For this, pass a dictionary with the control strengths (called "scales") to [`~loaders.peft.PeftAdapterMixin.set_adapters`].
+For even more customization, you can control how strongly the adapter affects each part of the pipeline. For this, pass a dictionary with the control strengths (called "scales") to [`~PeftAdapterMixin.set_adapters`].
 
 For example, here's how you can turn on the adapter for the `down` parts, but turn it off for the `mid` and `up` parts:
 ```python
@@ -214,7 +214,7 @@ list_adapters_component_wise
 {"text_encoder": ["toy", "pixel"], "unet": ["toy", "pixel"], "text_encoder_2": ["toy", "pixel"]}
 ```
 
-The [`~loaders.peft.PeftAdapterMixin.delete_adapters`] function completely removes an adapter and their LoRA layers from a model.
+The [`~PeftAdapterMixin.delete_adapters`] function completely removes an adapter and their LoRA layers from a model.
 
 ```py
 pipe.delete_adapters("toy")

examples/advanced_diffusion_training/train_dreambooth_lora_sd15_advanced.py

@@ -160,7 +160,7 @@ to trigger concept `{key}` → use `{tokens}` in your prompt \n
 from diffusers import AutoPipelineForText2Image
 import torch
 {diffusers_imports_pivotal}
-pipeline = AutoPipelineForText2Image.from_pretrained('stable-diffusion-v1-5/stable-diffusion-v1-5', torch_dtype=torch.float16).to('cuda')
+pipeline = AutoPipelineForText2Image.from_pretrained('runwayml/stable-diffusion-v1-5', torch_dtype=torch.float16).to('cuda')
 pipeline.load_lora_weights('{repo_id}', weight_name='pytorch_lora_weights.safetensors')
 {diffusers_example_pivotal}
 image = pipeline('{validation_prompt if validation_prompt else instance_prompt}').images[0]

examples/community/rerender_a_video.py

@@ -30,17 +30,10 @@ from diffusers.pipelines.controlnet.multicontrolnet import MultiControlNetModel
 from diffusers.pipelines.controlnet.pipeline_controlnet_img2img import StableDiffusionControlNetImg2ImgPipeline
 from diffusers.pipelines.stable_diffusion.safety_checker import StableDiffusionSafetyChecker
 from diffusers.schedulers import KarrasDiffusionSchedulers
-from diffusers.utils import BaseOutput, deprecate, is_torch_xla_available, logging
+from diffusers.utils import BaseOutput, deprecate, logging
 from diffusers.utils.torch_utils import is_compiled_module, randn_tensor
 
 
-if is_torch_xla_available():
-    import torch_xla.core.xla_model as xm
-
-    XLA_AVAILABLE = True
-else:
-    XLA_AVAILABLE = False
-
 logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
 
 
@@ -782,7 +775,7 @@ class RerenderAVideoPipeline(StableDiffusionControlNetImg2ImgPipeline):
         self.attn_state.reset()
 
         # 4.1 prepare frames
-        image = self.image_processor.preprocess(frames[0]).to(dtype=self.dtype)
+        image = self.image_processor.preprocess(frames[0]).to(dtype=torch.float32)
         first_image = image[0]  # C, H, W
 
         # 4.2 Prepare controlnet_conditioning_image
@@ -926,8 +919,8 @@ class RerenderAVideoPipeline(StableDiffusionControlNetImg2ImgPipeline):
             prev_image = frames[idx - 1]
             control_image = control_frames[idx]
             # 5.1 prepare frames
-            image = self.image_processor.preprocess(image).to(dtype=self.dtype)
-            prev_image = self.image_processor.preprocess(prev_image).to(dtype=self.dtype)
+            image = self.image_processor.preprocess(image).to(dtype=torch.float32)
+            prev_image = self.image_processor.preprocess(prev_image).to(dtype=torch.float32)
 
             warped_0, bwd_occ_0, bwd_flow_0 = get_warped_and_mask(
                 self.flow_model, first_image, image[0], first_result, False, self.device
@@ -1107,9 +1100,6 @@ class RerenderAVideoPipeline(StableDiffusionControlNetImg2ImgPipeline):
                             if callback is not None and i % callback_steps == 0:
                                 callback(i, t, latents)
 
-                        if XLA_AVAILABLE:
-                            xm.mark_step()
-
                     return latents
 
             if mask_start_t <= mask_end_t:

examples/text_to_image/train_text_to_image_sdxl.py

@@ -919,7 +919,7 @@ def main(args):
         # fingerprint used by the cache for the other processes to load the result
         # details: https://github.com/huggingface/diffusers/pull/4038#discussion_r1266078401
         new_fingerprint = Hasher.hash(args)
-        new_fingerprint_for_vae = Hasher.hash((vae_path, args))
+        new_fingerprint_for_vae = Hasher.hash(vae_path)
         train_dataset_with_embeddings = train_dataset.map(
             compute_embeddings_fn, batched=True, new_fingerprint=new_fingerprint
         )

scripts/convert_blipdiffusion_to_diffusers.py

@@ -303,11 +303,10 @@ def save_blip_diffusion_model(model, args):
     qformer = get_qformer(model)
     qformer.eval()
 
-    text_encoder = ContextCLIPTextModel.from_pretrained(
-        "stable-diffusion-v1-5/stable-diffusion-v1-5", subfolder="text_encoder"
-    )
-    vae = AutoencoderKL.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", subfolder="vae")
-    unet = UNet2DConditionModel.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", subfolder="unet")
+    text_encoder = ContextCLIPTextModel.from_pretrained("runwayml/stable-diffusion-v1-5", subfolder="text_encoder")
+    vae = AutoencoderKL.from_pretrained("runwayml/stable-diffusion-v1-5", subfolder="vae")
+
+    unet = UNet2DConditionModel.from_pretrained("runwayml/stable-diffusion-v1-5", subfolder="unet")
     vae.eval()
     text_encoder.eval()
     scheduler = PNDMScheduler(
@@ -317,7 +316,7 @@ def save_blip_diffusion_model(model, args):
         set_alpha_to_one=False,
         skip_prk_steps=True,
     )
-    tokenizer = CLIPTokenizer.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", subfolder="tokenizer")
+    tokenizer = CLIPTokenizer.from_pretrained("runwayml/stable-diffusion-v1-5", subfolder="tokenizer")
     image_processor = BlipImageProcessor()
     blip_diffusion = BlipDiffusionPipeline(
         tokenizer=tokenizer,

src/diffusers/loaders/lora_pipeline.py

@@ -2277,24 +2277,8 @@ class FluxLoraLoaderMixin(LoraBaseMixin):
 
         super().unfuse_lora(components=components)
 
-    # We override this here account for `_transformer_norm_layers` and `_overwritten_params`.
-    def unload_lora_weights(self, reset_to_overwritten_params=False):
-        """
-        Unloads the LoRA parameters.
-
-        Args:
-            reset_to_overwritten_params (`bool`, defaults to `False`): Whether to reset the LoRA-loaded modules
-                to their original params. Refer to the [Flux
-                documentation](https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux) to learn more.
-
-        Examples:
-
-        ```python
-        >>> # Assuming `pipeline` is already loaded with the LoRA parameters.
-        >>> pipeline.unload_lora_weights()
-        >>> ...
-        ```
-        """
+    # We override this here account for `_transformer_norm_layers`.
+    def unload_lora_weights(self):
         super().unload_lora_weights()
 
         transformer = getattr(self, self.transformer_name) if not hasattr(self, "transformer") else self.transformer
@@ -2302,7 +2286,7 @@ class FluxLoraLoaderMixin(LoraBaseMixin):
             transformer.load_state_dict(transformer._transformer_norm_layers, strict=False)
             transformer._transformer_norm_layers = None
 
-        if reset_to_overwritten_params and getattr(transformer, "_overwritten_params", None) is not None:
+        if getattr(transformer, "_overwritten_params", None) is not None:
             overwritten_params = transformer._overwritten_params
             module_names = set()
 
@@ -2482,9 +2466,7 @@ class FluxLoraLoaderMixin(LoraBaseMixin):
                 continue
 
             base_param_name = (
-                f"{k.replace(prefix, '')}.base_layer.weight"
-                if is_peft_loaded and f"{k.replace(prefix, '')}.base_layer.weight" in transformer_state_dict
-                else f"{k.replace(prefix, '')}.weight"
+                f"{k.replace(prefix, '')}.base_layer.weight" if is_peft_loaded else f"{k.replace(prefix, '')}.weight"
             )
             base_weight_param = transformer_state_dict[base_param_name]
             lora_A_param = lora_state_dict[f"{prefix}{k}.lora_A.weight"]

src/diffusers/loaders/single_file.py

@@ -329,7 +329,7 @@ class FromSingleFileMixin:
 
         >>> # Enable float16 and move to GPU
         >>> pipeline = StableDiffusionPipeline.from_single_file(
-        ...     "https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5/blob/main/v1-5-pruned-emaonly.ckpt",
+        ...     "https://huggingface.co/runwayml/stable-diffusion-v1-5/blob/main/v1-5-pruned-emaonly.ckpt",
         ...     torch_dtype=torch.float16,
         ... )
         >>> pipeline.to("cuda")

src/diffusers/loaders/single_file_utils.py

@@ -109,7 +109,6 @@ CHECKPOINT_KEY_NAMES = {
     "autoencoder-dc-sana": "encoder.project_in.conv.bias",
     "mochi-1-preview": ["model.diffusion_model.blocks.0.attn.qkv_x.weight", "blocks.0.attn.qkv_x.weight"],
     "hunyuan-video": "txt_in.individual_token_refiner.blocks.0.adaLN_modulation.1.bias",
-    "instruct-pix2pix": "model.diffusion_model.input_blocks.0.0.weight",
 }
 
 DIFFUSERS_DEFAULT_PIPELINE_PATHS = {
@@ -166,7 +165,6 @@ DIFFUSERS_DEFAULT_PIPELINE_PATHS = {
     "autoencoder-dc-f32c32-sana": {"pretrained_model_name_or_path": "mit-han-lab/dc-ae-f32c32-sana-1.0-diffusers"},
     "mochi-1-preview": {"pretrained_model_name_or_path": "genmo/mochi-1-preview"},
     "hunyuan-video": {"pretrained_model_name_or_path": "hunyuanvideo-community/HunyuanVideo"},
-    "instruct-pix2pix": {"pretrained_model_name_or_path": "timbrooks/instruct-pix2pix"},
 }
 
 # Use to configure model sample size when original config is provided
@@ -635,12 +633,6 @@ def infer_diffusers_model_type(checkpoint):
     elif CHECKPOINT_KEY_NAMES["hunyuan-video"] in checkpoint:
         model_type = "hunyuan-video"
 
-    elif (
-        CHECKPOINT_KEY_NAMES["instruct-pix2pix"] in checkpoint
-        and checkpoint[CHECKPOINT_KEY_NAMES["instruct-pix2pix"]].shape[1] == 8
-    ):
-        model_type = "instruct-pix2pix"
-
     else:
         model_type = "v1"
 

src/diffusers/loaders/textual_inversion.py

@@ -333,7 +333,7 @@ class TextualInversionLoaderMixin:
         from diffusers import StableDiffusionPipeline
         import torch
 
-        model_id = "stable-diffusion-v1-5/stable-diffusion-v1-5"
+        model_id = "runwayml/stable-diffusion-v1-5"
         pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16).to("cuda")
 
         pipe.load_textual_inversion("sd-concepts-library/cat-toy")
@@ -352,7 +352,7 @@ class TextualInversionLoaderMixin:
         from diffusers import StableDiffusionPipeline
         import torch
 
-        model_id = "stable-diffusion-v1-5/stable-diffusion-v1-5"
+        model_id = "runwayml/stable-diffusion-v1-5"
         pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16).to("cuda")
 
         pipe.load_textual_inversion("./charturnerv2.pt", token="charturnerv2")
@@ -469,7 +469,7 @@ class TextualInversionLoaderMixin:
         from diffusers import AutoPipelineForText2Image
         import torch
 
-        pipeline = AutoPipelineForText2Image.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5")
+        pipeline = AutoPipelineForText2Image.from_pretrained("runwayml/stable-diffusion-v1-5")
 
         # Example 1
         pipeline.load_textual_inversion("sd-concepts-library/gta5-artwork")

src/diffusers/loaders/unet.py

@@ -343,17 +343,6 @@ class UNet2DConditionLoadersMixin:
                 else:
                     if is_peft_version("<", "0.9.0"):
                         lora_config_kwargs.pop("use_dora")
-
-            if "lora_bias" in lora_config_kwargs:
-                if lora_config_kwargs["lora_bias"]:
-                    if is_peft_version("<=", "0.13.2"):
-                        raise ValueError(
-                            "You need `peft` 0.14.0 at least to use `bias` in LoRAs. Please upgrade your installation of `peft`."
-                        )
-                else:
-                    if is_peft_version("<=", "0.13.2"):
-                        lora_config_kwargs.pop("lora_bias")
-
             lora_config = LoraConfig(**lora_config_kwargs)
 
             # adapter_name

src/diffusers/models/autoencoders/consistency_decoder_vae.py

@@ -60,7 +60,7 @@ class ConsistencyDecoderVAE(ModelMixin, ConfigMixin):
 
         >>> vae = ConsistencyDecoderVAE.from_pretrained("openai/consistency-decoder", torch_dtype=torch.float16)
         >>> pipe = StableDiffusionPipeline.from_pretrained(
-        ...     "stable-diffusion-v1-5/stable-diffusion-v1-5", vae=vae, torch_dtype=torch.float16
+        ...     "runwayml/stable-diffusion-v1-5", vae=vae, torch_dtype=torch.float16
         ... ).to("cuda")
 
         >>> image = pipe("horse", generator=torch.manual_seed(0)).images[0]

src/diffusers/models/embeddings.py

@@ -1248,8 +1248,7 @@ class FluxPosEmbed(nn.Module):
         sin_out = []
         pos = ids.float()
         is_mps = ids.device.type == "mps"
-        is_npu = ids.device.type == "npu"
-        freqs_dtype = torch.float32 if (is_mps or is_npu) else torch.float64
+        freqs_dtype = torch.float32 if is_mps else torch.float64
         for i in range(n_axes):
             cos, sin = get_1d_rotary_pos_embed(
                 self.axes_dim[i],

src/diffusers/models/hooks.py

@@ -0,0 +1,227 @@
+# Copyright 2024 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.
+
+import functools
+from typing import Any, Dict, Tuple
+
+import torch
+
+
+# Reference: https://github.com/huggingface/accelerate/blob/ba7ab93f5e688466ea56908ea3b056fae2f9a023/src/accelerate/hooks.py
+class ModelHook:
+    r"""
+    A hook that contains callbacks to be executed just before and after the forward method of a model.
+    """
+
+    _is_stateful = False
+
+    def init_hook(self, module: torch.nn.Module) -> torch.nn.Module:
+        r"""
+        Hook that is executed when a model is initialized.
+
+        Args:
+            module (`torch.nn.Module`):
+                The module attached to this hook.
+        """
+        return module
+
+    def pre_forward(self, module: torch.nn.Module, *args, **kwargs) -> Tuple[Tuple[Any], Dict[str, Any]]:
+        r"""
+        Hook that is executed just before the forward method of the model.
+
+        Args:
+            module (`torch.nn.Module`):
+                The module whose forward pass will be executed just after this event.
+            args (`Tuple[Any]`):
+                The positional arguments passed to the module.
+            kwargs (`Dict[Str, Any]`):
+                The keyword arguments passed to the module.
+        Returns:
+            `Tuple[Tuple[Any], Dict[Str, Any]]`:
+                A tuple with the treated `args` and `kwargs`.
+        """
+        return args, kwargs
+
+    def post_forward(self, module: torch.nn.Module, output: Any) -> Any:
+        r"""
+        Hook that is executed just after the forward method of the model.
+
+        Args:
+            module (`torch.nn.Module`):
+                The module whose forward pass been executed just before this event.
+            output (`Any`):
+                The output of the module.
+        Returns:
+            `Any`: The processed `output`.
+        """
+        return output
+
+    def detach_hook(self, module: torch.nn.Module) -> torch.nn.Module:
+        r"""
+        Hook that is executed when the hook is detached from a module.
+
+        Args:
+            module (`torch.nn.Module`):
+                The module detached from this hook.
+        """
+        return module
+
+    def reset_state(self, module: torch.nn.Module) -> torch.nn.Module:
+        if self._is_stateful:
+            raise NotImplementedError("This hook is stateful and needs to implement the `reset_state` method.")
+        return module
+
+
+class SequentialHook(ModelHook):
+    r"""A hook that can contain several hooks and iterates through them at each event."""
+
+    def __init__(self, *hooks):
+        self.hooks = hooks
+
+    def init_hook(self, module):
+        for hook in self.hooks:
+            module = hook.init_hook(module)
+        return module
+
+    def pre_forward(self, module, *args, **kwargs):
+        for hook in self.hooks:
+            args, kwargs = hook.pre_forward(module, *args, **kwargs)
+        return args, kwargs
+
+    def post_forward(self, module, output):
+        for hook in self.hooks:
+            output = hook.post_forward(module, output)
+        return output
+
+    def detach_hook(self, module):
+        for hook in self.hooks:
+            module = hook.detach_hook(module)
+        return module
+
+    def reset_state(self, module):
+        for hook in self.hooks:
+            if hook._is_stateful:
+                hook.reset_state(module)
+        return module
+
+
+def add_hook_to_module(module: torch.nn.Module, hook: ModelHook, append: bool = False) -> torch.nn.Module:
+    r"""
+    Adds a hook to a given module. This will rewrite the `forward` method of the module to include the hook, to remove
+    this behavior and restore the original `forward` method, use `remove_hook_from_module`.
+
+    <Tip warning={true}>
+
+    If the module already contains a hook, this will replace it with the new hook passed by default. To chain two hooks
+    together, pass `append=True`, so it chains the current and new hook into an instance of the `SequentialHook` class.
+
+    </Tip>
+
+    Args:
+        module (`torch.nn.Module`):
+            The module to attach a hook to.
+        hook (`ModelHook`):
+            The hook to attach.
+        append (`bool`, *optional*, defaults to `False`):
+            Whether the hook should be chained with an existing one (if module already contains a hook) or not.
+    Returns:
+        `torch.nn.Module`:
+            The same module, with the hook attached (the module is modified in place, so the result can be discarded).
+    """
+    original_hook = hook
+
+    if append and getattr(module, "_diffusers_hook", None) is not None:
+        old_hook = module._diffusers_hook
+        remove_hook_from_module(module)
+        hook = SequentialHook(old_hook, hook)
+
+    if hasattr(module, "_diffusers_hook") and hasattr(module, "_old_forward"):
+        # If we already put some hook on this module, we replace it with the new one.
+        old_forward = module._old_forward
+    else:
+        old_forward = module.forward
+        module._old_forward = old_forward
+
+    module = hook.init_hook(module)
+    module._diffusers_hook = hook
+
+    if hasattr(original_hook, "new_forward"):
+        new_forward = original_hook.new_forward
+    else:
+
+        def new_forward(module, *args, **kwargs):
+            args, kwargs = module._diffusers_hook.pre_forward(module, *args, **kwargs)
+            output = module._old_forward(*args, **kwargs)
+            return module._diffusers_hook.post_forward(module, output)
+
+    # Overriding a GraphModuleImpl forward freezes the forward call and later modifications on the graph will fail.
+    # Reference: https://pytorch.slack.com/archives/C3PDTEV8E/p1705929610405409
+    if "GraphModuleImpl" in str(type(module)):
+        module.__class__.forward = functools.update_wrapper(functools.partial(new_forward, module), old_forward)
+    else:
+        module.forward = functools.update_wrapper(functools.partial(new_forward, module), old_forward)
+
+    return module
+
+
+def remove_hook_from_module(module: torch.nn.Module, recurse: bool = False) -> torch.nn.Module:
+    """
+    Removes any hook attached to a module via `add_hook_to_module`.
+
+    Args:
+        module (`torch.nn.Module`):
+            The module to attach a hook to.
+        recurse (`bool`, defaults to `False`):
+            Whether to remove the hooks recursively
+    Returns:
+        `torch.nn.Module`:
+            The same module, with the hook detached (the module is modified in place, so the result can be discarded).
+    """
+
+    if hasattr(module, "_diffusers_hook"):
+        module._diffusers_hook.detach_hook(module)
+        delattr(module, "_diffusers_hook")
+
+    if hasattr(module, "_old_forward"):
+        # Overriding a GraphModuleImpl forward freezes the forward call and later modifications on the graph will fail.
+        # Reference: https://pytorch.slack.com/archives/C3PDTEV8E/p1705929610405409
+        if "GraphModuleImpl" in str(type(module)):
+            module.__class__.forward = module._old_forward
+        else:
+            module.forward = module._old_forward
+        delattr(module, "_old_forward")
+
+    if recurse:
+        for child in module.children():
+            remove_hook_from_module(child, recurse)
+
+    return module
+
+
+def reset_stateful_hooks(module: torch.nn.Module, recurse: bool = False):
+    """
+    Resets the state of all stateful hooks attached to a module.
+
+    Args:
+        module (`torch.nn.Module`):
+            The module to reset the stateful hooks from.
+    """
+    if hasattr(module, "_diffusers_hook") and (
+        module._diffusers_hook._is_stateful or isinstance(module._diffusers_hook, SequentialHook)
+    ):
+        module._diffusers_hook.reset_state(module)
+
+    if recurse:
+        for child in module.children():
+            reset_stateful_hooks(child, recurse)

src/diffusers/models/transformers/sana_transformer.py

@@ -250,6 +250,7 @@ class SanaTransformer2DModel(ModelMixin, ConfigMixin, PeftAdapterMixin):
         inner_dim = num_attention_heads * attention_head_dim
 
         # 1. Patch Embedding
+        interpolation_scale = interpolation_scale if interpolation_scale is not None else max(sample_size // 64, 1)
         self.patch_embed = PatchEmbed(
             height=sample_size,
             width=sample_size,
@@ -257,7 +258,6 @@ class SanaTransformer2DModel(ModelMixin, ConfigMixin, PeftAdapterMixin):
             in_channels=in_channels,
             embed_dim=inner_dim,
             interpolation_scale=interpolation_scale,
-            pos_embed_type="sincos" if interpolation_scale is not None else None,
         )
 
         # 2. Additional condition embeddings

src/diffusers/models/transformers/transformer_flux.py

@@ -85,11 +85,11 @@ class FluxSingleTransformerBlock(nn.Module):
 
     def forward(
         self,
-        hidden_states: torch.Tensor,
-        temb: torch.Tensor,
-        image_rotary_emb: Optional[Tuple[torch.Tensor, torch.Tensor]] = None,
-        joint_attention_kwargs: Optional[Dict[str, Any]] = None,
-    ) -> torch.Tensor:
+        hidden_states: torch.FloatTensor,
+        temb: torch.FloatTensor,
+        image_rotary_emb=None,
+        joint_attention_kwargs=None,
+    ):
         residual = hidden_states
         norm_hidden_states, gate = self.norm(hidden_states, emb=temb)
         mlp_hidden_states = self.act_mlp(self.proj_mlp(norm_hidden_states))
@@ -117,22 +117,15 @@ class FluxTransformerBlock(nn.Module):
 
     Reference: https://arxiv.org/abs/2403.03206
 
-    Args:
-        dim (`int`):
-            The embedding dimension of the block.
-        num_attention_heads (`int`):
-            The number of attention heads to use.
-        attention_head_dim (`int`):
-            The number of dimensions to use for each attention head.
-        qk_norm (`str`, defaults to `"rms_norm"`):
-            The normalization to use for the query and key tensors.
-        eps (`float`, defaults to `1e-6`):
-            The epsilon value to use for the normalization.
+    Parameters:
+        dim (`int`): The number of channels in the input and output.
+        num_attention_heads (`int`): The number of heads to use for multi-head attention.
+        attention_head_dim (`int`): The number of channels in each head.
+        context_pre_only (`bool`): Boolean to determine if we should add some blocks associated with the
+            processing of `context` conditions.
     """
 
-    def __init__(
-        self, dim: int, num_attention_heads: int, attention_head_dim: int, qk_norm: str = "rms_norm", eps: float = 1e-6
-    ):
+    def __init__(self, dim, num_attention_heads, attention_head_dim, qk_norm="rms_norm", eps=1e-6):
         super().__init__()
 
         self.norm1 = AdaLayerNormZero(dim)
@@ -171,12 +164,12 @@ class FluxTransformerBlock(nn.Module):
 
     def forward(
         self,
-        hidden_states: torch.Tensor,
-        encoder_hidden_states: torch.Tensor,
-        temb: torch.Tensor,
-        image_rotary_emb: Optional[Tuple[torch.Tensor, torch.Tensor]] = None,
-        joint_attention_kwargs: Optional[Dict[str, Any]] = None,
-    ) -> Tuple[torch.Tensor, torch.Tensor]:
+        hidden_states: torch.FloatTensor,
+        encoder_hidden_states: torch.FloatTensor,
+        temb: torch.FloatTensor,
+        image_rotary_emb=None,
+        joint_attention_kwargs=None,
+    ):
         norm_hidden_states, gate_msa, shift_mlp, scale_mlp, gate_mlp = self.norm1(hidden_states, emb=temb)
 
         norm_encoder_hidden_states, c_gate_msa, c_shift_mlp, c_scale_mlp, c_gate_mlp = self.norm1_context(
@@ -234,30 +227,16 @@ class FluxTransformer2DModel(
 
     Reference: https://blackforestlabs.ai/announcing-black-forest-labs/
 
-    Args:
-        patch_size (`int`, defaults to `1`):
-            Patch size to turn the input data into small patches.
-        in_channels (`int`, defaults to `64`):
-            The number of channels in the input.
-        out_channels (`int`, *optional*, defaults to `None`):
-            The number of channels in the output. If not specified, it defaults to `in_channels`.
-        num_layers (`int`, defaults to `19`):
-            The number of layers of dual stream DiT blocks to use.
-        num_single_layers (`int`, defaults to `38`):
-            The number of layers of single stream DiT blocks to use.
-        attention_head_dim (`int`, defaults to `128`):
-            The number of dimensions to use for each attention head.
-        num_attention_heads (`int`, defaults to `24`):
-            The number of attention heads to use.
-        joint_attention_dim (`int`, defaults to `4096`):
-            The number of dimensions to use for the joint attention (embedding/channel dimension of
-            `encoder_hidden_states`).
-        pooled_projection_dim (`int`, defaults to `768`):
-            The number of dimensions to use for the pooled projection.
-        guidance_embeds (`bool`, defaults to `False`):
-            Whether to use guidance embeddings for guidance-distilled variant of the model.
-        axes_dims_rope (`Tuple[int]`, defaults to `(16, 56, 56)`):
-            The dimensions to use for the rotary positional embeddings.
+    Parameters:
+        patch_size (`int`): Patch size to turn the input data into small patches.
+        in_channels (`int`, *optional*, defaults to 16): The number of channels in the input.
+        num_layers (`int`, *optional*, defaults to 18): The number of layers of MMDiT blocks to use.
+        num_single_layers (`int`, *optional*, defaults to 18): The number of layers of single DiT blocks to use.
+        attention_head_dim (`int`, *optional*, defaults to 64): The number of channels in each head.
+        num_attention_heads (`int`, *optional*, defaults to 18): The number of heads to use for multi-head attention.
+        joint_attention_dim (`int`, *optional*): The number of `encoder_hidden_states` dimensions to use.
+        pooled_projection_dim (`int`): Number of dimensions to use when projecting the `pooled_projections`.
+        guidance_embeds (`bool`, defaults to False): Whether to use guidance embeddings.
     """
 
     _supports_gradient_checkpointing = True
@@ -280,7 +259,7 @@ class FluxTransformer2DModel(
     ):
         super().__init__()
         self.out_channels = out_channels or in_channels
-        self.inner_dim = num_attention_heads * attention_head_dim
+        self.inner_dim = self.config.num_attention_heads * self.config.attention_head_dim
 
         self.pos_embed = FluxPosEmbed(theta=10000, axes_dim=axes_dims_rope)
 
@@ -288,20 +267,20 @@ class FluxTransformer2DModel(
             CombinedTimestepGuidanceTextProjEmbeddings if guidance_embeds else CombinedTimestepTextProjEmbeddings
         )
         self.time_text_embed = text_time_guidance_cls(
-            embedding_dim=self.inner_dim, pooled_projection_dim=pooled_projection_dim
+            embedding_dim=self.inner_dim, pooled_projection_dim=self.config.pooled_projection_dim
         )
 
-        self.context_embedder = nn.Linear(joint_attention_dim, self.inner_dim)
-        self.x_embedder = nn.Linear(in_channels, self.inner_dim)
+        self.context_embedder = nn.Linear(self.config.joint_attention_dim, self.inner_dim)
+        self.x_embedder = nn.Linear(self.config.in_channels, self.inner_dim)
 
         self.transformer_blocks = nn.ModuleList(
             [
                 FluxTransformerBlock(
                     dim=self.inner_dim,
-                    num_attention_heads=num_attention_heads,
-                    attention_head_dim=attention_head_dim,
+                    num_attention_heads=self.config.num_attention_heads,
+                    attention_head_dim=self.config.attention_head_dim,
                 )
-                for _ in range(num_layers)
+                for i in range(self.config.num_layers)
             ]
         )
 
@@ -309,10 +288,10 @@ class FluxTransformer2DModel(
             [
                 FluxSingleTransformerBlock(
                     dim=self.inner_dim,
-                    num_attention_heads=num_attention_heads,
-                    attention_head_dim=attention_head_dim,
+                    num_attention_heads=self.config.num_attention_heads,
+                    attention_head_dim=self.config.attention_head_dim,
                 )
-                for _ in range(num_single_layers)
+                for i in range(self.config.num_single_layers)
             ]
         )
 
@@ -439,16 +418,16 @@ class FluxTransformer2DModel(
         controlnet_single_block_samples=None,
         return_dict: bool = True,
         controlnet_blocks_repeat: bool = False,
-    ) -> Union[torch.Tensor, Transformer2DModelOutput]:
+    ) -> Union[torch.FloatTensor, Transformer2DModelOutput]:
         """
         The [`FluxTransformer2DModel`] forward method.
 
         Args:
-            hidden_states (`torch.Tensor` of shape `(batch_size, image_sequence_length, in_channels)`):
+            hidden_states (`torch.FloatTensor` of shape `(batch size, channel, height, width)`):
                 Input `hidden_states`.
-            encoder_hidden_states (`torch.Tensor` of shape `(batch_size, text_sequence_length, joint_attention_dim)`):
+            encoder_hidden_states (`torch.FloatTensor` of shape `(batch size, sequence_len, embed_dims)`):
                 Conditional embeddings (embeddings computed from the input conditions such as prompts) to use.
-            pooled_projections (`torch.Tensor` of shape `(batch_size, projection_dim)`): Embeddings projected
+            pooled_projections (`torch.FloatTensor` of shape `(batch_size, projection_dim)`): Embeddings projected
                 from the embeddings of input conditions.
             timestep ( `torch.LongTensor`):
                 Used to indicate denoising step.

src/diffusers/models/transformers/transformer_hunyuan_video.py

@@ -721,7 +721,6 @@ class HunyuanVideoTransformer3DModel(ModelMixin, ConfigMixin, PeftAdapterMixin,
 
         for i in range(batch_size):
             attention_mask[i, : effective_sequence_length[i], : effective_sequence_length[i]] = True
-        attention_mask = attention_mask.unsqueeze(1)  # [B, 1, N, N], for broadcasting across attention heads
 
         # 4. Transformer blocks
         if torch.is_grad_enabled() and self.gradient_checkpointing:

src/diffusers/pipelines/auto_pipeline.py

@@ -293,7 +293,7 @@ class AutoPipelineForText2Image(ConfigMixin):
         If you get the error message below, you need to finetune the weights for your downstream task:
 
         ```
-        Some weights of UNet2DConditionModel were not initialized from the model checkpoint at stable-diffusion-v1-5/stable-diffusion-v1-5 and are newly initialized because the shapes did not match:
+        Some weights of UNet2DConditionModel were not initialized from the model checkpoint at runwayml/stable-diffusion-v1-5 and are newly initialized because the shapes did not match:
         - conv_in.weight: found shape torch.Size([320, 4, 3, 3]) in the checkpoint and torch.Size([320, 9, 3, 3]) in the model instantiated
         You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
         ```
@@ -385,7 +385,7 @@ class AutoPipelineForText2Image(ConfigMixin):
         ```py
         >>> from diffusers import AutoPipelineForText2Image
 
-        >>> pipeline = AutoPipelineForText2Image.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5")
+        >>> pipeline = AutoPipelineForText2Image.from_pretrained("runwayml/stable-diffusion-v1-5")
         >>> image = pipeline(prompt).images[0]
         ```
         """
@@ -448,7 +448,7 @@ class AutoPipelineForText2Image(ConfigMixin):
         >>> from diffusers import AutoPipelineForText2Image, AutoPipelineForImage2Image
 
         >>> pipe_i2i = AutoPipelineForImage2Image.from_pretrained(
-        ...     "stable-diffusion-v1-5/stable-diffusion-v1-5", requires_safety_checker=False
+        ...     "runwayml/stable-diffusion-v1-5", requires_safety_checker=False
         ... )
 
         >>> pipe_t2i = AutoPipelineForText2Image.from_pipe(pipe_i2i)
@@ -528,9 +528,7 @@ class AutoPipelineForText2Image(ConfigMixin):
             if k not in text_2_image_kwargs
         }
 
-        missing_modules = (
-            set(expected_modules) - set(text_2_image_cls._optional_components) - set(text_2_image_kwargs.keys())
-        )
+        missing_modules = set(expected_modules) - set(pipeline._optional_components) - set(text_2_image_kwargs.keys())
 
         if len(missing_modules) > 0:
             raise ValueError(
@@ -589,7 +587,7 @@ class AutoPipelineForImage2Image(ConfigMixin):
         If you get the error message below, you need to finetune the weights for your downstream task:
 
         ```
-        Some weights of UNet2DConditionModel were not initialized from the model checkpoint at stable-diffusion-v1-5/stable-diffusion-v1-5 and are newly initialized because the shapes did not match:
+        Some weights of UNet2DConditionModel were not initialized from the model checkpoint at runwayml/stable-diffusion-v1-5 and are newly initialized because the shapes did not match:
         - conv_in.weight: found shape torch.Size([320, 4, 3, 3]) in the checkpoint and torch.Size([320, 9, 3, 3]) in the model instantiated
         You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
         ```
@@ -681,7 +679,7 @@ class AutoPipelineForImage2Image(ConfigMixin):
         ```py
         >>> from diffusers import AutoPipelineForImage2Image
 
-        >>> pipeline = AutoPipelineForImage2Image.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5")
+        >>> pipeline = AutoPipelineForImage2Image.from_pretrained("runwayml/stable-diffusion-v1-5")
         >>> image = pipeline(prompt, image).images[0]
         ```
         """
@@ -756,7 +754,7 @@ class AutoPipelineForImage2Image(ConfigMixin):
         >>> from diffusers import AutoPipelineForText2Image, AutoPipelineForImage2Image
 
         >>> pipe_t2i = AutoPipelineForText2Image.from_pretrained(
-        ...     "stable-diffusion-v1-5/stable-diffusion-v1-5", requires_safety_checker=False
+        ...     "runwayml/stable-diffusion-v1-5", requires_safety_checker=False
         ... )
 
         >>> pipe_i2i = AutoPipelineForImage2Image.from_pipe(pipe_t2i)
@@ -840,9 +838,7 @@ class AutoPipelineForImage2Image(ConfigMixin):
             if k not in image_2_image_kwargs
         }
 
-        missing_modules = (
-            set(expected_modules) - set(image_2_image_cls._optional_components) - set(image_2_image_kwargs.keys())
-        )
+        missing_modules = set(expected_modules) - set(pipeline._optional_components) - set(image_2_image_kwargs.keys())
 
         if len(missing_modules) > 0:
             raise ValueError(
@@ -900,7 +896,7 @@ class AutoPipelineForInpainting(ConfigMixin):
         If you get the error message below, you need to finetune the weights for your downstream task:
 
         ```
-        Some weights of UNet2DConditionModel were not initialized from the model checkpoint at stable-diffusion-v1-5/stable-diffusion-v1-5 and are newly initialized because the shapes did not match:
+        Some weights of UNet2DConditionModel were not initialized from the model checkpoint at runwayml/stable-diffusion-v1-5 and are newly initialized because the shapes did not match:
         - conv_in.weight: found shape torch.Size([320, 4, 3, 3]) in the checkpoint and torch.Size([320, 9, 3, 3]) in the model instantiated
         You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
         ```
@@ -992,7 +988,7 @@ class AutoPipelineForInpainting(ConfigMixin):
         ```py
         >>> from diffusers import AutoPipelineForInpainting
 
-        >>> pipeline = AutoPipelineForInpainting.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5")
+        >>> pipeline = AutoPipelineForInpainting.from_pretrained("runwayml/stable-diffusion-v1-5")
         >>> image = pipeline(prompt, image=init_image, mask_image=mask_image).images[0]
         ```
         """
@@ -1145,9 +1141,7 @@ class AutoPipelineForInpainting(ConfigMixin):
             if k not in inpainting_kwargs
         }
 
-        missing_modules = (
-            set(expected_modules) - set(inpainting_cls._optional_components) - set(inpainting_kwargs.keys())
-        )
+        missing_modules = set(expected_modules) - set(pipeline._optional_components) - set(inpainting_kwargs.keys())
 
         if len(missing_modules) > 0:
             raise ValueError(

src/diffusers/pipelines/controlnet/pipeline_controlnet.py

@@ -80,7 +80,7 @@ EXAMPLE_DOC_STRING = """
         >>> # load control net and stable diffusion v1-5
         >>> controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", torch_dtype=torch.float16)
         >>> pipe = StableDiffusionControlNetPipeline.from_pretrained(
-        ...     "stable-diffusion-v1-5/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16
+        ...     "runwayml/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16
         ... )
 
         >>> # speed up diffusion process with faster scheduler and memory optimization
@@ -198,8 +198,8 @@ class StableDiffusionControlNetPipeline(
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for
-            more details about a model's potential harms.
+            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            about a model's potential harms.
         feature_extractor ([`~transformers.CLIPImageProcessor`]):
             A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
     """

src/diffusers/pipelines/controlnet/pipeline_controlnet_img2img.py

@@ -71,7 +71,7 @@ EXAMPLE_DOC_STRING = """
         >>> # load control net and stable diffusion v1-5
         >>> controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", torch_dtype=torch.float16)
         >>> pipe = StableDiffusionControlNetImg2ImgPipeline.from_pretrained(
-        ...     "stable-diffusion-v1-5/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16
+        ...     "runwayml/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16
         ... )
 
         >>> # speed up diffusion process with faster scheduler and memory optimization
@@ -168,8 +168,8 @@ class StableDiffusionControlNetImg2ImgPipeline(
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for
-            more details about a model's potential harms.
+            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            about a model's potential harms.
         feature_extractor ([`~transformers.CLIPImageProcessor`]):
             A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
     """

src/diffusers/pipelines/controlnet/pipeline_controlnet_inpaint.py

@@ -83,7 +83,7 @@ EXAMPLE_DOC_STRING = """
         ...     "lllyasviel/control_v11p_sd15_inpaint", torch_dtype=torch.float16
         ... )
         >>> pipe = StableDiffusionControlNetInpaintPipeline.from_pretrained(
-        ...     "stable-diffusion-v1-5/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16
+        ...     "runwayml/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16
         ... )
 
         >>> pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config)
@@ -141,11 +141,11 @@ class StableDiffusionControlNetInpaintPipeline(
     <Tip>
 
     This pipeline can be used with checkpoints that have been specifically fine-tuned for inpainting
-    ([stable-diffusion-v1-5/stable-diffusion-inpainting](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-inpainting))
-    as well as default text-to-image Stable Diffusion checkpoints
-    ([stable-diffusion-v1-5/stable-diffusion-v1-5](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5)).
-    Default text-to-image Stable Diffusion checkpoints might be preferable for ControlNets that have been fine-tuned on
-    those, such as [lllyasviel/control_v11p_sd15_inpaint](https://huggingface.co/lllyasviel/control_v11p_sd15_inpaint).
+    ([runwayml/stable-diffusion-inpainting](https://huggingface.co/runwayml/stable-diffusion-inpainting)) as well as
+    default text-to-image Stable Diffusion checkpoints
+    ([runwayml/stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5)). Default text-to-image
+    Stable Diffusion checkpoints might be preferable for ControlNets that have been fine-tuned on those, such as
+    [lllyasviel/control_v11p_sd15_inpaint](https://huggingface.co/lllyasviel/control_v11p_sd15_inpaint).
 
     </Tip>
 
@@ -167,8 +167,8 @@ class StableDiffusionControlNetInpaintPipeline(
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for
-            more details about a model's potential harms.
+            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            about a model's potential harms.
         feature_extractor ([`~transformers.CLIPImageProcessor`]):
             A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
     """

src/diffusers/pipelines/controlnet/pipeline_controlnet_inpaint_sd_xl.py

@@ -1622,7 +1622,7 @@ class StableDiffusionXLControlNetInpaintPipeline(
 
         # 8. Check that sizes of mask, masked image and latents match
         if num_channels_unet == 9:
-            # default case for stable-diffusion-v1-5/stable-diffusion-inpainting
+            # default case for runwayml/stable-diffusion-inpainting
             num_channels_mask = mask.shape[1]
             num_channels_masked_image = masked_image_latents.shape[1]
             if num_channels_latents + num_channels_mask + num_channels_masked_image != self.unet.config.in_channels:

src/diffusers/pipelines/controlnet/pipeline_flax_controlnet.py

@@ -75,10 +75,7 @@ EXAMPLE_DOC_STRING = """
         ...     "lllyasviel/sd-controlnet-canny", from_pt=True, dtype=jnp.float32
         ... )
         >>> pipe, params = FlaxStableDiffusionControlNetPipeline.from_pretrained(
-        ...     "stable-diffusion-v1-5/stable-diffusion-v1-5",
-        ...     controlnet=controlnet,
-        ...     revision="flax",
-        ...     dtype=jnp.float32,
+        ...     "runwayml/stable-diffusion-v1-5", controlnet=controlnet, revision="flax", dtype=jnp.float32
         ... )
         >>> params["controlnet"] = controlnet_params
 
@@ -135,8 +132,8 @@ class FlaxStableDiffusionControlNetPipeline(FlaxDiffusionPipeline):
             [`FlaxDPMSolverMultistepScheduler`].
         safety_checker ([`FlaxStableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for
-            more details about a model's potential harms.
+            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            about a model's potential harms.
         feature_extractor ([`~transformers.CLIPImageProcessor`]):
             A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
     """

src/diffusers/pipelines/controlnet_sd3/pipeline_stable_diffusion_3_controlnet.py

@@ -17,16 +17,14 @@ from typing import Any, Callable, Dict, List, Optional, Tuple, Union
 
 import torch
 from transformers import (
-    BaseImageProcessor,
     CLIPTextModelWithProjection,
     CLIPTokenizer,
-    PreTrainedModel,
     T5EncoderModel,
     T5TokenizerFast,
 )
 
 from ...image_processor import PipelineImageInput, VaeImageProcessor
-from ...loaders import FromSingleFileMixin, SD3IPAdapterMixin, SD3LoraLoaderMixin
+from ...loaders import FromSingleFileMixin, SD3LoraLoaderMixin
 from ...models.autoencoders import AutoencoderKL
 from ...models.controlnets.controlnet_sd3 import SD3ControlNetModel, SD3MultiControlNetModel
 from ...models.transformers import SD3Transformer2DModel
@@ -140,9 +138,7 @@ def retrieve_timesteps(
     return timesteps, num_inference_steps
 
 
-class StableDiffusion3ControlNetPipeline(
-    DiffusionPipeline, SD3LoraLoaderMixin, FromSingleFileMixin, SD3IPAdapterMixin
-):
+class StableDiffusion3ControlNetPipeline(DiffusionPipeline, SD3LoraLoaderMixin, FromSingleFileMixin):
     r"""
     Args:
         transformer ([`SD3Transformer2DModel`]):
@@ -178,14 +174,10 @@ class StableDiffusion3ControlNetPipeline(
             Provides additional conditioning to the `unet` during the denoising process. If you set multiple
             ControlNets as a list, the outputs from each ControlNet are added together to create one combined
             additional conditioning.
-        image_encoder (`PreTrainedModel`, *optional*):
-            Pre-trained Vision Model for IP Adapter.
-        feature_extractor (`BaseImageProcessor`, *optional*):
-            Image processor for IP Adapter.
     """
 
-    model_cpu_offload_seq = "text_encoder->text_encoder_2->text_encoder_3->image_encoder->transformer->vae"
-    _optional_components = ["image_encoder", "feature_extractor"]
+    model_cpu_offload_seq = "text_encoder->text_encoder_2->text_encoder_3->transformer->vae"
+    _optional_components = []
     _callback_tensor_inputs = ["latents", "prompt_embeds", "negative_prompt_embeds", "negative_pooled_prompt_embeds"]
 
     def __init__(
@@ -202,8 +194,6 @@ class StableDiffusion3ControlNetPipeline(
         controlnet: Union[
             SD3ControlNetModel, List[SD3ControlNetModel], Tuple[SD3ControlNetModel], SD3MultiControlNetModel
         ],
-        image_encoder: PreTrainedModel = None,
-        feature_extractor: BaseImageProcessor = None,
     ):
         super().__init__()
         if isinstance(controlnet, (list, tuple)):
@@ -233,8 +223,6 @@ class StableDiffusion3ControlNetPipeline(
             transformer=transformer,
             scheduler=scheduler,
             controlnet=controlnet,
-            image_encoder=image_encoder,
-            feature_extractor=feature_extractor,
         )
         self.vae_scale_factor = (
             2 ** (len(self.vae.config.block_out_channels) - 1) if hasattr(self, "vae") and self.vae is not None else 8
@@ -739,84 +727,6 @@ class StableDiffusion3ControlNetPipeline(
     def interrupt(self):
         return self._interrupt
 
-    # Copied from diffusers.pipelines.stable_diffusion_3.pipeline_stable_diffusion_3.StableDiffusion3Pipeline.encode_image
-    def encode_image(self, image: PipelineImageInput, device: torch.device) -> torch.Tensor:
-        """Encodes the given image into a feature representation using a pre-trained image encoder.
-
-        Args:
-            image (`PipelineImageInput`):
-                Input image to be encoded.
-            device: (`torch.device`):
-                Torch device.
-
-        Returns:
-            `torch.Tensor`: The encoded image feature representation.
-        """
-        if not isinstance(image, torch.Tensor):
-            image = self.feature_extractor(image, return_tensors="pt").pixel_values
-
-        image = image.to(device=device, dtype=self.dtype)
-
-        return self.image_encoder(image, output_hidden_states=True).hidden_states[-2]
-
-    # Copied from diffusers.pipelines.stable_diffusion_3.pipeline_stable_diffusion_3.StableDiffusion3Pipeline.prepare_ip_adapter_image_embeds
-    def prepare_ip_adapter_image_embeds(
-        self,
-        ip_adapter_image: Optional[PipelineImageInput] = None,
-        ip_adapter_image_embeds: Optional[torch.Tensor] = None,
-        device: Optional[torch.device] = None,
-        num_images_per_prompt: int = 1,
-        do_classifier_free_guidance: bool = True,
-    ) -> torch.Tensor:
-        """Prepares image embeddings for use in the IP-Adapter.
-
-        Either `ip_adapter_image` or `ip_adapter_image_embeds` must be passed.
-
-        Args:
-            ip_adapter_image (`PipelineImageInput`, *optional*):
-                The input image to extract features from for IP-Adapter.
-            ip_adapter_image_embeds (`torch.Tensor`, *optional*):
-                Precomputed image embeddings.
-            device: (`torch.device`, *optional*):
-                Torch device.
-            num_images_per_prompt (`int`, defaults to 1):
-                Number of images that should be generated per prompt.
-            do_classifier_free_guidance (`bool`, defaults to True):
-                Whether to use classifier free guidance or not.
-        """
-        device = device or self._execution_device
-
-        if ip_adapter_image_embeds is not None:
-            if do_classifier_free_guidance:
-                single_negative_image_embeds, single_image_embeds = ip_adapter_image_embeds.chunk(2)
-            else:
-                single_image_embeds = ip_adapter_image_embeds
-        elif ip_adapter_image is not None:
-            single_image_embeds = self.encode_image(ip_adapter_image, device)
-            if do_classifier_free_guidance:
-                single_negative_image_embeds = torch.zeros_like(single_image_embeds)
-        else:
-            raise ValueError("Neither `ip_adapter_image_embeds` or `ip_adapter_image_embeds` were provided.")
-
-        image_embeds = torch.cat([single_image_embeds] * num_images_per_prompt, dim=0)
-
-        if do_classifier_free_guidance:
-            negative_image_embeds = torch.cat([single_negative_image_embeds] * num_images_per_prompt, dim=0)
-            image_embeds = torch.cat([negative_image_embeds, image_embeds], dim=0)
-
-        return image_embeds.to(device=device)
-
-    # Copied from diffusers.pipelines.stable_diffusion_3.pipeline_stable_diffusion_3.StableDiffusion3Pipeline.enable_sequential_cpu_offload
-    def enable_sequential_cpu_offload(self, *args, **kwargs):
-        if self.image_encoder is not None and "image_encoder" not in self._exclude_from_cpu_offload:
-            logger.warning(
-                "`pipe.enable_sequential_cpu_offload()` might fail for `image_encoder` if it uses "
-                "`torch.nn.MultiheadAttention`. You can exclude `image_encoder` from CPU offloading by calling "
-                "`pipe._exclude_from_cpu_offload.append('image_encoder')` before `pipe.enable_sequential_cpu_offload()`."
-            )
-
-        super().enable_sequential_cpu_offload(*args, **kwargs)
-
     @torch.no_grad()
     @replace_example_docstring(EXAMPLE_DOC_STRING)
     def __call__(
@@ -844,8 +754,6 @@ class StableDiffusion3ControlNetPipeline(
         negative_prompt_embeds: Optional[torch.FloatTensor] = None,
         pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
         negative_pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
-        ip_adapter_image: Optional[PipelineImageInput] = None,
-        ip_adapter_image_embeds: Optional[torch.Tensor] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
         joint_attention_kwargs: Optional[Dict[str, Any]] = None,
@@ -935,12 +843,6 @@ class StableDiffusion3ControlNetPipeline(
                 Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                 weighting. If not provided, pooled negative_prompt_embeds will be generated from `negative_prompt`
                 input argument.
-            ip_adapter_image (`PipelineImageInput`, *optional*):
-                Optional image input to work with IP Adapters.
-            ip_adapter_image_embeds (`torch.Tensor`, *optional*):
-                Pre-generated image embeddings for IP-Adapter. Should be a tensor of shape `(batch_size, num_images,
-                emb_dim)`. It should contain the negative image embedding if `do_classifier_free_guidance` is set to
-                `True`. If not provided, embeddings are computed from the `ip_adapter_image` input argument.
             output_type (`str`, *optional*, defaults to `"pil"`):
                 The output format of the generate image. Choose between
                 [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
@@ -1138,22 +1040,7 @@ class StableDiffusion3ControlNetPipeline(
             # SD35 official 8b controlnet does not use encoder_hidden_states
             controlnet_encoder_hidden_states = None
 
-        # 7. Prepare image embeddings
-        if (ip_adapter_image is not None and self.is_ip_adapter_active) or ip_adapter_image_embeds is not None:
-            ip_adapter_image_embeds = self.prepare_ip_adapter_image_embeds(
-                ip_adapter_image,
-                ip_adapter_image_embeds,
-                device,
-                batch_size * num_images_per_prompt,
-                self.do_classifier_free_guidance,
-            )
-
-            if self.joint_attention_kwargs is None:
-                self._joint_attention_kwargs = {"ip_adapter_image_embeds": ip_adapter_image_embeds}
-            else:
-                self._joint_attention_kwargs.update(ip_adapter_image_embeds=ip_adapter_image_embeds)
-
-        # 8. Denoising loop
+        # 7. Denoising loop
         with self.progress_bar(total=num_inference_steps) as progress_bar:
             for i, t in enumerate(timesteps):
                 if self.interrupt:

src/diffusers/pipelines/ledits_pp/pipeline_leditspp_stable_diffusion.py

@@ -34,19 +34,21 @@ logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
 EXAMPLE_DOC_STRING = """
     Examples:
         ```py
+        >>> import PIL
+        >>> import requests
         >>> import torch
+        >>> from io import BytesIO
 
         >>> from diffusers import LEditsPPPipelineStableDiffusion
         >>> from diffusers.utils import load_image
 
         >>> pipe = LEditsPPPipelineStableDiffusion.from_pretrained(
-        ...     "runwayml/stable-diffusion-v1-5", variant="fp16", torch_dtype=torch.float16
+        ...     "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16
         ... )
-        >>> pipe.enable_vae_tiling()
         >>> pipe = pipe.to("cuda")
 
         >>> img_url = "https://www.aiml.informatik.tu-darmstadt.de/people/mbrack/cherry_blossom.png"
-        >>> image = load_image(img_url).resize((512, 512))
+        >>> image = load_image(img_url).convert("RGB")
 
         >>> _ = pipe.invert(image=image, num_inversion_steps=50, skip=0.1)
 
@@ -150,7 +152,7 @@ class LeditsGaussianSmoothing:
 
         # The gaussian kernel is the product of the gaussian function of each dimension.
         kernel = 1
-        meshgrids = torch.meshgrid([torch.arange(size, dtype=torch.float32) for size in kernel_size], indexing="ij")
+        meshgrids = torch.meshgrid([torch.arange(size, dtype=torch.float32) for size in kernel_size])
         for size, std, mgrid in zip(kernel_size, sigma, meshgrids):
             mean = (size - 1) / 2
             kernel *= 1 / (std * math.sqrt(2 * math.pi)) * torch.exp(-(((mgrid - mean) / (2 * std)) ** 2))
@@ -704,35 +706,6 @@ class LEditsPPPipelineStableDiffusion(
     def cross_attention_kwargs(self):
         return self._cross_attention_kwargs
 
-    def enable_vae_slicing(self):
-        r"""
-        Enable sliced VAE decoding. When this option is enabled, the VAE will split the input tensor in slices to
-        compute decoding in several steps. This is useful to save some memory and allow larger batch sizes.
-        """
-        self.vae.enable_slicing()
-
-    def disable_vae_slicing(self):
-        r"""
-        Disable sliced VAE decoding. If `enable_vae_slicing` was previously enabled, this method will go back to
-        computing decoding in one step.
-        """
-        self.vae.disable_slicing()
-
-    def enable_vae_tiling(self):
-        r"""
-        Enable tiled VAE decoding. When this option is enabled, the VAE will split the input tensor into tiles to
-        compute decoding and encoding in several steps. This is useful for saving a large amount of memory and to allow
-        processing larger images.
-        """
-        self.vae.enable_tiling()
-
-    def disable_vae_tiling(self):
-        r"""
-        Disable tiled VAE decoding. If `enable_vae_tiling` was previously enabled, this method will go back to
-        computing decoding in one step.
-        """
-        self.vae.disable_tiling()
-
     @torch.no_grad()
     @replace_example_docstring(EXAMPLE_DOC_STRING)
     def __call__(
@@ -1298,8 +1271,6 @@ class LEditsPPPipelineStableDiffusion(
             [`~pipelines.ledits_pp.LEditsPPInversionPipelineOutput`]: Output will contain the resized input image(s)
             and respective VAE reconstruction(s).
         """
-        if height is not None and height % 32 != 0 or width is not None and width % 32 != 0:
-            raise ValueError("height and width must be a factor of 32.")
         # Reset attn processor, we do not want to store attn maps during inversion
         self.unet.set_attn_processor(AttnProcessor())
 
@@ -1389,12 +1360,6 @@ class LEditsPPPipelineStableDiffusion(
         image = self.image_processor.preprocess(
             image=image, height=height, width=width, resize_mode=resize_mode, crops_coords=crops_coords
         )
-        height, width = image.shape[-2:]
-        if height % 32 != 0 or width % 32 != 0:
-            raise ValueError(
-                "Image height and width must be a factor of 32. "
-                "Consider down-sampling the input using the `height` and `width` parameters"
-            )
         resized = self.image_processor.postprocess(image=image, output_type="pil")
 
         if max(image.shape[-2:]) > self.vae.config["sample_size"] * 1.5:

src/diffusers/pipelines/ledits_pp/pipeline_leditspp_stable_diffusion_xl.py

@@ -72,18 +72,25 @@ EXAMPLE_DOC_STRING = """
     Examples:
         ```py
         >>> import torch
+        >>> import PIL
+        >>> import requests
+        >>> from io import BytesIO
 
         >>> from diffusers import LEditsPPPipelineStableDiffusionXL
-        >>> from diffusers.utils import load_image
 
         >>> pipe = LEditsPPPipelineStableDiffusionXL.from_pretrained(
-        ...     "stabilityai/stable-diffusion-xl-base-1.0", variant="fp16", torch_dtype=torch.float16
+        ...     "stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16
         ... )
-        >>> pipe.enable_vae_tiling()
         >>> pipe = pipe.to("cuda")
 
+
+        >>> def download_image(url):
+        ...     response = requests.get(url)
+        ...     return PIL.Image.open(BytesIO(response.content)).convert("RGB")
+
+
         >>> img_url = "https://www.aiml.informatik.tu-darmstadt.de/people/mbrack/tennis.jpg"
-        >>> image = load_image(img_url).resize((1024, 1024))
+        >>> image = download_image(img_url)
 
         >>> _ = pipe.invert(image=image, num_inversion_steps=50, skip=0.2)
 
@@ -190,7 +197,7 @@ class LeditsGaussianSmoothing:
 
         # The gaussian kernel is the product of the gaussian function of each dimension.
         kernel = 1
-        meshgrids = torch.meshgrid([torch.arange(size, dtype=torch.float32) for size in kernel_size], indexing="ij")
+        meshgrids = torch.meshgrid([torch.arange(size, dtype=torch.float32) for size in kernel_size])
         for size, std, mgrid in zip(kernel_size, sigma, meshgrids):
             mean = (size - 1) / 2
             kernel *= 1 / (std * math.sqrt(2 * math.pi)) * torch.exp(-(((mgrid - mean) / (2 * std)) ** 2))
@@ -761,35 +768,6 @@ class LEditsPPPipelineStableDiffusionXL(
     def num_timesteps(self):
         return self._num_timesteps
 
-    def enable_vae_slicing(self):
-        r"""
-        Enable sliced VAE decoding. When this option is enabled, the VAE will split the input tensor in slices to
-        compute decoding in several steps. This is useful to save some memory and allow larger batch sizes.
-        """
-        self.vae.enable_slicing()
-
-    def disable_vae_slicing(self):
-        r"""
-        Disable sliced VAE decoding. If `enable_vae_slicing` was previously enabled, this method will go back to
-        computing decoding in one step.
-        """
-        self.vae.disable_slicing()
-
-    def enable_vae_tiling(self):
-        r"""
-        Enable tiled VAE decoding. When this option is enabled, the VAE will split the input tensor into tiles to
-        compute decoding and encoding in several steps. This is useful for saving a large amount of memory and to allow
-        processing larger images.
-        """
-        self.vae.enable_tiling()
-
-    def disable_vae_tiling(self):
-        r"""
-        Disable tiled VAE decoding. If `enable_vae_tiling` was previously enabled, this method will go back to
-        computing decoding in one step.
-        """
-        self.vae.disable_tiling()
-
     # Copied from diffusers.pipelines.ledits_pp.pipeline_leditspp_stable_diffusion.LEditsPPPipelineStableDiffusion.prepare_unet
     def prepare_unet(self, attention_store, PnP: bool = False):
         attn_procs = {}
@@ -1423,12 +1401,6 @@ class LEditsPPPipelineStableDiffusionXL(
         image = self.image_processor.preprocess(
             image=image, height=height, width=width, resize_mode=resize_mode, crops_coords=crops_coords
         )
-        height, width = image.shape[-2:]
-        if height % 32 != 0 or width % 32 != 0:
-            raise ValueError(
-                "Image height and width must be a factor of 32. "
-                "Consider down-sampling the input using the `height` and `width` parameters"
-            )
         resized = self.image_processor.postprocess(image=image, output_type="pil")
 
         if max(image.shape[-2:]) > self.vae.config["sample_size"] * 1.5:
@@ -1467,10 +1439,6 @@ class LEditsPPPipelineStableDiffusionXL(
         crops_coords_top_left: Tuple[int, int] = (0, 0),
         num_zero_noise_steps: int = 3,
         cross_attention_kwargs: Optional[Dict[str, Any]] = None,
-        height: Optional[int] = None,
-        width: Optional[int] = None,
-        resize_mode: Optional[str] = "default",
-        crops_coords: Optional[Tuple[int, int, int, int]] = None,
     ):
         r"""
         The function to the pipeline for image inversion as described by the [LEDITS++
@@ -1518,8 +1486,6 @@ class LEditsPPPipelineStableDiffusionXL(
             [`~pipelines.ledits_pp.LEditsPPInversionPipelineOutput`]: Output will contain the resized input image(s)
             and respective VAE reconstruction(s).
         """
-        if height is not None and height % 32 != 0 or width is not None and width % 32 != 0:
-            raise ValueError("height and width must be a factor of 32.")
 
         # Reset attn processor, we do not want to store attn maps during inversion
         self.unet.set_attn_processor(AttnProcessor())
@@ -1544,14 +1510,7 @@ class LEditsPPPipelineStableDiffusionXL(
             do_classifier_free_guidance = source_guidance_scale > 1.0
 
         # 1. prepare image
-        x0, resized = self.encode_image(
-            image,
-            dtype=self.text_encoder_2.dtype,
-            height=height,
-            width=width,
-            resize_mode=resize_mode,
-            crops_coords=crops_coords,
-        )
+        x0, resized = self.encode_image(image, dtype=self.text_encoder_2.dtype)
         width = x0.shape[2] * self.vae_scale_factor
         height = x0.shape[3] * self.vae_scale_factor
         self.size = (height, width)

src/diffusers/pipelines/ltx/pipeline_ltx.py

@@ -186,22 +186,16 @@ class LTXPipeline(DiffusionPipeline, FromSingleFileMixin, LTXVideoLoraLoaderMixi
             scheduler=scheduler,
         )
 
-        self.vae_spatial_compression_ratio = (
-            self.vae.spatial_compression_ratio if getattr(self, "vae", None) is not None else 32
-        )
-        self.vae_temporal_compression_ratio = (
-            self.vae.temporal_compression_ratio if getattr(self, "vae", None) is not None else 8
-        )
-        self.transformer_spatial_patch_size = (
-            self.transformer.config.patch_size if getattr(self, "transformer", None) is not None else 1
-        )
+        self.vae_spatial_compression_ratio = self.vae.spatial_compression_ratio if hasattr(self, "vae") else 32
+        self.vae_temporal_compression_ratio = self.vae.temporal_compression_ratio if hasattr(self, "vae") else 8
+        self.transformer_spatial_patch_size = self.transformer.config.patch_size if hasattr(self, "transformer") else 1
         self.transformer_temporal_patch_size = (
-            self.transformer.config.patch_size_t if getattr(self, "transformer") is not None else 1
+            self.transformer.config.patch_size_t if hasattr(self, "transformer") else 1
         )
 
         self.video_processor = VideoProcessor(vae_scale_factor=self.vae_spatial_compression_ratio)
         self.tokenizer_max_length = (
-            self.tokenizer.model_max_length if getattr(self, "tokenizer", None) is not None else 128
+            self.tokenizer.model_max_length if hasattr(self, "tokenizer") and self.tokenizer is not None else 128
         )
 
     def _get_t5_prompt_embeds(

src/diffusers/pipelines/ltx/pipeline_ltx_image2video.py

@@ -205,22 +205,16 @@ class LTXImageToVideoPipeline(DiffusionPipeline, FromSingleFileMixin, LTXVideoLo
             scheduler=scheduler,
         )
 
-        self.vae_spatial_compression_ratio = (
-            self.vae.spatial_compression_ratio if getattr(self, "vae", None) is not None else 32
-        )
-        self.vae_temporal_compression_ratio = (
-            self.vae.temporal_compression_ratio if getattr(self, "vae", None) is not None else 8
-        )
-        self.transformer_spatial_patch_size = (
-            self.transformer.config.patch_size if getattr(self, "transformer", None) is not None else 1
-        )
+        self.vae_spatial_compression_ratio = self.vae.spatial_compression_ratio if hasattr(self, "vae") else 32
+        self.vae_temporal_compression_ratio = self.vae.temporal_compression_ratio if hasattr(self, "vae") else 8
+        self.transformer_spatial_patch_size = self.transformer.config.patch_size if hasattr(self, "transformer") else 1
         self.transformer_temporal_patch_size = (
-            self.transformer.config.patch_size_t if getattr(self, "transformer") is not None else 1
+            self.transformer.config.patch_size_t if hasattr(self, "transformer") else 1
         )
 
         self.video_processor = VideoProcessor(vae_scale_factor=self.vae_spatial_compression_ratio)
         self.tokenizer_max_length = (
-            self.tokenizer.model_max_length if getattr(self, "tokenizer", None) is not None else 128
+            self.tokenizer.model_max_length if hasattr(self, "tokenizer") and self.tokenizer is not None else 128
         )
 
         self.default_height = 512

src/diffusers/pipelines/pipeline_flax_utils.py

@@ -237,15 +237,15 @@ class FlaxDiffusionPipeline(ConfigMixin, PushToHubMixin):
         If you get the error message below, you need to finetune the weights for your downstream task:
 
         ```
-        Some weights of FlaxUNet2DConditionModel were not initialized from the model checkpoint at stable-diffusion-v1-5/stable-diffusion-v1-5 and are newly initialized because the shapes did not match:
+        Some weights of FlaxUNet2DConditionModel were not initialized from the model checkpoint at runwayml/stable-diffusion-v1-5 and are newly initialized because the shapes did not match:
         ```
 
         Parameters:
             pretrained_model_name_or_path (`str` or `os.PathLike`, *optional*):
                 Can be either:
 
-                    - A string, the *repo id* (for example `stable-diffusion-v1-5/stable-diffusion-v1-5`) of a
-                      pretrained pipeline hosted on the Hub.
+                    - A string, the *repo id* (for example `runwayml/stable-diffusion-v1-5`) of a pretrained pipeline
+                      hosted on the Hub.
                     - A path to a *directory* (for example `./my_model_directory`) containing the model weights saved
                       using [`~FlaxDiffusionPipeline.save_pretrained`].
             dtype (`str` or `jnp.dtype`, *optional*):
@@ -293,7 +293,7 @@ class FlaxDiffusionPipeline(ConfigMixin, PushToHubMixin):
         >>> # Requires to be logged in to Hugging Face hub,
         >>> # see more in [the documentation](https://huggingface.co/docs/hub/security-tokens)
         >>> pipeline, params = FlaxDiffusionPipeline.from_pretrained(
-        ...     "stable-diffusion-v1-5/stable-diffusion-v1-5",
+        ...     "runwayml/stable-diffusion-v1-5",
         ...     variant="bf16",
         ...     dtype=jnp.bfloat16,
         ... )
@@ -301,7 +301,7 @@ class FlaxDiffusionPipeline(ConfigMixin, PushToHubMixin):
         >>> # Download pipeline, but use a different scheduler
         >>> from diffusers import FlaxDPMSolverMultistepScheduler
 
-        >>> model_id = "stable-diffusion-v1-5/stable-diffusion-v1-5"
+        >>> model_id = "runwayml/stable-diffusion-v1-5"
         >>> dpmpp, dpmpp_state = FlaxDPMSolverMultistepScheduler.from_pretrained(
         ...     model_id,
         ...     subfolder="scheduler",
@@ -559,7 +559,7 @@ class FlaxDiffusionPipeline(ConfigMixin, PushToHubMixin):
         ... )
 
         >>> text2img = FlaxStableDiffusionPipeline.from_pretrained(
-        ...     "stable-diffusion-v1-5/stable-diffusion-v1-5", variant="bf16", dtype=jnp.bfloat16
+        ...     "runwayml/stable-diffusion-v1-5", variant="bf16", dtype=jnp.bfloat16
         ... )
         >>> img2img = FlaxStableDiffusionImg2ImgPipeline(**text2img.components)
         ```

src/diffusers/pipelines/pipeline_loading_utils.py

@@ -813,9 +813,9 @@ def _maybe_raise_warning_for_inpainting(pipeline_class, pretrained_model_name_or
             "You are using a legacy checkpoint for inpainting with Stable Diffusion, therefore we are loading the"
             f" {StableDiffusionInpaintPipelineLegacy} class instead of {StableDiffusionInpaintPipeline}. For"
             " better inpainting results, we strongly suggest using Stable Diffusion's official inpainting"
-            " checkpoint: https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-inpainting instead or adapting your"
+            " checkpoint: https://huggingface.co/runwayml/stable-diffusion-inpainting instead or adapting your"
             f" checkpoint {pretrained_model_name_or_path} to the format of"
-            " https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-inpainting. Note that we do not actively maintain"
+            " https://huggingface.co/runwayml/stable-diffusion-inpainting. Note that we do not actively maintain"
             " the {StableDiffusionInpaintPipelineLegacy} class and will likely remove it in version 1.0.0."
         )
         deprecate("StableDiffusionInpaintPipelineLegacy", "1.0.0", deprecation_message, standard_warn=False)

src/diffusers/pipelines/pipeline_utils.py

@@ -516,7 +516,7 @@ class DiffusionPipeline(ConfigMixin, PushToHubMixin):
         If you get the error message below, you need to finetune the weights for your downstream task:
 
         ```
-        Some weights of UNet2DConditionModel were not initialized from the model checkpoint at stable-diffusion-v1-5/stable-diffusion-v1-5 and are newly initialized because the shapes did not match:
+        Some weights of UNet2DConditionModel were not initialized from the model checkpoint at runwayml/stable-diffusion-v1-5 and are newly initialized because the shapes did not match:
         - conv_in.weight: found shape torch.Size([320, 4, 3, 3]) in the checkpoint and torch.Size([320, 9, 3, 3]) in the model instantiated
         You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
         ```
@@ -643,7 +643,7 @@ class DiffusionPipeline(ConfigMixin, PushToHubMixin):
         >>> # Download pipeline that requires an authorization token
         >>> # For more information on access tokens, please refer to this section
         >>> # of the documentation](https://huggingface.co/docs/hub/security-tokens)
-        >>> pipeline = DiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5")
+        >>> pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")
 
         >>> # Use a different scheduler
         >>> from diffusers import LMSDiscreteScheduler
@@ -1555,7 +1555,7 @@ class DiffusionPipeline(ConfigMixin, PushToHubMixin):
         ...     StableDiffusionInpaintPipeline,
         ... )
 
-        >>> text2img = StableDiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5")
+        >>> text2img = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")
         >>> img2img = StableDiffusionImg2ImgPipeline(**text2img.components)
         >>> inpaint = StableDiffusionInpaintPipeline(**text2img.components)
         ```
@@ -1688,7 +1688,7 @@ class DiffusionPipeline(ConfigMixin, PushToHubMixin):
         >>> from diffusers import StableDiffusionPipeline
 
         >>> pipe = StableDiffusionPipeline.from_pretrained(
-        ...     "stable-diffusion-v1-5/stable-diffusion-v1-5",
+        ...     "runwayml/stable-diffusion-v1-5",
         ...     torch_dtype=torch.float16,
         ...     use_safetensors=True,
         ... )
@@ -1735,7 +1735,7 @@ class DiffusionPipeline(ConfigMixin, PushToHubMixin):
         ```py
         >>> from diffusers import StableDiffusionPipeline, StableDiffusionSAGPipeline
 
-        >>> pipe = StableDiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5")
+        >>> pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")
         >>> new_pipe = StableDiffusionSAGPipeline.from_pipe(pipe)
         ```
         """

src/diffusers/pipelines/stable_diffusion/pipeline_flax_stable_diffusion.py

@@ -55,7 +55,7 @@ EXAMPLE_DOC_STRING = """
         >>> from diffusers import FlaxStableDiffusionPipeline
 
         >>> pipeline, params = FlaxStableDiffusionPipeline.from_pretrained(
-        ...     "stable-diffusion-v1-5/stable-diffusion-v1-5", variant="bf16", dtype=jax.numpy.bfloat16
+        ...     "runwayml/stable-diffusion-v1-5", variant="bf16", dtype=jax.numpy.bfloat16
         ... )
 
         >>> prompt = "a photo of an astronaut riding a horse on mars"
@@ -100,8 +100,8 @@ class FlaxStableDiffusionPipeline(FlaxDiffusionPipeline):
             [`FlaxDPMSolverMultistepScheduler`].
         safety_checker ([`FlaxStableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for
-            more details about a model's potential harms.
+            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            about a model's potential harms.
         feature_extractor ([`~transformers.CLIPImageProcessor`]):
             A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
     """
@@ -141,8 +141,8 @@ class FlaxStableDiffusionPipeline(FlaxDiffusionPipeline):
                 "The configuration file of the unet has set the default `sample_size` to smaller than"
                 " 64 which seems highly unlikely .If you're checkpoint is a fine-tuned version of any of the"
                 " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
-                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
+                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                 " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                 " in the config might lead to incorrect results in future versions. If you have downloaded this"
                 " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"

src/diffusers/pipelines/stable_diffusion/pipeline_flax_stable_diffusion_img2img.py

@@ -124,8 +124,8 @@ class FlaxStableDiffusionImg2ImgPipeline(FlaxDiffusionPipeline):
             [`FlaxDPMSolverMultistepScheduler`].
         safety_checker ([`FlaxStableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for
-            more details about a model's potential harms.
+            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            about a model's potential harms.
         feature_extractor ([`~transformers.CLIPImageProcessor`]):
             A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
     """

src/diffusers/pipelines/stable_diffusion/pipeline_flax_stable_diffusion_inpaint.py

@@ -127,8 +127,8 @@ class FlaxStableDiffusionInpaintPipeline(FlaxDiffusionPipeline):
             [`FlaxDPMSolverMultistepScheduler`].
         safety_checker ([`FlaxStableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for
-            more details about a model's potential harms.
+            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            about a model's potential harms.
         feature_extractor ([`~transformers.CLIPImageProcessor`]):
             A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
     """
@@ -168,8 +168,8 @@ class FlaxStableDiffusionInpaintPipeline(FlaxDiffusionPipeline):
                 "The configuration file of the unet has set the default `sample_size` to smaller than"
                 " 64 which seems highly unlikely .If you're checkpoint is a fine-tuned version of any of the"
                 " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
-                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
+                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                 " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                 " in the config might lead to incorrect results in future versions. If you have downloaded this"
                 " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"

src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion_img2img.py

@@ -78,8 +78,7 @@ class OnnxStableDiffusionImg2ImgPipeline(DiffusionPipeline):
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please, refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for
-            details.
+            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
         feature_extractor ([`CLIPImageProcessor`]):
             Model that extracts features from generated images to be used as inputs for the `safety_checker`.
     """

src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion_inpaint.py

@@ -76,8 +76,7 @@ class OnnxStableDiffusionInpaintPipeline(DiffusionPipeline):
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please, refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for
-            details.
+            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
         feature_extractor ([`CLIPImageProcessor`]):
             Model that extracts features from generated images to be used as inputs for the `safety_checker`.
     """

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py

@@ -55,9 +55,7 @@ EXAMPLE_DOC_STRING = """
         >>> import torch
         >>> from diffusers import StableDiffusionPipeline
 
-        >>> pipe = StableDiffusionPipeline.from_pretrained(
-        ...     "stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16
-        ... )
+        >>> 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"
@@ -186,8 +184,8 @@ class StableDiffusionPipeline(
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for
-            more details about a model's potential harms.
+            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            about a model's potential harms.
         feature_extractor ([`~transformers.CLIPImageProcessor`]):
             A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
     """
@@ -268,8 +266,8 @@ class StableDiffusionPipeline(
                 "The configuration file of the unet has set the default `sample_size` to smaller than"
                 " 64 which seems highly unlikely. If your checkpoint is a fine-tuned version of any of the"
                 " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
-                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
+                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                 " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                 " in the config might lead to incorrect results in future versions. If you have downloaded this"
                 " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_depth2img.py

@@ -124,8 +124,8 @@ class StableDiffusionDepth2ImgPipeline(DiffusionPipeline, TextualInversionLoader
                 "The configuration file of the unet has set the default `sample_size` to smaller than"
                 " 64 which seems highly unlikely .If you're checkpoint is a fine-tuned version of any of the"
                 " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
-                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
+                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                 " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                 " in the config might lead to incorrect results in future versions. If you have downloaded this"
                 " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_image_variation.py

@@ -57,8 +57,8 @@ class StableDiffusionImageVariationPipeline(DiffusionPipeline, StableDiffusionMi
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for
-            more details about a model's potential harms.
+            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            about a model's potential harms.
         feature_extractor ([`~transformers.CLIPImageProcessor`]):
             A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
     """
@@ -106,8 +106,8 @@ class StableDiffusionImageVariationPipeline(DiffusionPipeline, StableDiffusionMi
                 "The configuration file of the unet has set the default `sample_size` to smaller than"
                 " 64 which seems highly unlikely .If you're checkpoint is a fine-tuned version of any of the"
                 " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
-                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
+                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                 " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                 " in the config might lead to incorrect results in future versions. If you have downloaded this"
                 " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py

@@ -56,7 +56,7 @@ EXAMPLE_DOC_STRING = """
         >>> from diffusers import StableDiffusionImg2ImgPipeline
 
         >>> device = "cuda"
-        >>> model_id_or_path = "stable-diffusion-v1-5/stable-diffusion-v1-5"
+        >>> model_id_or_path = "runwayml/stable-diffusion-v1-5"
         >>> pipe = StableDiffusionImg2ImgPipeline.from_pretrained(model_id_or_path, torch_dtype=torch.float16)
         >>> pipe = pipe.to(device)
 
@@ -205,8 +205,8 @@ class StableDiffusionImg2ImgPipeline(
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for
-            more details about a model's potential harms.
+            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            about a model's potential harms.
         feature_extractor ([`~transformers.CLIPImageProcessor`]):
             A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
     """
@@ -282,8 +282,8 @@ class StableDiffusionImg2ImgPipeline(
                 "The configuration file of the unet has set the default `sample_size` to smaller than"
                 " 64 which seems highly unlikely. If your checkpoint is a fine-tuned version of any of the"
                 " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
-                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
+                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                 " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                 " in the config might lead to incorrect results in future versions. If you have downloaded this"
                 " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_inpaint.py

@@ -146,8 +146,8 @@ class StableDiffusionInpaintPipeline(
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for
-            more details about a model's potential harms.
+            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            about a model's potential harms.
         feature_extractor ([`~transformers.CLIPImageProcessor`]):
             A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
     """
@@ -224,8 +224,8 @@ class StableDiffusionInpaintPipeline(
                 "The configuration file of the unet has set the default `sample_size` to smaller than"
                 " 64 which seems highly unlikely .If you're checkpoint is a fine-tuned version of any of the"
                 " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
-                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
+                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                 " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                 " in the config might lead to incorrect results in future versions. If you have downloaded this"
                 " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"
@@ -1014,7 +1014,7 @@ class StableDiffusionInpaintPipeline(
         >>> mask_image = download_image(mask_url).resize((512, 512))
 
         >>> pipe = StableDiffusionInpaintPipeline.from_pretrained(
-        ...     "stable-diffusion-v1-5/stable-diffusion-inpainting", torch_dtype=torch.float16
+        ...     "runwayml/stable-diffusion-inpainting", torch_dtype=torch.float16
         ... )
         >>> pipe = pipe.to("cuda")
 
@@ -1200,7 +1200,7 @@ class StableDiffusionInpaintPipeline(
 
         # 8. Check that sizes of mask, masked image and latents match
         if num_channels_unet == 9:
-            # default case for stable-diffusion-v1-5/stable-diffusion-inpainting
+            # default case for runwayml/stable-diffusion-inpainting
             num_channels_mask = mask.shape[1]
             num_channels_masked_image = masked_image_latents.shape[1]
             if num_channels_latents + num_channels_mask + num_channels_masked_image != self.unet.config.in_channels:

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_instruct_pix2pix.py

@@ -22,23 +22,16 @@ from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer, CLIPV
 
 from ...callbacks import MultiPipelineCallbacks, PipelineCallback
 from ...image_processor import PipelineImageInput, VaeImageProcessor
-from ...loaders import FromSingleFileMixin, IPAdapterMixin, StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin
+from ...loaders import IPAdapterMixin, StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin
 from ...models import AutoencoderKL, ImageProjection, UNet2DConditionModel
 from ...schedulers import KarrasDiffusionSchedulers
-from ...utils import PIL_INTERPOLATION, deprecate, is_torch_xla_available, logging
+from ...utils import PIL_INTERPOLATION, deprecate, logging
 from ...utils.torch_utils import randn_tensor
 from ..pipeline_utils import DiffusionPipeline, StableDiffusionMixin
 from . import StableDiffusionPipelineOutput
 from .safety_checker import StableDiffusionSafetyChecker
 
 
-if is_torch_xla_available():
-    import torch_xla.core.xla_model as xm
-
-    XLA_AVAILABLE = True
-else:
-    XLA_AVAILABLE = False
-
 logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
 
 
@@ -86,7 +79,6 @@ class StableDiffusionInstructPix2PixPipeline(
     TextualInversionLoaderMixin,
     StableDiffusionLoraLoaderMixin,
     IPAdapterMixin,
-    FromSingleFileMixin,
 ):
     r"""
     Pipeline for pixel-level image editing by following text instructions (based on Stable Diffusion).
@@ -114,8 +106,8 @@ class StableDiffusionInstructPix2PixPipeline(
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for
-            more details about a model's potential harms.
+            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            about a model's potential harms.
         feature_extractor ([`~transformers.CLIPImageProcessor`]):
             A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
     """
@@ -465,9 +457,6 @@ class StableDiffusionInstructPix2PixPipeline(
                         step_idx = i // getattr(self.scheduler, "order", 1)
                         callback(step_idx, t, latents)
 
-                if XLA_AVAILABLE:
-                    xm.mark_step()
-
         if not output_type == "latent":
             image = self.vae.decode(latents / self.vae.config.scaling_factor, return_dict=False)[0]
             image, has_nsfw_concept = self.run_safety_checker(image, device, prompt_embeds.dtype)

src/diffusers/pipelines/stable_diffusion_3/pipeline_stable_diffusion_3.py

@@ -870,8 +870,7 @@ class StableDiffusion3Pipeline(DiffusionPipeline, SD3LoraLoaderMixin, FromSingle
                 Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                 weighting. If not provided, pooled negative_prompt_embeds will be generated from `negative_prompt`
                 input argument.
-            ip_adapter_image (`PipelineImageInput`, *optional*):
-                Optional image input to work with IP Adapters.
+            ip_adapter_image (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
             ip_adapter_image_embeds (`torch.Tensor`, *optional*):
                 Pre-generated image embeddings for IP-Adapter. Should be a tensor of shape `(batch_size, num_images,
                 emb_dim)`. It should contain the negative image embedding if `do_classifier_free_guidance` is set to

src/diffusers/pipelines/stable_diffusion_attend_and_excite/pipeline_stable_diffusion_attend_and_excite.py

@@ -194,8 +194,8 @@ class StableDiffusionAttendAndExcitePipeline(DiffusionPipeline, StableDiffusionM
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for
-            more details about a model's potential harms.
+            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            about a model's potential harms.
         feature_extractor ([`~transformers.CLIPImageProcessor`]):
             A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
     """

src/diffusers/pipelines/stable_diffusion_diffedit/pipeline_stable_diffusion_diffedit.py

@@ -268,8 +268,8 @@ class StableDiffusionDiffEditPipeline(
             A scheduler to be used in combination with `unet` to fill in the unmasked part of the input latents.
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for
-            more details about a model's potential harms.
+            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            about a model's potential harms.
         feature_extractor ([`~transformers.CLIPImageProcessor`]):
             A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
     """
@@ -345,8 +345,8 @@ class StableDiffusionDiffEditPipeline(
                 "The configuration file of the unet has set the default `sample_size` to smaller than"
                 " 64 which seems highly unlikely .If you're checkpoint is a fine-tuned version of any of the"
                 " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
-                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
+                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                 " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                 " in the config might lead to incorrect results in future versions. If you have downloaded this"
                 " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"

src/diffusers/pipelines/stable_diffusion_gligen/pipeline_stable_diffusion_gligen.py

@@ -120,8 +120,8 @@ class StableDiffusionGLIGENPipeline(DiffusionPipeline, StableDiffusionMixin):
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for
-            more details about a model's potential harms.
+            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            about a model's potential harms.
         feature_extractor ([`~transformers.CLIPImageProcessor`]):
             A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
     """

src/diffusers/pipelines/stable_diffusion_gligen/pipeline_stable_diffusion_gligen_text_image.py

@@ -172,8 +172,8 @@ class StableDiffusionGLIGENTextImagePipeline(DiffusionPipeline, StableDiffusionM
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for
-            more details about a model's potential harms.
+            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            about a model's potential harms.
         feature_extractor ([`~transformers.CLIPImageProcessor`]):
             A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
     """

src/diffusers/pipelines/stable_diffusion_k_diffusion/pipeline_stable_diffusion_k_diffusion.py

@@ -83,8 +83,7 @@ class StableDiffusionKDiffusionPipeline(
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please, refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for
-            details.
+            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
         feature_extractor ([`CLIPImageProcessor`]):
             Model that extracts features from generated images to be used as inputs for the `safety_checker`.
     """