Release: v0.30.2

update to a place holder

.github/workflows/nightly_tests.yml

@@ -79,7 +79,7 @@ jobs:
           python utils/print_env.py
       - name: Pipeline CUDA Test
         env:
-          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
           # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
@@ -116,7 +116,6 @@ jobs:
       run:
         shell: bash
     strategy:
-      fail-fast: false
       max-parallel: 2
       matrix:
         module: [models, schedulers, lora, others, single_file, examples]
@@ -139,7 +138,7 @@ jobs:
     - name: Run nightly PyTorch CUDA tests for non-pipeline modules
       if: ${{ matrix.module != 'examples'}}
       env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
         # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
@@ -152,7 +151,7 @@ jobs:
     - name: Run nightly example tests with Torch
       if: ${{ matrix.module == 'examples' }}
       env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
         # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
@@ -209,7 +208,7 @@ jobs:
 
     - name: Run nightly Flax TPU tests
       env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
       run: |
         python -m pytest -n 0 \
           -s -v -k "Flax" \
@@ -264,7 +263,7 @@ jobs:
 
     - name: Run Nightly ONNXRuntime CUDA tests
       env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
       run: |
         python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
           -s -v -k "Onnx" \
@@ -291,118 +290,64 @@ jobs:
         pip install slack_sdk tabulate
         python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
 
-# M1 runner currently not well supported
-# TODO: (Dhruv) add these back when we setup better testing for Apple Silicon
-#  run_nightly_tests_apple_m1:
-#    name: Nightly PyTorch MPS tests on MacOS
-#    runs-on: [ self-hosted, apple-m1 ]
-#    if: github.event_name == 'schedule'
-#
-#    steps:
-#      - name: Checkout diffusers
-#        uses: actions/checkout@v3
-#        with:
-#          fetch-depth: 2
-#
-#      - name: Clean checkout
-#        shell: arch -arch arm64 bash {0}
-#        run: |
-#          git clean -fxd
-#      - name: Setup miniconda
-#        uses: ./.github/actions/setup-miniconda
-#        with:
-#          python-version: 3.9
-#
-#      - name: Install dependencies
-#        shell: arch -arch arm64 bash {0}
-#        run: |
-#          ${CONDA_RUN} python -m pip install --upgrade pip uv
-#          ${CONDA_RUN} python -m uv pip install -e [quality,test]
-#          ${CONDA_RUN} python -m uv pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cpu
-#          ${CONDA_RUN} python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate
-#          ${CONDA_RUN} python -m uv pip install pytest-reportlog
-#      - name: Environment
-#        shell: arch -arch arm64 bash {0}
-#        run: |
-#          ${CONDA_RUN} python utils/print_env.py
-#      - name: Run nightly PyTorch tests on M1 (MPS)
-#        shell: arch -arch arm64 bash {0}
-#        env:
-#          HF_HOME: /System/Volumes/Data/mnt/cache
-#          HF_TOKEN: ${{ secrets.HF_TOKEN }}
-#        run: |
-#          ${CONDA_RUN} python -m pytest -n 1 -s -v --make-reports=tests_torch_mps \
-#            --report-log=tests_torch_mps.log \
-#            tests/
-#      - name: Failure short reports
-#        if: ${{ failure() }}
-#        run: cat reports/tests_torch_mps_failures_short.txt
-#
-#      - name: Test suite reports artifacts
-#        if: ${{ always() }}
-#        uses: actions/upload-artifact@v2
-#        with:
-#          name: torch_mps_test_reports
-#          path: reports
-#
-#      - name: Generate Report and Notify Channel
-#        if: always()
-#        run: |
-#          pip install slack_sdk tabulate
-#          python utils/log_reports.py >> $GITHUB_STEP_SUMMARY  run_nightly_tests_apple_m1:
-#    name: Nightly PyTorch MPS tests on MacOS
-#    runs-on: [ self-hosted, apple-m1 ]
-#    if: github.event_name == 'schedule'
-#
-#    steps:
-#      - name: Checkout diffusers
-#        uses: actions/checkout@v3
-#        with:
-#          fetch-depth: 2
-#
-#      - name: Clean checkout
-#        shell: arch -arch arm64 bash {0}
-#        run: |
-#          git clean -fxd
-#      - name: Setup miniconda
-#        uses: ./.github/actions/setup-miniconda
-#        with:
-#          python-version: 3.9
-#
-#      - name: Install dependencies
-#        shell: arch -arch arm64 bash {0}
-#        run: |
-#          ${CONDA_RUN} python -m pip install --upgrade pip uv
-#          ${CONDA_RUN} python -m uv pip install -e [quality,test]
-#          ${CONDA_RUN} python -m uv pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cpu
-#          ${CONDA_RUN} python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate
-#          ${CONDA_RUN} python -m uv pip install pytest-reportlog
-#      - name: Environment
-#        shell: arch -arch arm64 bash {0}
-#        run: |
-#          ${CONDA_RUN} python utils/print_env.py
-#      - name: Run nightly PyTorch tests on M1 (MPS)
-#        shell: arch -arch arm64 bash {0}
-#        env:
-#          HF_HOME: /System/Volumes/Data/mnt/cache
-#          HF_TOKEN: ${{ secrets.HF_TOKEN }}
-#        run: |
-#          ${CONDA_RUN} python -m pytest -n 1 -s -v --make-reports=tests_torch_mps \
-#            --report-log=tests_torch_mps.log \
-#            tests/
-#      - name: Failure short reports
-#        if: ${{ failure() }}
-#        run: cat reports/tests_torch_mps_failures_short.txt
-#
-#      - name: Test suite reports artifacts
-#        if: ${{ always() }}
-#        uses: actions/upload-artifact@v2
-#        with:
-#          name: torch_mps_test_reports
-#          path: reports
-#
-#      - name: Generate Report and Notify Channel
-#        if: always()
-#        run: |
-#          pip install slack_sdk tabulate
-#          python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
+  run_nightly_tests_apple_m1:
+    name: Nightly PyTorch MPS tests on MacOS
+    runs-on: [ self-hosted, apple-m1 ]
+    if: github.event_name == 'schedule'
+
+    steps:
+      - name: Checkout diffusers
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 2
+
+      - name: Clean checkout
+        shell: arch -arch arm64 bash {0}
+        run: |
+          git clean -fxd
+
+      - name: Setup miniconda
+        uses: ./.github/actions/setup-miniconda
+        with:
+          python-version: 3.9
+
+      - name: Install dependencies
+        shell: arch -arch arm64 bash {0}
+        run: |
+          ${CONDA_RUN} python -m pip install --upgrade pip uv
+          ${CONDA_RUN} python -m uv pip install -e [quality,test]
+          ${CONDA_RUN} python -m uv pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cpu
+          ${CONDA_RUN} python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate
+          ${CONDA_RUN} python -m uv pip install pytest-reportlog
+
+      - name: Environment
+        shell: arch -arch arm64 bash {0}
+        run: |
+          ${CONDA_RUN} python utils/print_env.py
+
+      - name: Run nightly PyTorch tests on M1 (MPS)
+        shell: arch -arch arm64 bash {0}
+        env:
+          HF_HOME: /System/Volumes/Data/mnt/cache
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        run: |
+          ${CONDA_RUN} python -m pytest -n 1 -s -v --make-reports=tests_torch_mps \
+            --report-log=tests_torch_mps.log \
+            tests/
+
+      - name: Failure short reports
+        if: ${{ failure() }}
+        run: cat reports/tests_torch_mps_failures_short.txt
+
+      - name: Test suite reports artifacts
+        if: ${{ always() }}
+        uses: actions/upload-artifact@v2
+        with:
+          name: torch_mps_test_reports
+          path: reports
+
+      - name: Generate Report and Notify Channel
+        if: always()
+        run: |
+          pip install slack_sdk tabulate
+          python utils/log_reports.py >> $GITHUB_STEP_SUMMARY

.github/workflows/push_tests.yml

@@ -1,4 +1,4 @@
-name: Fast GPU Tests on main
+name: Slow Tests on main
 
 on:
   push:
@@ -112,8 +112,6 @@ jobs:
       run:
         shell: bash
     strategy:
-      fail-fast: false
-      max-parallel: 2
       matrix:
         module: [models, schedulers, lora, others, single_file]
     steps:

.github/workflows/release_tests_fast.yml

@@ -1,389 +0,0 @@
-# Duplicate workflow to push_tests.yml that is meant to run on release/patch branches as a final check
-# Creating a duplicate workflow here is simpler than adding complex path/branch parsing logic to push_tests.yml
-# Needs to be updated if push_tests.yml updated
-name: (Release) Fast GPU Tests on main
-
-on:
-  push:
-    branches:
-      - "v*.*.*-release"
-      - "v*.*.*-patch"
-
-env:
-  DIFFUSERS_IS_CI: yes
-  OMP_NUM_THREADS: 8
-  MKL_NUM_THREADS: 8
-  PYTEST_TIMEOUT: 600
-  PIPELINE_USAGE_CUTOFF: 50000
-
-jobs:
-  setup_torch_cuda_pipeline_matrix:
-    name: Setup Torch Pipelines CUDA Slow Tests Matrix
-    runs-on:
-      group: aws-general-8-plus
-    container:
-      image: diffusers/diffusers-pytorch-cpu
-    outputs:
-      pipeline_test_matrix: ${{ steps.fetch_pipeline_matrix.outputs.pipeline_test_matrix }}
-    steps:
-      - name: Checkout diffusers
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 2
-      - name: Install dependencies
-        run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          python -m uv pip install -e [quality,test]
-      - name: Environment
-        run: |
-          python utils/print_env.py
-      - name: Fetch Pipeline Matrix
-        id: fetch_pipeline_matrix
-        run: |
-          matrix=$(python utils/fetch_torch_cuda_pipeline_test_matrix.py)
-          echo $matrix
-          echo "pipeline_test_matrix=$matrix" >> $GITHUB_OUTPUT
-      - name: Pipeline Tests Artifacts
-        if: ${{ always() }}
-        uses: actions/upload-artifact@v2
-        with:
-          name: test-pipelines.json
-          path: reports
-
-  torch_pipelines_cuda_tests:
-    name: Torch Pipelines CUDA Tests
-    needs: setup_torch_cuda_pipeline_matrix
-    strategy:
-      fail-fast: false
-      max-parallel: 8
-      matrix:
-        module: ${{ fromJson(needs.setup_torch_cuda_pipeline_matrix.outputs.pipeline_test_matrix) }}
-    runs-on:
-      group: aws-g4dn-2xlarge
-    container:
-      image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host --gpus 0
-    steps:
-      - name: Checkout diffusers
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 2
-      - name: NVIDIA-SMI
-        run: |
-          nvidia-smi
-      - name: Install dependencies
-        run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          python -m uv pip install -e [quality,test]
-          python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
-      - name: Environment
-        run: |
-          python utils/print_env.py
-      - name: Slow PyTorch CUDA checkpoint tests on Ubuntu
-        env:
-          HF_TOKEN: ${{ secrets.HF_TOKEN }}
-          # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
-          CUBLAS_WORKSPACE_CONFIG: :16:8
-        run: |
-          python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            -s -v -k "not Flax and not Onnx" \
-            --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
-            tests/pipelines/${{ matrix.module }}
-      - name: Failure short reports
-        if: ${{ failure() }}
-        run: |
-          cat reports/tests_pipeline_${{ matrix.module }}_cuda_stats.txt
-          cat reports/tests_pipeline_${{ matrix.module }}_cuda_failures_short.txt
-      - name: Test suite reports artifacts
-        if: ${{ always() }}
-        uses: actions/upload-artifact@v2
-        with:
-          name: pipeline_${{ matrix.module }}_test_reports
-          path: reports
-
-  torch_cuda_tests:
-    name: Torch CUDA Tests
-    runs-on:
-      group: aws-g4dn-2xlarge
-    container:
-      image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host --gpus 0
-    defaults:
-      run:
-        shell: bash
-    strategy:
-      fail-fast: false
-      max-parallel: 2
-      matrix:
-        module: [models, schedulers, lora, others, single_file]
-    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 accelerate@git+https://github.com/huggingface/accelerate.git
-        python -m uv pip install peft@git+https://github.com/huggingface/peft.git
-
-    - name: Environment
-      run: |
-        python utils/print_env.py
-
-    - name: Run PyTorch CUDA tests
-      env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
-        # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
-        CUBLAS_WORKSPACE_CONFIG: :16:8
-      run: |
-        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "not Flax and not Onnx" \
-          --make-reports=tests_torch_cuda \
-          tests/${{ matrix.module }}
-
-    - name: Failure short reports
-      if: ${{ failure() }}
-      run: |
-        cat reports/tests_torch_cuda_stats.txt
-        cat reports/tests_torch_cuda_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v2
-      with:
-        name: torch_cuda_test_reports
-        path: reports
-
-  flax_tpu_tests:
-    name: Flax TPU Tests
-    runs-on: docker-tpu
-    container:
-      image: diffusers/diffusers-flax-tpu
-      options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/ --privileged
-    defaults:
-      run:
-        shell: bash
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: Install dependencies
-      run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
-        python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
-
-    - name: Environment
-      run: |
-        python utils/print_env.py
-
-    - name: Run slow Flax TPU tests
-      env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
-      run: |
-        python -m pytest -n 0 \
-          -s -v -k "Flax" \
-          --make-reports=tests_flax_tpu \
-          tests/
-
-    - name: Failure short reports
-      if: ${{ failure() }}
-      run: |
-        cat reports/tests_flax_tpu_stats.txt
-        cat reports/tests_flax_tpu_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v2
-      with:
-        name: flax_tpu_test_reports
-        path: reports
-
-  onnx_cuda_tests:
-    name: ONNX CUDA Tests
-    runs-on:
-      group: aws-g4dn-2xlarge
-    container:
-      image: diffusers/diffusers-onnxruntime-cuda
-      options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/ --gpus 0
-    defaults:
-      run:
-        shell: bash
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: Install dependencies
-      run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
-        python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
-
-    - name: Environment
-      run: |
-        python utils/print_env.py
-
-    - name: Run slow ONNXRuntime CUDA tests
-      env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
-      run: |
-        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "Onnx" \
-          --make-reports=tests_onnx_cuda \
-          tests/
-
-    - name: Failure short reports
-      if: ${{ failure() }}
-      run: |
-        cat reports/tests_onnx_cuda_stats.txt
-        cat reports/tests_onnx_cuda_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v2
-      with:
-        name: onnx_cuda_test_reports
-        path: reports
-
-  run_torch_compile_tests:
-    name: PyTorch Compile CUDA tests
-
-    runs-on:
-      group: aws-g4dn-2xlarge
-
-    container:
-      image: diffusers/diffusers-pytorch-compile-cuda
-      options: --gpus 0 --shm-size "16gb" --ipc host
-
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: NVIDIA-SMI
-      run: |
-        nvidia-smi
-    - name: Install dependencies
-      run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test,training]
-    - name: Environment
-      run: |
-        python utils/print_env.py
-    - name: Run example tests on GPU
-      env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
-        RUN_COMPILE: yes
-      run: |
-        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v -k "compile" --make-reports=tests_torch_compile_cuda tests/
-    - name: Failure short reports
-      if: ${{ failure() }}
-      run: cat reports/tests_torch_compile_cuda_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v2
-      with:
-        name: torch_compile_test_reports
-        path: reports
-
-  run_xformers_tests:
-    name: PyTorch xformers CUDA tests
-
-    runs-on:
-      group: aws-g4dn-2xlarge
-
-    container:
-      image: diffusers/diffusers-pytorch-xformers-cuda
-      options: --gpus 0 --shm-size "16gb" --ipc host
-
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: NVIDIA-SMI
-      run: |
-        nvidia-smi
-    - name: Install dependencies
-      run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test,training]
-    - name: Environment
-      run: |
-        python utils/print_env.py
-    - name: Run example tests on GPU
-      env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
-      run: |
-        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v -k "xformers" --make-reports=tests_torch_xformers_cuda tests/
-    - name: Failure short reports
-      if: ${{ failure() }}
-      run: cat reports/tests_torch_xformers_cuda_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v2
-      with:
-        name: torch_xformers_test_reports
-        path: reports
-
-  run_examples_tests:
-    name: Examples PyTorch CUDA tests on Ubuntu
-
-    runs-on:
-      group: aws-g4dn-2xlarge
-
-    container:
-      image: diffusers/diffusers-pytorch-cuda
-      options: --gpus 0 --shm-size "16gb" --ipc host
-
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: NVIDIA-SMI
-      run: |
-        nvidia-smi
-
-    - name: Install dependencies
-      run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test,training]
-
-    - name: Environment
-      run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python utils/print_env.py
-
-    - name: Run example tests on GPU
-      env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
-      run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install timm
-        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v --make-reports=examples_torch_cuda examples/
-
-    - name: Failure short reports
-      if: ${{ failure() }}
-      run: |
-        cat reports/examples_torch_cuda_stats.txt
-        cat reports/examples_torch_cuda_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v2
-      with:
-        name: examples_test_reports
-        path: reports

CONTRIBUTING.md

@@ -57,7 +57,7 @@ Any question or comment related to the Diffusers library can be asked on the [di
 - ...
 
 Every question that is asked on the forum or on Discord actively encourages the community to publicly
-share knowledge and might very well help a beginner in the future who has the same question you're
+share knowledge and might very well help a beginner in the future that has the same question you're
 having. Please do pose any questions you might have.
 In the same spirit, you are of immense help to the community by answering such questions because this way you are publicly documenting knowledge for everybody to learn from.
 
@@ -503,4 +503,4 @@ $ git push --set-upstream origin your-branch-for-syncing
 
 ### Style guide
 
-For documentation strings, 🧨 Diffusers follows the [Google style](https://google.github.io/styleguide/pyguide.html).
+For documentation strings, 🧨 Diffusers follows the [Google style](https://google.github.io/styleguide/pyguide.html).

PHILOSOPHY.md

@@ -15,7 +15,7 @@ specific language governing permissions and limitations under the License.
 🧨 Diffusers provides **state-of-the-art** pretrained diffusion models across multiple modalities.
 Its purpose is to serve as a **modular toolbox** for both inference and training.
 
-We aim to build a library that stands the test of time and therefore take API design very seriously.
+We aim at building a library that stands the test of time and therefore take API design very seriously.
 
 In a nutshell, Diffusers is built to be a natural extension of PyTorch. Therefore, most of our design choices are based on [PyTorch's Design Principles](https://pytorch.org/docs/stable/community/design.html#pytorch-design-philosophy). Let's go over the most important ones:
 
@@ -107,4 +107,4 @@ The following design principles are followed:
 - Every scheduler exposes the timesteps to be "looped over" via a `timesteps` attribute, which is an array of timesteps the model will be called upon.
 - The `step(...)` function takes a predicted model output and the "current" sample (x_t) and returns the "previous", slightly more denoised sample (x_t-1).
 - Given the complexity of diffusion schedulers, the `step` function does not expose all the complexity and can be a bit of a "black box".
-- In almost all cases, novel schedulers shall be implemented in a new scheduling file.
+- In almost all cases, novel schedulers shall be implemented in a new scheduling file.

README.md

@@ -202,7 +202,6 @@ Also, say 👋 in our public Discord channel <a href="https://discord.gg/G7tWnz9
 
 - https://github.com/microsoft/TaskMatrix
 - https://github.com/invoke-ai/InvokeAI
-- https://github.com/InstantID/InstantID
 - https://github.com/apple/ml-stable-diffusion
 - https://github.com/Sanster/lama-cleaner
 - https://github.com/IDEA-Research/Grounded-Segment-Anything

docs/source/en/_toctree.yml

@@ -223,78 +223,68 @@
     sections:
     - local: api/models/overview
       title: Overview
-    - sections:
-      - local: api/models/controlnet
-        title: ControlNetModel
-      - local: api/models/controlnet_flux
-        title: FluxControlNetModel
-      - local: api/models/controlnet_hunyuandit
-        title: HunyuanDiT2DControlNetModel
-      - local: api/models/controlnet_sd3
-        title: SD3ControlNetModel
-      - local: api/models/controlnet_sparsectrl
-        title: SparseControlNetModel
-      title: ControlNets
-    - sections:
-      - local: api/models/aura_flow_transformer2d
-        title: AuraFlowTransformer2DModel
-      - local: api/models/cogvideox_transformer3d
-        title: CogVideoXTransformer3DModel
-      - local: api/models/dit_transformer2d
-        title: DiTTransformer2DModel
-      - local: api/models/flux_transformer
-        title: FluxTransformer2DModel
-      - local: api/models/hunyuan_transformer2d
-        title: HunyuanDiT2DModel
-      - local: api/models/latte_transformer3d
-        title: LatteTransformer3DModel
-      - local: api/models/lumina_nextdit2d
-        title: LuminaNextDiT2DModel
-      - local: api/models/pixart_transformer2d
-        title: PixArtTransformer2DModel
-      - local: api/models/prior_transformer
-        title: PriorTransformer
-      - local: api/models/sd3_transformer2d
-        title: SD3Transformer2DModel
-      - local: api/models/stable_audio_transformer
-        title: StableAudioDiTModel
-      - local: api/models/transformer2d
-        title: Transformer2DModel
-      - local: api/models/transformer_temporal
-        title: TransformerTemporalModel
-      title: Transformers
-    - sections:
-      - local: api/models/stable_cascade_unet
-        title: StableCascadeUNet
-      - local: api/models/unet
-        title: UNet1DModel
-      - local: api/models/unet2d
-        title: UNet2DModel
-      - local: api/models/unet2d-cond
-        title: UNet2DConditionModel
-      - local: api/models/unet3d-cond
-        title: UNet3DConditionModel
-      - local: api/models/unet-motion
-        title: UNetMotionModel
-      - local: api/models/uvit2d
-        title: UViT2DModel
-      title: UNets
-    - sections:
-      - local: api/models/autoencoderkl
-        title: AutoencoderKL
-      - local: api/models/autoencoderkl_cogvideox
-        title: AutoencoderKLCogVideoX
-      - local: api/models/asymmetricautoencoderkl
-        title: AsymmetricAutoencoderKL
-      - local: api/models/consistency_decoder_vae
-        title: ConsistencyDecoderVAE
-      - local: api/models/autoencoder_oobleck
-        title: Oobleck AutoEncoder
-      - local: api/models/autoencoder_tiny
-        title: Tiny AutoEncoder
-      - local: api/models/vq
-        title: VQModel
-      title: VAEs
+    - local: api/models/unet
+      title: UNet1DModel
+    - local: api/models/unet2d
+      title: UNet2DModel
+    - local: api/models/unet2d-cond
+      title: UNet2DConditionModel
+    - local: api/models/unet3d-cond
+      title: UNet3DConditionModel
+    - local: api/models/unet-motion
+      title: UNetMotionModel
+    - local: api/models/uvit2d
+      title: UViT2DModel
+    - local: api/models/vq
+      title: VQModel
+    - local: api/models/autoencoderkl
+      title: AutoencoderKL
+    - local: api/models/autoencoderkl_cogvideox
+      title: AutoencoderKLCogVideoX
+    - local: api/models/asymmetricautoencoderkl
+      title: AsymmetricAutoencoderKL
+    - local: api/models/stable_cascade_unet
+      title: StableCascadeUNet
+    - local: api/models/autoencoder_tiny
+      title: Tiny AutoEncoder
+    - local: api/models/autoencoder_oobleck
+      title: Oobleck AutoEncoder
+    - local: api/models/consistency_decoder_vae
+      title: ConsistencyDecoderVAE
+    - local: api/models/transformer2d
+      title: Transformer2DModel
+    - local: api/models/pixart_transformer2d
+      title: PixArtTransformer2DModel
+    - local: api/models/dit_transformer2d
+      title: DiTTransformer2DModel
+    - local: api/models/hunyuan_transformer2d
+      title: HunyuanDiT2DModel
+    - local: api/models/aura_flow_transformer2d
+      title: AuraFlowTransformer2DModel
+    - local: api/models/flux_transformer
+      title: FluxTransformer2DModel
+    - local: api/models/latte_transformer3d
+      title: LatteTransformer3DModel
+    - local: api/models/cogvideox_transformer3d
+      title: CogVideoXTransformer3DModel
+    - local: api/models/lumina_nextdit2d
+      title: LuminaNextDiT2DModel
+    - local: api/models/transformer_temporal
+      title: TransformerTemporalModel
+    - local: api/models/sd3_transformer2d
+      title: SD3Transformer2DModel
+    - local: api/models/stable_audio_transformer
+      title: StableAudioDiTModel
+    - local: api/models/prior_transformer
+      title: PriorTransformer
+    - local: api/models/controlnet
+      title: ControlNetModel
+    - local: api/models/controlnet_hunyuandit
+      title: HunyuanDiT2DControlNetModel
+    - local: api/models/controlnet_sd3
+      title: SD3ControlNetModel
+    - local: api/models/controlnet_sparsectrl
+      title: SparseControlNetModel
     title: Models
   - isExpanded: false
     sections:
@@ -322,8 +312,6 @@
       title: Consistency Models
     - local: api/pipelines/controlnet
       title: ControlNet
-    - local: api/pipelines/controlnet_flux
-      title: ControlNet with Flux.1
     - local: api/pipelines/controlnet_hunyuandit
       title: ControlNet with Hunyuan-DiT
     - local: api/pipelines/controlnet_sd3

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

@@ -1,45 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team and The InstantX 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.
--->
-
-# FluxControlNetModel
-
-FluxControlNetModel is an implementation of ControlNet for Flux.1.
-
-The ControlNet model was introduced in [Adding Conditional Control to Text-to-Image Diffusion Models](https://huggingface.co/papers/2302.05543) by Lvmin Zhang, Anyi Rao, Maneesh Agrawala. It provides a greater degree of control over text-to-image generation by conditioning the model on additional inputs such as edge maps, depth maps, segmentation maps, and keypoints for pose detection.
-
-The abstract from the paper is:
-
-*We present ControlNet, a neural network architecture to add spatial conditioning controls to large, pretrained text-to-image diffusion models. ControlNet locks the production-ready large diffusion models, and reuses their deep and robust encoding layers pretrained with billions of images as a strong backbone to learn a diverse set of conditional controls. The neural architecture is connected with "zero convolutions" (zero-initialized convolution layers) that progressively grow the parameters from zero and ensure that no harmful noise could affect the finetuning. We test various conditioning controls, eg, edges, depth, segmentation, human pose, etc, with Stable Diffusion, using single or multiple conditions, with or without prompts. We show that the training of ControlNets is robust with small (<50k) and large (>1m) datasets. Extensive results show that ControlNet may facilitate wider applications to control image diffusion models.*
-
-## Loading from the original format
-
-By default the [`FluxControlNetModel`] should be loaded with [`~ModelMixin.from_pretrained`].
-
-```py
-from diffusers import FluxControlNetPipeline
-from diffusers.models import FluxControlNetModel, FluxMultiControlNetModel
-
-controlnet = FluxControlNetModel.from_pretrained("InstantX/FLUX.1-dev-Controlnet-Canny")
-pipe = FluxControlNetPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", controlnet=controlnet)
-
-controlnet = FluxControlNetModel.from_pretrained("InstantX/FLUX.1-dev-Controlnet-Canny")
-controlnet = FluxMultiControlNetModel([controlnet])
-pipe = FluxControlNetPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", controlnet=controlnet)
-```
-
-## FluxControlNetModel
-
-[[autodoc]] FluxControlNetModel
-
-## FluxControlNetOutput
-
-[[autodoc]] models.controlnet_flux.FluxControlNetOutput

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

@@ -77,33 +77,16 @@ CogVideoX-2b requires about 19 GB of GPU memory to decode 49 frames (6 seconds o
 - `pipe.enable_model_cpu_offload()`:
   - Without enabling cpu offloading, memory usage is `33 GB`
   - With enabling cpu offloading, memory usage is `19 GB`
-- `pipe.enable_sequential_cpu_offload()`:
-  - Similar to `enable_model_cpu_offload` but can significantly reduce memory usage at the cost of slow inference
-  - When enabled, memory usage is under `4 GB`
 - `pipe.vae.enable_tiling()`:
   - With enabling cpu offloading and tiling, memory usage is `11 GB`
 - `pipe.vae.enable_slicing()`
 
-### Quantized inference
-
-[torchao](https://github.com/pytorch/ao) and [optimum-quanto](https://github.com/huggingface/optimum-quanto/) can be used to quantize the text encoder, transformer and VAE modules to lower the memory requirements. This makes it possible to run the model on a free-tier T4 Colab or lower VRAM GPUs!
-
-It is also worth noting that torchao quantization is fully compatible with [torch.compile](/optimization/torch2.0#torchcompile), which allows for much faster inference speed. Additionally, models can be serialized and stored in a quantized datatype to save disk space with torchao. Find examples and benchmarks in the gists below.
-- [torchao](https://gist.github.com/a-r-r-o-w/4d9732d17412888c885480c6521a9897)
-- [quanto](https://gist.github.com/a-r-r-o-w/31be62828b00a9292821b85c1017effa)
-
 ## CogVideoXPipeline
 
 [[autodoc]] CogVideoXPipeline
   - all
   - __call__
 
-## CogVideoXVideoToVideoPipeline
-
-[[autodoc]] CogVideoXVideoToVideoPipeline
-  - all
-  - __call__
-
 ## CogVideoXPipelineOutput
 
-[[autodoc]] pipelines.cogvideo.pipeline_output.CogVideoXPipelineOutput
+[[autodoc]] pipelines.cogvideo.pipeline_cogvideox.CogVideoXPipelineOutput

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

@@ -1,48 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team and The InstantX 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.
--->
-
-# ControlNet with Flux.1
-
-FluxControlNetPipeline is an implementation of ControlNet for Flux.1.
-
-ControlNet was introduced in [Adding Conditional Control to Text-to-Image Diffusion Models](https://huggingface.co/papers/2302.05543) by Lvmin Zhang, Anyi Rao, and Maneesh Agrawala.
-
-With a ControlNet model, you can provide an additional control image to condition and control Stable Diffusion generation. For example, if you provide a depth map, the ControlNet model generates an image that'll preserve the spatial information from the depth map. It is a more flexible and accurate way to control the image generation process.
-
-The abstract from the paper is:
-
-*We present ControlNet, a neural network architecture to add spatial conditioning controls to large, pretrained text-to-image diffusion models. ControlNet locks the production-ready large diffusion models, and reuses their deep and robust encoding layers pretrained with billions of images as a strong backbone to learn a diverse set of conditional controls. The neural architecture is connected with "zero convolutions" (zero-initialized convolution layers) that progressively grow the parameters from zero and ensure that no harmful noise could affect the finetuning. We test various conditioning controls, eg, edges, depth, segmentation, human pose, etc, with Stable Diffusion, using single or multiple conditions, with or without prompts. We show that the training of ControlNets is robust with small (<50k) and large (>1m) datasets. Extensive results show that ControlNet may facilitate wider applications to control image diffusion models.*
-
-This controlnet code is implemented by [The InstantX Team](https://huggingface.co/InstantX). You can find pre-trained checkpoints for Flux-ControlNet in the table below:
-
-
-| ControlNet type | Developer | Link |
-| -------- | ---------- | ---- |
-| Canny | [The InstantX Team](https://huggingface.co/InstantX) | [Link](https://huggingface.co/InstantX/FLUX.1-dev-Controlnet-Canny) |
-| Depth | [The InstantX Team](https://huggingface.co/InstantX) | [Link](https://huggingface.co/Shakker-Labs/FLUX.1-dev-ControlNet-Depth) |
-| Union | [The InstantX Team](https://huggingface.co/InstantX) | [Link](https://huggingface.co/InstantX/FLUX.1-dev-Controlnet-Union) |
-
-
-<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-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
-
-</Tip>
-
-## FluxControlNetPipeline
-[[autodoc]] FluxControlNetPipeline
-	- all
-	- __call__
-
-
-## FluxPipelineOutput
-[[autodoc]] pipelines.flux.pipeline_output.FluxPipelineOutput

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

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team and The InstantX 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
@@ -22,16 +22,7 @@ The abstract from the paper is:
 
 *We present ControlNet, a neural network architecture to add spatial conditioning controls to large, pretrained text-to-image diffusion models. ControlNet locks the production-ready large diffusion models, and reuses their deep and robust encoding layers pretrained with billions of images as a strong backbone to learn a diverse set of conditional controls. The neural architecture is connected with "zero convolutions" (zero-initialized convolution layers) that progressively grow the parameters from zero and ensure that no harmful noise could affect the finetuning. We test various conditioning controls, eg, edges, depth, segmentation, human pose, etc, with Stable Diffusion, using single or multiple conditions, with or without prompts. We show that the training of ControlNets is robust with small (<50k) and large (>1m) datasets. Extensive results show that ControlNet may facilitate wider applications to control image diffusion models.*
 
-This controlnet code is mainly implemented by [The InstantX Team](https://huggingface.co/InstantX). The inpainting-related code was developed by [The Alimama Creative Team](https://huggingface.co/alimama-creative). You can find pre-trained checkpoints for SD3-ControlNet in the table below:
-
-
-| ControlNet type | Developer | Link |
-| -------- | ---------- | ---- |
-| Canny | [The InstantX Team](https://huggingface.co/InstantX) | [Link](https://huggingface.co/InstantX/SD3-Controlnet-Canny) |
-| Pose | [The InstantX Team](https://huggingface.co/InstantX) | [Link](https://huggingface.co/InstantX/SD3-Controlnet-Pose) |
-| Tile | [The InstantX Team](https://huggingface.co/InstantX) | [Link](https://huggingface.co/InstantX/SD3-Controlnet-Tile) |
-| Inpainting | [The AlimamaCreative Team](https://huggingface.co/alimama-creative) | [link](https://huggingface.co/alimama-creative/SD3-Controlnet-Inpainting) |
-
+This code is implemented by [The InstantX Team](https://huggingface.co/InstantX). You can find pre-trained checkpoints for SD3-ControlNet on [The InstantX Team](https://huggingface.co/InstantX) Hub profile.
 
 <Tip>
 
@@ -44,10 +35,5 @@ Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers)
 	- all
 	- __call__
 
-## StableDiffusion3ControlNetInpaintingPipeline
-[[autodoc]] pipelines.controlnet_sd3.pipeline_stable_diffusion_3_controlnet_inpainting.StableDiffusion3ControlNetInpaintingPipeline
-	- all
-	- __call__
-
 ## StableDiffusion3PipelineOutput
 [[autodoc]] pipelines.stable_diffusion_3.pipeline_output.StableDiffusion3PipelineOutput

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

@@ -14,7 +14,7 @@ specific language governing permissions and limitations under the License.
 
 ![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/kolors/kolors_header_collage.png)
 
-Kolors is a large-scale text-to-image generation model based on latent diffusion, developed by [the Kuaishou Kolors team](https://github.com/Kwai-Kolors/Kolors). Trained on billions of text-image pairs, Kolors exhibits significant advantages over both open-source and closed-source models in visual quality, complex semantic accuracy, and text rendering for both Chinese and English characters. Furthermore, Kolors supports both Chinese and English inputs, demonstrating strong performance in understanding and generating Chinese-specific content. For more details, please refer to this [technical report](https://github.com/Kwai-Kolors/Kolors/blob/master/imgs/Kolors_paper.pdf).
+Kolors is a large-scale text-to-image generation model based on latent diffusion, developed by [the Kuaishou Kolors team](kwai-kolors@kuaishou.com). Trained on billions of text-image pairs, Kolors exhibits significant advantages over both open-source and closed-source models in visual quality, complex semantic accuracy, and text rendering for both Chinese and English characters. Furthermore, Kolors supports both Chinese and English inputs, demonstrating strong performance in understanding and generating Chinese-specific content. For more details, please refer to this [technical report](https://github.com/Kwai-Kolors/Kolors/blob/master/imgs/Kolors_paper.pdf).
 
 The abstract from the technical report is:
 
@@ -74,7 +74,7 @@ image_encoder = CLIPVisionModelWithProjection.from_pretrained(
 
 pipe = KolorsPipeline.from_pretrained(
     "Kwai-Kolors/Kolors-diffusers", image_encoder=image_encoder, torch_dtype=torch.float16, variant="fp16"
-)
+).to("cuda")
 pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config, use_karras_sigmas=True)
 
 pipe.load_ip_adapter(

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

@@ -30,64 +30,63 @@ The table below lists all the pipelines currently available in 🤗 Diffusers an
 
 | Pipeline | Tasks |
 |---|---|
-| [aMUSEd](amused) | text2image |
+| [AltDiffusion](alt_diffusion) | image2image |
 | [AnimateDiff](animatediff) | text2video |
 | [Attend-and-Excite](attend_and_excite) | text2image |
+| [Audio Diffusion](audio_diffusion) | image2audio |
 | [AudioLDM](audioldm) | text2audio |
 | [AudioLDM2](audioldm2) | text2audio |
-| [AuraFlow](auraflow) | text2image |
 | [BLIP Diffusion](blip_diffusion) | text2image |
-| [CogVideoX](cogvideox) | text2video |
 | [Consistency Models](consistency_models) | unconditional image generation |
 | [ControlNet](controlnet) | text2image, image2image, inpainting |
-| [ControlNet with Flux.1](controlnet_flux) | text2image |
-| [ControlNet with Hunyuan-DiT](controlnet_hunyuandit) | text2image |
-| [ControlNet with Stable Diffusion 3](controlnet_sd3) | text2image |
 | [ControlNet with Stable Diffusion XL](controlnet_sdxl) | text2image |
 | [ControlNet-XS](controlnetxs) | text2image |
 | [ControlNet-XS with Stable Diffusion XL](controlnetxs_sdxl) | text2image |
+| [Cycle Diffusion](cycle_diffusion) | image2image |
 | [Dance Diffusion](dance_diffusion) | unconditional audio generation |
 | [DDIM](ddim) | unconditional image generation |
 | [DDPM](ddpm) | unconditional image generation |
 | [DeepFloyd IF](deepfloyd_if) | text2image, image2image, inpainting, super-resolution |
 | [DiffEdit](diffedit) | inpainting |
 | [DiT](dit) | text2image |
-| [Flux](flux) | text2image |
-| [Hunyuan-DiT](hunyuandit) | text2image |
-| [I2VGen-XL](i2vgenxl) | text2video |
+| [GLIGEN](stable_diffusion/gligen) | text2image |
 | [InstructPix2Pix](pix2pix) | image editing |
 | [Kandinsky 2.1](kandinsky) | text2image, image2image, inpainting, interpolation |
 | [Kandinsky 2.2](kandinsky_v22) | text2image, image2image, inpainting |
 | [Kandinsky 3](kandinsky3) | text2image, image2image |
-| [Kolors](kolors) | text2image |
 | [Latent Consistency Models](latent_consistency_models) | text2image |
 | [Latent Diffusion](latent_diffusion) | text2image, super-resolution |
-| [Latte](latte) | text2image |
+| [LDM3D](stable_diffusion/ldm3d_diffusion) | text2image, text-to-3D, text-to-pano, upscaling |
 | [LEDITS++](ledits_pp) | image editing |
-| [Lumina-T2X](lumina) | text2image |
-| [Marigold](marigold) | depth |
 | [MultiDiffusion](panorama) | text2image |
 | [MusicLDM](musicldm) | text2audio |
-| [PAG](pag) | text2image |
 | [Paint by Example](paint_by_example) | inpainting |
-| [PIA](pia) | image2video |
+| [ParaDiGMS](paradigms) | text2image |
+| [Pix2Pix Zero](pix2pix_zero) | image editing |
 | [PixArt-α](pixart) | text2image |
-| [PixArt-Σ](pixart_sigma) | text2image |
+| [PNDM](pndm) | unconditional image generation |
+| [RePaint](repaint) | inpainting |
+| [Score SDE VE](score_sde_ve) | unconditional image generation |
 | [Self-Attention Guidance](self_attention_guidance) | text2image |
 | [Semantic Guidance](semantic_stable_diffusion) | text2image |
 | [Shap-E](shap_e) | text-to-3D, image-to-3D |
+| [Spectrogram Diffusion](spectrogram_diffusion) |  |
 | [Stable Audio](stable_audio) | text2audio |
-| [Stable Cascade](stable_cascade) | text2image |
 | [Stable Diffusion](stable_diffusion/overview) | text2image, image2image, depth2image, inpainting, image variation, latent upscaler, super-resolution |
+| [Stable Diffusion Model Editing](model_editing) | model editing |
 | [Stable Diffusion XL](stable_diffusion/stable_diffusion_xl) | text2image, image2image, inpainting |
 | [Stable Diffusion XL Turbo](stable_diffusion/sdxl_turbo) | text2image, image2image, inpainting |
 | [Stable unCLIP](stable_unclip) | text2image, image variation |
+| [Stochastic Karras VE](stochastic_karras_ve) | unconditional image generation |
 | [T2I-Adapter](stable_diffusion/adapter) | text2image |
 | [Text2Video](text_to_video) | text2video, video2video |
 | [Text2Video-Zero](text_to_video_zero) | text2video |
 | [unCLIP](unclip) | text2image, image variation |
+| [Unconditional Latent Diffusion](latent_diffusion_uncond) | unconditional image generation |
 | [UniDiffuser](unidiffuser) | text2image, image2text, image variation, text variation, unconditional image generation, unconditional audio generation |
 | [Value-guided planning](value_guided_sampling) | value guided sampling |
+| [Versatile Diffusion](versatile_diffusion) | text2image, image variation |
+| [VQ Diffusion](vq_diffusion) | text2image |
 | [Wuerstchen](wuerstchen) | text2image |
 
 ## DiffusionPipeline

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

@@ -20,7 +20,7 @@ The abstract from the paper is:
 
 *Recent studies have demonstrated that diffusion models are capable of generating high-quality samples, but their quality heavily depends on sampling guidance techniques, such as classifier guidance (CG) and classifier-free guidance (CFG). These techniques are often not applicable in unconditional generation or in various downstream tasks such as image restoration. In this paper, we propose a novel sampling guidance, called Perturbed-Attention Guidance (PAG), which improves diffusion sample quality across both unconditional and conditional settings, achieving this without requiring additional training or the integration of external modules. PAG is designed to progressively enhance the structure of samples throughout the denoising process. It involves generating intermediate samples with degraded structure by substituting selected self-attention maps in diffusion U-Net with an identity matrix, by considering the self-attention mechanisms' ability to capture structural information, and guiding the denoising process away from these degraded samples. In both ADM and Stable Diffusion, PAG surprisingly improves sample quality in conditional and even unconditional scenarios. Moreover, PAG significantly improves the baseline performance in various downstream tasks where existing guidances such as CG or CFG cannot be fully utilized, including ControlNet with empty prompts and image restoration such as inpainting and deblurring.*
 
-PAG can be used by specifying the `pag_applied_layers` as a parameter when instantiating a PAG pipeline. It can be a single string or a list of strings. Each string can be a unique layer identifier or a regular expression to identify one or more layers.
+PAG can be used by specifying the `pag_applied_layers` as a parameter when instantiating a PAG pipeline. It can be a single string or a list of strings. Each string can be a unique layer identifier or a regular expression to identify one or more layers. 
 
 - Full identifier as a normal string: `down_blocks.2.attentions.0.transformer_blocks.0.attn1.processor`
 - Full identifier as a RegEx: `down_blocks.2.(attentions|motion_modules).0.transformer_blocks.0.attn1.processor`
@@ -46,7 +46,7 @@ Since RegEx is supported as a way for matching layer identifiers, it is crucial
 ## KolorsPAGPipeline
 [[autodoc]] KolorsPAGPipeline
   - all
-  - __call__
+  - __call__  
 
 ## StableDiffusionPAGPipeline
 [[autodoc]] StableDiffusionPAGPipeline
@@ -78,10 +78,6 @@ Since RegEx is supported as a way for matching layer identifiers, it is crucial
 	- all
 	- __call__
 
-## StableDiffusionXLControlNetPAGImg2ImgPipeline
-[[autodoc]] StableDiffusionXLControlNetPAGImg2ImgPipeline
-	- all
-	- __call__
 
 ## StableDiffusion3PAGPipeline
 [[autodoc]] StableDiffusion3PAGPipeline

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

@@ -21,7 +21,7 @@ Stable Audio is trained on a corpus of around 48k audio recordings, where around
 The abstract of the paper is the following:
 *Open generative models are vitally important for the community, allowing for fine-tunes and serving as baselines when presenting new models. However, most current text-to-audio models are private and not accessible for artists and researchers to build upon. Here we describe the architecture and training process of a new open-weights text-to-audio model trained with Creative Commons data. Our evaluation shows that the model's performance is competitive with the state-of-the-art across various metrics. Notably, the reported FDopenl3 results (measuring the realism of the generations) showcase its potential for high-quality stereo sound synthesis at 44.1kHz.*
 
-This pipeline was contributed by [Yoach Lacombe](https://huggingface.co/ylacombe). The original codebase can be found at [Stability-AI/stable-audio-tools](https://github.com/Stability-AI/stable-audio-tools).
+This pipeline was contributed by [Yoach Lacombe](https://huggingface.co/ylacombe). The original codebase can be found at [Stability-AI/stable-audio-tool](https://github.com/Stability-AI/stable-audio-tool).
 
 ## Tips
 

docs/source/en/optimization/fp16.md

@@ -125,5 +125,3 @@ image
     <figcaption class="mt-2 text-center text-sm text-gray-500">distilled Stable Diffusion + Tiny AutoEncoder</figcaption>
   </div>
 </div>
-
-More tiny autoencoder models for other Stable Diffusion models, like Stable Diffusion 3, are available from [madebyollin](https://huggingface.co/madebyollin).

docs/source/en/stable_diffusion.md

@@ -238,7 +238,7 @@ Pretty impressive! Let's tweak the second image - corresponding to the `Generato
 ```python
 prompts = [
     "portrait photo of the oldest warrior chief, tribal panther make up, blue on red, side profile, looking away, serious eyes 50mm portrait photography, hard rim lighting photography--beta --ar 2:3  --beta --upbeta",
-    "portrait photo of an old warrior chief, tribal panther make up, blue on red, side profile, looking away, serious eyes 50mm portrait photography, hard rim lighting photography--beta --ar 2:3  --beta --upbeta",
+    "portrait photo of a old warrior chief, tribal panther make up, blue on red, side profile, looking away, serious eyes 50mm portrait photography, hard rim lighting photography--beta --ar 2:3  --beta --upbeta",
     "portrait photo of a warrior chief, tribal panther make up, blue on red, side profile, looking away, serious eyes 50mm portrait photography, hard rim lighting photography--beta --ar 2:3  --beta --upbeta",
     "portrait photo of a young warrior chief, tribal panther make up, blue on red, side profile, looking away, serious eyes 50mm portrait photography, hard rim lighting photography--beta --ar 2:3  --beta --upbeta",
 ]

docs/source/en/training/distributed_inference.md

@@ -48,7 +48,7 @@ accelerate launch run_distributed.py --num_processes=2
 
 <Tip>
 
-Refer to this minimal example [script](https://gist.github.com/sayakpaul/cfaebd221820d7b43fae638b4dfa01ba) for running inference across multiple GPUs. To learn more, take a look at the [Distributed Inference with 🤗 Accelerate](https://huggingface.co/docs/accelerate/en/usage_guides/distributed_inference#distributed-inference-with-accelerate) guide.
+To learn more, take a look at the [Distributed Inference with 🤗 Accelerate](https://huggingface.co/docs/accelerate/en/usage_guides/distributed_inference#distributed-inference-with-accelerate) guide.
 
 </Tip>
 
@@ -108,4 +108,4 @@ torchrun run_distributed.py --nproc_per_node=2
 ```
 
 > [!TIP]
-> You can use `device_map` within a [`DiffusionPipeline`] to distribute its model-level components on multiple devices. Refer to the [Device placement](../tutorials/inference_with_big_models#device-placement) guide to learn more.
+> You can use `device_map` within a [`DiffusionPipeline`] to distribute its model-level components on multiple devices. Refer to the [Device placement](../tutorials/inference_with_big_models#device-placement) guide to learn more.

docs/source/en/using-diffusers/merge_loras.md

@@ -14,9 +14,9 @@ specific language governing permissions and limitations under the License.
 
 It can be fun and creative to use multiple [LoRAs]((https://huggingface.co/docs/peft/conceptual_guides/adapter#low-rank-adaptation-lora)) together to generate something entirely new and unique. This works by merging multiple LoRA weights together to produce images that are a blend of different styles. Diffusers provides a few methods to merge LoRAs depending on *how* you want to merge their weights, which can affect image quality.
 
-This guide will show you how to merge LoRAs using the [`~loaders.PeftAdapterMixin.set_adapters`] and [add_weighted_adapter](https://huggingface.co/docs/peft/package_reference/lora#peft.LoraModel.add_weighted_adapter) methods. To improve inference speed and reduce memory-usage of merged LoRAs, you'll also see how to use the [`~loaders.StableDiffusionLoraLoaderMixin.fuse_lora`] method to fuse the LoRA weights with the original weights of the underlying model.
+This guide will show you how to merge LoRAs using the [`~loaders.UNet2DConditionLoadersMixin.set_adapters`] and [`~peft.LoraModel.add_weighted_adapter`] methods. To improve inference speed and reduce memory-usage of merged LoRAs, you'll also see how to use the [`~loaders.StableDiffusionLoraLoaderMixin.fuse_lora`] method to fuse the LoRA weights with the original weights of the underlying model.
 
-For this guide, load a Stable Diffusion XL (SDXL) checkpoint and the [KappaNeuro/studio-ghibli-style](https://huggingface.co/KappaNeuro/studio-ghibli-style) and [Norod78/sdxl-chalkboarddrawing-lora](https://huggingface.co/Norod78/sdxl-chalkboarddrawing-lora) LoRAs with the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method. You'll need to assign each LoRA an `adapter_name` to combine them later.
+For this guide, load a Stable Diffusion XL (SDXL) checkpoint and the [KappaNeuro/studio-ghibli-style]() and [Norod78/sdxl-chalkboarddrawing-lora]() LoRAs with the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method. You'll need to assign each LoRA an `adapter_name` to combine them later.
 
 ```py
 from diffusers import DiffusionPipeline
@@ -29,7 +29,7 @@ pipeline.load_lora_weights("lordjia/by-feng-zikai", weight_name="fengzikai_v1.0_
 
 ## set_adapters
 
-The [`~loaders.PeftAdapterMixin.set_adapters`] method merges LoRA adapters by concatenating their weighted matrices. Use the adapter name to specify which LoRAs to merge, and the `adapter_weights` parameter to control the scaling for each LoRA. For example, if `adapter_weights=[0.5, 0.5]`, then the merged LoRA output is an average of both LoRAs. Try adjusting the adapter weights to see how it affects the generated image!
+The [`~loaders.UNet2DConditionLoadersMixin.set_adapters`] method merges LoRA adapters by concatenating their weighted matrices. Use the adapter name to specify which LoRAs to merge, and the `adapter_weights` parameter to control the scaling for each LoRA. For example, if `adapter_weights=[0.5, 0.5]`, then the merged LoRA output is an average of both LoRAs. Try adjusting the adapter weights to see how it affects the generated image!
 
 ```py
 pipeline.set_adapters(["ikea", "feng"], adapter_weights=[0.7, 0.8])
@@ -47,19 +47,19 @@ image
 ## add_weighted_adapter
 
 > [!WARNING]
-> This is an experimental method that adds PEFTs [add_weighted_adapter](https://huggingface.co/docs/peft/package_reference/lora#peft.LoraModel.add_weighted_adapter) method to Diffusers to enable more efficient merging methods. Check out this [issue](https://github.com/huggingface/diffusers/issues/6892) if you're interested in learning more about the motivation and design behind this integration.
+> This is an experimental method that adds PEFTs [`~peft.LoraModel.add_weighted_adapter`] method to Diffusers to enable more efficient merging methods. Check out this [issue](https://github.com/huggingface/diffusers/issues/6892) if you're interested in learning more about the motivation and design behind this integration.
 
-The [add_weighted_adapter](https://huggingface.co/docs/peft/package_reference/lora#peft.LoraModel.add_weighted_adapter) method provides access to more efficient merging method such as [TIES and DARE](https://huggingface.co/docs/peft/developer_guides/model_merging). To use these merging methods, make sure you have the latest stable version of Diffusers and PEFT installed.
+The [`~peft.LoraModel.add_weighted_adapter`] method provides access to more efficient merging method such as [TIES and DARE](https://huggingface.co/docs/peft/developer_guides/model_merging). To use these merging methods, make sure you have the latest stable version of Diffusers and PEFT installed.
 
 ```bash
 pip install -U diffusers peft
 ```
 
-There are three steps to merge LoRAs with the [add_weighted_adapter](https://huggingface.co/docs/peft/package_reference/lora#peft.LoraModel.add_weighted_adapter) method:
+There are three steps to merge LoRAs with the [`~peft.LoraModel.add_weighted_adapter`] method:
 
-1. Create a [PeftModel](https://huggingface.co/docs/peft/package_reference/peft_model#peft.PeftModel) from the underlying model and LoRA checkpoint.
+1. Create a [`~peft.PeftModel`] from the underlying model and LoRA checkpoint.
 2. Load a base UNet model and the LoRA adapters.
-3. Merge the adapters using the [add_weighted_adapter](https://huggingface.co/docs/peft/package_reference/lora#peft.LoraModel.add_weighted_adapter) method and the merging method of your choice.
+3. Merge the adapters using the [`~peft.LoraModel.add_weighted_adapter`] method and the merging method of your choice.
 
 Let's dive deeper into what these steps entail.
 
@@ -92,7 +92,7 @@ pipeline = DiffusionPipeline.from_pretrained(
 pipeline.load_lora_weights("ostris/ikea-instructions-lora-sdxl", weight_name="ikea_instructions_xl_v1_5.safetensors", adapter_name="ikea")
 ```
 
-Now you'll create a [PeftModel](https://huggingface.co/docs/peft/package_reference/peft_model#peft.PeftModel) from the loaded LoRA checkpoint by combining the SDXL UNet and the LoRA UNet from the pipeline.
+Now you'll create a [`~peft.PeftModel`] from the loaded LoRA checkpoint by combining the SDXL UNet and the LoRA UNet from the pipeline.
 
 ```python
 from peft import get_peft_model, LoraConfig
@@ -112,7 +112,7 @@ ikea_peft_model.load_state_dict(original_state_dict, strict=True)
 > [!TIP]
 > You can optionally push the ikea_peft_model to the Hub by calling `ikea_peft_model.push_to_hub("ikea_peft_model", token=TOKEN)`.
 
-Repeat this process to create a [PeftModel](https://huggingface.co/docs/peft/package_reference/peft_model#peft.PeftModel) from the [lordjia/by-feng-zikai](https://huggingface.co/lordjia/by-feng-zikai) LoRA.
+Repeat this process to create a [`~peft.PeftModel`] from the [lordjia/by-feng-zikai](https://huggingface.co/lordjia/by-feng-zikai) LoRA.
 
 ```python
 pipeline.delete_adapters("ikea")
@@ -148,7 +148,7 @@ model = PeftModel.from_pretrained(base_unet, "stevhliu/ikea_peft_model", use_saf
 model.load_adapter("stevhliu/feng_peft_model", use_safetensors=True, subfolder="feng", adapter_name="feng")
 ```
 
-3. Merge the adapters using the [add_weighted_adapter](https://huggingface.co/docs/peft/package_reference/lora#peft.LoraModel.add_weighted_adapter) method and the merging method of your choice (learn more about other merging methods in this [blog post](https://huggingface.co/blog/peft_merging)). For this example, let's use the `"dare_linear"` method to merge the LoRAs.
+3. Merge the adapters using the [`~peft.LoraModel.add_weighted_adapter`] method and the merging method of your choice (learn more about other merging methods in this [blog post](https://huggingface.co/blog/peft_merging)). For this example, let's use the `"dare_linear"` method to merge the LoRAs.
 
 > [!WARNING]
 > Keep in mind the LoRAs need to have the same rank to be merged!
@@ -182,9 +182,9 @@ image
 
 ## fuse_lora
 
-Both the [`~loaders.PeftAdapterMixin.set_adapters`] and [add_weighted_adapter](https://huggingface.co/docs/peft/package_reference/lora#peft.LoraModel.add_weighted_adapter) methods require loading the base model and the LoRA adapters separately which incurs some overhead. The [`~loaders.lora_base.LoraBaseMixin.fuse_lora`] method allows you to fuse the LoRA weights directly with the original weights of the underlying model. This way, you're only loading the model once which can increase inference and lower memory-usage.
+Both the [`~loaders.UNet2DConditionLoadersMixin.set_adapters`] and [`~peft.LoraModel.add_weighted_adapter`] methods require loading the base model and the LoRA adapters separately which incurs some overhead. The [`~loaders.StableDiffusionLoraLoaderMixin.fuse_lora`] method allows you to fuse the LoRA weights directly with the original weights of the underlying model. This way, you're only loading the model once which can increase inference and lower memory-usage.
 
-You can use PEFT to easily fuse/unfuse multiple adapters directly into the model weights (both UNet and text encoder) using the [`~loaders.lora_base.LoraBaseMixin.fuse_lora`] method, which can lead to a speed-up in inference and lower VRAM usage.
+You can use PEFT to easily fuse/unfuse multiple adapters directly into the model weights (both UNet and text encoder) using the [`~loaders.StableDiffusionLoraLoaderMixin.fuse_lora`] method, which can lead to a speed-up in inference and lower VRAM usage.
 
 For example, if you have a base model and adapters loaded and set as active with the following adapter weights:
 
@@ -199,7 +199,7 @@ pipeline.load_lora_weights("lordjia/by-feng-zikai", weight_name="fengzikai_v1.0_
 pipeline.set_adapters(["ikea", "feng"], adapter_weights=[0.7, 0.8])
 ```
 
-Fuse these LoRAs into the UNet with the [`~loaders.lora_base.LoraBaseMixin.fuse_lora`] method. The `lora_scale` parameter controls how much to scale the output by with the LoRA weights. It is important to make the `lora_scale` adjustments in the [`~loaders.lora_base.LoraBaseMixin.fuse_lora`] method because it won’t work if you try to pass `scale` to the `cross_attention_kwargs` in the pipeline.
+Fuse these LoRAs into the UNet with the [`~loaders.StableDiffusionLoraLoaderMixin.fuse_lora`] method. The `lora_scale` parameter controls how much to scale the output by with the LoRA weights. It is important to make the `lora_scale` adjustments in the [`~loaders.StableDiffusionLoraLoaderMixin.fuse_lora`] method because it won’t work if you try to pass `scale` to the `cross_attention_kwargs` in the pipeline.
 
 ```py
 pipeline.fuse_lora(adapter_names=["ikea", "feng"], lora_scale=1.0)
@@ -226,7 +226,7 @@ image = pipeline("A bowl of ramen shaped like a cute kawaii bear, by Feng Zikai"
 image
 ```
 
-You can call [`~~loaders.lora_base.LoraBaseMixin.unfuse_lora`] to restore the original model's weights (for example, if you want to use a different `lora_scale` value). However, this only works if you've only fused one LoRA adapter to the original model. If you've fused multiple LoRAs, you'll need to reload the model.
+You can call [`~loaders.StableDiffusionLoraLoaderMixin.unfuse_lora`] to restore the original model's weights (for example, if you want to use a different `lora_scale` value). However, this only works if you've only fused one LoRA adapter to the original model. If you've fused multiple LoRAs, you'll need to reload the model.
 
 ```py
 pipeline.unfuse_lora()

docs/source/ko/conceptual/contribution.md

@@ -10,7 +10,7 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
 specific language governing permissions and limitations under the License.
 -->
 
-# Diffusers에 기여하는 방법 🧨 [[how-to-contribute-to-diffusers-]]
+# Diffusers에 기여하는 방법 🧨
 
 오픈 소스 커뮤니티에서의 기여를 환영합니다! 누구나 참여할 수 있으며, 코드뿐만 아니라 질문에 답변하거나 문서를 개선하는 등 모든 유형의 참여가 가치 있고 감사히 여겨집니다. 질문에 답변하고 다른 사람들을 도와주며 소통하고 문서를 개선하는 것은 모두 커뮤니티에게 큰 도움이 됩니다. 따라서 관심이 있다면 두려워하지 말고 참여해보세요!
 
@@ -18,9 +18,9 @@ specific language governing permissions and limitations under the License.
 
 어떤 방식으로든 기여하려는 경우, 우리는 개방적이고 환영하며 친근한 커뮤니티의 일부가 되기 위해 노력하고 있습니다. 우리의 [행동 강령](https://github.com/huggingface/diffusers/blob/main/CODE_OF_CONDUCT.md)을 읽고 상호 작용 중에 이를 존중하도록 주의해주시기 바랍니다. 또한 프로젝트를 안내하는 [윤리 지침](https://huggingface.co/docs/diffusers/conceptual/ethical_guidelines)에 익숙해지고 동일한 투명성과 책임성의 원칙을 준수해주시기를 부탁드립니다.
 
-우리는 커뮤니티로부터의 피드백을 매우 중요하게 생각하므로, 라이브러리를 개선하는 데 도움이 될 가치 있는 피드백이 있다고 생각되면 망설이지 말고 의견을 제시해주세요 - 모든 메시지, 댓글, 이슈, Pull Request(PR)는 읽히고 고려됩니다.
+우리는 커뮤니티로부터의 피드백을 매우 중요하게 생각하므로, 라이브러리를 개선하는 데 도움이 될 가치 있는 피드백이 있다고 생각되면 망설이지 말고 의견을 제시해주세요 - 모든 메시지, 댓글, 이슈, 풀 리퀘스트(PR)는 읽히고 고려됩니다.
 
-## 개요 [[overview]]
+## 개요
 
 이슈에 있는 질문에 답변하는 것에서부터 코어 라이브러리에 새로운 diffusion 모델을 추가하는 것까지 다양한 방법으로 기여를 할 수 있습니다.
 
@@ -38,9 +38,9 @@ specific language governing permissions and limitations under the License.
 
 앞서 말한 대로, **모든 기여는 커뮤니티에게 가치가 있습니다**. 이어지는 부분에서 각 기여에 대해 조금 더 자세히 설명하겠습니다.
 
-4부터 9까지의 모든 기여에는 Pull Request을 열어야 합니다. [Pull Request 열기](#how-to-open-a-pr)에서 자세히 설명되어 있습니다.
+4부터 9까지의 모든 기여에는 PR을 열어야 합니다. [PR을 열기](#how-to-open-a-pr)에서 자세히 설명되어 있습니다.
 
-### 1. Diffusers 토론 포럼이나 Diffusers Discord에서 질문하고 답변하기 [[1-asking-and-answering-questions-on-the-diffusers-discussion-forum-or-on-the-diffusers-discord]]
+### 1. Diffusers 토론 포럼이나 Diffusers Discord에서 질문하고 답변하기
 
 Diffusers 라이브러리와 관련된 모든 질문이나 의견은 [토론 포럼](https://discuss.huggingface.co/c/discussion-related-to-httpsgithubcomhuggingfacediffusers/63)이나 [Discord](https://discord.gg/G7tWnz98XR)에서 할 수 있습니다. 이러한 질문과 의견에는 다음과 같은 내용이 포함됩니다(하지만 이에 국한되지는 않습니다):
 - 지식을 공유하기 위해서 훈련 또는 추론 실험에 대한 결과 보고
@@ -54,7 +54,7 @@ Diffusers 라이브러리와 관련된 모든 질문이나 의견은 [토론 포
 - Diffusion 모델에 대한 윤리적 질문
 - ...
 
-포럼이나 Discord에서 질문을 하면 커뮤니티가 지식을 공개적으로 공유하도록 장려되며, 향후 동일한 질문을 가진 초보자에게도 도움이 될 수 있습니다. 따라서 궁금한 질문은 언제든지 하시기 바랍니다.
+포럼이나 Discord에서 질문을 하면 커뮤니티가 지식을 공개적으로 공유하도록 장려되며, 미래에 동일한 질문을 가진 초보자에게도 도움이 될 수 있습니다. 따라서 궁금한 질문은 언제든지 하시기 바랍니다.
 또한, 이러한 질문에 답변하는 것은 커뮤니티에게 매우 큰 도움이 됩니다. 왜냐하면 이렇게 하면 모두가 학습할 수 있는 공개적인 지식을 문서화하기 때문입니다.
 
 **주의**하십시오. 질문이나 답변에 투자하는 노력이 많을수록 공개적으로 문서화된 지식의 품질이 높아집니다. 마찬가지로, 잘 정의되고 잘 답변된 질문은 모두에게 접근 가능한 고품질 지식 데이터베이스를 만들어줍니다. 반면에 잘못된 질문이나 답변은 공개 지식 데이터베이스의 전반적인 품질을 낮출 수 있습니다.
@@ -64,9 +64,9 @@ Diffusers 라이브러리와 관련된 모든 질문이나 의견은 [토론 포
 [*포럼*](https://discuss.huggingface.co/c/discussion-related-to-httpsgithubcomhuggingfacediffusers/63)은 구글과 같은 검색 엔진에서 더 잘 색인화됩니다. 게시물은 인기에 따라 순위가 매겨지며, 시간순으로 정렬되지 않습니다. 따라서 이전에 게시한 질문과 답변을 쉽게 찾을 수 있습니다.
 또한, 포럼에 게시된 질문과 답변은 쉽게 링크할 수 있습니다.
 반면 *Discord*는 채팅 형식으로 되어 있어 빠른 대화를 유도합니다.
-질문에 대한 답변을 빠르게 받을 수는 있겠지만, 시간이 지나면 질문이 더 이상 보이지 않습니다. 또한, Discord에서 이전에 게시된 정보를 찾는 것은 훨씬 어렵습니다. 따라서 포럼을 사용하여 고품질의 질문과 답변을 하여 커뮤니티를 위한 오래 지속되는 지식을 만들기를 권장합니다. Discord에서의 토론이 매우 흥미로운 답변과 결론을 이끌어내는 경우, 해당 정보를 포럼에 게시하여 향후 독자들에게 더 쉽게 액세스할 수 있도록 권장합니다.
+질문에 대한 답변을 빠르게 받을 수는 있겠지만, 시간이 지나면 질문이 더 이상 보이지 않습니다. 또한, Discord에서 이전에 게시된 정보를 찾는 것은 훨씬 어렵습니다. 따라서 포럼을 사용하여 고품질의 질문과 답변을 하여 커뮤니티를 위한 오래 지속되는 지식을 만들기를 권장합니다. Discord에서의 토론이 매우 흥미로운 답변과 결론을 이끌어내는 경우, 해당 정보를 포럼에 게시하여 미래 독자들에게 더 쉽게 액세스할 수 있도록 권장합니다.
 
-### 2. GitHub 이슈 탭에서 새로운 이슈 열기 [[2-opening-new-issues-on-the-github-issues-tab]]
+### 2. GitHub 이슈 탭에서 새로운 이슈 열기
 
 🧨 Diffusers 라이브러리는 사용자들이 마주치는 문제를 알려주는 덕분에 견고하고 신뢰할 수 있습니다. 따라서 이슈를 보고해주셔서 감사합니다.
 
@@ -81,52 +81,53 @@ Diffusers 라이브러리와 관련된 모든 질문이나 의견은 [토론 포
 - 이슈가 최신 Diffusers 버전으로 업데이트하면 해결될 수 있는지 확인해주세요. 이슈를 게시하기 전에 `python -c "import diffusers; print(diffusers.__version__)"` 명령을 실행하여 현재 사용 중인 Diffusers 버전이 최신 버전과 일치하거나 더 높은지 확인해주세요.
 - 새로운 이슈를 열 때 투자하는 노력이 많을수록 답변의 품질이 높아지고 Diffusers 이슈 전체의 품질도 향상됩니다.
 
-#### 2.1 재현 가능한 최소한의 버그 리포트 [[21-reproducible-minimal-bug-reports]]
+#### 2.1 재현가능하고 최소한인 버그 리포트
 
+새로운 이슈는 일반적으로 다음과 같은 내용을 포함합니다.
 
-버그 리포트는 항상 재현 가능한 코드 조각을 포함하고 가능한 한 최소한이어야 하며 간결해야 합니다.
+버그 보고서는 항상 재현 가능한 코드 조각을 포함하고 가능한 한 최소한이어야 하며 간결해야 합니다.
 자세히 말하면:
 - 버그를 가능한 한 좁혀야 합니다. **전체 코드 파일을 그냥 던지지 마세요**.
 - 코드의 서식을 지정해야 합니다.
 - Diffusers가 의존하는 외부 라이브러리를 제외한 다른 외부 라이브러리는 포함하지 마십시오.
-- **항상** 사용자 환경에 대한 모든 필요한 정보를 제공하세요. 이를 위해 쉘에서 `diffusers-cli env`를 실행하고 표시된 정보를 이슈에 복사하여 붙여넣을 수 있습니다.
-- 이슈를 설명해야 합니다. 독자가 문제가 무엇인지, 왜 문제가 되는지 모른다면 이슈를 해결할 수 없습니다. 
-- **항상** 독자가 가능한 한 적은 노력으로 문제를 재현할 수 있어야 합니다. 코드 조각이 라이브러리가 없거나 정의되지 않은 변수 때문에 실행되지 않는 경우 독자가 도움을 줄 수 없습니다. 재현 가능한 코드 조각이 가능한 한 최소화되고 간단한 Python 셸에 복사하여 붙여넣을 수 있도록 해야 합니다.
+- **반드시** 환경에 대한 모든 필요한 정보를 제공해야 합니다. 이를 위해 쉘에서 `diffusers-cli env`를 실행하고 표시된 정보를 이슈에 복사하여 붙여넣을 수 있습니다.
+- 이슈를 설명해야 합니다. 독자가 문제가 무엇이며 왜 문제인지 모르면 해결할 수 없습니다.
+- **항상** 독자가 가능한 한 적은 노력으로 문제를 재현할 수 있도록 해야 합니다. 코드 조각이 라이브러리가 없거나 정의되지 않은 변수 때문에 실행되지 않는 경우 독자가 도움을 줄 수 없습니다. 재현 가능한 코드 조각이 가능한 한 최소화되고 간단한 Python 셸에 복사하여 붙여넣을 수 있도록 해야 합니다.
 - 문제를 재현하기 위해 모델과/또는 데이터셋이 필요한 경우 독자가 해당 모델이나 데이터셋에 접근할 수 있도록 해야 합니다. 모델이나 데이터셋을 [Hub](https://huggingface.co)에 업로드하여 쉽게 다운로드할 수 있도록 할 수 있습니다. 문제 재현을 가능한 한 쉽게하기 위해 모델과 데이터셋을 가능한 한 작게 유지하려고 노력하세요.
 
 자세한 내용은 [좋은 이슈 작성 방법](#how-to-write-a-good-issue) 섹션을 참조하세요.
 
-버그 리포트를 열려면 [여기](https://github.com/huggingface/diffusers/issues/new?assignees=&labels=bug&projects=&template=bug-report.yml)를 클릭하세요.
+버그 보고서를 열려면 [여기](https://github.com/huggingface/diffusers/issues/new?assignees=&labels=bug&projects=&template=bug-report.yml)를 클릭하세요.
 
 
-#### 2.2. 기능 요청 [[22-feature-requests]]
+#### 2.2. 기능 요청
 
 세계적인 기능 요청은 다음 사항을 다룹니다:
 
 1. 먼저 동기부여:
-* 라이브러리와 관련된 문제/불만이 있나요? 그렇다면 왜 그런지 설명해주세요. 문제를 보여주는 코드 조각을 제공하는 것이 가장 좋습니다.
+* 라이브러리와 관련된 문제/불만이 있는가요? 그렇다면 왜 그런지 설명해주세요. 문제를 보여주는 코드 조각을 제공하는 것이 가장 좋습니다.
 * 프로젝트에 필요한 기능인가요? 우리는 그에 대해 듣고 싶습니다!
 * 커뮤니티에 도움이 될 수 있는 것을 작업했고 그것에 대해 생각하고 있는가요? 멋지네요! 어떤 문제를 해결했는지 알려주세요.
 2. 기능을 *상세히 설명하는* 문단을 작성해주세요;
-3. 향후 사용을 보여주는 **코드 조각**을 제공해주세요;
-4. 논문과 관련된 내용인 경우 링크를 첨부해주세요;
-5. 도움이 될 수 있다고 생각되는 추가 정보(그림, 스크린샷 등)를 첨부해주세요.
+3. 미래 사용을 보여주는 **코드 조각**을 제공해주세요;
+4. 이것이 논문과 관련된 경우 링크를 첨부해주세요;
+5. 도움이 될 수 있는 추가 정보(그림, 스크린샷 등)를 첨부해주세요.
 
 기능 요청은 [여기](https://github.com/huggingface/diffusers/issues/new?assignees=&labels=&template=feature_request.md&title=)에서 열 수 있습니다.
 
-#### 2.3 피드백 [[23-feedback]]
+#### 2.3 피드백
 
-라이브러리 디자인과 그것이 왜 좋은지 또는 나쁜지에 대한 이유에 대한 피드백은 핵심 메인테이너가 사용자 친화적인 라이브러리를 만드는 데 엄청난 도움이 됩니다. 현재 디자인 철학을 이해하려면 [여기](https://huggingface.co/docs/diffusers/conceptual/philosophy)를 참조해 주세요. 특정 디자인 선택이 현재 디자인 철학과 맞지 않는다고 생각되면, 그 이유와 어떻게 변경되어야 하는지 설명해 주세요. 반대로 특정 디자인 선택이 디자인 철학을 너무 따르기 때문에 사용 사례를 제한한다고 생각되면, 그 이유와 어떻게 변경되어야 하는지 설명해 주세요. 특정 디자인 선택이 매우 유용하다고 생각되면, 향후 디자인 결정에 큰 도움이 되므로 이에 대한 의견을 남겨 주세요.
+라이브러리 디자인과 그것이 왜 좋은지 또는 나쁜지에 대한 이유에 대한 피드백은 핵심 메인테이너가 사용자 친화적인 라이브러리를 만드는 데 엄청난 도움이 됩니다. 현재 디자인 철학을 이해하려면 [여기](https://huggingface.co/docs/diffusers/conceptual/philosophy)를 참조해 주세요. 특정 디자인 선택이 현재 디자인 철학과 맞지 않는다고 생각되면, 그 이유와 어떻게 변경되어야 하는지 설명해 주세요. 반대로 특정 디자인 선택이 디자인 철학을 너무 따르기 때문에 사용 사례를 제한한다고 생각되면, 그 이유와 어떻게 변경되어야 하는지 설명해 주세요. 특정 디자인 선택이 매우 유용하다고 생각되면, 미래의 디자인 결정에 큰 도움이 되므로 이에 대한 의견을 남겨 주세요.
 
 피드백에 관한 이슈는 [여기](https://github.com/huggingface/diffusers/issues/new?assignees=&labels=&template=feedback.md&title=)에서 열 수 있습니다.
 
-#### 2.4 기술적인 질문 [[24-technical-questions]]
+#### 2.4 기술적인 질문
 
 기술적인 질문은 주로 라이브러리의 특정 코드가 왜 특정 방식으로 작성되었는지 또는 코드의 특정 부분이 무엇을 하는지에 대한 질문입니다. 질문하신 코드 부분에 대한 링크를 제공하고 해당 코드 부분이 이해하기 어려운 이유에 대한 자세한 설명을 해주시기 바랍니다.
 
 기술적인 질문에 관한 이슈를 [여기](https://github.com/huggingface/diffusers/issues/new?assignees=&labels=bug&template=bug-report.yml)에서 열 수 있습니다.
 
-#### 2.5 새로운 모델, 스케줄러 또는 파이프라인 추가 제안 [[25-proposal-to-add-a-new-model-scheduler-or-pipeline]]
+#### 2.5 새로운 모델, 스케줄러 또는 파이프라인 추가 제안
 
 만약 diffusion 모델 커뮤니티에서 Diffusers 라이브러리에 추가하고 싶은 새로운 모델, 파이프라인 또는 스케줄러가 있다면, 다음 정보를 제공해주세요:
 
@@ -134,34 +135,34 @@ Diffusers 라이브러리와 관련된 모든 질문이나 의견은 [토론 포
 * 해당 모델의 오픈 소스 구현에 대한 링크
 * 모델 가중치가 있는 경우, 가중치의 링크
 
-직접 모델에 기여하고 싶다면, 가장 잘 안내해드릴 수 있습니다. 또한, 가능하다면 구성 요소(모델, 스케줄러, 파이프라인 등)의 원저자를 GitHub 핸들로 태그하는 것을 잊지 마세요.
+모델에 직접 기여하고자 하는 경우, 최선의 안내를 위해 우리에게 알려주세요. 또한, 가능하다면 구성 요소(모델, 스케줄러, 파이프라인 등)의 원래 저자를 GitHub 핸들로 태그하는 것을 잊지 마세요.
 
 모델/파이프라인/스케줄러에 대한 요청을 [여기](https://github.com/huggingface/diffusers/issues/new?assignees=&labels=New+model%2Fpipeline%2Fscheduler&template=new-model-addition.yml)에서 열 수 있습니다.
 
-### 3. GitHub 이슈 탭에서 문제에 대한 답변하기 [[3-answering-issues-on-the-github-issues-tab]]
+### 3. GitHub 이슈 탭에서 문제에 대한 답변하기
 
 GitHub에서 이슈에 대한 답변을 하기 위해서는 Diffusers에 대한 기술적인 지식이 필요할 수 있지만, 정확한 답변이 아니더라도 모두가 시도해기를 권장합니다. 이슈에 대한 고품질 답변을 제공하기 위한 몇 가지 팁:
 - 가능한 한 간결하고 최소한으로 유지합니다.
 - 주제에 집중합니다. 이슈에 대한 답변은 해당 이슈에 관련된 내용에만 집중해야 합니다.
-- 자신의 주장을 증명하거나 장려하는 코드, 논문 또는 기타 출처는 링크를 제공하세요.
+- 코드, 논문 또는 다른 소스를 제공하여 답변을 증명하거나 지지합니다.
 - 코드로 답변합니다. 간단한 코드 조각이 이슈에 대한 답변이거나 이슈를 해결하는 방법을 보여준다면, 완전히 재현 가능한 코드 조각을 제공해주세요.
 
 또한, 많은 이슈들은 단순히 주제와 무관하거나 다른 이슈의 중복이거나 관련이 없는 경우가 많습니다. 이러한 이슈들에 대한 답변을 제공하고, 이슈 작성자에게 더 정확한 정보를 제공하거나, 중복된 이슈에 대한 링크를 제공하거나, [포럼](https://discuss.huggingface.co/c/discussion-related-to-httpsgithubcomhuggingfacediffusers/63) 이나 [Discord](https://discord.gg/G7tWnz98XR)로 리디렉션하는 것은 메인테이너에게 큰 도움이 됩니다.
 
 이슈가 올바른 버그 보고서이고 소스 코드에서 수정이 필요하다고 확인한 경우, 다음 섹션을 살펴보세요.
 
-다음 모든 기여에 대해서는 PR을 열여야 합니다. [Pull Request 열기](#how-to-open-a-pr) 섹션에서 자세히 설명되어 있습니다.
+다음 모든 기여에 대해서는 PR을 열여야 합니다. [PR 열기](#how-to-open-a-pr) 섹션에서 자세히 설명되어 있습니다.
 
-### 4. "Good first issue" 고치기 [[4-fixing-a-good-first-issue]]
+### 4. "Good first issue" 고치기
 
 *Good first issues*는 [Good first issue](https://github.com/huggingface/diffusers/issues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22) 라벨로 표시됩니다. 일반적으로, 이슈는 이미 잠재적인 해결책이 어떻게 보이는지 설명하고 있어서 수정하기 쉽습니다.
 만약 이슈가 아직 닫히지 않았고 이 문제를 해결해보고 싶다면, "이 이슈를 해결해보고 싶습니다."라는 메시지를 남기면 됩니다. 일반적으로 세 가지 시나리오가 있습니다:
-- a.) 이슈 설명에 이미 수정 사항을 제안하는 경우, 해결책이 이해되고 합리적으로 보인다면, PR 또는 드래프트 PR을 열어서 수정할 수 있습니다.
-- b.) 이슈 설명에 수정 사항이 제안되어 있지 않은 경우, 제안한 수정 사항이 가능할지 물어볼 수 있고, Diffusers 팀의 누군가가 곧 답변해줄 것입니다. 만약 어떻게 수정할지 좋은 아이디어가 있다면, 직접 PR을 열어도 됩니다.
+- a.) 이슈 설명이 이미 해결책을 제안합니다. 이 경우, 해결책이 이해되고 합리적으로 보인다면, PR 또는 드래프트 PR을 열어서 수정할 수 있습니다.
+- b.) 이슈 설명이 해결책을 제안하지 않습니다. 이 경우, 어떤 해결책이 가능할지 물어볼 수 있고, Diffusers 팀의 누군가가 곧 답변해줄 것입니다. 만약 어떻게 수정할지 좋은 아이디어가 있다면, 직접 PR을 열어도 됩니다.
 - c.) 이미 이 문제를 해결하기 위해 열린 PR이 있지만, 이슈가 아직 닫히지 않았습니다. PR이 더 이상 진행되지 않았다면, 새로운 PR을 열고 이전 PR에 링크를 걸면 됩니다. PR은 종종 원래 기여자가 갑자기 시간을 내지 못해 더 이상 진행하지 못하는 경우에 더 이상 진행되지 않게 됩니다. 이는 오픈 소스에서 자주 발생하는 일이며 매우 정상적인 상황입니다. 이 경우, 커뮤니티는 새로 시도하고 기존 PR의 지식을 활용해주면 매우 기쁠 것입니다. 이미 PR이 있고 활성화되어 있다면, 제안을 해주거나 PR을 검토하거나 PR에 기여할 수 있는지 물어보는 등 작성자를 도와줄 수 있습니다.
 
 
-### 5. 문서에 기여하기 [[5-contribute-to-the-documentation]]
+### 5. 문서에 기여하기
 
 좋은 라이브러리는 항상 좋은 문서를 갖고 있습니다! 공식 문서는 라이브러리를 처음 사용하는 사용자들에게 첫 번째 접점 중 하나이며, 따라서 문서에 기여하는 것은 매우 가치 있는 기여입니다.
 
@@ -179,7 +180,7 @@ GitHub에서 이슈에 대한 답변을 하기 위해서는 Diffusers에 대한
 문서에 대한 변경 사항을 로컬에서 확인하는 방법은 [이 페이지](https://github.com/huggingface/diffusers/tree/main/docs)를 참조해주세요.
 
 
-### 6. 커뮤니티 파이프라인에 기여하기 [[6-contribute-a-community-pipeline]]
+### 6. 커뮤니티 파이프라인에 기여하기
 
 > [!TIP]
 > 커뮤니티 파이프라인에 대해 자세히 알아보려면 [커뮤니티 파이프라인](../using-diffusers/custom_pipeline_overview#community-pipelines) 가이드를 읽어보세요. 커뮤니티 파이프라인이 왜 필요한지 궁금하다면 GitHub 이슈 [#841](https://github.com/huggingface/diffusers/issues/841)를 확인해보세요 (기본적으로, 우리는 diffusion 모델이 추론에 사용될 수 있는 모든 방법을 유지할 수 없지만 커뮤니티가 이를 구축하는 것을 방해하고 싶지 않습니다).
@@ -245,7 +246,7 @@ output = pipeline()
 <hfoptions id="pipeline type">
 <hfoption id="GitHub pipeline">
 
-GitHub 파이프라인을 공유하려면 Diffusers [저장소](https://github.com/huggingface/diffusers)에서 Pull Request를 열고 one_step_unet.py 파일을 [examples/community](https://github.com/huggingface/diffusers/tree/main/examples/community) 하위 폴더에 추가하세요.
+GitHub 파이프라인을 공유하려면 Diffusers [저장소](https://github.com/huggingface/diffusers)에서 PR을 열고 one_step_unet.py 파일을 [examples/community](https://github.com/huggingface/diffusers/tree/main/examples/community) 하위 폴더에 추가하세요.
 
 </hfoption>
 <hfoption id="Hub pipeline">
@@ -255,7 +256,7 @@ Hub 파이프라인을 공유하려면, 허브에 모델 저장소를 생성하
 </hfoption>
 </hfoptions>
 
-### 7. 훈련 예제에 기여하기 [[7-contribute-to-training-examples]]
+### 7. 훈련 예제에 기여하기
 
 Diffusers 예제는 [examples](https://github.com/huggingface/diffusers/tree/main/examples) 폴더에 있는 훈련 스크립트의 모음입니다.
 
@@ -267,7 +268,7 @@ Diffusers 예제는 [examples](https://github.com/huggingface/diffusers/tree/mai
 연구용 훈련 예제는 [examples/research_projects](https://github.com/huggingface/diffusers/tree/main/examples/research_projects)에 위치하며, 공식 훈련 예제는 `research_projects` 및 `community` 폴더를 제외한 [examples](https://github.com/huggingface/diffusers/tree/main/examples)의 모든 폴더를 포함합니다.
 공식 훈련 예제는 Diffusers의 핵심 메인테이너가 유지 관리하며, 연구용 훈련 예제는 커뮤니티가 유지 관리합니다.
 이는 공식 파이프라인 vs 커뮤니티 파이프라인에 대한 [6. 커뮤니티 파이프라인 기여하기](#6-contribute-a-community-pipeline)에서 제시한 이유와 동일합니다: 핵심 메인테이너가 diffusion 모델의 모든 가능한 훈련 방법을 유지 관리하는 것은 현실적으로 불가능합니다.
-Diffusers 핵심 메인테이너와 커뮤니티가 특정 훈련 패러다임을 너무 실험적이거나 충분히 대중적이지 않다고 판단한다면, 해당 훈련 코드는 `research_projects` 폴더에 넣고 작성자에 의해 관리되어야 합니다.
+Diffusers 핵심 메인테잉너와 커뮤니티가 특정 훈련 패러다임을 너무 실험적이거나 충분히 인기 없는 것으로 간주하는 경우, 해당 훈련 코드는 `research_projects` 폴더에 넣고 작성자가 유지 관리해야 합니다.
 
 공식 훈련 및 연구 예제는 하나 이상의 훈련 스크립트, requirements.txt 파일 및 README.md 파일을 포함하는 디렉토리로 구성됩니다. 사용자가 훈련 예제를 사용하려면 리포지토리를 복제해야 합니다:
 
@@ -297,14 +298,14 @@ Diffusers와 긴밀하게 통합되어 있기 때문에, 기여자들이 [Accele
 
 만약 공식 훈련 예제에 기여하는 경우, [examples/test_examples.py](https://github.com/huggingface/diffusers/blob/main/examples/test_examples.py)에 테스트를 추가하는 것도 확인해주세요. 비공식 훈련 예제에는 이 작업이 필요하지 않습니다.
 
-### 8. "Good second issue" 고치기 [[8-fixing-a-good-second-issue]]
+### 8. "Good second issue" 고치기
 
 "Good second issue"는 [Good second issue](https://github.com/huggingface/diffusers/issues?q=is%3Aopen+is%3Aissue+label%3A%22Good+second+issue%22) 라벨로 표시됩니다. Good second issue는 [Good first issues](https://github.com/huggingface/diffusers/issues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22)보다 해결하기가 더 복잡합니다.
 이슈 설명은 일반적으로 이슈를 해결하는 방법에 대해 덜 구체적이며, 관심 있는 기여자는 라이브러리에 대한 꽤 깊은 이해가 필요합니다.
 Good second issue를 해결하고자 하는 경우, 해당 이슈를 해결하기 위해 PR을 열고 PR을 이슈에 링크하세요. 이미 해당 이슈에 대한 PR이 열려있지만 병합되지 않은 경우, 왜 병합되지 않았는지 이해하기 위해 살펴보고 개선된 PR을 열어보세요.
 Good second issue는 일반적으로 Good first issue 이슈보다 병합하기가 더 어려우므로, 핵심 메인테이너에게 도움을 요청하는 것이 좋습니다. PR이 거의 완료된 경우, 핵심 메인테이너는 PR에 참여하여 커밋하고 병합을 진행할 수 있습니다.
 
-### 9. 파이프라인, 모델, 스케줄러 추가하기 [[9-adding-pipelines-models-schedulers]]
+### 9. 파이프라인, 모델, 스케줄러 추가하기
 
 파이프라인, 모델, 스케줄러는 Diffusers 라이브러리에서 가장 중요한 부분입니다.
 이들은 최첨단 diffusion 기술에 쉽게 접근하도록 하며, 따라서 커뮤니티가 강력한 생성형 AI 애플리케이션을 만들 수 있도록 합니다.
@@ -322,9 +323,9 @@ PR에 원본 코드베이스/논문 링크를 추가하고, 가능하면 PR에
 
 PR에서 막힌 경우나 도움이 필요한 경우, 첫 번째 리뷰나 도움을 요청하는 메시지를 남기는 것을 주저하지 마세요.
 
-#### Copied from mechanism [[copied-from-mechanism]]
+#### Copied from mechanism
 
-`# Copied from mechanism` 은 파이프라인, 모델 또는 스케줄러 코드를 추가할 때 이해해야 할 독특하고 중요한 기능입니다. 이것은 Diffusers 코드베이스 전반에서 볼 수 있으며, 이를 사용하는 이유는 코드베이스를 이해하고 유지 관리하기 쉽게 만들기 위해서입니다. `# Copied from mechanism` 으로 표시된 코드는 복사한 코드와 정확히 동일하도록 강제됩니다. 이렇게 하면 `make fix-copies`를 실행할 때마다 여러 파일에 걸쳐 변경 사항을 쉽게 업데이트하고 전파할 수 있습니다.
+`# Copied from mechanism` 은 파이프라인, 모델 또는 스케줄러 코드를 추가할 때 이해해야 할 독특하고 중요한 기능입니다. Diffusers 코드베이스 전체에서 이를 자주 볼 수 있는데, 이를 사용하는 이유는 코드베이스를 이해하기 쉽고 유지 관리하기 쉽게 유지하기 위함입니다. `# Copied from mechanism` 으로 표시된 코드는 복사한 코드와 정확히 동일하도록 강제됩니다. 이를 통해 `make fix-copies`를 실행할 때 많은 파일에 걸쳐 변경 사항을 쉽게 업데이트하고 전파할 수 있습니다.
 
 예를 들어, 아래 코드 예제에서 [`~diffusers.pipelines.stable_diffusion.StableDiffusionPipelineOutput`]은 원래 코드이며, `AltDiffusionPipelineOutput`은 `# Copied from mechanism`을 사용하여 복사합니다. 유일한 차이점은 클래스 접두사를 `Stable`에서 `Alt`로 변경한 것입니다.
 
@@ -346,7 +347,7 @@ class AltDiffusionPipelineOutput(BaseOutput):
 
 더 자세히 알고 싶다면 [~Don't~ Repeat Yourself*](https://huggingface.co/blog/transformers-design-philosophy#4-machine-learning-models-are-static) 블로그 포스트의 이 섹션을 읽어보세요.
 
-## 좋은 이슈 작성 방법 [[how-to-write-a-good-issue]]
+## 좋은 이슈 작성 방법
 
 **이슈를 잘 작성할수록 빠르게 해결될 가능성이 높아집니다.**
 
@@ -355,16 +356,16 @@ class AltDiffusionPipelineOutput(BaseOutput):
 3. **재현 가능성**: 재현 가능한 코드 조각이 없으면 해결할 수 없습니다. 버그를 발견한 경우, 유지 관리자는 그 버그를 재현할 수 있어야 합니다. 이슈에 재현 가능한 코드 조각을 포함해야 합니다. 코드 조각은 Python 인터프리터에 복사하여 붙여넣을 수 있는 형태여야 합니다. 코드 조각이 작동해야 합니다. 즉, 누락된 import나 이미지에 대한 링크가 없어야 합니다. 이슈에는 오류 메시지와 정확히 동일한 오류 메시지를 재현하기 위해 수정하지 않고 복사하여 붙여넣을 수 있는 코드 조각이 포함되어야 합니다. 이슈에 사용자의 로컬 모델 가중치나 로컬 데이터를 사용하는 경우, 독자가 액세스할 수 없는 경우 이슈를 해결할 수 없습니다. 데이터나 모델을 공유할 수 없는 경우, 더미 모델이나 더미 데이터를 만들어 사용해보세요.
 4. **간결성**: 가능한 한 간결하게 유지하여 독자가 문제를 빠르게 이해할 수 있도록 도와주세요. 문제와 관련이 없는 코드나 정보는 모두 제거해주세요. 버그를 발견한 경우, 문제를 설명하는 가장 간단한 코드 예제를 만들어보세요. 버그를 발견한 후에는 작업 흐름 전체를 문제에 던지는 것이 아니라, 에러가 발생하는 훈련 코드의 어느 부분이 문제인지 먼저 이해하고 몇 줄로 재현해보세요. 전체 데이터셋 대신 더미 데이터를 사용해보세요.
 5. 링크 추가하기. 특정한 이름, 메서드, 또는 모델을 참조하는 경우, 독자가 더 잘 이해할 수 있도록 링크를 제공해주세요. 특정 PR이나 이슈를 참조하는 경우, 해당 이슈에 링크를 걸어주세요. 독자가 무엇을 말하는지 알고 있다고 가정하지 마세요. 이슈에 링크를 추가할수록 좋습니다.
-6. 포맷팅. 코드를 파이썬 코드 구문으로, 에러 메시지를 일반 코드 구문으로 형식화하여 이슈를 깔끔하게 작성하세요. 자세한 내용은 [GitHub 공식 포맷팅 문서](https://docs.github.com/en/get-started/writing-on-github/getting-started-with-writing-and-formatting-on-github/basic-writing-and-formatting-syntax)를 참조하세요.
-7. 여러분의 이슈를 단순히 해결해야 할 티켓으로 생각하지 말고, 잘 작성된 백과사전 항목으로 생각해보세요. 추가된 모든 이슈는 공개적으로 이용 가능한 지식에 대한 기여입니다. 잘 작성된 이슈를 추가함으로써 메인테이너가 여러분의 이슈를 더 쉽게 해결할 수 있게 할 뿐만 아니라, 전체 커뮤니티가 라이브러리의 특정 측면을 더 잘 이해할 수 있도록 도움을 주게 됩니다.
+6. 포맷팅. 파이썬 코드 구문으로 코드를 포맷팅하고, 일반 코드 구문으로 에러 메시지를 포맷팅해주세요. 자세한 내용은 [공식 GitHub 포맷팅 문서](https://docs.github.com/en/get-started/writing-on-github/getting-started-with-writing-and-formatting-on-github/basic-writing-and-formatting-syntax)를 참조하세요.
+7. 이슈를 해결해야 하는 티켓이 아니라, 잘 작성된 백과사전 항목으로 생각해보세요. 추가된 이슈는 공개적으로 사용 가능한 지식에 기여하는 것입니다. 잘 작성된 이슈를 추가함으로써 메인테이너가 문제를 해결하는 데 도움을 주는 것뿐만 아니라, 전체 커뮤니티가 라이브러리의 특정 측면을 더 잘 이해할 수 있도록 도움을 주는 것입니다.
 
-## 좋은 PR 작성 방법 [[how-to-write-a-good-pr]]
+## 좋은 PR 작성 방법
 
-1. 카멜레온이 되세요. 기존의 디자인 패턴과 구문을 이해하고, 여러분이 추가하는 코드가 기존 코드베이스와 자연스럽게 어우러지도록 해야 합니다. 기존 디자인 패턴이나 사용자 인터페이스와 크게 다른 Pull Request들은 병합되지 않습니다.
-2. 레이저처럼 집중하세요. Pull Request는 하나의 문제, 오직 하나의 문제만 해결해야 합니다. "이왕 추가하는 김에 다른 문제도 고치자"는 함정에 빠지지 않도록 주의하세요. 여러 개의 관련 없는 문제를 해결하는 한 번에 해결하는 Pull Request들은 검토하기가 훨씬 더 어렵습니다.
+1. 카멜레온이 되세요. 기존의 디자인 패턴과 구문을 이해하고, 코드 추가가 기존 코드베이스에 매끄럽게 흐르도록 해야 합니다. 기존 디자인 패턴이나 사용자 인터페이스와 크게 다른 PR은 병합되지 않습니다.
+2. 초점을 맞추세요. 하나의 문제만 해결하는 PR을 작성해야 합니다. "추가하면서 다른 문제도 해결하기"에 빠지지 않도록 주의하세요. 여러 개의 관련 없는 문제를 해결하는 PR을 작성하는 것은 리뷰하기가 훨씬 어렵습니다.
 3. 도움이 되는 경우, 추가한 내용이 어떻게 사용되는지 예제 코드 조각을 추가해보세요.
-4. Pull Request의 제목은 기여 내용을 요약해야 합니다.
-5. Pull Request가 이슈를 해결하는 경우, Pull Request의 설명에 이슈 번호를 언급하여 연결되도록 해주세요 (이슈를 참조하는 사람들이 작업 중임을 알 수 있도록).
+4. PR의 제목은 기여 내용을 요약해야 합니다.
+5. PR이 이슈를 해결하는 경우, PR 설명에 이슈 번호를 언급하여 연결되도록 해주세요 (이슈를 참조하는 사람들이 작업 중임을 알 수 있도록).
 6. 진행 중인 작업을 나타내려면 제목에 `[WIP]`를 접두사로 붙여주세요. 이는 중복 작업을 피하고, 병합 준비가 된 PR과 구분할 수 있도록 도움이 됩니다.
 7. [좋은 이슈를 작성하는 방법](#how-to-write-a-good-issue)에 설명된 대로 텍스트를 구성하고 형식을 지정해보세요.
 8. 기존 테스트가 통과하는지 확인하세요
@@ -373,10 +374,10 @@ class AltDiffusionPipelineOutput(BaseOutput):
 `RUN_SLOW=1 python -m pytest tests/test_my_new_model.py`.
 CircleCI는 느린 테스트를 실행하지 않지만, GitHub Actions는 매일 실행합니다!
 10. 모든 공개 메서드는 마크다운과 잘 작동하는 정보성 docstring을 가져야 합니다. 예시로 [`pipeline_latent_diffusion.py`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/latent_diffusion/pipeline_latent_diffusion.py)를 참조하세요.
-11. 리포지토리가 빠르게 성장하고 있기 때문에, 리포지토리에 큰 부담을 주는 파일이 추가되지 않도록 주의해야 합니다. 이미지, 비디오 및 기타 텍스트가 아닌 파일을 포함합니다. 이러한 파일을 배치하기 위해 hf.co 호스팅 `dataset`인 [`hf-internal-testing`](https://huggingface.co/hf-internal-testing) 또는 [huggingface/documentation-images](https://huggingface.co/datasets/huggingface/documentation-images)를 활용하는 것이 우선입니다.
+11. 레포지토리가 빠르게 성장하고 있기 때문에, 레포지토리에 큰 부담을 주는 파일이 추가되지 않도록 주의해야 합니다. 이미지, 비디오 및 기타 텍스트가 아닌 파일을 포함합니다. 이러한 파일을 배치하기 위해 hf.co 호스팅 `dataset`인 [`hf-internal-testing`](https://huggingface.co/hf-internal-testing) 또는 [huggingface/documentation-images](https://huggingface.co/datasets/huggingface/documentation-images)를 활용하는 것이 우선입니다.
 외부 기여인 경우, 이미지를 PR에 추가하고 Hugging Face 구성원에게 이미지를 이 데이터셋으로 이동하도록 요청하세요.
 
-## PR을 열기 위한 방법 [[how-to-open-a-pr]]
+## PR을 열기 위한 방법
 
 코드를 작성하기 전에, 이미 누군가가 같은 작업을 하고 있는지 확인하기 위해 기존의 PR이나 이슈를 검색하는 것이 좋습니다. 확실하지 않은 경우, 피드백을 받기 위해 이슈를 열어보는 것이 항상 좋은 아이디어입니다.
 
@@ -402,7 +403,7 @@ CircleCI는 느린 테스트를 실행하지 않지만, GitHub Actions는 매일
 
 `main` 브랜치 위에서 **절대** 작업하지 마세요.
 
-4. 가상 환경에서 다음 명령을 실행하여 개발 환경을 설정하세요:
+1. 가상 환경에서 다음 명령을 실행하여 개발 환경을 설정하세요:
 
  ```bash
  $ pip install -e ".[dev]"
@@ -466,7 +467,7 @@ CircleCI는 느린 테스트를 실행하지 않지만, GitHub Actions는 매일
 
 7. 메인테이너가 변경 사항을 요청하는 것은 괜찮습니다. 핵심 기여자들에게도 일어나는 일입니다! 따라서 변경 사항을 Pull request에서 볼 수 있도록 로컬 브랜치에서 작업하고 변경 사항을 포크에 푸시하면 자동으로 Pull request에 나타납니다.
 
-### 테스트 [[tests]]
+### 테스트
 
 라이브러리 동작과 여러 예제를 테스트하기 위해 포괄적인 테스트 묶음이 포함되어 있습니다. 라이브러리 테스트는 [tests 폴더](https://github.com/huggingface/diffusers/tree/main/tests)에서 찾을 수 있습니다.
 
@@ -493,7 +494,7 @@ $ python -m unittest discover -s tests -t . -v
 $ python -m unittest discover -s examples -t examples -v
 ```
 
-### upstream(HuggingFace) main과 forked main 동기화하기 [[syncing-forked-main-with-upstream-huggingface-main]]
+### upstream(main)과 forked main 동기화하기
 
 upstream 저장소에 불필요한 참조 노트를 추가하고 관련 개발자에게 알림을 보내는 것을 피하기 위해,
 forked 저장소의 main 브랜치를 동기화할 때 다음 단계를 따르세요:
@@ -506,6 +507,6 @@ $ git commit -m '<your message without GitHub references>'
 $ git push --set-upstream origin your-branch-for-syncing
 ```
 
-### 스타일 가이드 [[style-guide]]
+### 스타일 가이드
 
 Documentation string에 대해서는, 🧨 Diffusers는 [Google 스타일](https://google.github.io/styleguide/pyguide.html)을 따릅니다.

examples/advanced_diffusion_training/train_dreambooth_lora_sd15_advanced.py

@@ -71,7 +71,7 @@ from diffusers.utils.import_utils import is_xformers_available
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = get_logger(__name__)
 

examples/advanced_diffusion_training/train_dreambooth_lora_sdxl_advanced.py

@@ -79,7 +79,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = get_logger(__name__)
 

examples/community/README.md

@@ -71,7 +71,6 @@ Please also check out our [Community Scripts](https://github.com/huggingface/dif
 | Stable Diffusion BoxDiff Pipeline | Training-free controlled generation with bounding boxes using [BoxDiff](https://github.com/showlab/BoxDiff) | [Stable Diffusion BoxDiff Pipeline](#stable-diffusion-boxdiff) | - | [Jingyang Zhang](https://github.com/zjysteven/) |
 |   FRESCO V2V Pipeline                                                                                                    | Implementation of [[CVPR 2024] FRESCO: Spatial-Temporal Correspondence for Zero-Shot Video Translation](https://arxiv.org/abs/2403.12962)                                                                                                                                                                                                                                                                                                                                                                                                                                      | [FRESCO V2V Pipeline](#fresco)      | - |              [Yifan Zhou](https://github.com/SingleZombie) |
 | AnimateDiff IPEX Pipeline | Accelerate AnimateDiff inference pipeline with BF16/FP32 precision on Intel Xeon CPUs with [IPEX](https://github.com/intel/intel-extension-for-pytorch) | [AnimateDiff on IPEX](#animatediff-on-ipex) | - | [Dan Li](https://github.com/ustcuna/) |
-| HunyuanDiT Differential Diffusion Pipeline | Applies [Differential Diffsuion](https://github.com/exx8/differential-diffusion) to [HunyuanDiT](https://github.com/huggingface/diffusers/pull/8240). | [HunyuanDiT with Differential Diffusion](#hunyuandit-with-differential-diffusion) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1v44a5fpzyr4Ffr4v2XBQ7BajzG874N4P?usp=sharing) | [Monjoy Choudhury](https://github.com/MnCSSJ4x) |
 
 To load a custom pipeline you just need to pass the `custom_pipeline` argument to `DiffusionPipeline`, as one of the files in `diffusers/examples/community`. Feel free to send a PR with your own pipelines, we will merge them quickly.
 
@@ -1647,6 +1646,7 @@ from diffusers import DiffusionPipeline
 scheduler = DDIMScheduler.from_pretrained("stabilityai/stable-diffusion-2-1",
                                             subfolder="scheduler")
 
+
 pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-2-1",
                                             custom_pipeline="stable_diffusion_tensorrt_img2img",
                                             variant='fp16',
@@ -1661,6 +1661,7 @@ pipe = pipe.to("cuda")
 url = "https://pajoca.com/wp-content/uploads/2022/09/tekito-yamakawa-1.png"
 response = requests.get(url)
 input_image = Image.open(BytesIO(response.content)).convert("RGB")
+
 prompt = "photorealistic new zealand hills"
 image = pipe(prompt, image=input_image, strength=0.75,).images[0]
 image.save('tensorrt_img2img_new_zealand_hills.png')
@@ -4208,52 +4209,6 @@ print("Latency of AnimateDiffPipelineIpex--fp32", latency, "s for total", step,
 latency = elapsed_time(pipe4, num_inference_steps=step)
 print("Latency of AnimateDiffPipeline--fp32",latency, "s for total", step, "steps")
 ```
-### HunyuanDiT with Differential Diffusion
-
-#### Usage
-
-```python
-import torch
-from diffusers import FlowMatchEulerDiscreteScheduler
-from diffusers.utils import load_image
-from PIL import Image
-from torchvision import transforms
-
-from pipeline_hunyuandit_differential_img2img import (
-    HunyuanDiTDifferentialImg2ImgPipeline,
-)
-
-
-pipe = HunyuanDiTDifferentialImg2ImgPipeline.from_pretrained(
-    "Tencent-Hunyuan/HunyuanDiT-Diffusers", torch_dtype=torch.float16
-).to("cuda")
-
-
-source_image = load_image(
-    "https://huggingface.co/datasets/OzzyGT/testing-resources/resolve/main/differential/20240329211129_4024911930.png"
-)
-map = load_image(
-    "https://huggingface.co/datasets/OzzyGT/testing-resources/resolve/main/differential/gradient_mask_2.png"
-)
-prompt = "a green pear"
-negative_prompt = "blurry"
-
-image = pipe(
-    prompt=prompt,
-    negative_prompt=negative_prompt,
-    image=source_image,
-    num_inference_steps=28,
-    guidance_scale=4.5,
-    strength=1.0,
-    map=map,
-).images[0]
-```
-
-| ![Gradient](https://github.com/user-attachments/assets/e38ce4d5-1ae6-4df0-ab43-adc1b45716b5) | ![Input](https://github.com/user-attachments/assets/9c95679c-e9d7-4f5a-90d6-560203acd6b3) | ![Output](https://github.com/user-attachments/assets/5313ff64-a0c4-418b-8b55-a38f1a5e7532) |
-| ------------------------------------------------------------------------------------------ | --------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------- |
-| Gradient                                                                                   | Input                                                                                   | Output                                                                                   |
-
-A colab notebook demonstrating all results can be found [here](https://colab.research.google.com/drive/1v44a5fpzyr4Ffr4v2XBQ7BajzG874N4P?usp=sharing). Depth Maps have also been added in the same colab.
 
 # Perturbed-Attention Guidance
 
@@ -4330,4 +4285,4 @@ grid_image.save(grid_dir + "sample.png")
 
 `pag_scale` : guidance scale of PAG (ex: 5.0)
 
-`pag_applied_layers_index` : index of the layer to apply perturbation (ex: ['m0'])
+`pag_applied_layers_index` : index of the layer to apply perturbation (ex: ['m0'])

examples/community/marigold_depth_estimation.py

@@ -43,8 +43,7 @@ from diffusers.utils import BaseOutput, check_min_version
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
-
+check_min_version("0.30.0")
 
 class MarigoldDepthOutput(BaseOutput):
     """

examples/consistency_distillation/train_lcm_distill_lora_sd_wds.py

@@ -73,7 +73,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = get_logger(__name__)
 

examples/consistency_distillation/train_lcm_distill_lora_sdxl.py

@@ -66,7 +66,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = get_logger(__name__)
 

examples/consistency_distillation/train_lcm_distill_lora_sdxl_wds.py

@@ -79,7 +79,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = get_logger(__name__)
 

examples/consistency_distillation/train_lcm_distill_sd_wds.py

@@ -72,7 +72,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = get_logger(__name__)
 

examples/consistency_distillation/train_lcm_distill_sdxl_wds.py

@@ -78,7 +78,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = get_logger(__name__)
 

examples/controlnet/train_controlnet.py

@@ -60,7 +60,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = get_logger(__name__)
 

examples/controlnet/train_controlnet_flax.py

@@ -60,7 +60,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = logging.getLogger(__name__)
 

examples/controlnet/train_controlnet_sdxl.py

@@ -61,7 +61,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = get_logger(__name__)
 if is_torch_npu_available():

examples/custom_diffusion/train_custom_diffusion.py

@@ -63,7 +63,7 @@ from diffusers.utils.import_utils import is_xformers_available
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = get_logger(__name__)
 
@@ -314,12 +314,11 @@ def save_new_embed(text_encoder, modifier_token_id, accelerator, args, output_di
     for x, y in zip(modifier_token_id, args.modifier_token):
         learned_embeds_dict = {}
         learned_embeds_dict[y] = learned_embeds[x]
+        filename = f"{output_dir}/{y}.bin"
 
         if safe_serialization:
-            filename = f"{output_dir}/{y}.safetensors"
             safetensors.torch.save_file(learned_embeds_dict, filename, metadata={"format": "pt"})
         else:
-            filename = f"{output_dir}/{y}.bin"
             torch.save(learned_embeds_dict, filename)
 
 
@@ -1041,22 +1040,17 @@ def main(args):
     )
 
     # Scheduler and math around the number of training steps.
-    # Check the PR https://github.com/huggingface/diffusers/pull/8312 for detailed explanation.
-    num_warmup_steps_for_scheduler = args.lr_warmup_steps * accelerator.num_processes
+    overrode_max_train_steps = False
+    num_update_steps_per_epoch = math.ceil(len(train_dataloader) / args.gradient_accumulation_steps)
     if args.max_train_steps is None:
-        len_train_dataloader_after_sharding = math.ceil(len(train_dataloader) / accelerator.num_processes)
-        num_update_steps_per_epoch = math.ceil(len_train_dataloader_after_sharding / args.gradient_accumulation_steps)
-        num_training_steps_for_scheduler = (
-            args.num_train_epochs * num_update_steps_per_epoch * accelerator.num_processes
-        )
-    else:
-        num_training_steps_for_scheduler = args.max_train_steps * accelerator.num_processes
+        args.max_train_steps = args.num_train_epochs * num_update_steps_per_epoch
+        overrode_max_train_steps = True
 
     lr_scheduler = get_scheduler(
         args.lr_scheduler,
         optimizer=optimizer,
-        num_warmup_steps=num_warmup_steps_for_scheduler,
-        num_training_steps=num_training_steps_for_scheduler,
+        num_warmup_steps=args.lr_warmup_steps * accelerator.num_processes,
+        num_training_steps=args.max_train_steps * accelerator.num_processes,
     )
 
     # Prepare everything with our `accelerator`.
@@ -1071,14 +1065,8 @@ def main(args):
 
     # We need to recalculate our total training steps as the size of the training dataloader may have changed.
     num_update_steps_per_epoch = math.ceil(len(train_dataloader) / args.gradient_accumulation_steps)
-    if args.max_train_steps is None:
+    if overrode_max_train_steps:
         args.max_train_steps = args.num_train_epochs * num_update_steps_per_epoch
-        if num_training_steps_for_scheduler != args.max_train_steps * accelerator.num_processes:
-            logger.warning(
-                f"The length of the 'train_dataloader' after 'accelerator.prepare' ({len(train_dataloader)}) does not match "
-                f"the expected length ({len_train_dataloader_after_sharding}) when the learning rate scheduler was created. "
-                f"This inconsistency may result in the learning rate scheduler not functioning properly."
-            )
     # Afterwards we recalculate our number of training epochs
     args.num_train_epochs = math.ceil(args.max_train_steps / num_update_steps_per_epoch)
 

examples/dreambooth/README_flux.md

@@ -1,195 +0,0 @@
-# DreamBooth training example for FLUX.1 [dev]
-
-[DreamBooth](https://arxiv.org/abs/2208.12242) is a method to personalize text2image models like stable diffusion given just a few (3~5) images of a subject.
-
-The `train_dreambooth_flux.py` script shows how to implement the training procedure and adapt it for [FLUX.1 [dev]](https://blackforestlabs.ai/announcing-black-forest-labs/). We also provide a LoRA implementation in the `train_dreambooth_lora_flux.py` script.
-> [!NOTE]
-> **Memory consumption**
->
-> Flux can be quite expensive to run on consumer hardware devices and as a result finetuning it comes with high memory requirements -
-> a LoRA with a rank of 16 (w/ all components trained) can exceed 40GB of VRAM for training.
-> For more tips & guidance on training on a resource-constrained device please visit [`@bghira`'s guide](https://github.com/bghira/SimpleTuner/blob/main/documentation/quickstart/FLUX.md)
-
-
-> [!NOTE]
-> **Gated model**
->
-> As the model is gated, before using it with diffusers you first need to go to the [FLUX.1 [dev] Hugging Face page](https://huggingface.co/black-forest-labs/FLUX.1-dev), fill in the form and accept the gate. Once you are in, you need to log in so that your system knows you’ve accepted the gate. Use the command below to log in:
-
-```bash
-huggingface-cli login
-```
-
-This will also allow us to push the trained model parameters to the Hugging Face Hub platform.
-
-## Running locally with PyTorch
-
-### Installing the dependencies
-
-Before running the scripts, make sure to install the library's training dependencies:
-
-**Important**
-
-To make sure you can successfully run the latest versions of the example scripts, we highly recommend **installing from source** and keeping the install up to date as we update the example scripts frequently and install some example-specific requirements. To do this, execute the following steps in a new virtual environment:
-
-```bash
-git clone https://github.com/huggingface/diffusers
-cd diffusers
-pip install -e .
-```
-
-Then cd in the `examples/dreambooth` folder and run
-```bash
-pip install -r requirements_flux.txt
-```
-
-And initialize an [🤗Accelerate](https://github.com/huggingface/accelerate/) environment with:
-
-```bash
-accelerate config
-```
-
-Or for a default accelerate configuration without answering questions about your environment
-
-```bash
-accelerate config default
-```
-
-Or if your environment doesn't support an interactive shell (e.g., a notebook)
-
-```python
-from accelerate.utils import write_basic_config
-write_basic_config()
-```
-
-When running `accelerate config`, if we specify torch compile mode to True there can be dramatic speedups.
-Note also that we use PEFT library as backend for LoRA training, make sure to have `peft>=0.6.0` installed in your environment.
-
-
-### Dog toy example
-
-Now let's get our dataset. For this example we will use some dog images: https://huggingface.co/datasets/diffusers/dog-example.
-
-Let's first download it locally:
-
-```python
-from huggingface_hub import snapshot_download
-
-local_dir = "./dog"
-snapshot_download(
-    "diffusers/dog-example",
-    local_dir=local_dir, repo_type="dataset",
-    ignore_patterns=".gitattributes",
-)
-```
-
-This will also allow us to push the trained LoRA parameters to the Hugging Face Hub platform.
-
-Now, we can launch training using:
-
-```bash
-export MODEL_NAME="black-forest-labs/FLUX.1-dev"
-export INSTANCE_DIR="dog"
-export OUTPUT_DIR="trained-flux"
-
-accelerate launch train_dreambooth_flux.py \
-  --pretrained_model_name_or_path=$MODEL_NAME  \
-  --instance_data_dir=$INSTANCE_DIR \
-  --output_dir=$OUTPUT_DIR \
-  --mixed_precision="bf16" \
-  --instance_prompt="a photo of sks dog" \
-  --resolution=1024 \
-  --train_batch_size=1 \
-  --gradient_accumulation_steps=4 \
-  --learning_rate=1e-4 \
-  --report_to="wandb" \
-  --lr_scheduler="constant" \
-  --lr_warmup_steps=0 \
-  --max_train_steps=500 \
-  --validation_prompt="A photo of sks dog in a bucket" \
-  --validation_epochs=25 \
-  --seed="0" \
-  --push_to_hub
-```
-
-To better track our training experiments, we're using the following flags in the command above:
-
-* `report_to="wandb` will ensure the training runs are tracked on Weights and Biases. To use it, be sure to install `wandb` with `pip install wandb`.
-* `validation_prompt` and `validation_epochs` to allow the script to do a few validation inference runs. This allows us to qualitatively check if the training is progressing as expected.
-
-> [!NOTE]
-> If you want to train using long prompts with the T5 text encoder, you can use `--max_sequence_length` to set the token limit. The default is 77, but it can be increased to as high as 512. Note that this will use more resources and may slow down the training in some cases.
-
-> [!TIP]
-> You can pass `--use_8bit_adam` to reduce the memory requirements of training. Make sure to install `bitsandbytes` if you want to do so.
-
-## LoRA + DreamBooth
-
-[LoRA](https://huggingface.co/docs/peft/conceptual_guides/adapter#low-rank-adaptation-lora) is a popular parameter-efficient fine-tuning technique that allows you to achieve full-finetuning like performance but with a fraction of learnable parameters.
-
-Note also that we use PEFT library as backend for LoRA training, make sure to have `peft>=0.6.0` installed in your environment.
-
-To perform DreamBooth with LoRA, run:
-
-```bash
-export MODEL_NAME="black-forest-labs/FLUX.1-dev"
-export INSTANCE_DIR="dog"
-export OUTPUT_DIR="trained-flux-lora"
-
-accelerate launch train_dreambooth_lora_flux.py \
-  --pretrained_model_name_or_path=$MODEL_NAME  \
-  --instance_data_dir=$INSTANCE_DIR \
-  --output_dir=$OUTPUT_DIR \
-  --mixed_precision="bf16" \
-  --instance_prompt="a photo of sks dog" \
-  --resolution=512 \
-  --train_batch_size=1 \
-  --gradient_accumulation_steps=4 \
-  --learning_rate=1e-5 \
-  --report_to="wandb" \
-  --lr_scheduler="constant" \
-  --lr_warmup_steps=0 \
-  --max_train_steps=500 \
-  --validation_prompt="A photo of sks dog in a bucket" \
-  --validation_epochs=25 \
-  --seed="0" \
-  --push_to_hub
-```
-
-### Text Encoder Training
-
-Alongside the transformer, fine-tuning of the CLIP text encoder is also supported.
-To do so, just specify `--train_text_encoder` while launching training. Please keep the following points in mind:
-
-> [!NOTE]
-> FLUX.1 has 2 text encoders (CLIP L/14 and T5-v1.1-XXL).
-By enabling `--train_text_encoder`, fine-tuning of the **CLIP encoder** is performed.
-> At the moment, T5 fine-tuning is not supported and weights remain frozen when text encoder training is enabled.
-
-To perform DreamBooth LoRA with text-encoder training, run:
-```bash
-export MODEL_NAME="black-forest-labs/FLUX.1-dev"
-export OUTPUT_DIR="trained-flux-dev-dreambooth-lora"
-
-accelerate launch train_dreambooth_lora_flux.py \
-  --pretrained_model_name_or_path=$MODEL_NAME  \
-  --instance_data_dir=$INSTANCE_DIR \
-  --output_dir=$OUTPUT_DIR \
-  --mixed_precision="bf16" \
-  --train_text_encoder\
-  --instance_prompt="a photo of sks dog" \
-  --resolution=512 \
-  --train_batch_size=1 \
-  --gradient_accumulation_steps=4 \
-  --learning_rate=1e-5 \
-  --report_to="wandb" \
-  --lr_scheduler="constant" \
-  --lr_warmup_steps=0 \
-  --max_train_steps=500 \
-  --validation_prompt="A photo of sks dog in a bucket" \
-  --seed="0" \
-  --push_to_hub
-```
-
-## Other notes
-Thanks to `bghira` for their help with reviewing & insight sharing ♥️

examples/dreambooth/requirements_flux.txt

@@ -1,8 +0,0 @@
-accelerate>=0.31.0
-torchvision
-transformers>=4.41.2
-ftfy
-tensorboard
-Jinja2
-peft>=0.11.1
-sentencepiece

examples/dreambooth/test_dreambooth_flux.py

@@ -1,203 +0,0 @@
-# coding=utf-8
-# Copyright 2024 HuggingFace Inc.
-#
-# 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 logging
-import os
-import shutil
-import sys
-import tempfile
-
-from diffusers import DiffusionPipeline, FluxTransformer2DModel
-
-
-sys.path.append("..")
-from test_examples_utils import ExamplesTestsAccelerate, run_command  # noqa: E402
-
-
-logging.basicConfig(level=logging.DEBUG)
-
-logger = logging.getLogger()
-stream_handler = logging.StreamHandler(sys.stdout)
-logger.addHandler(stream_handler)
-
-
-class DreamBoothFlux(ExamplesTestsAccelerate):
-    instance_data_dir = "docs/source/en/imgs"
-    instance_prompt = "photo"
-    pretrained_model_name_or_path = "hf-internal-testing/tiny-flux-pipe"
-    script_path = "examples/dreambooth/train_dreambooth_flux.py"
-
-    def test_dreambooth(self):
-        with tempfile.TemporaryDirectory() as tmpdir:
-            test_args = f"""
-                {self.script_path}
-                --pretrained_model_name_or_path {self.pretrained_model_name_or_path}
-                --instance_data_dir {self.instance_data_dir}
-                --instance_prompt {self.instance_prompt}
-                --resolution 64
-                --train_batch_size 1
-                --gradient_accumulation_steps 1
-                --max_train_steps 2
-                --learning_rate 5.0e-04
-                --scale_lr
-                --lr_scheduler constant
-                --lr_warmup_steps 0
-                --output_dir {tmpdir}
-                """.split()
-
-            run_command(self._launch_args + test_args)
-            # save_pretrained smoke test
-            self.assertTrue(os.path.isfile(os.path.join(tmpdir, "transformer", "diffusion_pytorch_model.safetensors")))
-            self.assertTrue(os.path.isfile(os.path.join(tmpdir, "scheduler", "scheduler_config.json")))
-
-    def test_dreambooth_checkpointing(self):
-        with tempfile.TemporaryDirectory() as tmpdir:
-            # Run training script with checkpointing
-            # max_train_steps == 4, checkpointing_steps == 2
-            # Should create checkpoints at steps 2, 4
-
-            initial_run_args = f"""
-                {self.script_path}
-                --pretrained_model_name_or_path {self.pretrained_model_name_or_path}
-                --instance_data_dir {self.instance_data_dir}
-                --instance_prompt {self.instance_prompt}
-                --resolution 64
-                --train_batch_size 1
-                --gradient_accumulation_steps 1
-                --max_train_steps 4
-                --learning_rate 5.0e-04
-                --scale_lr
-                --lr_scheduler constant
-                --lr_warmup_steps 0
-                --output_dir {tmpdir}
-                --checkpointing_steps=2
-                --seed=0
-                """.split()
-
-            run_command(self._launch_args + initial_run_args)
-
-            # check can run the original fully trained output pipeline
-            pipe = DiffusionPipeline.from_pretrained(tmpdir)
-            pipe(self.instance_prompt, num_inference_steps=1)
-
-            # check checkpoint directories exist
-            self.assertTrue(os.path.isdir(os.path.join(tmpdir, "checkpoint-2")))
-            self.assertTrue(os.path.isdir(os.path.join(tmpdir, "checkpoint-4")))
-
-            # check can run an intermediate checkpoint
-            transformer = FluxTransformer2DModel.from_pretrained(tmpdir, subfolder="checkpoint-2/transformer")
-            pipe = DiffusionPipeline.from_pretrained(self.pretrained_model_name_or_path, transformer=transformer)
-            pipe(self.instance_prompt, num_inference_steps=1)
-
-            # Remove checkpoint 2 so that we can check only later checkpoints exist after resuming
-            shutil.rmtree(os.path.join(tmpdir, "checkpoint-2"))
-
-            # Run training script for 7 total steps resuming from checkpoint 4
-
-            resume_run_args = f"""
-                {self.script_path}
-                --pretrained_model_name_or_path {self.pretrained_model_name_or_path}
-                --instance_data_dir {self.instance_data_dir}
-                --instance_prompt {self.instance_prompt}
-                --resolution 64
-                --train_batch_size 1
-                --gradient_accumulation_steps 1
-                --max_train_steps 6
-                --learning_rate 5.0e-04
-                --scale_lr
-                --lr_scheduler constant
-                --lr_warmup_steps 0
-                --output_dir {tmpdir}
-                --checkpointing_steps=2
-                --resume_from_checkpoint=checkpoint-4
-                --seed=0
-                """.split()
-
-            run_command(self._launch_args + resume_run_args)
-
-            # check can run new fully trained pipeline
-            pipe = DiffusionPipeline.from_pretrained(tmpdir)
-            pipe(self.instance_prompt, num_inference_steps=1)
-
-            # check old checkpoints do not exist
-            self.assertFalse(os.path.isdir(os.path.join(tmpdir, "checkpoint-2")))
-
-            # check new checkpoints exist
-            self.assertTrue(os.path.isdir(os.path.join(tmpdir, "checkpoint-4")))
-            self.assertTrue(os.path.isdir(os.path.join(tmpdir, "checkpoint-6")))
-
-    def test_dreambooth_checkpointing_checkpoints_total_limit(self):
-        with tempfile.TemporaryDirectory() as tmpdir:
-            test_args = f"""
-            {self.script_path}
-            --pretrained_model_name_or_path={self.pretrained_model_name_or_path}
-            --instance_data_dir={self.instance_data_dir}
-            --output_dir={tmpdir}
-            --instance_prompt={self.instance_prompt}
-            --resolution=64
-            --train_batch_size=1
-            --gradient_accumulation_steps=1
-            --max_train_steps=6
-            --checkpoints_total_limit=2
-            --checkpointing_steps=2
-            """.split()
-
-            run_command(self._launch_args + test_args)
-
-            self.assertEqual(
-                {x for x in os.listdir(tmpdir) if "checkpoint" in x},
-                {"checkpoint-4", "checkpoint-6"},
-            )
-
-    def test_dreambooth_checkpointing_checkpoints_total_limit_removes_multiple_checkpoints(self):
-        with tempfile.TemporaryDirectory() as tmpdir:
-            test_args = f"""
-            {self.script_path}
-            --pretrained_model_name_or_path={self.pretrained_model_name_or_path}
-            --instance_data_dir={self.instance_data_dir}
-            --output_dir={tmpdir}
-            --instance_prompt={self.instance_prompt}
-            --resolution=64
-            --train_batch_size=1
-            --gradient_accumulation_steps=1
-            --max_train_steps=4
-            --checkpointing_steps=2
-            """.split()
-
-            run_command(self._launch_args + test_args)
-
-            self.assertEqual(
-                {x for x in os.listdir(tmpdir) if "checkpoint" in x},
-                {"checkpoint-2", "checkpoint-4"},
-            )
-
-            resume_run_args = f"""
-            {self.script_path}
-            --pretrained_model_name_or_path={self.pretrained_model_name_or_path}
-            --instance_data_dir={self.instance_data_dir}
-            --output_dir={tmpdir}
-            --instance_prompt={self.instance_prompt}
-            --resolution=64
-            --train_batch_size=1
-            --gradient_accumulation_steps=1
-            --max_train_steps=8
-            --checkpointing_steps=2
-            --resume_from_checkpoint=checkpoint-4
-            --checkpoints_total_limit=2
-            """.split()
-
-            run_command(self._launch_args + resume_run_args)
-
-            self.assertEqual({x for x in os.listdir(tmpdir) if "checkpoint" in x}, {"checkpoint-6", "checkpoint-8"})

examples/dreambooth/test_dreambooth_lora_flux.py

@@ -1,165 +0,0 @@
-# coding=utf-8
-# Copyright 2024 HuggingFace Inc.
-#
-# 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 logging
-import os
-import sys
-import tempfile
-
-import safetensors
-
-
-sys.path.append("..")
-from test_examples_utils import ExamplesTestsAccelerate, run_command  # noqa: E402
-
-
-logging.basicConfig(level=logging.DEBUG)
-
-logger = logging.getLogger()
-stream_handler = logging.StreamHandler(sys.stdout)
-logger.addHandler(stream_handler)
-
-
-class DreamBoothLoRAFlux(ExamplesTestsAccelerate):
-    instance_data_dir = "docs/source/en/imgs"
-    instance_prompt = "photo"
-    pretrained_model_name_or_path = "hf-internal-testing/tiny-flux-pipe"
-    script_path = "examples/dreambooth/train_dreambooth_lora_flux.py"
-
-    def test_dreambooth_lora_flux(self):
-        with tempfile.TemporaryDirectory() as tmpdir:
-            test_args = f"""
-                {self.script_path}
-                --pretrained_model_name_or_path {self.pretrained_model_name_or_path}
-                --instance_data_dir {self.instance_data_dir}
-                --instance_prompt {self.instance_prompt}
-                --resolution 64
-                --train_batch_size 1
-                --gradient_accumulation_steps 1
-                --max_train_steps 2
-                --learning_rate 5.0e-04
-                --scale_lr
-                --lr_scheduler constant
-                --lr_warmup_steps 0
-                --output_dir {tmpdir}
-                """.split()
-
-            run_command(self._launch_args + test_args)
-            # save_pretrained smoke test
-            self.assertTrue(os.path.isfile(os.path.join(tmpdir, "pytorch_lora_weights.safetensors")))
-
-            # make sure the state_dict has the correct naming in the parameters.
-            lora_state_dict = safetensors.torch.load_file(os.path.join(tmpdir, "pytorch_lora_weights.safetensors"))
-            is_lora = all("lora" in k for k in lora_state_dict.keys())
-            self.assertTrue(is_lora)
-
-            # when not training the text encoder, all the parameters in the state dict should start
-            # with `"transformer"` in their names.
-            starts_with_transformer = all(key.startswith("transformer") for key in lora_state_dict.keys())
-            self.assertTrue(starts_with_transformer)
-
-    def test_dreambooth_lora_text_encoder_flux(self):
-        with tempfile.TemporaryDirectory() as tmpdir:
-            test_args = f"""
-                {self.script_path}
-                --pretrained_model_name_or_path {self.pretrained_model_name_or_path}
-                --instance_data_dir {self.instance_data_dir}
-                --instance_prompt {self.instance_prompt}
-                --resolution 64
-                --train_batch_size 1
-                --train_text_encoder
-                --gradient_accumulation_steps 1
-                --max_train_steps 2
-                --learning_rate 5.0e-04
-                --scale_lr
-                --lr_scheduler constant
-                --lr_warmup_steps 0
-                --output_dir {tmpdir}
-                """.split()
-
-            run_command(self._launch_args + test_args)
-            # save_pretrained smoke test
-            self.assertTrue(os.path.isfile(os.path.join(tmpdir, "pytorch_lora_weights.safetensors")))
-
-            # make sure the state_dict has the correct naming in the parameters.
-            lora_state_dict = safetensors.torch.load_file(os.path.join(tmpdir, "pytorch_lora_weights.safetensors"))
-            is_lora = all("lora" in k for k in lora_state_dict.keys())
-            self.assertTrue(is_lora)
-
-            starts_with_expected_prefix = all(
-                (key.startswith("transformer") or key.startswith("text_encoder")) for key in lora_state_dict.keys()
-            )
-            self.assertTrue(starts_with_expected_prefix)
-
-    def test_dreambooth_lora_flux_checkpointing_checkpoints_total_limit(self):
-        with tempfile.TemporaryDirectory() as tmpdir:
-            test_args = f"""
-            {self.script_path}
-            --pretrained_model_name_or_path={self.pretrained_model_name_or_path}
-            --instance_data_dir={self.instance_data_dir}
-            --output_dir={tmpdir}
-            --instance_prompt={self.instance_prompt}
-            --resolution=64
-            --train_batch_size=1
-            --gradient_accumulation_steps=1
-            --max_train_steps=6
-            --checkpoints_total_limit=2
-            --checkpointing_steps=2
-            """.split()
-
-            run_command(self._launch_args + test_args)
-
-            self.assertEqual(
-                {x for x in os.listdir(tmpdir) if "checkpoint" in x},
-                {"checkpoint-4", "checkpoint-6"},
-            )
-
-    def test_dreambooth_lora_flux_checkpointing_checkpoints_total_limit_removes_multiple_checkpoints(self):
-        with tempfile.TemporaryDirectory() as tmpdir:
-            test_args = f"""
-            {self.script_path}
-            --pretrained_model_name_or_path={self.pretrained_model_name_or_path}
-            --instance_data_dir={self.instance_data_dir}
-            --output_dir={tmpdir}
-            --instance_prompt={self.instance_prompt}
-            --resolution=64
-            --train_batch_size=1
-            --gradient_accumulation_steps=1
-            --max_train_steps=4
-            --checkpointing_steps=2
-            """.split()
-
-            run_command(self._launch_args + test_args)
-
-            self.assertEqual({x for x in os.listdir(tmpdir) if "checkpoint" in x}, {"checkpoint-2", "checkpoint-4"})
-
-            resume_run_args = f"""
-            {self.script_path}
-            --pretrained_model_name_or_path={self.pretrained_model_name_or_path}
-            --instance_data_dir={self.instance_data_dir}
-            --output_dir={tmpdir}
-            --instance_prompt={self.instance_prompt}
-            --resolution=64
-            --train_batch_size=1
-            --gradient_accumulation_steps=1
-            --max_train_steps=8
-            --checkpointing_steps=2
-            --resume_from_checkpoint=checkpoint-4
-            --checkpoints_total_limit=2
-            """.split()
-
-            run_command(self._launch_args + resume_run_args)
-
-            self.assertEqual({x for x in os.listdir(tmpdir) if "checkpoint" in x}, {"checkpoint-6", "checkpoint-8"})

examples/dreambooth/train_dreambooth.py

@@ -63,7 +63,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = get_logger(__name__)
 

examples/dreambooth/train_dreambooth_flax.py

@@ -35,7 +35,7 @@ from diffusers.utils import check_min_version
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 # Cache compiled models across invocations of this script.
 cc.initialize_cache(os.path.expanduser("~/.cache/jax/compilation_cache"))

examples/dreambooth/train_dreambooth_lora.py

@@ -70,7 +70,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = get_logger(__name__)
 

examples/dreambooth/train_dreambooth_lora_sd3.py

@@ -72,7 +72,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = get_logger(__name__)
 
@@ -1454,7 +1454,7 @@ def main(args):
             )
 
     # Clear the memory here
-    if not args.train_text_encoder and not train_dataset.custom_instance_prompts:
+    if not args.train_text_encoder and train_dataset.custom_instance_prompts:
         del tokenizers, text_encoders
         # Explicitly delete the objects as well, otherwise only the lists are deleted and the original references remain, preventing garbage collection
         del text_encoder_one, text_encoder_two, text_encoder_three

examples/dreambooth/train_dreambooth_lora_sdxl.py

@@ -78,7 +78,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = get_logger(__name__)
 

examples/dreambooth/train_dreambooth_sd3.py

@@ -64,7 +64,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = get_logger(__name__)
 

examples/instruct_pix2pix/train_instruct_pix2pix.py

@@ -57,7 +57,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = get_logger(__name__, log_level="INFO")
 

examples/instruct_pix2pix/train_instruct_pix2pix_sdxl.py

@@ -60,7 +60,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = get_logger(__name__, log_level="INFO")
 

examples/kandinsky2_2/text_to_image/train_text_to_image_decoder.py

@@ -52,7 +52,7 @@ if is_wandb_available():
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = get_logger(__name__, log_level="INFO")
 

examples/kandinsky2_2/text_to_image/train_text_to_image_lora_decoder.py

@@ -46,7 +46,7 @@ from diffusers.utils import check_min_version, is_wandb_available
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = get_logger(__name__, log_level="INFO")
 

examples/kandinsky2_2/text_to_image/train_text_to_image_lora_prior.py

@@ -46,7 +46,7 @@ from diffusers.utils import check_min_version, is_wandb_available
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = get_logger(__name__, log_level="INFO")
 

examples/kandinsky2_2/text_to_image/train_text_to_image_prior.py

@@ -51,7 +51,7 @@ if is_wandb_available():
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = get_logger(__name__, log_level="INFO")
 

examples/research_projects/realfill/requirements.txt

@@ -2,8 +2,8 @@ diffusers==0.20.1
 accelerate==0.23.0
 transformers==4.38.0
 peft==0.5.0
-torch==2.2.0
+torch==2.0.1
 torchvision>=0.16
 ftfy==6.1.1
 tensorboard==2.14.0
-Jinja2==3.1.4
+Jinja2==3.1.3

examples/t2i_adapter/train_t2i_adapter_sdxl.py

@@ -60,7 +60,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = get_logger(__name__)
 

examples/text_to_image/train_text_to_image.py

@@ -57,7 +57,7 @@ if is_wandb_available():
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = get_logger(__name__, log_level="INFO")
 
@@ -826,22 +826,17 @@ def main():
     )
 
     # Scheduler and math around the number of training steps.
-    # Check the PR https://github.com/huggingface/diffusers/pull/8312 for detailed explanation.
-    num_warmup_steps_for_scheduler = args.lr_warmup_steps * accelerator.num_processes
+    overrode_max_train_steps = False
+    num_update_steps_per_epoch = math.ceil(len(train_dataloader) / args.gradient_accumulation_steps)
     if args.max_train_steps is None:
-        len_train_dataloader_after_sharding = math.ceil(len(train_dataloader) / accelerator.num_processes)
-        num_update_steps_per_epoch = math.ceil(len_train_dataloader_after_sharding / args.gradient_accumulation_steps)
-        num_training_steps_for_scheduler = (
-            args.num_train_epochs * num_update_steps_per_epoch * accelerator.num_processes
-        )
-    else:
-        num_training_steps_for_scheduler = args.max_train_steps * accelerator.num_processes
+        args.max_train_steps = args.num_train_epochs * num_update_steps_per_epoch
+        overrode_max_train_steps = True
 
     lr_scheduler = get_scheduler(
         args.lr_scheduler,
         optimizer=optimizer,
-        num_warmup_steps=num_warmup_steps_for_scheduler,
-        num_training_steps=num_training_steps_for_scheduler,
+        num_warmup_steps=args.lr_warmup_steps * accelerator.num_processes,
+        num_training_steps=args.max_train_steps * accelerator.num_processes,
     )
 
     # Prepare everything with our `accelerator`.
@@ -871,14 +866,8 @@ def main():
 
     # We need to recalculate our total training steps as the size of the training dataloader may have changed.
     num_update_steps_per_epoch = math.ceil(len(train_dataloader) / args.gradient_accumulation_steps)
-    if args.max_train_steps is None:
+    if overrode_max_train_steps:
         args.max_train_steps = args.num_train_epochs * num_update_steps_per_epoch
-        if num_training_steps_for_scheduler != args.max_train_steps * accelerator.num_processes:
-            logger.warning(
-                f"The length of the 'train_dataloader' after 'accelerator.prepare' ({len(train_dataloader)}) does not match "
-                f"the expected length ({len_train_dataloader_after_sharding}) when the learning rate scheduler was created. "
-                f"This inconsistency may result in the learning rate scheduler not functioning properly."
-            )
     # Afterwards we recalculate our number of training epochs
     args.num_train_epochs = math.ceil(args.max_train_steps / num_update_steps_per_epoch)
 

examples/text_to_image/train_text_to_image_flax.py

@@ -49,7 +49,7 @@ from diffusers.utils import check_min_version
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = logging.getLogger(__name__)
 

examples/text_to_image/train_text_to_image_lora.py

@@ -56,7 +56,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = get_logger(__name__, log_level="INFO")
 

examples/text_to_image/train_text_to_image_lora_sdxl.py

@@ -68,7 +68,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = get_logger(__name__)
 if is_torch_npu_available():
@@ -478,7 +478,7 @@ def parse_args(input_args=None):
     parser.add_argument(
         "--debug_loss",
         action="store_true",
-        help="debug loss for each image, if filenames are available in the dataset",
+        help="debug loss for each image, if filenames are awailable in the dataset",
     )
 
     if input_args is not None:

examples/text_to_image/train_text_to_image_sdxl.py

@@ -55,7 +55,7 @@ from diffusers.utils.torch_utils import is_compiled_module
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = get_logger(__name__)
 if is_torch_npu_available():
@@ -1084,7 +1084,7 @@ def main(args):
 
                 # Add noise to the model input according to the noise magnitude at each timestep
                 # (this is the forward diffusion process)
-                noisy_model_input = noise_scheduler.add_noise(model_input, noise, timesteps).to(dtype=weight_dtype)
+                noisy_model_input = noise_scheduler.add_noise(model_input, noise, timesteps)
 
                 # time ids
                 def compute_time_ids(original_size, crops_coords_top_left):
@@ -1101,7 +1101,7 @@ def main(args):
 
                 # Predict the noise residual
                 unet_added_conditions = {"time_ids": add_time_ids}
-                prompt_embeds = batch["prompt_embeds"].to(accelerator.device, dtype=weight_dtype)
+                prompt_embeds = batch["prompt_embeds"].to(accelerator.device)
                 pooled_prompt_embeds = batch["pooled_prompt_embeds"].to(accelerator.device)
                 unet_added_conditions.update({"text_embeds": pooled_prompt_embeds})
                 model_pred = unet(

examples/textual_inversion/README.md

@@ -109,9 +109,6 @@ import torch
 model_id = "path-to-your-trained-model"
 pipe = StableDiffusionPipeline.from_pretrained(model_id,torch_dtype=torch.float16).to("cuda")
 
-repo_id_embeds = "path-to-your-learned-embeds"
-pipe.load_textual_inversion(repo_id_embeds)
-
 prompt = "A <cat-toy> backpack"
 
 image = pipe(prompt, num_inference_steps=50, guidance_scale=7.5).images[0]

examples/textual_inversion/README_sdxl.md

@@ -23,25 +23,4 @@ accelerate launch textual_inversion_sdxl.py \
   --output_dir="./textual_inversion_cat_sdxl"
 ```
 
-Training of both text encoders is supported.
-
-### Inference Example
-
-Once you have trained a model using above command, the inference can be done simply using the `StableDiffusionXLPipeline`.
-Make sure to include the `placeholder_token` in your prompt.
-
-```python
-from diffusers import StableDiffusionXLPipeline
-import torch
-
-model_id = "./textual_inversion_cat_sdxl"
-pipe = StableDiffusionXLPipeline.from_pretrained(model_id,torch_dtype=torch.float16).to("cuda")
-
-prompt = "A <cat-toy> backpack"
-
-image = pipe(prompt, num_inference_steps=50, guidance_scale=7.5).images[0]
-image.save("cat-backpack.png")
-
-image = pipe(prompt="", prompt_2=prompt, num_inference_steps=50, guidance_scale=7.5).images[0]
-image.save("cat-backpack-prompt_2.png")
-```
+For now, only training of the first text encoder is supported.

examples/textual_inversion/textual_inversion.py

@@ -81,7 +81,7 @@ else:
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = get_logger(__name__)
 

examples/textual_inversion/textual_inversion_flax.py

@@ -56,7 +56,7 @@ else:
 # ------------------------------------------------------------------------------
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = logging.getLogger(__name__)
 

examples/textual_inversion/textual_inversion_sdxl.py

@@ -76,7 +76,7 @@ else:
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = get_logger(__name__)
 
@@ -135,7 +135,7 @@ def log_validation(
     pipeline = DiffusionPipeline.from_pretrained(
         args.pretrained_model_name_or_path,
         text_encoder=accelerator.unwrap_model(text_encoder_1),
-        text_encoder_2=accelerator.unwrap_model(text_encoder_2),
+        text_encoder_2=text_encoder_2,
         tokenizer=tokenizer_1,
         tokenizer_2=tokenizer_2,
         unet=unet,
@@ -678,54 +678,36 @@ def main():
             f"The tokenizer already contains the token {args.placeholder_token}. Please pass a different"
             " `placeholder_token` that is not already in the tokenizer."
         )
-    num_added_tokens = tokenizer_2.add_tokens(placeholder_tokens)
-    if num_added_tokens != args.num_vectors:
-        raise ValueError(
-            f"The 2nd tokenizer already contains the token {args.placeholder_token}. Please pass a different"
-            " `placeholder_token` that is not already in the tokenizer."
-        )
 
     # Convert the initializer_token, placeholder_token to ids
     token_ids = tokenizer_1.encode(args.initializer_token, add_special_tokens=False)
-    token_ids_2 = tokenizer_2.encode(args.initializer_token, add_special_tokens=False)
-
     # Check if initializer_token is a single token or a sequence of tokens
-    if len(token_ids) > 1 or len(token_ids_2) > 1:
+    if len(token_ids) > 1:
         raise ValueError("The initializer token must be a single token.")
 
     initializer_token_id = token_ids[0]
     placeholder_token_ids = tokenizer_1.convert_tokens_to_ids(placeholder_tokens)
-    initializer_token_id_2 = token_ids_2[0]
-    placeholder_token_ids_2 = tokenizer_2.convert_tokens_to_ids(placeholder_tokens)
 
     # Resize the token embeddings as we are adding new special tokens to the tokenizer
     text_encoder_1.resize_token_embeddings(len(tokenizer_1))
-    text_encoder_2.resize_token_embeddings(len(tokenizer_2))
 
     # Initialise the newly added placeholder token with the embeddings of the initializer token
     token_embeds = text_encoder_1.get_input_embeddings().weight.data
-    token_embeds_2 = text_encoder_2.get_input_embeddings().weight.data
     with torch.no_grad():
         for token_id in placeholder_token_ids:
             token_embeds[token_id] = token_embeds[initializer_token_id].clone()
-        for token_id in placeholder_token_ids_2:
-            token_embeds_2[token_id] = token_embeds_2[initializer_token_id_2].clone()
 
     # Freeze vae and unet
     vae.requires_grad_(False)
     unet.requires_grad_(False)
-
+    text_encoder_2.requires_grad_(False)
     # Freeze all parameters except for the token embeddings in text encoder
     text_encoder_1.text_model.encoder.requires_grad_(False)
     text_encoder_1.text_model.final_layer_norm.requires_grad_(False)
     text_encoder_1.text_model.embeddings.position_embedding.requires_grad_(False)
-    text_encoder_2.text_model.encoder.requires_grad_(False)
-    text_encoder_2.text_model.final_layer_norm.requires_grad_(False)
-    text_encoder_2.text_model.embeddings.position_embedding.requires_grad_(False)
 
     if args.gradient_checkpointing:
         text_encoder_1.gradient_checkpointing_enable()
-        text_encoder_2.gradient_checkpointing_enable()
 
     if args.enable_xformers_memory_efficient_attention:
         if is_xformers_available():
@@ -764,11 +746,7 @@ def main():
         optimizer_class = torch.optim.AdamW
 
     optimizer = optimizer_class(
-        # only optimize the embeddings
-        [
-            text_encoder_1.text_model.embeddings.token_embedding.weight,
-            text_encoder_2.text_model.embeddings.token_embedding.weight,
-        ],
+        text_encoder_1.get_input_embeddings().parameters(),  # only optimize the embeddings
         lr=args.learning_rate,
         betas=(args.adam_beta1, args.adam_beta2),
         weight_decay=args.adam_weight_decay,
@@ -808,10 +786,9 @@ def main():
     )
 
     text_encoder_1.train()
-    text_encoder_2.train()
     # Prepare everything with our `accelerator`.
-    text_encoder_1, text_encoder_2, optimizer, train_dataloader, lr_scheduler = accelerator.prepare(
-        text_encoder_1, text_encoder_2, optimizer, train_dataloader, lr_scheduler
+    text_encoder_1, optimizer, train_dataloader, lr_scheduler = accelerator.prepare(
+        text_encoder_1, optimizer, train_dataloader, lr_scheduler
     )
 
     # For mixed precision training we cast all non-trainable weigths (vae, non-lora text_encoder and non-lora unet) to half-precision
@@ -889,13 +866,11 @@ def main():
 
     # keep original embeddings as reference
     orig_embeds_params = accelerator.unwrap_model(text_encoder_1).get_input_embeddings().weight.data.clone()
-    orig_embeds_params_2 = accelerator.unwrap_model(text_encoder_2).get_input_embeddings().weight.data.clone()
 
     for epoch in range(first_epoch, args.num_train_epochs):
         text_encoder_1.train()
-        text_encoder_2.train()
         for step, batch in enumerate(train_dataloader):
-            with accelerator.accumulate([text_encoder_1, text_encoder_2]):
+            with accelerator.accumulate(text_encoder_1):
                 # Convert images to latent space
                 latents = vae.encode(batch["pixel_values"].to(dtype=weight_dtype)).latent_dist.sample().detach()
                 latents = latents * vae.config.scaling_factor
@@ -917,7 +892,9 @@ def main():
                     .hidden_states[-2]
                     .to(dtype=weight_dtype)
                 )
-                encoder_output_2 = text_encoder_2(batch["input_ids_2"], output_hidden_states=True)
+                encoder_output_2 = text_encoder_2(
+                    batch["input_ids_2"].reshape(batch["input_ids_1"].shape[0], -1), output_hidden_states=True
+                )
                 encoder_hidden_states_2 = encoder_output_2.hidden_states[-2].to(dtype=weight_dtype)
                 original_size = [
                     (batch["original_size"][0][i].item(), batch["original_size"][1][i].item())
@@ -961,16 +938,11 @@ def main():
                 # Let's make sure we don't update any embedding weights besides the newly added token
                 index_no_updates = torch.ones((len(tokenizer_1),), dtype=torch.bool)
                 index_no_updates[min(placeholder_token_ids) : max(placeholder_token_ids) + 1] = False
-                index_no_updates_2 = torch.ones((len(tokenizer_2),), dtype=torch.bool)
-                index_no_updates_2[min(placeholder_token_ids_2) : max(placeholder_token_ids_2) + 1] = False
 
                 with torch.no_grad():
                     accelerator.unwrap_model(text_encoder_1).get_input_embeddings().weight[
                         index_no_updates
                     ] = orig_embeds_params[index_no_updates]
-                    accelerator.unwrap_model(text_encoder_2).get_input_embeddings().weight[
-                        index_no_updates_2
-                    ] = orig_embeds_params_2[index_no_updates_2]
 
             # Checks if the accelerator has performed an optimization step behind the scenes
             if accelerator.sync_gradients:
@@ -988,16 +960,6 @@ def main():
                         save_path,
                         safe_serialization=True,
                     )
-                    weight_name = f"learned_embeds_2-steps-{global_step}.safetensors"
-                    save_path = os.path.join(args.output_dir, weight_name)
-                    save_progress(
-                        text_encoder_2,
-                        placeholder_token_ids_2,
-                        accelerator,
-                        args,
-                        save_path,
-                        safe_serialization=True,
-                    )
 
                 if accelerator.is_main_process:
                     if global_step % args.checkpointing_steps == 0:
@@ -1072,7 +1034,7 @@ def main():
             pipeline = DiffusionPipeline.from_pretrained(
                 args.pretrained_model_name_or_path,
                 text_encoder=accelerator.unwrap_model(text_encoder_1),
-                text_encoder_2=accelerator.unwrap_model(text_encoder_2),
+                text_encoder_2=text_encoder_2,
                 vae=vae,
                 unet=unet,
                 tokenizer=tokenizer_1,
@@ -1090,16 +1052,6 @@ def main():
             save_path,
             safe_serialization=True,
         )
-        weight_name = "learned_embeds_2.safetensors"
-        save_path = os.path.join(args.output_dir, weight_name)
-        save_progress(
-            text_encoder_2,
-            placeholder_token_ids_2,
-            accelerator,
-            args,
-            save_path,
-            safe_serialization=True,
-        )
 
         if args.push_to_hub:
             save_model_card(

examples/unconditional_image_generation/train_unconditional.py

@@ -29,7 +29,7 @@ from diffusers.utils.import_utils import is_xformers_available
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = get_logger(__name__, log_level="INFO")
 

examples/vqgan/train_vqgan.py

@@ -50,7 +50,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = get_logger(__name__, log_level="INFO")
 

examples/wuerstchen/text_to_image/train_text_to_image_lora_prior.py

@@ -50,7 +50,7 @@ if is_wandb_available():
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = get_logger(__name__, log_level="INFO")
 

examples/wuerstchen/text_to_image/train_text_to_image_prior.py

@@ -51,7 +51,7 @@ if is_wandb_available():
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.30.0")
 
 logger = get_logger(__name__, log_level="INFO")
 

setup.py

@@ -254,7 +254,7 @@ version_range_max = max(sys.version_info[1], 10) + 1
 
 setup(
     name="diffusers",
-    version="0.31.0.dev0",  # expected format is one of x.y.z.dev0, or x.y.z.rc1 or x.y.z (no to dashes, yes to dots)
+    version="0.30.2",  # expected format is one of x.y.z.dev0, or x.y.z.rc1 or x.y.z (no to dashes, yes to dots)
     description="State-of-the-art diffusion in PyTorch and JAX.",
     long_description=open("README.md", "r", encoding="utf-8").read(),
     long_description_content_type="text/markdown",

src/diffusers/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "0.31.0.dev0"
+__version__ = "0.30.2"
 
 from typing import TYPE_CHECKING
 
@@ -88,8 +88,6 @@ else:
             "ControlNetModel",
             "ControlNetXSAdapter",
             "DiTTransformer2DModel",
-            "FluxControlNetModel",
-            "FluxMultiControlNetModel",
             "FluxTransformer2DModel",
             "HunyuanDiT2DControlNetModel",
             "HunyuanDiT2DModel",
@@ -255,9 +253,7 @@ else:
             "BlipDiffusionPipeline",
             "CLIPImageProjection",
             "CogVideoXPipeline",
-            "CogVideoXVideoToVideoPipeline",
             "CycleDiffusionPipeline",
-            "FluxControlNetPipeline",
             "FluxPipeline",
             "HunyuanDiTControlNetPipeline",
             "HunyuanDiTPAGPipeline",
@@ -312,7 +308,6 @@ else:
             "StableCascadeCombinedPipeline",
             "StableCascadeDecoderPipeline",
             "StableCascadePriorPipeline",
-            "StableDiffusion3ControlNetInpaintingPipeline",
             "StableDiffusion3ControlNetPipeline",
             "StableDiffusion3Img2ImgPipeline",
             "StableDiffusion3InpaintPipeline",
@@ -348,7 +343,6 @@ else:
             "StableDiffusionXLAdapterPipeline",
             "StableDiffusionXLControlNetImg2ImgPipeline",
             "StableDiffusionXLControlNetInpaintPipeline",
-            "StableDiffusionXLControlNetPAGImg2ImgPipeline",
             "StableDiffusionXLControlNetPAGPipeline",
             "StableDiffusionXLControlNetPipeline",
             "StableDiffusionXLControlNetXSPipeline",
@@ -555,8 +549,6 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             ControlNetModel,
             ControlNetXSAdapter,
             DiTTransformer2DModel,
-            FluxControlNetModel,
-            FluxMultiControlNetModel,
             FluxTransformer2DModel,
             HunyuanDiT2DControlNetModel,
             HunyuanDiT2DModel,
@@ -700,9 +692,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             AuraFlowPipeline,
             CLIPImageProjection,
             CogVideoXPipeline,
-            CogVideoXVideoToVideoPipeline,
             CycleDiffusionPipeline,
-            FluxControlNetPipeline,
             FluxPipeline,
             HunyuanDiTControlNetPipeline,
             HunyuanDiTPAGPipeline,
@@ -792,7 +782,6 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             StableDiffusionXLAdapterPipeline,
             StableDiffusionXLControlNetImg2ImgPipeline,
             StableDiffusionXLControlNetInpaintPipeline,
-            StableDiffusionXLControlNetPAGImg2ImgPipeline,
             StableDiffusionXLControlNetPAGPipeline,
             StableDiffusionXLControlNetPipeline,
             StableDiffusionXLControlNetXSPipeline,

src/diffusers/loaders/ip_adapter.py

@@ -224,11 +224,7 @@ class IPAdapterMixin:
 
             # create feature extractor if it has not been registered to the pipeline yet
             if hasattr(self, "feature_extractor") and getattr(self, "feature_extractor", None) is None:
-                # FaceID IP adapters don't need the image encoder so it's not present, in this case we default to 224
-                default_clip_size = 224
-                clip_image_size = (
-                    self.image_encoder.config.image_size if self.image_encoder is not None else default_clip_size
-                )
+                clip_image_size = self.image_encoder.config.image_size
                 feature_extractor = CLIPImageProcessor(size=clip_image_size, crop_size=clip_image_size)
                 self.register_modules(feature_extractor=feature_extractor)
 

src/diffusers/loaders/lora_conversion_utils.py

@@ -14,8 +14,6 @@
 
 import re
 
-import torch
-
 from ..utils import is_peft_version, logging
 
 
@@ -328,296 +326,3 @@ def _get_alpha_name(lora_name_alpha, diffusers_name, alpha):
         prefix = "text_encoder_2."
     new_name = prefix + diffusers_name.split(".lora.")[0] + ".alpha"
     return {new_name: alpha}
-
-
-# The utilities under `_convert_kohya_flux_lora_to_diffusers()`
-# are taken from https://github.com/kohya-ss/sd-scripts/blob/a61cf73a5cb5209c3f4d1a3688dd276a4dfd1ecb/networks/convert_flux_lora.py
-# All credits go to `kohya-ss`.
-def _convert_kohya_flux_lora_to_diffusers(state_dict):
-    def _convert_to_ai_toolkit(sds_sd, ait_sd, sds_key, ait_key):
-        if sds_key + ".lora_down.weight" not in sds_sd:
-            return
-        down_weight = sds_sd.pop(sds_key + ".lora_down.weight")
-
-        # scale weight by alpha and dim
-        rank = down_weight.shape[0]
-        alpha = sds_sd.pop(sds_key + ".alpha").item()  # alpha is scalar
-        scale = alpha / rank  # LoRA is scaled by 'alpha / rank' in forward pass, so we need to scale it back here
-
-        # calculate scale_down and scale_up to keep the same value. if scale is 4, scale_down is 2 and scale_up is 2
-        scale_down = scale
-        scale_up = 1.0
-        while scale_down * 2 < scale_up:
-            scale_down *= 2
-            scale_up /= 2
-
-        ait_sd[ait_key + ".lora_A.weight"] = down_weight * scale_down
-        ait_sd[ait_key + ".lora_B.weight"] = sds_sd.pop(sds_key + ".lora_up.weight") * scale_up
-
-    def _convert_to_ai_toolkit_cat(sds_sd, ait_sd, sds_key, ait_keys, dims=None):
-        if sds_key + ".lora_down.weight" not in sds_sd:
-            return
-        down_weight = sds_sd.pop(sds_key + ".lora_down.weight")
-        up_weight = sds_sd.pop(sds_key + ".lora_up.weight")
-        sd_lora_rank = down_weight.shape[0]
-
-        # scale weight by alpha and dim
-        alpha = sds_sd.pop(sds_key + ".alpha")
-        scale = alpha / sd_lora_rank
-
-        # calculate scale_down and scale_up
-        scale_down = scale
-        scale_up = 1.0
-        while scale_down * 2 < scale_up:
-            scale_down *= 2
-            scale_up /= 2
-
-        down_weight = down_weight * scale_down
-        up_weight = up_weight * scale_up
-
-        # calculate dims if not provided
-        num_splits = len(ait_keys)
-        if dims is None:
-            dims = [up_weight.shape[0] // num_splits] * num_splits
-        else:
-            assert sum(dims) == up_weight.shape[0]
-
-        # check upweight is sparse or not
-        is_sparse = False
-        if sd_lora_rank % num_splits == 0:
-            ait_rank = sd_lora_rank // num_splits
-            is_sparse = True
-            i = 0
-            for j in range(len(dims)):
-                for k in range(len(dims)):
-                    if j == k:
-                        continue
-                    is_sparse = is_sparse and torch.all(
-                        up_weight[i : i + dims[j], k * ait_rank : (k + 1) * ait_rank] == 0
-                    )
-                i += dims[j]
-            if is_sparse:
-                logger.info(f"weight is sparse: {sds_key}")
-
-        # make ai-toolkit weight
-        ait_down_keys = [k + ".lora_A.weight" for k in ait_keys]
-        ait_up_keys = [k + ".lora_B.weight" for k in ait_keys]
-        if not is_sparse:
-            # down_weight is copied to each split
-            ait_sd.update({k: down_weight for k in ait_down_keys})
-
-            # up_weight is split to each split
-            ait_sd.update({k: v for k, v in zip(ait_up_keys, torch.split(up_weight, dims, dim=0))})  # noqa: C416
-        else:
-            # down_weight is chunked to each split
-            ait_sd.update({k: v for k, v in zip(ait_down_keys, torch.chunk(down_weight, num_splits, dim=0))})  # noqa: C416
-
-            # up_weight is sparse: only non-zero values are copied to each split
-            i = 0
-            for j in range(len(dims)):
-                ait_sd[ait_up_keys[j]] = up_weight[i : i + dims[j], j * ait_rank : (j + 1) * ait_rank].contiguous()
-                i += dims[j]
-
-    def _convert_sd_scripts_to_ai_toolkit(sds_sd):
-        ait_sd = {}
-        for i in range(19):
-            _convert_to_ai_toolkit(
-                sds_sd,
-                ait_sd,
-                f"lora_unet_double_blocks_{i}_img_attn_proj",
-                f"transformer.transformer_blocks.{i}.attn.to_out.0",
-            )
-            _convert_to_ai_toolkit_cat(
-                sds_sd,
-                ait_sd,
-                f"lora_unet_double_blocks_{i}_img_attn_qkv",
-                [
-                    f"transformer.transformer_blocks.{i}.attn.to_q",
-                    f"transformer.transformer_blocks.{i}.attn.to_k",
-                    f"transformer.transformer_blocks.{i}.attn.to_v",
-                ],
-            )
-            _convert_to_ai_toolkit(
-                sds_sd,
-                ait_sd,
-                f"lora_unet_double_blocks_{i}_img_mlp_0",
-                f"transformer.transformer_blocks.{i}.ff.net.0.proj",
-            )
-            _convert_to_ai_toolkit(
-                sds_sd,
-                ait_sd,
-                f"lora_unet_double_blocks_{i}_img_mlp_2",
-                f"transformer.transformer_blocks.{i}.ff.net.2",
-            )
-            _convert_to_ai_toolkit(
-                sds_sd,
-                ait_sd,
-                f"lora_unet_double_blocks_{i}_img_mod_lin",
-                f"transformer.transformer_blocks.{i}.norm1.linear",
-            )
-            _convert_to_ai_toolkit(
-                sds_sd,
-                ait_sd,
-                f"lora_unet_double_blocks_{i}_txt_attn_proj",
-                f"transformer.transformer_blocks.{i}.attn.to_add_out",
-            )
-            _convert_to_ai_toolkit_cat(
-                sds_sd,
-                ait_sd,
-                f"lora_unet_double_blocks_{i}_txt_attn_qkv",
-                [
-                    f"transformer.transformer_blocks.{i}.attn.add_q_proj",
-                    f"transformer.transformer_blocks.{i}.attn.add_k_proj",
-                    f"transformer.transformer_blocks.{i}.attn.add_v_proj",
-                ],
-            )
-            _convert_to_ai_toolkit(
-                sds_sd,
-                ait_sd,
-                f"lora_unet_double_blocks_{i}_txt_mlp_0",
-                f"transformer.transformer_blocks.{i}.ff_context.net.0.proj",
-            )
-            _convert_to_ai_toolkit(
-                sds_sd,
-                ait_sd,
-                f"lora_unet_double_blocks_{i}_txt_mlp_2",
-                f"transformer.transformer_blocks.{i}.ff_context.net.2",
-            )
-            _convert_to_ai_toolkit(
-                sds_sd,
-                ait_sd,
-                f"lora_unet_double_blocks_{i}_txt_mod_lin",
-                f"transformer.transformer_blocks.{i}.norm1_context.linear",
-            )
-
-        for i in range(38):
-            _convert_to_ai_toolkit_cat(
-                sds_sd,
-                ait_sd,
-                f"lora_unet_single_blocks_{i}_linear1",
-                [
-                    f"transformer.single_transformer_blocks.{i}.attn.to_q",
-                    f"transformer.single_transformer_blocks.{i}.attn.to_k",
-                    f"transformer.single_transformer_blocks.{i}.attn.to_v",
-                    f"transformer.single_transformer_blocks.{i}.proj_mlp",
-                ],
-                dims=[3072, 3072, 3072, 12288],
-            )
-            _convert_to_ai_toolkit(
-                sds_sd,
-                ait_sd,
-                f"lora_unet_single_blocks_{i}_linear2",
-                f"transformer.single_transformer_blocks.{i}.proj_out",
-            )
-            _convert_to_ai_toolkit(
-                sds_sd,
-                ait_sd,
-                f"lora_unet_single_blocks_{i}_modulation_lin",
-                f"transformer.single_transformer_blocks.{i}.norm.linear",
-            )
-
-        if len(sds_sd) > 0:
-            logger.warning(f"Unsuppored keys for ai-toolkit: {sds_sd.keys()}")
-
-        return ait_sd
-
-    return _convert_sd_scripts_to_ai_toolkit(state_dict)
-
-
-# Adapted from https://gist.github.com/Leommm-byte/6b331a1e9bd53271210b26543a7065d6
-# Some utilities were reused from
-# https://github.com/kohya-ss/sd-scripts/blob/a61cf73a5cb5209c3f4d1a3688dd276a4dfd1ecb/networks/convert_flux_lora.py
-def _convert_xlabs_flux_lora_to_diffusers(old_state_dict):
-    new_state_dict = {}
-    orig_keys = list(old_state_dict.keys())
-
-    def handle_qkv(sds_sd, ait_sd, sds_key, ait_keys, dims=None):
-        down_weight = sds_sd.pop(sds_key)
-        up_weight = sds_sd.pop(sds_key.replace(".down.weight", ".up.weight"))
-
-        # calculate dims if not provided
-        num_splits = len(ait_keys)
-        if dims is None:
-            dims = [up_weight.shape[0] // num_splits] * num_splits
-        else:
-            assert sum(dims) == up_weight.shape[0]
-
-        # make ai-toolkit weight
-        ait_down_keys = [k + ".lora_A.weight" for k in ait_keys]
-        ait_up_keys = [k + ".lora_B.weight" for k in ait_keys]
-
-        # down_weight is copied to each split
-        ait_sd.update({k: down_weight for k in ait_down_keys})
-
-        # up_weight is split to each split
-        ait_sd.update({k: v for k, v in zip(ait_up_keys, torch.split(up_weight, dims, dim=0))})  # noqa: C416
-
-    for old_key in orig_keys:
-        # Handle double_blocks
-        if old_key.startswith(("diffusion_model.double_blocks", "double_blocks")):
-            block_num = re.search(r"double_blocks\.(\d+)", old_key).group(1)
-            new_key = f"transformer.transformer_blocks.{block_num}"
-
-            if "processor.proj_lora1" in old_key:
-                new_key += ".attn.to_out.0"
-            elif "processor.proj_lora2" in old_key:
-                new_key += ".attn.to_add_out"
-            # Handle text latents.
-            elif "processor.qkv_lora2" in old_key and "up" not in old_key:
-                handle_qkv(
-                    old_state_dict,
-                    new_state_dict,
-                    old_key,
-                    [
-                        f"transformer.transformer_blocks.{block_num}.attn.add_q_proj",
-                        f"transformer.transformer_blocks.{block_num}.attn.add_k_proj",
-                        f"transformer.transformer_blocks.{block_num}.attn.add_v_proj",
-                    ],
-                )
-                # continue
-            # Handle image latents.
-            elif "processor.qkv_lora1" in old_key and "up" not in old_key:
-                handle_qkv(
-                    old_state_dict,
-                    new_state_dict,
-                    old_key,
-                    [
-                        f"transformer.transformer_blocks.{block_num}.attn.to_q",
-                        f"transformer.transformer_blocks.{block_num}.attn.to_k",
-                        f"transformer.transformer_blocks.{block_num}.attn.to_v",
-                    ],
-                )
-                # continue
-
-            if "down" in old_key:
-                new_key += ".lora_A.weight"
-            elif "up" in old_key:
-                new_key += ".lora_B.weight"
-
-        # Handle single_blocks
-        elif old_key.startswith("diffusion_model.single_blocks", "single_blocks"):
-            block_num = re.search(r"single_blocks\.(\d+)", old_key).group(1)
-            new_key = f"transformer.single_transformer_blocks.{block_num}"
-
-            if "proj_lora1" in old_key or "proj_lora2" in old_key:
-                new_key += ".proj_out"
-            elif "qkv_lora1" in old_key or "qkv_lora2" in old_key:
-                new_key += ".norm.linear"
-
-            if "down" in old_key:
-                new_key += ".lora_A.weight"
-            elif "up" in old_key:
-                new_key += ".lora_B.weight"
-
-        else:
-            # Handle other potential key patterns here
-            new_key = old_key
-
-        # Since we already handle qkv above.
-        if "qkv" not in old_key:
-            new_state_dict[new_key] = old_state_dict.pop(old_key)
-
-    if len(old_state_dict) > 0:
-        raise ValueError(f"`old_state_dict` should be at this point but has: {list(old_state_dict.keys())}.")
-
-    return new_state_dict

src/diffusers/loaders/lora_pipeline.py

@@ -31,12 +31,7 @@ from ..utils import (
     scale_lora_layers,
 )
 from .lora_base import LoraBaseMixin
-from .lora_conversion_utils import (
-    _convert_kohya_flux_lora_to_diffusers,
-    _convert_non_diffusers_lora_to_diffusers,
-    _convert_xlabs_flux_lora_to_diffusers,
-    _maybe_map_sgm_blocks_to_diffusers,
-)
+from .lora_conversion_utils import _convert_non_diffusers_lora_to_diffusers, _maybe_map_sgm_blocks_to_diffusers
 
 
 if is_transformers_available():
@@ -285,9 +280,7 @@ class StableDiffusionLoraLoaderMixin(LoraBaseMixin):
                 A standard state dict containing the lora layer parameters. The key should be prefixed with an
                 additional `text_encoder` to distinguish between unet lora layers.
             network_alphas (`Dict[str, float]`):
-                The value of the network alpha used for stable learning and preventing underflow. This value has the
-                same meaning as the `--network_alpha` option in the kohya-ss trainer script. Refer to [this
-                link](https://github.com/darkstorm2150/sd-scripts/blob/main/docs/train_network_README-en.md#execute-learning).
+                See `LoRALinearLayer` for more details.
             text_encoder (`CLIPTextModel`):
                 The text encoder model to load the LoRA layers into.
             prefix (`str`):
@@ -760,9 +753,7 @@ class StableDiffusionXLLoraLoaderMixin(LoraBaseMixin):
                 A standard state dict containing the lora layer parameters. The key should be prefixed with an
                 additional `text_encoder` to distinguish between unet lora layers.
             network_alphas (`Dict[str, float]`):
-                The value of the network alpha used for stable learning and preventing underflow. This value has the
-                same meaning as the `--network_alpha` option in the kohya-ss trainer script. Refer to [this
-                link](https://github.com/darkstorm2150/sd-scripts/blob/main/docs/train_network_README-en.md#execute-learning).
+                See `LoRALinearLayer` for more details.
             text_encoder (`CLIPTextModel`):
                 The text encoder model to load the LoRA layers into.
             prefix (`str`):
@@ -1258,9 +1249,7 @@ class SD3LoraLoaderMixin(LoraBaseMixin):
                 A standard state dict containing the lora layer parameters. The key should be prefixed with an
                 additional `text_encoder` to distinguish between unet lora layers.
             network_alphas (`Dict[str, float]`):
-                The value of the network alpha used for stable learning and preventing underflow. This value has the
-                same meaning as the `--network_alpha` option in the kohya-ss trainer script. Refer to [this
-                link](https://github.com/darkstorm2150/sd-scripts/blob/main/docs/train_network_README-en.md#execute-learning).
+                See `LoRALinearLayer` for more details.
             text_encoder (`CLIPTextModel`):
                 The text encoder model to load the LoRA layers into.
             prefix (`str`):
@@ -1588,20 +1577,6 @@ class FluxLoraLoaderMixin(LoraBaseMixin):
             allow_pickle=allow_pickle,
         )
 
-        # TODO (sayakpaul): to a follow-up to clean and try to unify the conditions.
-
-        is_kohya = any(".lora_down.weight" in k for k in state_dict)
-        if is_kohya:
-            state_dict = _convert_kohya_flux_lora_to_diffusers(state_dict)
-            # Kohya already takes care of scaling the LoRA parameters with alpha.
-            return (state_dict, None) if return_alphas else state_dict
-
-        is_xlabs = any("processor" in k for k in state_dict)
-        if is_xlabs:
-            state_dict = _convert_xlabs_flux_lora_to_diffusers(state_dict)
-            # xlabs doesn't use `alpha`.
-            return (state_dict, None) if return_alphas else state_dict
-
         # For state dicts like
         # https://huggingface.co/TheLastBen/Jon_Snow_Flux_LoRA
         keys = list(state_dict.keys())
@@ -1790,9 +1765,7 @@ class FluxLoraLoaderMixin(LoraBaseMixin):
                 A standard state dict containing the lora layer parameters. The key should be prefixed with an
                 additional `text_encoder` to distinguish between unet lora layers.
             network_alphas (`Dict[str, float]`):
-                The value of the network alpha used for stable learning and preventing underflow. This value has the
-                same meaning as the `--network_alpha` option in the kohya-ss trainer script. Refer to [this
-                link](https://github.com/darkstorm2150/sd-scripts/blob/main/docs/train_network_README-en.md#execute-learning).
+                See `LoRALinearLayer` for more details.
             text_encoder (`CLIPTextModel`):
                 The text encoder model to load the LoRA layers into.
             prefix (`str`):
@@ -2025,9 +1998,7 @@ class AmusedLoraLoaderMixin(StableDiffusionLoraLoaderMixin):
                 into the unet or prefixed with an additional `unet` which can be used to distinguish between text
                 encoder lora layers.
             network_alphas (`Dict[str, float]`):
-                The value of the network alpha used for stable learning and preventing underflow. This value has the
-                same meaning as the `--network_alpha` option in the kohya-ss trainer script. Refer to [this
-                link](https://github.com/darkstorm2150/sd-scripts/blob/main/docs/train_network_README-en.md#execute-learning).
+                See `LoRALinearLayer` for more details.
             unet (`UNet2DConditionModel`):
                 The UNet model to load the LoRA layers into.
             adapter_name (`str`, *optional*):
@@ -2120,9 +2091,7 @@ class AmusedLoraLoaderMixin(StableDiffusionLoraLoaderMixin):
                 A standard state dict containing the lora layer parameters. The key should be prefixed with an
                 additional `text_encoder` to distinguish between unet lora layers.
             network_alphas (`Dict[str, float]`):
-                The value of the network alpha used for stable learning and preventing underflow. This value has the
-                same meaning as the `--network_alpha` option in the kohya-ss trainer script. Refer to [this
-                link](https://github.com/darkstorm2150/sd-scripts/blob/main/docs/train_network_README-en.md#execute-learning).
+                See `LoRALinearLayer` for more details.
             text_encoder (`CLIPTextModel`):
                 The text encoder model to load the LoRA layers into.
             prefix (`str`):

src/diffusers/loaders/single_file_utils.py

@@ -456,8 +456,6 @@ def infer_diffusers_model_type(checkpoint):
     ):
         if CHECKPOINT_KEY_NAMES["v2"] in checkpoint and checkpoint[CHECKPOINT_KEY_NAMES["v2"]].shape[-1] == 1024:
             model_type = "inpainting_v2"
-        elif CHECKPOINT_KEY_NAMES["xl_base"] in checkpoint:
-            model_type = "xl_inpaint"
         else:
             model_type = "inpainting"
 

src/diffusers/models/__init__.py

@@ -35,7 +35,6 @@ if is_torch_available():
     _import_structure["autoencoders.consistency_decoder_vae"] = ["ConsistencyDecoderVAE"]
     _import_structure["autoencoders.vq_model"] = ["VQModel"]
     _import_structure["controlnet"] = ["ControlNetModel"]
-    _import_structure["controlnet_flux"] = ["FluxControlNetModel", "FluxMultiControlNetModel"]
     _import_structure["controlnet_hunyuan"] = ["HunyuanDiT2DControlNetModel", "HunyuanDiT2DMultiControlNetModel"]
     _import_structure["controlnet_sd3"] = ["SD3ControlNetModel", "SD3MultiControlNetModel"]
     _import_structure["controlnet_sparsectrl"] = ["SparseControlNetModel"]
@@ -88,7 +87,6 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             VQModel,
         )
         from .controlnet import ControlNetModel
-        from .controlnet_flux import FluxControlNetModel, FluxMultiControlNetModel
         from .controlnet_hunyuan import HunyuanDiT2DControlNetModel, HunyuanDiT2DMultiControlNetModel
         from .controlnet_sd3 import SD3ControlNetModel, SD3MultiControlNetModel
         from .controlnet_sparsectrl import SparseControlNetModel

src/diffusers/models/attention.py

@@ -972,32 +972,15 @@ class FreeNoiseTransformerBlock(nn.Module):
         return frame_indices
 
     def _get_frame_weights(self, num_frames: int, weighting_scheme: str = "pyramid") -> List[float]:
-        if weighting_scheme == "flat":
-            weights = [1.0] * num_frames
-
-        elif weighting_scheme == "pyramid":
+        if weighting_scheme == "pyramid":
             if num_frames % 2 == 0:
                 # num_frames = 4 => [1, 2, 2, 1]
-                mid = num_frames // 2
-                weights = list(range(1, mid + 1))
+                weights = list(range(1, num_frames // 2 + 1))
                 weights = weights + weights[::-1]
             else:
                 # num_frames = 5 => [1, 2, 3, 2, 1]
-                mid = (num_frames + 1) // 2
-                weights = list(range(1, mid))
-                weights = weights + [mid] + weights[::-1]
-
-        elif weighting_scheme == "delayed_reverse_sawtooth":
-            if num_frames % 2 == 0:
-                # num_frames = 4 => [0.01, 2, 2, 1]
-                mid = num_frames // 2
-                weights = [0.01] * (mid - 1) + [mid]
-                weights = weights + list(range(mid, 0, -1))
-            else:
-                # num_frames = 5 => [0.01, 0.01, 3, 2, 1]
-                mid = (num_frames + 1) // 2
-                weights = [0.01] * mid
-                weights = weights + list(range(mid, 0, -1))
+                weights = list(range(1, num_frames // 2 + 1))
+                weights = weights + [num_frames // 2 + 1] + weights[::-1]
         else:
             raise ValueError(f"Unsupported value for weighting_scheme={weighting_scheme}")
 

src/diffusers/models/attention_processor.py

@@ -1695,6 +1695,81 @@ class FusedAuraFlowAttnProcessor2_0:
             return hidden_states
 
 
+# YiYi to-do: refactor rope related functions/classes
+def apply_rope(xq, xk, freqs_cis):
+    xq_ = xq.float().reshape(*xq.shape[:-1], -1, 1, 2)
+    xk_ = xk.float().reshape(*xk.shape[:-1], -1, 1, 2)
+    xq_out = freqs_cis[..., 0] * xq_[..., 0] + freqs_cis[..., 1] * xq_[..., 1]
+    xk_out = freqs_cis[..., 0] * xk_[..., 0] + freqs_cis[..., 1] * xk_[..., 1]
+    return xq_out.reshape(*xq.shape).type_as(xq), xk_out.reshape(*xk.shape).type_as(xk)
+
+
+class FluxSingleAttnProcessor2_0:
+    r"""
+    Processor for implementing scaled dot-product attention (enabled by default if you're using PyTorch 2.0).
+    """
+
+    def __init__(self):
+        if not hasattr(F, "scaled_dot_product_attention"):
+            raise ImportError("AttnProcessor2_0 requires PyTorch 2.0, to use it, please upgrade PyTorch to 2.0.")
+
+    def __call__(
+        self,
+        attn: Attention,
+        hidden_states: torch.Tensor,
+        encoder_hidden_states: Optional[torch.Tensor] = None,
+        attention_mask: Optional[torch.FloatTensor] = None,
+        image_rotary_emb: Optional[torch.Tensor] = None,
+    ) -> torch.Tensor:
+        input_ndim = hidden_states.ndim
+
+        if input_ndim == 4:
+            batch_size, channel, height, width = hidden_states.shape
+            hidden_states = hidden_states.view(batch_size, channel, height * width).transpose(1, 2)
+
+        batch_size, _, _ = hidden_states.shape if encoder_hidden_states is None else encoder_hidden_states.shape
+
+        query = attn.to_q(hidden_states)
+        if encoder_hidden_states is None:
+            encoder_hidden_states = hidden_states
+
+        key = attn.to_k(encoder_hidden_states)
+        value = attn.to_v(encoder_hidden_states)
+
+        inner_dim = key.shape[-1]
+        head_dim = inner_dim // attn.heads
+
+        query = query.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
+
+        key = key.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
+        value = value.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
+
+        if attn.norm_q is not None:
+            query = attn.norm_q(query)
+        if attn.norm_k is not None:
+            key = attn.norm_k(key)
+
+        # Apply RoPE if needed
+        if image_rotary_emb is not None:
+            # YiYi to-do: update uising apply_rotary_emb
+            # from ..embeddings import apply_rotary_emb
+            # query = apply_rotary_emb(query, image_rotary_emb)
+            # key = apply_rotary_emb(key, image_rotary_emb)
+            query, key = apply_rope(query, key, image_rotary_emb)
+
+        # the output of sdp = (batch, num_heads, seq_len, head_dim)
+        # TODO: add support for attn.scale when we move to Torch 2.1
+        hidden_states = F.scaled_dot_product_attention(query, key, value, dropout_p=0.0, is_causal=False)
+
+        hidden_states = hidden_states.transpose(1, 2).reshape(batch_size, -1, attn.heads * head_dim)
+        hidden_states = hidden_states.to(query.dtype)
+
+        if input_ndim == 4:
+            hidden_states = hidden_states.transpose(-1, -2).reshape(batch_size, channel, height, width)
+
+        return hidden_states
+
+
 class FluxAttnProcessor2_0:
     """Attention processor used typically in processing the SD3-like self-attention projections."""
 
@@ -1710,7 +1785,16 @@ class FluxAttnProcessor2_0:
         attention_mask: Optional[torch.FloatTensor] = None,
         image_rotary_emb: Optional[torch.Tensor] = None,
     ) -> torch.FloatTensor:
-        batch_size, _, _ = hidden_states.shape if encoder_hidden_states is None else encoder_hidden_states.shape
+        input_ndim = hidden_states.ndim
+        if input_ndim == 4:
+            batch_size, channel, height, width = hidden_states.shape
+            hidden_states = hidden_states.view(batch_size, channel, height * width).transpose(1, 2)
+        context_input_ndim = encoder_hidden_states.ndim
+        if context_input_ndim == 4:
+            batch_size, channel, height, width = encoder_hidden_states.shape
+            encoder_hidden_states = encoder_hidden_states.view(batch_size, channel, height * width).transpose(1, 2)
+
+        batch_size = encoder_hidden_states.shape[0]
 
         # `sample` projections.
         query = attn.to_q(hidden_states)
@@ -1729,152 +1813,59 @@ class FluxAttnProcessor2_0:
         if attn.norm_k is not None:
             key = attn.norm_k(key)
 
-        # the attention in FluxSingleTransformerBlock does not use `encoder_hidden_states`
-        if encoder_hidden_states is not None:
-            # `context` projections.
-            encoder_hidden_states_query_proj = attn.add_q_proj(encoder_hidden_states)
-            encoder_hidden_states_key_proj = attn.add_k_proj(encoder_hidden_states)
-            encoder_hidden_states_value_proj = attn.add_v_proj(encoder_hidden_states)
-
-            encoder_hidden_states_query_proj = encoder_hidden_states_query_proj.view(
-                batch_size, -1, attn.heads, head_dim
-            ).transpose(1, 2)
-            encoder_hidden_states_key_proj = encoder_hidden_states_key_proj.view(
-                batch_size, -1, attn.heads, head_dim
-            ).transpose(1, 2)
-            encoder_hidden_states_value_proj = encoder_hidden_states_value_proj.view(
-                batch_size, -1, attn.heads, head_dim
-            ).transpose(1, 2)
-
-            if attn.norm_added_q is not None:
-                encoder_hidden_states_query_proj = attn.norm_added_q(encoder_hidden_states_query_proj)
-            if attn.norm_added_k is not None:
-                encoder_hidden_states_key_proj = attn.norm_added_k(encoder_hidden_states_key_proj)
-
-            # attention
-            query = torch.cat([encoder_hidden_states_query_proj, query], dim=2)
-            key = torch.cat([encoder_hidden_states_key_proj, key], dim=2)
-            value = torch.cat([encoder_hidden_states_value_proj, value], dim=2)
-
-        if image_rotary_emb is not None:
-            from .embeddings import apply_rotary_emb
-
-            query = apply_rotary_emb(query, image_rotary_emb)
-            key = apply_rotary_emb(key, image_rotary_emb)
-
-        hidden_states = F.scaled_dot_product_attention(query, key, value, dropout_p=0.0, is_causal=False)
-        hidden_states = hidden_states.transpose(1, 2).reshape(batch_size, -1, attn.heads * head_dim)
-        hidden_states = hidden_states.to(query.dtype)
-
-        if encoder_hidden_states is not None:
-            encoder_hidden_states, hidden_states = (
-                hidden_states[:, : encoder_hidden_states.shape[1]],
-                hidden_states[:, encoder_hidden_states.shape[1] :],
-            )
-
-            # linear proj
-            hidden_states = attn.to_out[0](hidden_states)
-            # dropout
-            hidden_states = attn.to_out[1](hidden_states)
-            encoder_hidden_states = attn.to_add_out(encoder_hidden_states)
-
-            return hidden_states, encoder_hidden_states
-        else:
-            return hidden_states
-
-
-class FusedFluxAttnProcessor2_0:
-    """Attention processor used typically in processing the SD3-like self-attention projections."""
-
-    def __init__(self):
-        if not hasattr(F, "scaled_dot_product_attention"):
-            raise ImportError(
-                "FusedFluxAttnProcessor2_0 requires PyTorch 2.0, to use it, please upgrade PyTorch to 2.0."
-            )
-
-    def __call__(
-        self,
-        attn: Attention,
-        hidden_states: torch.FloatTensor,
-        encoder_hidden_states: torch.FloatTensor = None,
-        attention_mask: Optional[torch.FloatTensor] = None,
-        image_rotary_emb: Optional[torch.Tensor] = None,
-    ) -> torch.FloatTensor:
-        batch_size, _, _ = hidden_states.shape if encoder_hidden_states is None else encoder_hidden_states.shape
-
-        # `sample` projections.
-        qkv = attn.to_qkv(hidden_states)
-        split_size = qkv.shape[-1] // 3
-        query, key, value = torch.split(qkv, split_size, dim=-1)
-
-        inner_dim = key.shape[-1]
-        head_dim = inner_dim // attn.heads
-
-        query = query.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
-        key = key.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
-        value = value.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
-
-        if attn.norm_q is not None:
-            query = attn.norm_q(query)
-        if attn.norm_k is not None:
-            key = attn.norm_k(key)
-
-        # the attention in FluxSingleTransformerBlock does not use `encoder_hidden_states`
         # `context` projections.
-        if encoder_hidden_states is not None:
-            encoder_qkv = attn.to_added_qkv(encoder_hidden_states)
-            split_size = encoder_qkv.shape[-1] // 3
-            (
-                encoder_hidden_states_query_proj,
-                encoder_hidden_states_key_proj,
-                encoder_hidden_states_value_proj,
-            ) = torch.split(encoder_qkv, split_size, dim=-1)
+        encoder_hidden_states_query_proj = attn.add_q_proj(encoder_hidden_states)
+        encoder_hidden_states_key_proj = attn.add_k_proj(encoder_hidden_states)
+        encoder_hidden_states_value_proj = attn.add_v_proj(encoder_hidden_states)
 
-            encoder_hidden_states_query_proj = encoder_hidden_states_query_proj.view(
-                batch_size, -1, attn.heads, head_dim
-            ).transpose(1, 2)
-            encoder_hidden_states_key_proj = encoder_hidden_states_key_proj.view(
-                batch_size, -1, attn.heads, head_dim
-            ).transpose(1, 2)
-            encoder_hidden_states_value_proj = encoder_hidden_states_value_proj.view(
-                batch_size, -1, attn.heads, head_dim
-            ).transpose(1, 2)
+        encoder_hidden_states_query_proj = encoder_hidden_states_query_proj.view(
+            batch_size, -1, attn.heads, head_dim
+        ).transpose(1, 2)
+        encoder_hidden_states_key_proj = encoder_hidden_states_key_proj.view(
+            batch_size, -1, attn.heads, head_dim
+        ).transpose(1, 2)
+        encoder_hidden_states_value_proj = encoder_hidden_states_value_proj.view(
+            batch_size, -1, attn.heads, head_dim
+        ).transpose(1, 2)
 
-            if attn.norm_added_q is not None:
-                encoder_hidden_states_query_proj = attn.norm_added_q(encoder_hidden_states_query_proj)
-            if attn.norm_added_k is not None:
-                encoder_hidden_states_key_proj = attn.norm_added_k(encoder_hidden_states_key_proj)
+        if attn.norm_added_q is not None:
+            encoder_hidden_states_query_proj = attn.norm_added_q(encoder_hidden_states_query_proj)
+        if attn.norm_added_k is not None:
+            encoder_hidden_states_key_proj = attn.norm_added_k(encoder_hidden_states_key_proj)
 
-            # attention
-            query = torch.cat([encoder_hidden_states_query_proj, query], dim=2)
-            key = torch.cat([encoder_hidden_states_key_proj, key], dim=2)
-            value = torch.cat([encoder_hidden_states_value_proj, value], dim=2)
+        # attention
+        query = torch.cat([encoder_hidden_states_query_proj, query], dim=2)
+        key = torch.cat([encoder_hidden_states_key_proj, key], dim=2)
+        value = torch.cat([encoder_hidden_states_value_proj, value], dim=2)
 
         if image_rotary_emb is not None:
-            from .embeddings import apply_rotary_emb
-
-            query = apply_rotary_emb(query, image_rotary_emb)
-            key = apply_rotary_emb(key, image_rotary_emb)
+            # YiYi to-do: update uising apply_rotary_emb
+            # from ..embeddings import apply_rotary_emb
+            # query = apply_rotary_emb(query, image_rotary_emb)
+            # key = apply_rotary_emb(key, image_rotary_emb)
+            query, key = apply_rope(query, key, image_rotary_emb)
 
         hidden_states = F.scaled_dot_product_attention(query, key, value, dropout_p=0.0, is_causal=False)
         hidden_states = hidden_states.transpose(1, 2).reshape(batch_size, -1, attn.heads * head_dim)
         hidden_states = hidden_states.to(query.dtype)
 
-        if encoder_hidden_states is not None:
-            encoder_hidden_states, hidden_states = (
-                hidden_states[:, : encoder_hidden_states.shape[1]],
-                hidden_states[:, encoder_hidden_states.shape[1] :],
-            )
+        encoder_hidden_states, hidden_states = (
+            hidden_states[:, : encoder_hidden_states.shape[1]],
+            hidden_states[:, encoder_hidden_states.shape[1] :],
+        )
 
-            # linear proj
-            hidden_states = attn.to_out[0](hidden_states)
-            # dropout
-            hidden_states = attn.to_out[1](hidden_states)
-            encoder_hidden_states = attn.to_add_out(encoder_hidden_states)
+        # linear proj
+        hidden_states = attn.to_out[0](hidden_states)
+        # dropout
+        hidden_states = attn.to_out[1](hidden_states)
+        encoder_hidden_states = attn.to_add_out(encoder_hidden_states)
 
-            return hidden_states, encoder_hidden_states
-        else:
-            return hidden_states
+        if input_ndim == 4:
+            hidden_states = hidden_states.transpose(-1, -2).reshape(batch_size, channel, height, width)
+        if context_input_ndim == 4:
+            encoder_hidden_states = encoder_hidden_states.transpose(-1, -2).reshape(batch_size, channel, height, width)
+
+        return hidden_states, encoder_hidden_states
 
 
 class CogVideoXAttnProcessor2_0:
@@ -4256,17 +4247,6 @@ class LoRAAttnAddedKVProcessor:
         pass
 
 
-class FluxSingleAttnProcessor2_0(FluxAttnProcessor2_0):
-    r"""
-    Processor for implementing scaled dot-product attention (enabled by default if you're using PyTorch 2.0).
-    """
-
-    def __init__(self):
-        deprecation_message = "`FluxSingleAttnProcessor2_0` is deprecated and will be removed in a future version. Please use `FluxAttnProcessor2_0` instead."
-        deprecate("FluxSingleAttnProcessor2_0", "0.32.0", deprecation_message)
-        super().__init__()
-
-
 ADDED_KV_ATTENTION_PROCESSORS = (
     AttnAddedKVProcessor,
     SlicedAttnAddedKVProcessor,

src/diffusers/models/autoencoders/autoencoder_kl_cogvideox.py

@@ -999,7 +999,6 @@ class AutoencoderKLCogVideoX(ModelMixin, ConfigMixin, FromOriginalModelMixin):
         # setting it to anything other than 2 would give poor results because the VAE hasn't been trained to be adaptive with different
         # number of temporal frames.
         self.num_latent_frames_batch_size = 2
-        self.num_sample_frames_batch_size = 8
 
         # We make the minimum height and width of sample for tiling half that of the generally supported
         self.tile_sample_min_height = sample_height // 2
@@ -1082,29 +1081,6 @@ class AutoencoderKLCogVideoX(ModelMixin, ConfigMixin, FromOriginalModelMixin):
         """
         self.use_slicing = False
 
-    def _encode(self, x: torch.Tensor) -> torch.Tensor:
-        batch_size, num_channels, num_frames, height, width = x.shape
-
-        if self.use_tiling and (width > self.tile_sample_min_width or height > self.tile_sample_min_height):
-            return self.tiled_encode(x)
-
-        frame_batch_size = self.num_sample_frames_batch_size
-        enc = []
-        for i in range(num_frames // frame_batch_size):
-            remaining_frames = num_frames % frame_batch_size
-            start_frame = frame_batch_size * i + (0 if i == 0 else remaining_frames)
-            end_frame = frame_batch_size * (i + 1) + remaining_frames
-            x_intermediate = x[:, :, start_frame:end_frame]
-            x_intermediate = self.encoder(x_intermediate)
-            if self.quant_conv is not None:
-                x_intermediate = self.quant_conv(x_intermediate)
-            enc.append(x_intermediate)
-
-        self._clear_fake_context_parallel_cache()
-        enc = torch.cat(enc, dim=2)
-
-        return enc
-
     @apply_forward_hook
     def encode(
         self, x: torch.Tensor, return_dict: bool = True
@@ -1118,17 +1094,13 @@ class AutoencoderKLCogVideoX(ModelMixin, ConfigMixin, FromOriginalModelMixin):
                 Whether to return a [`~models.autoencoder_kl.AutoencoderKLOutput`] instead of a plain tuple.
 
         Returns:
-                The latent representations of the encoded videos. If `return_dict` is True, a
+                The latent representations of the encoded images. If `return_dict` is True, a
                 [`~models.autoencoder_kl.AutoencoderKLOutput`] is returned, otherwise a plain `tuple` is returned.
         """
-        if self.use_slicing and x.shape[0] > 1:
-            encoded_slices = [self._encode(x_slice) for x_slice in x.split(1)]
-            h = torch.cat(encoded_slices)
-        else:
-            h = self._encode(x)
-
+        h = self.encoder(x)
+        if self.quant_conv is not None:
+            h = self.quant_conv(h)
         posterior = DiagonalGaussianDistribution(h)
-
         if not return_dict:
             return (posterior,)
         return AutoencoderKLOutput(latent_dist=posterior)
@@ -1200,75 +1172,6 @@ class AutoencoderKLCogVideoX(ModelMixin, ConfigMixin, FromOriginalModelMixin):
             )
         return b
 
-    def tiled_encode(self, x: torch.Tensor) -> torch.Tensor:
-        r"""Encode a batch of images using a tiled encoder.
-
-        When this option is enabled, the VAE will split the input tensor into tiles to compute encoding in several
-        steps. This is useful to keep memory use constant regardless of image size. The end result of tiled encoding is
-        different from non-tiled encoding because each tile uses a different encoder. To avoid tiling artifacts, the
-        tiles overlap and are blended together to form a smooth output. You may still see tile-sized changes in the
-        output, but they should be much less noticeable.
-
-        Args:
-            x (`torch.Tensor`): Input batch of videos.
-
-        Returns:
-            `torch.Tensor`:
-                The latent representation of the encoded videos.
-        """
-        # For a rough memory estimate, take a look at the `tiled_decode` method.
-        batch_size, num_channels, num_frames, height, width = x.shape
-
-        overlap_height = int(self.tile_sample_min_height * (1 - self.tile_overlap_factor_height))
-        overlap_width = int(self.tile_sample_min_width * (1 - self.tile_overlap_factor_width))
-        blend_extent_height = int(self.tile_latent_min_height * self.tile_overlap_factor_height)
-        blend_extent_width = int(self.tile_latent_min_width * self.tile_overlap_factor_width)
-        row_limit_height = self.tile_latent_min_height - blend_extent_height
-        row_limit_width = self.tile_latent_min_width - blend_extent_width
-        frame_batch_size = self.num_sample_frames_batch_size
-
-        # Split x into overlapping tiles and encode them separately.
-        # The tiles have an overlap to avoid seams between tiles.
-        rows = []
-        for i in range(0, height, overlap_height):
-            row = []
-            for j in range(0, width, overlap_width):
-                time = []
-                for k in range(num_frames // frame_batch_size):
-                    remaining_frames = num_frames % frame_batch_size
-                    start_frame = frame_batch_size * k + (0 if k == 0 else remaining_frames)
-                    end_frame = frame_batch_size * (k + 1) + remaining_frames
-                    tile = x[
-                        :,
-                        :,
-                        start_frame:end_frame,
-                        i : i + self.tile_sample_min_height,
-                        j : j + self.tile_sample_min_width,
-                    ]
-                    tile = self.encoder(tile)
-                    if self.quant_conv is not None:
-                        tile = self.quant_conv(tile)
-                    time.append(tile)
-                self._clear_fake_context_parallel_cache()
-                row.append(torch.cat(time, dim=2))
-            rows.append(row)
-
-        result_rows = []
-        for i, row in enumerate(rows):
-            result_row = []
-            for j, tile in enumerate(row):
-                # blend the above tile and the left tile
-                # to the current tile and add the current tile to the result row
-                if i > 0:
-                    tile = self.blend_v(rows[i - 1][j], tile, blend_extent_height)
-                if j > 0:
-                    tile = self.blend_h(row[j - 1], tile, blend_extent_width)
-                result_row.append(tile[:, :, :, :row_limit_height, :row_limit_width])
-            result_rows.append(torch.cat(result_row, dim=4))
-
-        enc = torch.cat(result_rows, dim=3)
-        return enc
-
     def tiled_decode(self, z: torch.Tensor, return_dict: bool = True) -> Union[DecoderOutput, torch.Tensor]:
         r"""
         Decode a batch of images using a tiled decoder.

src/diffusers/models/controlnet_flux.py

@@ -1,517 +0,0 @@
-# Copyright 2024 Black Forest Labs, The HuggingFace Team and The InstantX 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.
-
-from dataclasses import dataclass
-from typing import Any, Dict, List, Optional, Tuple, Union
-
-import torch
-import torch.nn as nn
-
-from ..configuration_utils import ConfigMixin, register_to_config
-from ..loaders import PeftAdapterMixin
-from ..models.attention_processor import AttentionProcessor
-from ..models.modeling_utils import ModelMixin
-from ..utils import USE_PEFT_BACKEND, is_torch_version, logging, scale_lora_layers, unscale_lora_layers
-from .controlnet import BaseOutput, zero_module
-from .embeddings import CombinedTimestepGuidanceTextProjEmbeddings, CombinedTimestepTextProjEmbeddings, FluxPosEmbed
-from .modeling_outputs import Transformer2DModelOutput
-from .transformers.transformer_flux import FluxSingleTransformerBlock, FluxTransformerBlock
-
-
-logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
-
-
-@dataclass
-class FluxControlNetOutput(BaseOutput):
-    controlnet_block_samples: Tuple[torch.Tensor]
-    controlnet_single_block_samples: Tuple[torch.Tensor]
-
-
-class FluxControlNetModel(ModelMixin, ConfigMixin, PeftAdapterMixin):
-    _supports_gradient_checkpointing = True
-
-    @register_to_config
-    def __init__(
-        self,
-        patch_size: int = 1,
-        in_channels: int = 64,
-        num_layers: int = 19,
-        num_single_layers: int = 38,
-        attention_head_dim: int = 128,
-        num_attention_heads: int = 24,
-        joint_attention_dim: int = 4096,
-        pooled_projection_dim: int = 768,
-        guidance_embeds: bool = False,
-        axes_dims_rope: List[int] = [16, 56, 56],
-        num_mode: int = None,
-    ):
-        super().__init__()
-        self.out_channels = in_channels
-        self.inner_dim = num_attention_heads * attention_head_dim
-
-        self.pos_embed = FluxPosEmbed(theta=10000, axes_dim=axes_dims_rope)
-        text_time_guidance_cls = (
-            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
-        )
-
-        self.context_embedder = nn.Linear(joint_attention_dim, self.inner_dim)
-        self.x_embedder = torch.nn.Linear(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,
-                )
-                for i in range(num_layers)
-            ]
-        )
-
-        self.single_transformer_blocks = nn.ModuleList(
-            [
-                FluxSingleTransformerBlock(
-                    dim=self.inner_dim,
-                    num_attention_heads=num_attention_heads,
-                    attention_head_dim=attention_head_dim,
-                )
-                for i in range(num_single_layers)
-            ]
-        )
-
-        # controlnet_blocks
-        self.controlnet_blocks = nn.ModuleList([])
-        for _ in range(len(self.transformer_blocks)):
-            self.controlnet_blocks.append(zero_module(nn.Linear(self.inner_dim, self.inner_dim)))
-
-        self.controlnet_single_blocks = nn.ModuleList([])
-        for _ in range(len(self.single_transformer_blocks)):
-            self.controlnet_single_blocks.append(zero_module(nn.Linear(self.inner_dim, self.inner_dim)))
-
-        self.union = num_mode is not None
-        if self.union:
-            self.controlnet_mode_embedder = nn.Embedding(num_mode, self.inner_dim)
-
-        self.controlnet_x_embedder = zero_module(torch.nn.Linear(in_channels, self.inner_dim))
-
-        self.gradient_checkpointing = False
-
-    @property
-    # Copied from diffusers.models.unets.unet_2d_condition.UNet2DConditionModel.attn_processors
-    def attn_processors(self):
-        r"""
-        Returns:
-            `dict` of attention processors: A dictionary containing all attention processors used in the model with
-            indexed by its weight name.
-        """
-        # set recursively
-        processors = {}
-
-        def fn_recursive_add_processors(name: str, module: torch.nn.Module, processors: Dict[str, AttentionProcessor]):
-            if hasattr(module, "get_processor"):
-                processors[f"{name}.processor"] = module.get_processor()
-
-            for sub_name, child in module.named_children():
-                fn_recursive_add_processors(f"{name}.{sub_name}", child, processors)
-
-            return processors
-
-        for name, module in self.named_children():
-            fn_recursive_add_processors(name, module, processors)
-
-        return processors
-
-    # Copied from diffusers.models.unets.unet_2d_condition.UNet2DConditionModel.set_attn_processor
-    def set_attn_processor(self, processor):
-        r"""
-        Sets the attention processor to use to compute attention.
-
-        Parameters:
-            processor (`dict` of `AttentionProcessor` or only `AttentionProcessor`):
-                The instantiated processor class or a dictionary of processor classes that will be set as the processor
-                for **all** `Attention` layers.
-
-                If `processor` is a dict, the key needs to define the path to the corresponding cross attention
-                processor. This is strongly recommended when setting trainable attention processors.
-
-        """
-        count = len(self.attn_processors.keys())
-
-        if isinstance(processor, dict) and len(processor) != count:
-            raise ValueError(
-                f"A dict of processors was passed, but the number of processors {len(processor)} does not match the"
-                f" number of attention layers: {count}. Please make sure to pass {count} processor classes."
-            )
-
-        def fn_recursive_attn_processor(name: str, module: torch.nn.Module, processor):
-            if hasattr(module, "set_processor"):
-                if not isinstance(processor, dict):
-                    module.set_processor(processor)
-                else:
-                    module.set_processor(processor.pop(f"{name}.processor"))
-
-            for sub_name, child in module.named_children():
-                fn_recursive_attn_processor(f"{name}.{sub_name}", child, processor)
-
-        for name, module in self.named_children():
-            fn_recursive_attn_processor(name, module, processor)
-
-    def _set_gradient_checkpointing(self, module, value=False):
-        if hasattr(module, "gradient_checkpointing"):
-            module.gradient_checkpointing = value
-
-    @classmethod
-    def from_transformer(
-        cls,
-        transformer,
-        num_layers: int = 4,
-        num_single_layers: int = 10,
-        attention_head_dim: int = 128,
-        num_attention_heads: int = 24,
-        load_weights_from_transformer=True,
-    ):
-        config = transformer.config
-        config["num_layers"] = num_layers
-        config["num_single_layers"] = num_single_layers
-        config["attention_head_dim"] = attention_head_dim
-        config["num_attention_heads"] = num_attention_heads
-
-        controlnet = cls(**config)
-
-        if load_weights_from_transformer:
-            controlnet.pos_embed.load_state_dict(transformer.pos_embed.state_dict())
-            controlnet.time_text_embed.load_state_dict(transformer.time_text_embed.state_dict())
-            controlnet.context_embedder.load_state_dict(transformer.context_embedder.state_dict())
-            controlnet.x_embedder.load_state_dict(transformer.x_embedder.state_dict())
-            controlnet.transformer_blocks.load_state_dict(transformer.transformer_blocks.state_dict(), strict=False)
-            controlnet.single_transformer_blocks.load_state_dict(
-                transformer.single_transformer_blocks.state_dict(), strict=False
-            )
-
-            controlnet.controlnet_x_embedder = zero_module(controlnet.controlnet_x_embedder)
-
-        return controlnet
-
-    def forward(
-        self,
-        hidden_states: torch.Tensor,
-        controlnet_cond: torch.Tensor,
-        controlnet_mode: torch.Tensor = None,
-        conditioning_scale: float = 1.0,
-        encoder_hidden_states: torch.Tensor = None,
-        pooled_projections: torch.Tensor = None,
-        timestep: torch.LongTensor = None,
-        img_ids: torch.Tensor = None,
-        txt_ids: torch.Tensor = None,
-        guidance: torch.Tensor = None,
-        joint_attention_kwargs: Optional[Dict[str, Any]] = None,
-        return_dict: bool = True,
-    ) -> Union[torch.FloatTensor, Transformer2DModelOutput]:
-        """
-        The [`FluxTransformer2DModel`] forward method.
-
-        Args:
-            hidden_states (`torch.FloatTensor` of shape `(batch size, channel, height, width)`):
-                Input `hidden_states`.
-            controlnet_cond (`torch.Tensor`):
-                The conditional input tensor of shape `(batch_size, sequence_length, hidden_size)`.
-            controlnet_mode (`torch.Tensor`):
-                The mode tensor of shape `(batch_size, 1)`.
-            conditioning_scale (`float`, defaults to `1.0`):
-                The scale factor for ControlNet outputs.
-            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.FloatTensor` of shape `(batch_size, projection_dim)`): Embeddings projected
-                from the embeddings of input conditions.
-            timestep ( `torch.LongTensor`):
-                Used to indicate denoising step.
-            block_controlnet_hidden_states: (`list` of `torch.Tensor`):
-                A list of tensors that if specified are added to the residuals of transformer blocks.
-            joint_attention_kwargs (`dict`, *optional*):
-                A kwargs dictionary that if specified is passed along to the `AttentionProcessor` as defined under
-                `self.processor` in
-                [diffusers.models.attention_processor](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
-            return_dict (`bool`, *optional*, defaults to `True`):
-                Whether or not to return a [`~models.transformer_2d.Transformer2DModelOutput`] instead of a plain
-                tuple.
-
-        Returns:
-            If `return_dict` is True, an [`~models.transformer_2d.Transformer2DModelOutput`] is returned, otherwise a
-            `tuple` where the first element is the sample tensor.
-        """
-        if joint_attention_kwargs is not None:
-            joint_attention_kwargs = joint_attention_kwargs.copy()
-            lora_scale = joint_attention_kwargs.pop("scale", 1.0)
-        else:
-            lora_scale = 1.0
-
-        if USE_PEFT_BACKEND:
-            # weight the lora layers by setting `lora_scale` for each PEFT layer
-            scale_lora_layers(self, lora_scale)
-        else:
-            if joint_attention_kwargs is not None and joint_attention_kwargs.get("scale", None) is not None:
-                logger.warning(
-                    "Passing `scale` via `joint_attention_kwargs` when not using the PEFT backend is ineffective."
-                )
-        hidden_states = self.x_embedder(hidden_states)
-
-        # add
-        hidden_states = hidden_states + self.controlnet_x_embedder(controlnet_cond)
-
-        timestep = timestep.to(hidden_states.dtype) * 1000
-        if guidance is not None:
-            guidance = guidance.to(hidden_states.dtype) * 1000
-        else:
-            guidance = None
-        temb = (
-            self.time_text_embed(timestep, pooled_projections)
-            if guidance is None
-            else self.time_text_embed(timestep, guidance, pooled_projections)
-        )
-        encoder_hidden_states = self.context_embedder(encoder_hidden_states)
-
-        if self.union:
-            # union mode
-            if controlnet_mode is None:
-                raise ValueError("`controlnet_mode` cannot be `None` when applying ControlNet-Union")
-            # union mode emb
-            controlnet_mode_emb = self.controlnet_mode_embedder(controlnet_mode)
-            encoder_hidden_states = torch.cat([controlnet_mode_emb, encoder_hidden_states], dim=1)
-            txt_ids = torch.cat([txt_ids[:1], txt_ids], dim=0)
-
-        if txt_ids.ndim == 3:
-            logger.warning(
-                "Passing `txt_ids` 3d torch.Tensor is deprecated."
-                "Please remove the batch dimension and pass it as a 2d torch Tensor"
-            )
-            txt_ids = txt_ids[0]
-        if img_ids.ndim == 3:
-            logger.warning(
-                "Passing `img_ids` 3d torch.Tensor is deprecated."
-                "Please remove the batch dimension and pass it as a 2d torch Tensor"
-            )
-            img_ids = img_ids[0]
-
-        ids = torch.cat((txt_ids, img_ids), dim=0)
-        image_rotary_emb = self.pos_embed(ids)
-
-        block_samples = ()
-        for index_block, block in enumerate(self.transformer_blocks):
-            if self.training and self.gradient_checkpointing:
-
-                def create_custom_forward(module, return_dict=None):
-                    def custom_forward(*inputs):
-                        if return_dict is not None:
-                            return module(*inputs, return_dict=return_dict)
-                        else:
-                            return module(*inputs)
-
-                    return custom_forward
-
-                ckpt_kwargs: Dict[str, Any] = {"use_reentrant": False} if is_torch_version(">=", "1.11.0") else {}
-                encoder_hidden_states, hidden_states = torch.utils.checkpoint.checkpoint(
-                    create_custom_forward(block),
-                    hidden_states,
-                    encoder_hidden_states,
-                    temb,
-                    image_rotary_emb,
-                    **ckpt_kwargs,
-                )
-
-            else:
-                encoder_hidden_states, hidden_states = block(
-                    hidden_states=hidden_states,
-                    encoder_hidden_states=encoder_hidden_states,
-                    temb=temb,
-                    image_rotary_emb=image_rotary_emb,
-                )
-            block_samples = block_samples + (hidden_states,)
-
-        hidden_states = torch.cat([encoder_hidden_states, hidden_states], dim=1)
-
-        single_block_samples = ()
-        for index_block, block in enumerate(self.single_transformer_blocks):
-            if self.training and self.gradient_checkpointing:
-
-                def create_custom_forward(module, return_dict=None):
-                    def custom_forward(*inputs):
-                        if return_dict is not None:
-                            return module(*inputs, return_dict=return_dict)
-                        else:
-                            return module(*inputs)
-
-                    return custom_forward
-
-                ckpt_kwargs: Dict[str, Any] = {"use_reentrant": False} if is_torch_version(">=", "1.11.0") else {}
-                hidden_states = torch.utils.checkpoint.checkpoint(
-                    create_custom_forward(block),
-                    hidden_states,
-                    temb,
-                    image_rotary_emb,
-                    **ckpt_kwargs,
-                )
-
-            else:
-                hidden_states = block(
-                    hidden_states=hidden_states,
-                    temb=temb,
-                    image_rotary_emb=image_rotary_emb,
-                )
-            single_block_samples = single_block_samples + (hidden_states[:, encoder_hidden_states.shape[1] :],)
-
-        # controlnet block
-        controlnet_block_samples = ()
-        for block_sample, controlnet_block in zip(block_samples, self.controlnet_blocks):
-            block_sample = controlnet_block(block_sample)
-            controlnet_block_samples = controlnet_block_samples + (block_sample,)
-
-        controlnet_single_block_samples = ()
-        for single_block_sample, controlnet_block in zip(single_block_samples, self.controlnet_single_blocks):
-            single_block_sample = controlnet_block(single_block_sample)
-            controlnet_single_block_samples = controlnet_single_block_samples + (single_block_sample,)
-
-        # scaling
-        controlnet_block_samples = [sample * conditioning_scale for sample in controlnet_block_samples]
-        controlnet_single_block_samples = [sample * conditioning_scale for sample in controlnet_single_block_samples]
-
-        controlnet_block_samples = None if len(controlnet_block_samples) == 0 else controlnet_block_samples
-        controlnet_single_block_samples = (
-            None if len(controlnet_single_block_samples) == 0 else controlnet_single_block_samples
-        )
-
-        if USE_PEFT_BACKEND:
-            # remove `lora_scale` from each PEFT layer
-            unscale_lora_layers(self, lora_scale)
-
-        if not return_dict:
-            return (controlnet_block_samples, controlnet_single_block_samples)
-
-        return FluxControlNetOutput(
-            controlnet_block_samples=controlnet_block_samples,
-            controlnet_single_block_samples=controlnet_single_block_samples,
-        )
-
-
-class FluxMultiControlNetModel(ModelMixin):
-    r"""
-    `FluxMultiControlNetModel` wrapper class for Multi-FluxControlNetModel
-
-    This module is a wrapper for multiple instances of the `FluxControlNetModel`. The `forward()` API is designed to be
-    compatible with `FluxControlNetModel`.
-
-    Args:
-        controlnets (`List[FluxControlNetModel]`):
-            Provides additional conditioning to the unet during the denoising process. You must set multiple
-            `FluxControlNetModel` as a list.
-    """
-
-    def __init__(self, controlnets):
-        super().__init__()
-        self.nets = nn.ModuleList(controlnets)
-
-    def forward(
-        self,
-        hidden_states: torch.FloatTensor,
-        controlnet_cond: List[torch.tensor],
-        controlnet_mode: List[torch.tensor],
-        conditioning_scale: List[float],
-        encoder_hidden_states: torch.Tensor = None,
-        pooled_projections: torch.Tensor = None,
-        timestep: torch.LongTensor = None,
-        img_ids: torch.Tensor = None,
-        txt_ids: torch.Tensor = None,
-        guidance: torch.Tensor = None,
-        joint_attention_kwargs: Optional[Dict[str, Any]] = None,
-        return_dict: bool = True,
-    ) -> Union[FluxControlNetOutput, Tuple]:
-        # ControlNet-Union with multiple conditions
-        # only load one ControlNet for saving memories
-        if len(self.nets) == 1 and self.nets[0].union:
-            controlnet = self.nets[0]
-
-            for i, (image, mode, scale) in enumerate(zip(controlnet_cond, controlnet_mode, conditioning_scale)):
-                block_samples, single_block_samples = controlnet(
-                    hidden_states=hidden_states,
-                    controlnet_cond=image,
-                    controlnet_mode=mode[:, None],
-                    conditioning_scale=scale,
-                    timestep=timestep,
-                    guidance=guidance,
-                    pooled_projections=pooled_projections,
-                    encoder_hidden_states=encoder_hidden_states,
-                    txt_ids=txt_ids,
-                    img_ids=img_ids,
-                    joint_attention_kwargs=joint_attention_kwargs,
-                    return_dict=return_dict,
-                )
-
-                # merge samples
-                if i == 0:
-                    control_block_samples = block_samples
-                    control_single_block_samples = single_block_samples
-                else:
-                    control_block_samples = [
-                        control_block_sample + block_sample
-                        for control_block_sample, block_sample in zip(control_block_samples, block_samples)
-                    ]
-
-                    control_single_block_samples = [
-                        control_single_block_sample + block_sample
-                        for control_single_block_sample, block_sample in zip(
-                            control_single_block_samples, single_block_samples
-                        )
-                    ]
-
-        # Regular Multi-ControlNets
-        # load all ControlNets into memories
-        else:
-            for i, (image, mode, scale, controlnet) in enumerate(
-                zip(controlnet_cond, controlnet_mode, conditioning_scale, self.nets)
-            ):
-                block_samples, single_block_samples = controlnet(
-                    hidden_states=hidden_states,
-                    controlnet_cond=image,
-                    controlnet_mode=mode[:, None],
-                    conditioning_scale=scale,
-                    timestep=timestep,
-                    guidance=guidance,
-                    pooled_projections=pooled_projections,
-                    encoder_hidden_states=encoder_hidden_states,
-                    txt_ids=txt_ids,
-                    img_ids=img_ids,
-                    joint_attention_kwargs=joint_attention_kwargs,
-                    return_dict=return_dict,
-                )
-
-                # merge samples
-                if i == 0:
-                    control_block_samples = block_samples
-                    control_single_block_samples = single_block_samples
-                else:
-                    control_block_samples = [
-                        control_block_sample + block_sample
-                        for control_block_sample, block_sample in zip(control_block_samples, block_samples)
-                    ]
-
-                    control_single_block_samples = [
-                        control_single_block_sample + block_sample
-                        for control_single_block_sample, block_sample in zip(
-                            control_single_block_samples, single_block_samples
-                        )
-                    ]
-
-        return control_block_samples, control_single_block_samples

src/diffusers/models/controlnet_sd3.py

@@ -55,7 +55,6 @@ class SD3ControlNetModel(ModelMixin, ConfigMixin, PeftAdapterMixin, FromOriginal
         pooled_projection_dim: int = 2048,
         out_channels: int = 16,
         pos_embed_max_size: int = 96,
-        extra_conditioning_channels: int = 0,
     ):
         super().__init__()
         default_out_channels = in_channels
@@ -99,7 +98,7 @@ class SD3ControlNetModel(ModelMixin, ConfigMixin, PeftAdapterMixin, FromOriginal
             height=sample_size,
             width=sample_size,
             patch_size=patch_size,
-            in_channels=in_channels + extra_conditioning_channels,
+            in_channels=in_channels,
             embed_dim=self.inner_dim,
             pos_embed_type=None,
         )

src/diffusers/models/controlnet_sparsectrl.py

@@ -691,6 +691,7 @@ class SparseControlNetModel(ModelMixin, ConfigMixin, FromOriginalModelMixin):
 
         emb = self.time_embedding(t_emb, timestep_cond)
         emb = emb.repeat_interleave(sample_num_frames, dim=0)
+        encoder_hidden_states = encoder_hidden_states.repeat_interleave(sample_num_frames, dim=0)
 
         # 2. pre-process
         batch_size, channels, num_frames, height, width = sample.shape

src/diffusers/models/embeddings.py

@@ -391,16 +391,15 @@ def get_3d_rotary_pos_embed(
         The size of the temporal dimension.
     theta (`float`):
         Scaling factor for frequency computation.
+    use_real (`bool`):
+        If True, return real part and imaginary part separately. Otherwise, return complex numbers.
 
     Returns:
         `torch.Tensor`: positional embedding with shape `(temporal_size * grid_size[0] * grid_size[1], embed_dim/2)`.
     """
-    if use_real is not True:
-        raise ValueError(" `use_real = False` is not currently supported for get_3d_rotary_pos_embed")
     start, stop = crops_coords
-    grid_size_h, grid_size_w = grid_size
-    grid_h = np.linspace(start[0], stop[0], grid_size_h, endpoint=False, dtype=np.float32)
-    grid_w = np.linspace(start[1], stop[1], grid_size_w, endpoint=False, dtype=np.float32)
+    grid_h = np.linspace(start[0], stop[0], grid_size[0], endpoint=False, dtype=np.float32)
+    grid_w = np.linspace(start[1], stop[1], grid_size[1], endpoint=False, dtype=np.float32)
     grid_t = np.linspace(0, temporal_size, temporal_size, endpoint=False, dtype=np.float32)
 
     # Compute dimensions for each axis
@@ -409,37 +408,54 @@ def get_3d_rotary_pos_embed(
     dim_w = embed_dim // 8 * 3
 
     # Temporal frequencies
-    freqs_t = get_1d_rotary_pos_embed(dim_t, grid_t, use_real=True)
+    freqs_t = 1.0 / (theta ** (torch.arange(0, dim_t, 2).float() / dim_t))
+    grid_t = torch.from_numpy(grid_t).float()
+    freqs_t = torch.einsum("n , f -> n f", grid_t, freqs_t)
+    freqs_t = freqs_t.repeat_interleave(2, dim=-1)
+
     # Spatial frequencies for height and width
-    freqs_h = get_1d_rotary_pos_embed(dim_h, grid_h, use_real=True)
-    freqs_w = get_1d_rotary_pos_embed(dim_w, grid_w, use_real=True)
+    freqs_h = 1.0 / (theta ** (torch.arange(0, dim_h, 2).float() / dim_h))
+    freqs_w = 1.0 / (theta ** (torch.arange(0, dim_w, 2).float() / dim_w))
+    grid_h = torch.from_numpy(grid_h).float()
+    grid_w = torch.from_numpy(grid_w).float()
+    freqs_h = torch.einsum("n , f -> n f", grid_h, freqs_h)
+    freqs_w = torch.einsum("n , f -> n f", grid_w, freqs_w)
+    freqs_h = freqs_h.repeat_interleave(2, dim=-1)
+    freqs_w = freqs_w.repeat_interleave(2, dim=-1)
 
-    # BroadCast and concatenate temporal and spaial frequencie (height and width) into a 3d tensor
-    def combine_time_height_width(freqs_t, freqs_h, freqs_w):
-        freqs_t = freqs_t[:, None, None, :].expand(
-            -1, grid_size_h, grid_size_w, -1
-        )  # temporal_size, grid_size_h, grid_size_w, dim_t
-        freqs_h = freqs_h[None, :, None, :].expand(
-            temporal_size, -1, grid_size_w, -1
-        )  # temporal_size, grid_size_h, grid_size_2, dim_h
-        freqs_w = freqs_w[None, None, :, :].expand(
-            temporal_size, grid_size_h, -1, -1
-        )  # temporal_size, grid_size_h, grid_size_2, dim_w
+    # Broadcast and concatenate tensors along specified dimension
+    def broadcast(tensors, dim=-1):
+        num_tensors = len(tensors)
+        shape_lens = {len(t.shape) for t in tensors}
+        assert len(shape_lens) == 1, "tensors must all have the same number of dimensions"
+        shape_len = list(shape_lens)[0]
+        dim = (dim + shape_len) if dim < 0 else dim
+        dims = list(zip(*(list(t.shape) for t in tensors)))
+        expandable_dims = [(i, val) for i, val in enumerate(dims) if i != dim]
+        assert all(
+            [*(len(set(t[1])) <= 2 for t in expandable_dims)]
+        ), "invalid dimensions for broadcastable concatenation"
+        max_dims = [(t[0], max(t[1])) for t in expandable_dims]
+        expanded_dims = [(t[0], (t[1],) * num_tensors) for t in max_dims]
+        expanded_dims.insert(dim, (dim, dims[dim]))
+        expandable_shapes = list(zip(*(t[1] for t in expanded_dims)))
+        tensors = [t[0].expand(*t[1]) for t in zip(tensors, expandable_shapes)]
+        return torch.cat(tensors, dim=dim)
 
-        freqs = torch.cat(
-            [freqs_t, freqs_h, freqs_w], dim=-1
-        )  # temporal_size, grid_size_h, grid_size_w, (dim_t + dim_h + dim_w)
-        freqs = freqs.view(
-            temporal_size * grid_size_h * grid_size_w, -1
-        )  # (temporal_size * grid_size_h * grid_size_w), (dim_t + dim_h + dim_w)
-        return freqs
+    freqs = broadcast((freqs_t[:, None, None, :], freqs_h[None, :, None, :], freqs_w[None, None, :, :]), dim=-1)
 
-    t_cos, t_sin = freqs_t  # both t_cos and t_sin has shape: temporal_size, dim_t
-    h_cos, h_sin = freqs_h  # both h_cos and h_sin has shape: grid_size_h, dim_h
-    w_cos, w_sin = freqs_w  # both w_cos and w_sin has shape: grid_size_w, dim_w
-    cos = combine_time_height_width(t_cos, h_cos, w_cos)
-    sin = combine_time_height_width(t_sin, h_sin, w_sin)
-    return cos, sin
+    t, h, w, d = freqs.shape
+    freqs = freqs.view(t * h * w, d)
+
+    # Generate sine and cosine components
+    sin = freqs.sin()
+    cos = freqs.cos()
+
+    if use_real:
+        return cos, sin
+    else:
+        freqs_cis = torch.polar(torch.ones_like(freqs), freqs)
+        return freqs_cis
 
 
 def get_2d_rotary_pos_embed(embed_dim, crops_coords, grid_size, use_real=True):
@@ -514,7 +530,6 @@ def get_1d_rotary_pos_embed(
     linear_factor=1.0,
     ntk_factor=1.0,
     repeat_interleave_real=True,
-    freqs_dtype=torch.float32,  #  torch.float32, torch.float64 (flux)
 ):
     """
     Precompute the frequency tensor for complex exponentials (cis) with given dimensions.
@@ -537,34 +552,26 @@ def get_1d_rotary_pos_embed(
         repeat_interleave_real (`bool`, *optional*, defaults to `True`):
             If `True` and `use_real`, real part and imaginary part are each interleaved with themselves to reach `dim`.
             Otherwise, they are concateanted with themselves.
-        freqs_dtype (`torch.float32` or `torch.float64`, *optional*, defaults to `torch.float32`):
-            the dtype of the frequency tensor.
     Returns:
         `torch.Tensor`: Precomputed frequency tensor with complex exponentials. [S, D/2]
     """
     assert dim % 2 == 0
 
     if isinstance(pos, int):
-        pos = torch.arange(pos)
-    if isinstance(pos, np.ndarray):
-        pos = torch.from_numpy(pos)  # type: ignore  # [S]
-
+        pos = np.arange(pos)
     theta = theta * ntk_factor
-    freqs = 1.0 / (theta ** (torch.arange(0, dim, 2, dtype=freqs_dtype)[: (dim // 2)] / dim)) / linear_factor  # [D/2]
-    freqs = freqs.to(pos.device)
-    freqs = torch.outer(pos, freqs)  # type: ignore   # [S, D/2]
+    freqs = 1.0 / (theta ** (torch.arange(0, dim, 2)[: (dim // 2)].float() / dim)) / linear_factor  # [D/2]
+    t = torch.from_numpy(pos).to(freqs.device)  # type: ignore  # [S]
+    freqs = torch.outer(t, freqs).float()  # type: ignore   # [S, D/2]
     if use_real and repeat_interleave_real:
-        # flux, hunyuan-dit, cogvideox
-        freqs_cos = freqs.cos().repeat_interleave(2, dim=1).float()  # [S, D]
-        freqs_sin = freqs.sin().repeat_interleave(2, dim=1).float()  # [S, D]
+        freqs_cos = freqs.cos().repeat_interleave(2, dim=1)  # [S, D]
+        freqs_sin = freqs.sin().repeat_interleave(2, dim=1)  # [S, D]
         return freqs_cos, freqs_sin
     elif use_real:
-        # stable audio
-        freqs_cos = torch.cat([freqs.cos(), freqs.cos()], dim=-1).float()  # [S, D]
-        freqs_sin = torch.cat([freqs.sin(), freqs.sin()], dim=-1).float()  # [S, D]
+        freqs_cos = torch.cat([freqs.cos(), freqs.cos()], dim=-1)  # [S, D]
+        freqs_sin = torch.cat([freqs.sin(), freqs.sin()], dim=-1)  # [S, D]
         return freqs_cos, freqs_sin
     else:
-        # lumina
         freqs_cis = torch.polar(torch.ones_like(freqs), freqs)  # complex64     # [S, D/2]
         return freqs_cis
 
@@ -596,11 +603,11 @@ def apply_rotary_emb(
         cos, sin = cos.to(x.device), sin.to(x.device)
 
         if use_real_unbind_dim == -1:
-            # Used for flux, cogvideox, hunyuan-dit
+            # Use for example in Lumina
             x_real, x_imag = x.reshape(*x.shape[:-1], -1, 2).unbind(-1)  # [B, S, H, D//2]
             x_rotated = torch.stack([-x_imag, x_real], dim=-1).flatten(3)
         elif use_real_unbind_dim == -2:
-            # Used for Stable Audio
+            # Use for example in Stable Audio
             x_real, x_imag = x.reshape(*x.shape[:-1], 2, -1).unbind(-2)  # [B, S, H, D//2]
             x_rotated = torch.cat([-x_imag, x_real], dim=-1)
         else:
@@ -610,7 +617,6 @@ def apply_rotary_emb(
 
         return out
     else:
-        # used for lumina
         x_rotated = torch.view_as_complex(x.float().reshape(*x.shape[:-1], -1, 2))
         freqs_cis = freqs_cis.unsqueeze(2)
         x_out = torch.view_as_real(x_rotated * freqs_cis).flatten(3)
@@ -618,31 +624,6 @@ def apply_rotary_emb(
         return x_out.type_as(x)
 
 
-class FluxPosEmbed(nn.Module):
-    # modified from https://github.com/black-forest-labs/flux/blob/c00d7c60b085fce8058b9df845e036090873f2ce/src/flux/modules/layers.py#L11
-    def __init__(self, theta: int, axes_dim: List[int]):
-        super().__init__()
-        self.theta = theta
-        self.axes_dim = axes_dim
-
-    def forward(self, ids: torch.Tensor) -> torch.Tensor:
-        n_axes = ids.shape[-1]
-        cos_out = []
-        sin_out = []
-        pos = ids.squeeze().float()
-        is_mps = ids.device.type == "mps"
-        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], pos[:, i], repeat_interleave_real=True, use_real=True, freqs_dtype=freqs_dtype
-            )
-            cos_out.append(cos)
-            sin_out.append(sin)
-        freqs_cos = torch.cat(cos_out, dim=-1).to(ids.device)
-        freqs_sin = torch.cat(sin_out, dim=-1).to(ids.device)
-        return freqs_cos, freqs_sin
-
-
 class TimestepEmbedding(nn.Module):
     def __init__(
         self,

src/diffusers/models/transformers/auraflow_transformer_2d.py

@@ -274,7 +274,6 @@ class AuraFlowTransformer2DModel(ModelMixin, ConfigMixin):
         pos_embed_max_size (`int`, defaults to 4096): Maximum positions to embed from the image latents.
     """
 
-    _no_split_modules = ["AuraFlowJointTransformerBlock", "AuraFlowSingleTransformerBlock", "AuraFlowPatchEmbed"]
     _supports_gradient_checkpointing = True
 
     @register_to_config

src/diffusers/models/transformers/pixart_transformer_2d.py

@@ -19,7 +19,7 @@ from torch import nn
 from ...configuration_utils import ConfigMixin, register_to_config
 from ...utils import is_torch_version, logging
 from ..attention import BasicTransformerBlock
-from ..attention_processor import Attention, AttentionProcessor, AttnProcessor, FusedAttnProcessor2_0
+from ..attention_processor import Attention, AttentionProcessor, FusedAttnProcessor2_0
 from ..embeddings import PatchEmbed, PixArtAlphaTextProjection
 from ..modeling_outputs import Transformer2DModelOutput
 from ..modeling_utils import ModelMixin
@@ -247,14 +247,6 @@ class PixArtTransformer2DModel(ModelMixin, ConfigMixin):
         for name, module in self.named_children():
             fn_recursive_attn_processor(name, module, processor)
 
-    def set_default_attn_processor(self):
-        """
-        Disables custom attention processors and sets the default attention implementation.
-
-        Safe to just use `AttnProcessor()` as PixArt doesn't have any exotic attention processors in default model.
-        """
-        self.set_attn_processor(AttnProcessor())
-
     # Copied from diffusers.models.unets.unet_2d_condition.UNet2DConditionModel.fuse_qkv_projections
     def fuse_qkv_projections(self):
         """

src/diffusers/models/transformers/transformer_flux.py

@@ -1,4 +1,4 @@
-# Copyright 2024 Black Forest Labs, The HuggingFace Team and The InstantX Team. All rights reserved.
+# Copyright 2024 Black Forest Labs, 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.
@@ -13,9 +13,8 @@
 # limitations under the License.
 
 
-from typing import Any, Dict, Optional, Tuple, Union
+from typing import Any, Dict, List, Optional, Union
 
-import numpy as np
 import torch
 import torch.nn as nn
 import torch.nn.functional as F
@@ -23,23 +22,52 @@ import torch.nn.functional as F
 from ...configuration_utils import ConfigMixin, register_to_config
 from ...loaders import FromOriginalModelMixin, PeftAdapterMixin
 from ...models.attention import FeedForward
-from ...models.attention_processor import (
-    Attention,
-    AttentionProcessor,
-    FluxAttnProcessor2_0,
-    FusedFluxAttnProcessor2_0,
-)
+from ...models.attention_processor import Attention, FluxAttnProcessor2_0, FluxSingleAttnProcessor2_0
 from ...models.modeling_utils import ModelMixin
 from ...models.normalization import AdaLayerNormContinuous, AdaLayerNormZero, AdaLayerNormZeroSingle
 from ...utils import USE_PEFT_BACKEND, is_torch_version, logging, scale_lora_layers, unscale_lora_layers
 from ...utils.torch_utils import maybe_allow_in_graph
-from ..embeddings import CombinedTimestepGuidanceTextProjEmbeddings, CombinedTimestepTextProjEmbeddings, FluxPosEmbed
+from ..embeddings import CombinedTimestepGuidanceTextProjEmbeddings, CombinedTimestepTextProjEmbeddings
 from ..modeling_outputs import Transformer2DModelOutput
 
 
 logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
 
 
+# YiYi to-do: refactor rope related functions/classes
+def rope(pos: torch.Tensor, dim: int, theta: int) -> torch.Tensor:
+    assert dim % 2 == 0, "The dimension must be even."
+
+    scale = torch.arange(0, dim, 2, dtype=torch.float64, device=pos.device) / dim
+    omega = 1.0 / (theta**scale)
+
+    batch_size, seq_length = pos.shape
+    out = torch.einsum("...n,d->...nd", pos, omega)
+    cos_out = torch.cos(out)
+    sin_out = torch.sin(out)
+
+    stacked_out = torch.stack([cos_out, -sin_out, sin_out, cos_out], dim=-1)
+    out = stacked_out.view(batch_size, -1, dim // 2, 2, 2)
+    return out.float()
+
+
+# YiYi to-do: refactor rope related functions/classes
+class EmbedND(nn.Module):
+    def __init__(self, dim: int, theta: int, axes_dim: List[int]):
+        super().__init__()
+        self.dim = dim
+        self.theta = theta
+        self.axes_dim = axes_dim
+
+    def forward(self, ids: torch.Tensor) -> torch.Tensor:
+        n_axes = ids.shape[-1]
+        emb = torch.cat(
+            [rope(ids[..., i], self.axes_dim[i], self.theta) for i in range(n_axes)],
+            dim=-3,
+        )
+        return emb.unsqueeze(1)
+
+
 @maybe_allow_in_graph
 class FluxSingleTransformerBlock(nn.Module):
     r"""
@@ -64,7 +92,7 @@ class FluxSingleTransformerBlock(nn.Module):
         self.act_mlp = nn.GELU(approximate="tanh")
         self.proj_out = nn.Linear(dim + self.mlp_hidden_dim, dim)
 
-        processor = FluxAttnProcessor2_0()
+        processor = FluxSingleAttnProcessor2_0()
         self.attn = Attention(
             query_dim=dim,
             cross_attention_dim=None,
@@ -222,7 +250,6 @@ class FluxTransformer2DModel(ModelMixin, ConfigMixin, PeftAdapterMixin, FromOrig
     """
 
     _supports_gradient_checkpointing = True
-    _no_split_modules = ["FluxTransformerBlock", "FluxSingleTransformerBlock"]
 
     @register_to_config
     def __init__(
@@ -236,14 +263,13 @@ class FluxTransformer2DModel(ModelMixin, ConfigMixin, PeftAdapterMixin, FromOrig
         joint_attention_dim: int = 4096,
         pooled_projection_dim: int = 768,
         guidance_embeds: bool = False,
-        axes_dims_rope: Tuple[int] = (16, 56, 56),
+        axes_dims_rope: List[int] = [16, 56, 56],
     ):
         super().__init__()
         self.out_channels = in_channels
         self.inner_dim = self.config.num_attention_heads * self.config.attention_head_dim
 
-        self.pos_embed = FluxPosEmbed(theta=10000, axes_dim=axes_dims_rope)
-
+        self.pos_embed = EmbedND(dim=self.inner_dim, theta=10000, axes_dim=axes_dims_rope)
         text_time_guidance_cls = (
             CombinedTimestepGuidanceTextProjEmbeddings if guidance_embeds else CombinedTimestepTextProjEmbeddings
         )
@@ -281,106 +307,6 @@ class FluxTransformer2DModel(ModelMixin, ConfigMixin, PeftAdapterMixin, FromOrig
 
         self.gradient_checkpointing = False
 
-    @property
-    # Copied from diffusers.models.unets.unet_2d_condition.UNet2DConditionModel.attn_processors
-    def attn_processors(self) -> Dict[str, AttentionProcessor]:
-        r"""
-        Returns:
-            `dict` of attention processors: A dictionary containing all attention processors used in the model with
-            indexed by its weight name.
-        """
-        # set recursively
-        processors = {}
-
-        def fn_recursive_add_processors(name: str, module: torch.nn.Module, processors: Dict[str, AttentionProcessor]):
-            if hasattr(module, "get_processor"):
-                processors[f"{name}.processor"] = module.get_processor()
-
-            for sub_name, child in module.named_children():
-                fn_recursive_add_processors(f"{name}.{sub_name}", child, processors)
-
-            return processors
-
-        for name, module in self.named_children():
-            fn_recursive_add_processors(name, module, processors)
-
-        return processors
-
-    # Copied from diffusers.models.unets.unet_2d_condition.UNet2DConditionModel.set_attn_processor
-    def set_attn_processor(self, processor: Union[AttentionProcessor, Dict[str, AttentionProcessor]]):
-        r"""
-        Sets the attention processor to use to compute attention.
-
-        Parameters:
-            processor (`dict` of `AttentionProcessor` or only `AttentionProcessor`):
-                The instantiated processor class or a dictionary of processor classes that will be set as the processor
-                for **all** `Attention` layers.
-
-                If `processor` is a dict, the key needs to define the path to the corresponding cross attention
-                processor. This is strongly recommended when setting trainable attention processors.
-
-        """
-        count = len(self.attn_processors.keys())
-
-        if isinstance(processor, dict) and len(processor) != count:
-            raise ValueError(
-                f"A dict of processors was passed, but the number of processors {len(processor)} does not match the"
-                f" number of attention layers: {count}. Please make sure to pass {count} processor classes."
-            )
-
-        def fn_recursive_attn_processor(name: str, module: torch.nn.Module, processor):
-            if hasattr(module, "set_processor"):
-                if not isinstance(processor, dict):
-                    module.set_processor(processor)
-                else:
-                    module.set_processor(processor.pop(f"{name}.processor"))
-
-            for sub_name, child in module.named_children():
-                fn_recursive_attn_processor(f"{name}.{sub_name}", child, processor)
-
-        for name, module in self.named_children():
-            fn_recursive_attn_processor(name, module, processor)
-
-    # Copied from diffusers.models.unets.unet_2d_condition.UNet2DConditionModel.fuse_qkv_projections with FusedAttnProcessor2_0->FusedFluxAttnProcessor2_0
-    def fuse_qkv_projections(self):
-        """
-        Enables fused QKV projections. For self-attention modules, all projection matrices (i.e., query, key, value)
-        are fused. For cross-attention modules, key and value projection matrices are fused.
-
-        <Tip warning={true}>
-
-        This API is 🧪 experimental.
-
-        </Tip>
-        """
-        self.original_attn_processors = None
-
-        for _, attn_processor in self.attn_processors.items():
-            if "Added" in str(attn_processor.__class__.__name__):
-                raise ValueError("`fuse_qkv_projections()` is not supported for models having added KV projections.")
-
-        self.original_attn_processors = self.attn_processors
-
-        for module in self.modules():
-            if isinstance(module, Attention):
-                module.fuse_projections(fuse=True)
-
-        self.set_attn_processor(FusedFluxAttnProcessor2_0())
-
-    # Copied from diffusers.models.unets.unet_2d_condition.UNet2DConditionModel.unfuse_qkv_projections
-    def unfuse_qkv_projections(self):
-        """Disables the fused QKV projection if enabled.
-
-        <Tip warning={true}>
-
-        This API is 🧪 experimental.
-
-        </Tip>
-
-        """
-        if self.original_attn_processors is not None:
-            self.set_attn_processor(self.original_attn_processors)
-
     def _set_gradient_checkpointing(self, module, value=False):
         if hasattr(module, "gradient_checkpointing"):
             module.gradient_checkpointing = value
@@ -395,8 +321,6 @@ class FluxTransformer2DModel(ModelMixin, ConfigMixin, PeftAdapterMixin, FromOrig
         txt_ids: torch.Tensor = None,
         guidance: torch.Tensor = None,
         joint_attention_kwargs: Optional[Dict[str, Any]] = None,
-        controlnet_block_samples=None,
-        controlnet_single_block_samples=None,
         return_dict: bool = True,
     ) -> Union[torch.FloatTensor, Transformer2DModelOutput]:
         """
@@ -453,19 +377,7 @@ class FluxTransformer2DModel(ModelMixin, ConfigMixin, PeftAdapterMixin, FromOrig
         )
         encoder_hidden_states = self.context_embedder(encoder_hidden_states)
 
-        if txt_ids.ndim == 3:
-            logger.warning(
-                "Passing `txt_ids` 3d torch.Tensor is deprecated."
-                "Please remove the batch dimension and pass it as a 2d torch Tensor"
-            )
-            txt_ids = txt_ids[0]
-        if img_ids.ndim == 3:
-            logger.warning(
-                "Passing `img_ids` 3d torch.Tensor is deprecated."
-                "Please remove the batch dimension and pass it as a 2d torch Tensor"
-            )
-            img_ids = img_ids[0]
-        ids = torch.cat((txt_ids, img_ids), dim=0)
+        ids = torch.cat((txt_ids, img_ids), dim=1)
         image_rotary_emb = self.pos_embed(ids)
 
         for index_block, block in enumerate(self.transformer_blocks):
@@ -498,12 +410,6 @@ class FluxTransformer2DModel(ModelMixin, ConfigMixin, PeftAdapterMixin, FromOrig
                     image_rotary_emb=image_rotary_emb,
                 )
 
-            # controlnet residual
-            if controlnet_block_samples is not None:
-                interval_control = len(self.transformer_blocks) / len(controlnet_block_samples)
-                interval_control = int(np.ceil(interval_control))
-                hidden_states = hidden_states + controlnet_block_samples[index_block // interval_control]
-
         hidden_states = torch.cat([encoder_hidden_states, hidden_states], dim=1)
 
         for index_block, block in enumerate(self.single_transformer_blocks):
@@ -534,15 +440,6 @@ class FluxTransformer2DModel(ModelMixin, ConfigMixin, PeftAdapterMixin, FromOrig
                     image_rotary_emb=image_rotary_emb,
                 )
 
-            # controlnet residual
-            if controlnet_single_block_samples is not None:
-                interval_control = len(self.single_transformer_blocks) / len(controlnet_single_block_samples)
-                interval_control = int(np.ceil(interval_control))
-                hidden_states[:, encoder_hidden_states.shape[1] :, ...] = (
-                    hidden_states[:, encoder_hidden_states.shape[1] :, ...]
-                    + controlnet_single_block_samples[index_block // interval_control]
-                )
-
         hidden_states = hidden_states[:, encoder_hidden_states.shape[1] :, ...]
 
         hidden_states = self.norm_out(hidden_states, temb)

src/diffusers/models/unets/unet_motion_model.py

@@ -116,7 +116,7 @@ class AnimateDiffTransformer3D(nn.Module):
 
         self.in_channels = in_channels
 
-        self.norm = nn.GroupNorm(num_groups=norm_num_groups, num_channels=in_channels, eps=1e-6, affine=True)
+        self.norm = torch.nn.GroupNorm(num_groups=norm_num_groups, num_channels=in_channels, eps=1e-6, affine=True)
         self.proj_in = nn.Linear(in_channels, inner_dim)
 
         # 3. Define transformers blocks
@@ -2178,6 +2178,7 @@ class UNetMotionModel(ModelMixin, ConfigMixin, UNet2DConditionLoadersMixin, Peft
 
         emb = emb if aug_emb is None else emb + aug_emb
         emb = emb.repeat_interleave(repeats=num_frames, dim=0)
+        encoder_hidden_states = encoder_hidden_states.repeat_interleave(repeats=num_frames, dim=0)
 
         if self.encoder_hid_proj is not None and self.config.encoder_hid_dim_type == "ip_image_proj":
             if "image_embeds" not in added_cond_kwargs:

src/diffusers/pipelines/__init__.py

@@ -124,7 +124,7 @@ else:
         "AnimateDiffSparseControlNetPipeline",
         "AnimateDiffVideoToVideoPipeline",
     ]
-    _import_structure["flux"] = ["FluxPipeline", "FluxControlNetPipeline"]
+    _import_structure["flux"] = ["FluxPipeline"]
     _import_structure["audioldm"] = ["AudioLDMPipeline"]
     _import_structure["audioldm2"] = [
         "AudioLDM2Pipeline",
@@ -132,7 +132,7 @@ else:
         "AudioLDM2UNet2DConditionModel",
     ]
     _import_structure["blip_diffusion"] = ["BlipDiffusionPipeline"]
-    _import_structure["cogvideo"] = ["CogVideoXPipeline", "CogVideoXVideoToVideoPipeline"]
+    _import_structure["cogvideo"] = ["CogVideoXPipeline"]
     _import_structure["controlnet"].extend(
         [
             "BlipDiffusionControlNetPipeline",
@@ -154,7 +154,6 @@ else:
             "StableDiffusionControlNetPAGPipeline",
             "StableDiffusionXLPAGPipeline",
             "StableDiffusionXLPAGInpaintPipeline",
-            "StableDiffusionXLControlNetPAGImg2ImgPipeline",
             "StableDiffusionXLControlNetPAGPipeline",
             "StableDiffusionXLPAGImg2ImgPipeline",
             "PixArtSigmaPAGPipeline",
@@ -174,7 +173,6 @@ else:
     _import_structure["controlnet_sd3"].extend(
         [
             "StableDiffusion3ControlNetPipeline",
-            "StableDiffusion3ControlNetInpaintingPipeline",
         ]
     )
     _import_structure["deepfloyd_if"] = [
@@ -454,7 +452,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
         )
         from .aura_flow import AuraFlowPipeline
         from .blip_diffusion import BlipDiffusionPipeline
-        from .cogvideo import CogVideoXPipeline, CogVideoXVideoToVideoPipeline
+        from .cogvideo import CogVideoXPipeline
         from .controlnet import (
             BlipDiffusionControlNetPipeline,
             StableDiffusionControlNetImg2ImgPipeline,
@@ -467,7 +465,9 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
         from .controlnet_hunyuandit import (
             HunyuanDiTControlNetPipeline,
         )
-        from .controlnet_sd3 import StableDiffusion3ControlNetInpaintingPipeline, StableDiffusion3ControlNetPipeline
+        from .controlnet_sd3 import (
+            StableDiffusion3ControlNetPipeline,
+        )
         from .controlnet_xs import (
             StableDiffusionControlNetXSPipeline,
             StableDiffusionXLControlNetXSPipeline,
@@ -494,7 +494,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             VersatileDiffusionTextToImagePipeline,
             VQDiffusionPipeline,
         )
-        from .flux import FluxControlNetPipeline, FluxPipeline
+        from .flux import FluxPipeline
         from .hunyuandit import HunyuanDiTPipeline
         from .i2vgen_xl import I2VGenXLPipeline
         from .kandinsky import (
@@ -548,7 +548,6 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             StableDiffusion3PAGPipeline,
             StableDiffusionControlNetPAGPipeline,
             StableDiffusionPAGPipeline,
-            StableDiffusionXLControlNetPAGImg2ImgPipeline,
             StableDiffusionXLControlNetPAGPipeline,
             StableDiffusionXLPAGImg2ImgPipeline,
             StableDiffusionXLPAGInpaintPipeline,

src/diffusers/pipelines/animatediff/pipeline_animatediff.py

@@ -432,6 +432,7 @@ class AnimateDiffPipeline(
             extra_step_kwargs["generator"] = generator
         return extra_step_kwargs
 
+    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.check_inputs
     def check_inputs(
         self,
         prompt,
@@ -469,8 +470,8 @@ class AnimateDiffPipeline(
             raise ValueError(
                 "Provide either `prompt` or `prompt_embeds`. Cannot leave both `prompt` and `prompt_embeds` undefined."
             )
-        elif prompt is not None and not isinstance(prompt, (str, list, dict)):
-            raise ValueError(f"`prompt` has to be of type `str`, `list` or `dict` but is {type(prompt)=}")
+        elif prompt is not None and (not isinstance(prompt, str) and not isinstance(prompt, list)):
+            raise ValueError(f"`prompt` has to be of type `str` or `list` but is {type(prompt)}")
 
         if negative_prompt is not None and negative_prompt_embeds is not None:
             raise ValueError(
@@ -556,15 +557,11 @@ class AnimateDiffPipeline(
     def num_timesteps(self):
         return self._num_timesteps
 
-    @property
-    def interrupt(self):
-        return self._interrupt
-
     @torch.no_grad()
     @replace_example_docstring(EXAMPLE_DOC_STRING)
     def __call__(
         self,
-        prompt: Optional[Union[str, List[str]]] = None,
+        prompt: Union[str, List[str]] = None,
         num_frames: Optional[int] = 16,
         height: Optional[int] = None,
         width: Optional[int] = None,
@@ -704,10 +701,9 @@ class AnimateDiffPipeline(
         self._guidance_scale = guidance_scale
         self._clip_skip = clip_skip
         self._cross_attention_kwargs = cross_attention_kwargs
-        self._interrupt = False
 
         # 2. Define call parameters
-        if prompt is not None and isinstance(prompt, (str, dict)):
+        if prompt is not None and isinstance(prompt, str):
             batch_size = 1
         elif prompt is not None and isinstance(prompt, list):
             batch_size = len(prompt)
@@ -720,39 +716,22 @@ class AnimateDiffPipeline(
         text_encoder_lora_scale = (
             self.cross_attention_kwargs.get("scale", None) if self.cross_attention_kwargs is not None else None
         )
-        if self.free_noise_enabled:
-            prompt_embeds, negative_prompt_embeds = self._encode_prompt_free_noise(
-                prompt=prompt,
-                num_frames=num_frames,
-                device=device,
-                num_videos_per_prompt=num_videos_per_prompt,
-                do_classifier_free_guidance=self.do_classifier_free_guidance,
-                negative_prompt=negative_prompt,
-                prompt_embeds=prompt_embeds,
-                negative_prompt_embeds=negative_prompt_embeds,
-                lora_scale=text_encoder_lora_scale,
-                clip_skip=self.clip_skip,
-            )
-        else:
-            prompt_embeds, negative_prompt_embeds = self.encode_prompt(
-                prompt,
-                device,
-                num_videos_per_prompt,
-                self.do_classifier_free_guidance,
-                negative_prompt,
-                prompt_embeds=prompt_embeds,
-                negative_prompt_embeds=negative_prompt_embeds,
-                lora_scale=text_encoder_lora_scale,
-                clip_skip=self.clip_skip,
-            )
-
-            # For classifier free guidance, we need to do two forward passes.
-            # Here we concatenate the unconditional and text embeddings into a single batch
-            # to avoid doing two forward passes
-            if self.do_classifier_free_guidance:
-                prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds])
-
-            prompt_embeds = prompt_embeds.repeat_interleave(repeats=num_frames, dim=0)
+        prompt_embeds, negative_prompt_embeds = self.encode_prompt(
+            prompt,
+            device,
+            num_videos_per_prompt,
+            self.do_classifier_free_guidance,
+            negative_prompt,
+            prompt_embeds=prompt_embeds,
+            negative_prompt_embeds=negative_prompt_embeds,
+            lora_scale=text_encoder_lora_scale,
+            clip_skip=self.clip_skip,
+        )
+        # For classifier free guidance, we need to do two forward passes.
+        # Here we concatenate the unconditional and text embeddings into a single batch
+        # to avoid doing two forward passes
+        if self.do_classifier_free_guidance:
+            prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds])
 
         if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
             image_embeds = self.prepare_ip_adapter_image_embeds(
@@ -804,9 +783,6 @@ class AnimateDiffPipeline(
             # 8. Denoising loop
             with self.progress_bar(total=self._num_timesteps) as progress_bar:
                 for i, t in enumerate(timesteps):
-                    if self.interrupt:
-                        continue
-
                     # expand the latents if we are doing classifier free guidance
                     latent_model_input = torch.cat([latents] * 2) if self.do_classifier_free_guidance else latents
                     latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)

src/diffusers/pipelines/animatediff/pipeline_animatediff_controlnet.py

@@ -505,8 +505,8 @@ class AnimateDiffControlNetPipeline(
             raise ValueError(
                 "Provide either `prompt` or `prompt_embeds`. Cannot leave both `prompt` and `prompt_embeds` undefined."
             )
-        elif prompt is not None and not isinstance(prompt, (str, list, dict)):
-            raise ValueError(f"`prompt` has to be of type `str`, `list` or `dict` but is {type(prompt)}")
+        elif prompt is not None and (not isinstance(prompt, str) and not isinstance(prompt, list)):
+            raise ValueError(f"`prompt` has to be of type `str` or `list` but is {type(prompt)}")
 
         if negative_prompt is not None and negative_prompt_embeds is not None:
             raise ValueError(
@@ -699,10 +699,6 @@ class AnimateDiffControlNetPipeline(
     def num_timesteps(self):
         return self._num_timesteps
 
-    @property
-    def interrupt(self):
-        return self._interrupt
-
     @torch.no_grad()
     def __call__(
         self,
@@ -862,10 +858,9 @@ class AnimateDiffControlNetPipeline(
         self._guidance_scale = guidance_scale
         self._clip_skip = clip_skip
         self._cross_attention_kwargs = cross_attention_kwargs
-        self._interrupt = False
 
         # 2. Define call parameters
-        if prompt is not None and isinstance(prompt, (str, dict)):
+        if prompt is not None and isinstance(prompt, str):
             batch_size = 1
         elif prompt is not None and isinstance(prompt, list):
             batch_size = len(prompt)
@@ -888,39 +883,22 @@ class AnimateDiffControlNetPipeline(
         text_encoder_lora_scale = (
             cross_attention_kwargs.get("scale", None) if cross_attention_kwargs is not None else None
         )
-        if self.free_noise_enabled:
-            prompt_embeds, negative_prompt_embeds = self._encode_prompt_free_noise(
-                prompt=prompt,
-                num_frames=num_frames,
-                device=device,
-                num_videos_per_prompt=num_videos_per_prompt,
-                do_classifier_free_guidance=self.do_classifier_free_guidance,
-                negative_prompt=negative_prompt,
-                prompt_embeds=prompt_embeds,
-                negative_prompt_embeds=negative_prompt_embeds,
-                lora_scale=text_encoder_lora_scale,
-                clip_skip=self.clip_skip,
-            )
-        else:
-            prompt_embeds, negative_prompt_embeds = self.encode_prompt(
-                prompt,
-                device,
-                num_videos_per_prompt,
-                self.do_classifier_free_guidance,
-                negative_prompt,
-                prompt_embeds=prompt_embeds,
-                negative_prompt_embeds=negative_prompt_embeds,
-                lora_scale=text_encoder_lora_scale,
-                clip_skip=self.clip_skip,
-            )
-
-            # For classifier free guidance, we need to do two forward passes.
-            # Here we concatenate the unconditional and text embeddings into a single batch
-            # to avoid doing two forward passes
-            if self.do_classifier_free_guidance:
-                prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds])
-
-            prompt_embeds = prompt_embeds.repeat_interleave(repeats=num_frames, dim=0)
+        prompt_embeds, negative_prompt_embeds = self.encode_prompt(
+            prompt,
+            device,
+            num_videos_per_prompt,
+            self.do_classifier_free_guidance,
+            negative_prompt,
+            prompt_embeds=prompt_embeds,
+            negative_prompt_embeds=negative_prompt_embeds,
+            lora_scale=text_encoder_lora_scale,
+            clip_skip=self.clip_skip,
+        )
+        # For classifier free guidance, we need to do two forward passes.
+        # Here we concatenate the unconditional and text embeddings into a single batch
+        # to avoid doing two forward passes
+        if self.do_classifier_free_guidance:
+            prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds])
 
         if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
             image_embeds = self.prepare_ip_adapter_image_embeds(
@@ -1012,9 +990,6 @@ class AnimateDiffControlNetPipeline(
             # 8. Denoising loop
             with self.progress_bar(total=self._num_timesteps) as progress_bar:
                 for i, t in enumerate(timesteps):
-                    if self.interrupt:
-                        continue
-
                     # expand the latents if we are doing classifier free guidance
                     latent_model_input = torch.cat([latents] * 2) if self.do_classifier_free_guidance else latents
                     latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)
@@ -1027,6 +1002,7 @@ class AnimateDiffControlNetPipeline(
                     else:
                         control_model_input = latent_model_input
                         controlnet_prompt_embeds = prompt_embeds
+                    controlnet_prompt_embeds = controlnet_prompt_embeds.repeat_interleave(num_frames, dim=0)
 
                     if isinstance(controlnet_keep[i], list):
                         cond_scale = [c * s for c, s in zip(controlnet_conditioning_scale, controlnet_keep[i])]

src/diffusers/pipelines/animatediff/pipeline_animatediff_sdxl.py

@@ -1143,8 +1143,6 @@ class AnimateDiffSDXLPipeline(
             add_text_embeds = torch.cat([negative_pooled_prompt_embeds, add_text_embeds], dim=0)
             add_time_ids = torch.cat([negative_add_time_ids, add_time_ids], dim=0)
 
-        prompt_embeds = prompt_embeds.repeat_interleave(repeats=num_frames, dim=0)
-
         prompt_embeds = prompt_embeds.to(device)
         add_text_embeds = add_text_embeds.to(device)
         add_time_ids = add_time_ids.to(device).repeat(batch_size * num_videos_per_prompt, 1)

src/diffusers/pipelines/animatediff/pipeline_animatediff_sparsectrl.py

@@ -878,8 +878,6 @@ class AnimateDiffSparseControlNetPipeline(
         if self.do_classifier_free_guidance:
             prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds])
 
-        prompt_embeds = prompt_embeds.repeat_interleave(repeats=num_frames, dim=0)
-
         # 4. Prepare IP-Adapter embeddings
         if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
             image_embeds = self.prepare_ip_adapter_image_embeds(

src/diffusers/pipelines/animatediff/pipeline_animatediff_video2video.py

@@ -246,6 +246,7 @@ class AnimateDiffVideoToVideoPipeline(
         self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
         self.video_processor = VideoProcessor(vae_scale_factor=self.vae_scale_factor)
 
+    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.encode_prompt with num_images_per_prompt -> num_videos_per_prompt
     def encode_prompt(
         self,
         prompt,
@@ -298,7 +299,7 @@ class AnimateDiffVideoToVideoPipeline(
             else:
                 scale_lora_layers(self.text_encoder, lora_scale)
 
-        if prompt is not None and isinstance(prompt, (str, dict)):
+        if prompt is not None and isinstance(prompt, str):
             batch_size = 1
         elif prompt is not None and isinstance(prompt, list):
             batch_size = len(prompt)
@@ -581,8 +582,8 @@ class AnimateDiffVideoToVideoPipeline(
             raise ValueError(
                 "Provide either `prompt` or `prompt_embeds`. Cannot leave both `prompt` and `prompt_embeds` undefined."
             )
-        elif prompt is not None and not isinstance(prompt, (str, list, dict)):
-            raise ValueError(f"`prompt` has to be of type `str`, `list` or `dict` but is {type(prompt)}")
+        elif prompt is not None and (not isinstance(prompt, str) and not isinstance(prompt, list)):
+            raise ValueError(f"`prompt` has to be of type `str` or `list` but is {type(prompt)}")
 
         if negative_prompt is not None and negative_prompt_embeds is not None:
             raise ValueError(
@@ -627,20 +628,23 @@ class AnimateDiffVideoToVideoPipeline(
 
     def prepare_latents(
         self,
-        video: Optional[torch.Tensor] = None,
-        height: int = 64,
-        width: int = 64,
-        num_channels_latents: int = 4,
-        batch_size: int = 1,
-        timestep: Optional[int] = None,
-        dtype: Optional[torch.dtype] = None,
-        device: Optional[torch.device] = None,
-        generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
-        latents: Optional[torch.Tensor] = None,
+        video,
+        height,
+        width,
+        num_channels_latents,
+        batch_size,
+        timestep,
+        dtype,
+        device,
+        generator,
+        latents=None,
         decode_chunk_size: int = 16,
-        add_noise: bool = False,
-    ) -> torch.Tensor:
-        num_frames = video.shape[1] if latents is None else latents.shape[2]
+    ):
+        if latents is None:
+            num_frames = video.shape[1]
+        else:
+            num_frames = latents.shape[2]
+
         shape = (
             batch_size,
             num_channels_latents,
@@ -704,13 +708,8 @@ class AnimateDiffVideoToVideoPipeline(
             if shape != latents.shape:
                 # [B, C, F, H, W]
                 raise ValueError(f"`latents` expected to have {shape=}, but found {latents.shape=}")
-
             latents = latents.to(device, dtype=dtype)
 
-            if add_noise:
-                noise = randn_tensor(shape, generator=generator, device=device, dtype=dtype)
-                latents = self.scheduler.add_noise(latents, noise, timestep)
-
         return latents
 
     @property
@@ -736,10 +735,6 @@ class AnimateDiffVideoToVideoPipeline(
     def num_timesteps(self):
         return self._num_timesteps
 
-    @property
-    def interrupt(self):
-        return self._interrupt
-
     @torch.no_grad()
     def __call__(
         self,
@@ -748,7 +743,6 @@ class AnimateDiffVideoToVideoPipeline(
         height: Optional[int] = None,
         width: Optional[int] = None,
         num_inference_steps: int = 50,
-        enforce_inference_steps: bool = False,
         timesteps: Optional[List[int]] = None,
         sigmas: Optional[List[float]] = None,
         guidance_scale: float = 7.5,
@@ -880,10 +874,9 @@ class AnimateDiffVideoToVideoPipeline(
         self._guidance_scale = guidance_scale
         self._clip_skip = clip_skip
         self._cross_attention_kwargs = cross_attention_kwargs
-        self._interrupt = False
 
         # 2. Define call parameters
-        if prompt is not None and isinstance(prompt, (str, dict)):
+        if prompt is not None and isinstance(prompt, str):
             batch_size = 1
         elif prompt is not None and isinstance(prompt, list):
             batch_size = len(prompt)
@@ -891,85 +884,29 @@ class AnimateDiffVideoToVideoPipeline(
             batch_size = prompt_embeds.shape[0]
 
         device = self._execution_device
-        dtype = self.dtype
 
-        # 3. Prepare timesteps
-        if not enforce_inference_steps:
-            timesteps, num_inference_steps = retrieve_timesteps(
-                self.scheduler, num_inference_steps, device, timesteps, sigmas
-            )
-            timesteps, num_inference_steps = self.get_timesteps(num_inference_steps, timesteps, strength, device)
-            latent_timestep = timesteps[:1].repeat(batch_size * num_videos_per_prompt)
-        else:
-            denoising_inference_steps = int(num_inference_steps / strength)
-            timesteps, denoising_inference_steps = retrieve_timesteps(
-                self.scheduler, denoising_inference_steps, device, timesteps, sigmas
-            )
-            timesteps = timesteps[-num_inference_steps:]
-            latent_timestep = timesteps[:1].repeat(batch_size * num_videos_per_prompt)
-
-        # 4. Prepare latent variables
-        if latents is None:
-            video = self.video_processor.preprocess_video(video, height=height, width=width)
-            # Move the number of frames before the number of channels.
-            video = video.permute(0, 2, 1, 3, 4)
-            video = video.to(device=device, dtype=dtype)
-        num_channels_latents = self.unet.config.in_channels
-        latents = self.prepare_latents(
-            video=video,
-            height=height,
-            width=width,
-            num_channels_latents=num_channels_latents,
-            batch_size=batch_size * num_videos_per_prompt,
-            timestep=latent_timestep,
-            dtype=dtype,
-            device=device,
-            generator=generator,
-            latents=latents,
-            decode_chunk_size=decode_chunk_size,
-            add_noise=enforce_inference_steps,
-        )
-
-        # 5. Encode input prompt
+        # 3. Encode input prompt
         text_encoder_lora_scale = (
             self.cross_attention_kwargs.get("scale", None) if self.cross_attention_kwargs is not None else None
         )
-        num_frames = latents.shape[2]
-        if self.free_noise_enabled:
-            prompt_embeds, negative_prompt_embeds = self._encode_prompt_free_noise(
-                prompt=prompt,
-                num_frames=num_frames,
-                device=device,
-                num_videos_per_prompt=num_videos_per_prompt,
-                do_classifier_free_guidance=self.do_classifier_free_guidance,
-                negative_prompt=negative_prompt,
-                prompt_embeds=prompt_embeds,
-                negative_prompt_embeds=negative_prompt_embeds,
-                lora_scale=text_encoder_lora_scale,
-                clip_skip=self.clip_skip,
-            )
-        else:
-            prompt_embeds, negative_prompt_embeds = self.encode_prompt(
-                prompt,
-                device,
-                num_videos_per_prompt,
-                self.do_classifier_free_guidance,
-                negative_prompt,
-                prompt_embeds=prompt_embeds,
-                negative_prompt_embeds=negative_prompt_embeds,
-                lora_scale=text_encoder_lora_scale,
-                clip_skip=self.clip_skip,
-            )
+        prompt_embeds, negative_prompt_embeds = self.encode_prompt(
+            prompt,
+            device,
+            num_videos_per_prompt,
+            self.do_classifier_free_guidance,
+            negative_prompt,
+            prompt_embeds=prompt_embeds,
+            negative_prompt_embeds=negative_prompt_embeds,
+            lora_scale=text_encoder_lora_scale,
+            clip_skip=self.clip_skip,
+        )
 
-            # For classifier free guidance, we need to do two forward passes.
-            # Here we concatenate the unconditional and text embeddings into a single batch
-            # to avoid doing two forward passes
-            if self.do_classifier_free_guidance:
-                prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds])
+        # For classifier free guidance, we need to do two forward passes.
+        # Here we concatenate the unconditional and text embeddings into a single batch
+        # to avoid doing two forward passes
+        if self.do_classifier_free_guidance:
+            prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds])
 
-            prompt_embeds = prompt_embeds.repeat_interleave(repeats=num_frames, dim=0)
-
-        # 6. Prepare IP-Adapter embeddings
         if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
             image_embeds = self.prepare_ip_adapter_image_embeds(
                 ip_adapter_image,
@@ -979,10 +916,38 @@ class AnimateDiffVideoToVideoPipeline(
                 self.do_classifier_free_guidance,
             )
 
-        # 7. Prepare extra step kwargs. TODO: Logic should ideally just be moved out of the pipeline
+        # 4. Prepare timesteps
+        timesteps, num_inference_steps = retrieve_timesteps(
+            self.scheduler, num_inference_steps, device, timesteps, sigmas
+        )
+        timesteps, num_inference_steps = self.get_timesteps(num_inference_steps, timesteps, strength, device)
+        latent_timestep = timesteps[:1].repeat(batch_size * num_videos_per_prompt)
+
+        # 5. Prepare latent variables
+        if latents is None:
+            video = self.video_processor.preprocess_video(video, height=height, width=width)
+            # Move the number of frames before the number of channels.
+            video = video.permute(0, 2, 1, 3, 4)
+            video = video.to(device=device, dtype=prompt_embeds.dtype)
+        num_channels_latents = self.unet.config.in_channels
+        latents = self.prepare_latents(
+            video=video,
+            height=height,
+            width=width,
+            num_channels_latents=num_channels_latents,
+            batch_size=batch_size * num_videos_per_prompt,
+            timestep=latent_timestep,
+            dtype=prompt_embeds.dtype,
+            device=device,
+            generator=generator,
+            latents=latents,
+            decode_chunk_size=decode_chunk_size,
+        )
+
+        # 6. Prepare extra step kwargs. TODO: Logic should ideally just be moved out of the pipeline
         extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)
 
-        # 8. Add image embeds for IP-Adapter
+        # 7. Add image embeds for IP-Adapter
         added_cond_kwargs = (
             {"image_embeds": image_embeds}
             if ip_adapter_image is not None or ip_adapter_image_embeds is not None
@@ -1002,12 +967,9 @@ class AnimateDiffVideoToVideoPipeline(
             self._num_timesteps = len(timesteps)
             num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order
 
-            # 9. Denoising loop
+            # 8. Denoising loop
             with self.progress_bar(total=self._num_timesteps) as progress_bar:
                 for i, t in enumerate(timesteps):
-                    if self.interrupt:
-                        continue
-
                     # expand the latents if we are doing classifier free guidance
                     latent_model_input = torch.cat([latents] * 2) if self.do_classifier_free_guidance else latents
                     latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)
@@ -1043,14 +1005,14 @@ class AnimateDiffVideoToVideoPipeline(
                     if i == len(timesteps) - 1 or ((i + 1) > num_warmup_steps and (i + 1) % self.scheduler.order == 0):
                         progress_bar.update()
 
-        # 10. Post-processing
+        # 9. Post-processing
         if output_type == "latent":
             video = latents
         else:
             video_tensor = self.decode_latents(latents, decode_chunk_size)
             video = self.video_processor.postprocess_video(video=video_tensor, output_type=output_type)
 
-        # 11. Offload all models
+        # 10. Offload all models
         self.maybe_free_model_hooks()
 
         if not return_dict:

src/diffusers/pipelines/auto_pipeline.py

@@ -49,14 +49,12 @@ from .kandinsky2_2 import (
 )
 from .kandinsky3 import Kandinsky3Img2ImgPipeline, Kandinsky3Pipeline
 from .latent_consistency_models import LatentConsistencyModelImg2ImgPipeline, LatentConsistencyModelPipeline
-from .lumina import LuminaText2ImgPipeline
 from .pag import (
     HunyuanDiTPAGPipeline,
     PixArtSigmaPAGPipeline,
     StableDiffusion3PAGPipeline,
     StableDiffusionControlNetPAGPipeline,
     StableDiffusionPAGPipeline,
-    StableDiffusionXLControlNetPAGImg2ImgPipeline,
     StableDiffusionXLControlNetPAGPipeline,
     StableDiffusionXLPAGImg2ImgPipeline,
     StableDiffusionXLPAGInpaintPipeline,
@@ -108,7 +106,6 @@ AUTO_TEXT2IMAGE_PIPELINES_MAPPING = OrderedDict(
         ("pixart-sigma-pag", PixArtSigmaPAGPipeline),
         ("auraflow", AuraFlowPipeline),
         ("flux", FluxPipeline),
-        ("lumina", LuminaText2ImgPipeline),
     ]
 )
 
@@ -124,7 +121,6 @@ AUTO_IMAGE2IMAGE_PIPELINES_MAPPING = OrderedDict(
         ("stable-diffusion-controlnet", StableDiffusionControlNetImg2ImgPipeline),
         ("stable-diffusion-xl-controlnet", StableDiffusionXLControlNetImg2ImgPipeline),
         ("stable-diffusion-xl-pag", StableDiffusionXLPAGImg2ImgPipeline),
-        ("stable-diffusion-xl-controlnet-pag", StableDiffusionXLControlNetPAGImg2ImgPipeline),
         ("lcm", LatentConsistencyModelImg2ImgPipeline),
     ]
 )
@@ -165,12 +161,12 @@ _AUTO_INPAINT_DECODER_PIPELINES_MAPPING = OrderedDict(
 )
 
 if is_sentencepiece_available():
-    from .kolors import KolorsImg2ImgPipeline, KolorsPipeline
+    from .kolors import KolorsPipeline
     from .pag import KolorsPAGPipeline
 
     AUTO_TEXT2IMAGE_PIPELINES_MAPPING["kolors"] = KolorsPipeline
     AUTO_TEXT2IMAGE_PIPELINES_MAPPING["kolors-pag"] = KolorsPAGPipeline
-    AUTO_IMAGE2IMAGE_PIPELINES_MAPPING["kolors"] = KolorsImg2ImgPipeline
+    AUTO_IMAGE2IMAGE_PIPELINES_MAPPING["kolors"] = KolorsPipeline
 
 SUPPORTED_TASKS_MAPPINGS = [
     AUTO_TEXT2IMAGE_PIPELINES_MAPPING,
@@ -957,8 +953,7 @@ class AutoPipelineForInpainting(ConfigMixin):
         if "enable_pag" in kwargs:
             enable_pag = kwargs.pop("enable_pag")
             if enable_pag:
-                to_replace = "InpaintPipeline" if "Inpaint" in config["_class_name"] else "Pipeline"
-                orig_class_name = config["_class_name"].replace(to_replace, "PAG" + to_replace)
+                orig_class_name = config["_class_name"].replace("Pipeline", "PAGPipeline")
 
         inpainting_cls = _get_task_class(AUTO_INPAINT_PIPELINES_MAPPING, orig_class_name)
 

src/diffusers/pipelines/cogvideo/__init__.py

@@ -23,7 +23,6 @@ except OptionalDependencyNotAvailable:
     _dummy_objects.update(get_objects_from_module(dummy_torch_and_transformers_objects))
 else:
     _import_structure["pipeline_cogvideox"] = ["CogVideoXPipeline"]
-    _import_structure["pipeline_cogvideox_video2video"] = ["CogVideoXVideoToVideoPipeline"]
 
 if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
     try:
@@ -34,7 +33,6 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
         from ...utils.dummy_torch_and_transformers_objects import *
     else:
         from .pipeline_cogvideox import CogVideoXPipeline
-        from .pipeline_cogvideox_video2video import CogVideoXVideoToVideoPipeline
 
 else:
     import sys

src/diffusers/pipelines/cogvideo/pipeline_cogvideox.py

@@ -15,6 +15,7 @@
 
 import inspect
 import math
+from dataclasses import dataclass
 from typing import Callable, Dict, List, Optional, Tuple, Union
 
 import torch
@@ -25,10 +26,9 @@ from ...models import AutoencoderKLCogVideoX, CogVideoXTransformer3DModel
 from ...models.embeddings import get_3d_rotary_pos_embed
 from ...pipelines.pipeline_utils import DiffusionPipeline
 from ...schedulers import CogVideoXDDIMScheduler, CogVideoXDPMScheduler
-from ...utils import logging, replace_example_docstring
+from ...utils import BaseOutput, logging, replace_example_docstring
 from ...utils.torch_utils import randn_tensor
 from ...video_processor import VideoProcessor
-from .pipeline_output import CogVideoXPipelineOutput
 
 
 logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
@@ -136,6 +136,21 @@ def retrieve_timesteps(
     return timesteps, num_inference_steps
 
 
+@dataclass
+class CogVideoXPipelineOutput(BaseOutput):
+    r"""
+    Output class for CogVideo pipelines.
+
+    Args:
+        frames (`torch.Tensor`, `np.ndarray`, or List[List[PIL.Image.Image]]):
+            List of video outputs - It can be a nested list of length `batch_size,` with each sub-list containing
+            denoised PIL image sequences of length `num_frames.` It can also be a NumPy array or Torch tensor of shape
+            `(batch_size, num_frames, channels, height, width)`.
+    """
+
+    frames: torch.Tensor
+
+
 class CogVideoXPipeline(DiffusionPipeline):
     r"""
     Pipeline for text-to-video generation using CogVideoX.
@@ -448,6 +463,7 @@ class CogVideoXPipeline(DiffusionPipeline):
             crops_coords=grid_crops_coords,
             grid_size=(grid_height, grid_width),
             temporal_size=num_frames,
+            use_real=True,
         )
 
         freqs_cos = freqs_cos.to(device=device)

src/diffusers/pipelines/cogvideo/pipeline_cogvideox_video2video.py

@@ -1,812 +0,0 @@
-# Copyright 2024 The CogVideoX team, Tsinghua University & ZhipuAI and 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 inspect
-import math
-from typing import Callable, Dict, List, Optional, Tuple, Union
-
-import torch
-from PIL import Image
-from transformers import T5EncoderModel, T5Tokenizer
-
-from ...callbacks import MultiPipelineCallbacks, PipelineCallback
-from ...models import AutoencoderKLCogVideoX, CogVideoXTransformer3DModel
-from ...models.embeddings import get_3d_rotary_pos_embed
-from ...pipelines.pipeline_utils import DiffusionPipeline
-from ...schedulers import CogVideoXDDIMScheduler, CogVideoXDPMScheduler
-from ...utils import (
-    logging,
-    replace_example_docstring,
-)
-from ...utils.torch_utils import randn_tensor
-from ...video_processor import VideoProcessor
-from .pipeline_output import CogVideoXPipelineOutput
-
-
-logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
-
-
-EXAMPLE_DOC_STRING = """
-    Examples:
-        ```python
-        >>> import torch
-        >>> from diffusers import CogVideoXDPMScheduler, CogVideoXVideoToVideoPipeline
-        >>> from diffusers.utils import export_to_video, load_video
-
-        >>> # Models: "THUDM/CogVideoX-2b" or "THUDM/CogVideoX-5b"
-        >>> pipe = CogVideoXVideoToVideoPipeline.from_pretrained("THUDM/CogVideoX-5b", torch_dtype=torch.bfloat16)
-        >>> pipe.to("cuda")
-        >>> pipe.scheduler = CogVideoXDPMScheduler.from_config(pipe.scheduler.config)
-
-        >>> input_video = load_video(
-        ...     "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/hiker.mp4"
-        ... )
-        >>> prompt = (
-        ...     "An astronaut stands triumphantly at the peak of a towering mountain. Panorama of rugged peaks and "
-        ...     "valleys. Very futuristic vibe and animated aesthetic. Highlights of purple and golden colors in "
-        ...     "the scene. The sky is looks like an animated/cartoonish dream of galaxies, nebulae, stars, planets, "
-        ...     "moons, but the remainder of the scene is mostly realistic."
-        ... )
-
-        >>> video = pipe(
-        ...     video=input_video, prompt=prompt, strength=0.8, guidance_scale=6, num_inference_steps=50
-        ... ).frames[0]
-        >>> export_to_video(video, "output.mp4", fps=8)
-        ```
-"""
-
-
-# Similar to diffusers.pipelines.hunyuandit.pipeline_hunyuandit.get_resize_crop_region_for_grid
-def get_resize_crop_region_for_grid(src, tgt_width, tgt_height):
-    tw = tgt_width
-    th = tgt_height
-    h, w = src
-    r = h / w
-    if r > (th / tw):
-        resize_height = th
-        resize_width = int(round(th / h * w))
-    else:
-        resize_width = tw
-        resize_height = int(round(tw / w * h))
-
-    crop_top = int(round((th - resize_height) / 2.0))
-    crop_left = int(round((tw - resize_width) / 2.0))
-
-    return (crop_top, crop_left), (crop_top + resize_height, crop_left + resize_width)
-
-
-# Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.retrieve_timesteps
-def retrieve_timesteps(
-    scheduler,
-    num_inference_steps: Optional[int] = None,
-    device: Optional[Union[str, torch.device]] = None,
-    timesteps: Optional[List[int]] = None,
-    sigmas: Optional[List[float]] = None,
-    **kwargs,
-):
-    """
-    Calls the scheduler's `set_timesteps` method and retrieves timesteps from the scheduler after the call. Handles
-    custom timesteps. Any kwargs will be supplied to `scheduler.set_timesteps`.
-
-    Args:
-        scheduler (`SchedulerMixin`):
-            The scheduler to get timesteps from.
-        num_inference_steps (`int`):
-            The number of diffusion steps used when generating samples with a pre-trained model. If used, `timesteps`
-            must be `None`.
-        device (`str` or `torch.device`, *optional*):
-            The device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
-        timesteps (`List[int]`, *optional*):
-            Custom timesteps used to override the timestep spacing strategy of the scheduler. If `timesteps` is passed,
-            `num_inference_steps` and `sigmas` must be `None`.
-        sigmas (`List[float]`, *optional*):
-            Custom sigmas used to override the timestep spacing strategy of the scheduler. If `sigmas` is passed,
-            `num_inference_steps` and `timesteps` must be `None`.
-
-    Returns:
-        `Tuple[torch.Tensor, int]`: A tuple where the first element is the timestep schedule from the scheduler and the
-        second element is the number of inference steps.
-    """
-    if timesteps is not None and sigmas is not None:
-        raise ValueError("Only one of `timesteps` or `sigmas` can be passed. Please choose one to set custom values")
-    if timesteps is not None:
-        accepts_timesteps = "timesteps" in set(inspect.signature(scheduler.set_timesteps).parameters.keys())
-        if not accepts_timesteps:
-            raise ValueError(
-                f"The current scheduler class {scheduler.__class__}'s `set_timesteps` does not support custom"
-                f" timestep schedules. Please check whether you are using the correct scheduler."
-            )
-        scheduler.set_timesteps(timesteps=timesteps, device=device, **kwargs)
-        timesteps = scheduler.timesteps
-        num_inference_steps = len(timesteps)
-    elif sigmas is not None:
-        accept_sigmas = "sigmas" in set(inspect.signature(scheduler.set_timesteps).parameters.keys())
-        if not accept_sigmas:
-            raise ValueError(
-                f"The current scheduler class {scheduler.__class__}'s `set_timesteps` does not support custom"
-                f" sigmas schedules. Please check whether you are using the correct scheduler."
-            )
-        scheduler.set_timesteps(sigmas=sigmas, device=device, **kwargs)
-        timesteps = scheduler.timesteps
-        num_inference_steps = len(timesteps)
-    else:
-        scheduler.set_timesteps(num_inference_steps, device=device, **kwargs)
-        timesteps = scheduler.timesteps
-    return timesteps, num_inference_steps
-
-
-# Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_img2img.retrieve_latents
-def retrieve_latents(
-    encoder_output: torch.Tensor, generator: Optional[torch.Generator] = None, sample_mode: str = "sample"
-):
-    if hasattr(encoder_output, "latent_dist") and sample_mode == "sample":
-        return encoder_output.latent_dist.sample(generator)
-    elif hasattr(encoder_output, "latent_dist") and sample_mode == "argmax":
-        return encoder_output.latent_dist.mode()
-    elif hasattr(encoder_output, "latents"):
-        return encoder_output.latents
-    else:
-        raise AttributeError("Could not access latents of provided encoder_output")
-
-
-class CogVideoXVideoToVideoPipeline(DiffusionPipeline):
-    r"""
-    Pipeline for video-to-video generation using CogVideoX.
-
-    This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for the generic methods the
-    library implements for all the pipelines (such as downloading or saving, running on a particular device, etc.)
-
-    Args:
-        vae ([`AutoencoderKL`]):
-            Variational Auto-Encoder (VAE) Model to encode and decode videos to and from latent representations.
-        text_encoder ([`T5EncoderModel`]):
-            Frozen text-encoder. CogVideoX uses
-            [T5](https://huggingface.co/docs/transformers/model_doc/t5#transformers.T5EncoderModel); specifically the
-            [t5-v1_1-xxl](https://huggingface.co/PixArt-alpha/PixArt-alpha/tree/main/t5-v1_1-xxl) variant.
-        tokenizer (`T5Tokenizer`):
-            Tokenizer of class
-            [T5Tokenizer](https://huggingface.co/docs/transformers/model_doc/t5#transformers.T5Tokenizer).
-        transformer ([`CogVideoXTransformer3DModel`]):
-            A text conditioned `CogVideoXTransformer3DModel` to denoise the encoded video latents.
-        scheduler ([`SchedulerMixin`]):
-            A scheduler to be used in combination with `transformer` to denoise the encoded video latents.
-    """
-
-    _optional_components = []
-    model_cpu_offload_seq = "text_encoder->transformer->vae"
-
-    _callback_tensor_inputs = [
-        "latents",
-        "prompt_embeds",
-        "negative_prompt_embeds",
-    ]
-
-    def __init__(
-        self,
-        tokenizer: T5Tokenizer,
-        text_encoder: T5EncoderModel,
-        vae: AutoencoderKLCogVideoX,
-        transformer: CogVideoXTransformer3DModel,
-        scheduler: Union[CogVideoXDDIMScheduler, CogVideoXDPMScheduler],
-    ):
-        super().__init__()
-
-        self.register_modules(
-            tokenizer=tokenizer, text_encoder=text_encoder, vae=vae, transformer=transformer, scheduler=scheduler
-        )
-        self.vae_scale_factor_spatial = (
-            2 ** (len(self.vae.config.block_out_channels) - 1) if hasattr(self, "vae") and self.vae is not None else 8
-        )
-        self.vae_scale_factor_temporal = (
-            self.vae.config.temporal_compression_ratio if hasattr(self, "vae") and self.vae is not None else 4
-        )
-
-        self.video_processor = VideoProcessor(vae_scale_factor=self.vae_scale_factor_spatial)
-
-    # Copied from diffusers.pipelines.cogvideo.pipeline_cogvideox.CogVideoXPipeline._get_t5_prompt_embeds
-    def _get_t5_prompt_embeds(
-        self,
-        prompt: Union[str, List[str]] = None,
-        num_videos_per_prompt: int = 1,
-        max_sequence_length: int = 226,
-        device: Optional[torch.device] = None,
-        dtype: Optional[torch.dtype] = None,
-    ):
-        device = device or self._execution_device
-        dtype = dtype or self.text_encoder.dtype
-
-        prompt = [prompt] if isinstance(prompt, str) else prompt
-        batch_size = len(prompt)
-
-        text_inputs = self.tokenizer(
-            prompt,
-            padding="max_length",
-            max_length=max_sequence_length,
-            truncation=True,
-            add_special_tokens=True,
-            return_tensors="pt",
-        )
-        text_input_ids = text_inputs.input_ids
-        untruncated_ids = self.tokenizer(prompt, padding="longest", return_tensors="pt").input_ids
-
-        if untruncated_ids.shape[-1] >= text_input_ids.shape[-1] and not torch.equal(text_input_ids, untruncated_ids):
-            removed_text = self.tokenizer.batch_decode(untruncated_ids[:, max_sequence_length - 1 : -1])
-            logger.warning(
-                "The following part of your input was truncated because `max_sequence_length` is set to "
-                f" {max_sequence_length} tokens: {removed_text}"
-            )
-
-        prompt_embeds = self.text_encoder(text_input_ids.to(device))[0]
-        prompt_embeds = prompt_embeds.to(dtype=dtype, device=device)
-
-        # duplicate text embeddings for each generation per prompt, using mps friendly method
-        _, seq_len, _ = prompt_embeds.shape
-        prompt_embeds = prompt_embeds.repeat(1, num_videos_per_prompt, 1)
-        prompt_embeds = prompt_embeds.view(batch_size * num_videos_per_prompt, seq_len, -1)
-
-        return prompt_embeds
-
-    # Copied from diffusers.pipelines.cogvideo.pipeline_cogvideox.CogVideoXPipeline.encode_prompt
-    def encode_prompt(
-        self,
-        prompt: Union[str, List[str]],
-        negative_prompt: Optional[Union[str, List[str]]] = None,
-        do_classifier_free_guidance: bool = True,
-        num_videos_per_prompt: int = 1,
-        prompt_embeds: Optional[torch.Tensor] = None,
-        negative_prompt_embeds: Optional[torch.Tensor] = None,
-        max_sequence_length: int = 226,
-        device: Optional[torch.device] = None,
-        dtype: Optional[torch.dtype] = None,
-    ):
-        r"""
-        Encodes the prompt into text encoder hidden states.
-
-        Args:
-            prompt (`str` or `List[str]`, *optional*):
-                prompt to be encoded
-            negative_prompt (`str` or `List[str]`, *optional*):
-                The prompt or prompts not to guide the image generation. If not defined, one has to pass
-                `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
-                less than `1`).
-            do_classifier_free_guidance (`bool`, *optional*, defaults to `True`):
-                Whether to use classifier free guidance or not.
-            num_videos_per_prompt (`int`, *optional*, defaults to 1):
-                Number of videos that should be generated per prompt. torch device to place the resulting embeddings on
-            prompt_embeds (`torch.Tensor`, *optional*):
-                Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
-                provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.Tensor`, *optional*):
-                Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
-                weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
-                argument.
-            device: (`torch.device`, *optional*):
-                torch device
-            dtype: (`torch.dtype`, *optional*):
-                torch dtype
-        """
-        device = device or self._execution_device
-
-        prompt = [prompt] if isinstance(prompt, str) else prompt
-        if prompt is not None:
-            batch_size = len(prompt)
-        else:
-            batch_size = prompt_embeds.shape[0]
-
-        if prompt_embeds is None:
-            prompt_embeds = self._get_t5_prompt_embeds(
-                prompt=prompt,
-                num_videos_per_prompt=num_videos_per_prompt,
-                max_sequence_length=max_sequence_length,
-                device=device,
-                dtype=dtype,
-            )
-
-        if do_classifier_free_guidance and negative_prompt_embeds is None:
-            negative_prompt = negative_prompt or ""
-            negative_prompt = batch_size * [negative_prompt] if isinstance(negative_prompt, str) else negative_prompt
-
-            if prompt is not None and type(prompt) is not type(negative_prompt):
-                raise TypeError(
-                    f"`negative_prompt` should be the same type to `prompt`, but got {type(negative_prompt)} !="
-                    f" {type(prompt)}."
-                )
-            elif batch_size != len(negative_prompt):
-                raise ValueError(
-                    f"`negative_prompt`: {negative_prompt} has batch size {len(negative_prompt)}, but `prompt`:"
-                    f" {prompt} has batch size {batch_size}. Please make sure that passed `negative_prompt` matches"
-                    " the batch size of `prompt`."
-                )
-
-            negative_prompt_embeds = self._get_t5_prompt_embeds(
-                prompt=negative_prompt,
-                num_videos_per_prompt=num_videos_per_prompt,
-                max_sequence_length=max_sequence_length,
-                device=device,
-                dtype=dtype,
-            )
-
-        return prompt_embeds, negative_prompt_embeds
-
-    def prepare_latents(
-        self,
-        video: Optional[torch.Tensor] = None,
-        batch_size: int = 1,
-        num_channels_latents: int = 16,
-        height: int = 60,
-        width: int = 90,
-        dtype: Optional[torch.dtype] = None,
-        device: Optional[torch.device] = None,
-        generator: Optional[torch.Generator] = None,
-        latents: Optional[torch.Tensor] = None,
-        timestep: Optional[torch.Tensor] = None,
-    ):
-        num_frames = (video.size(2) - 1) // self.vae_scale_factor_temporal + 1 if latents is None else latents.size(1)
-
-        shape = (
-            batch_size,
-            num_frames,
-            num_channels_latents,
-            height // self.vae_scale_factor_spatial,
-            width // self.vae_scale_factor_spatial,
-        )
-
-        if isinstance(generator, list) and len(generator) != batch_size:
-            raise ValueError(
-                f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
-                f" size of {batch_size}. Make sure the batch size matches the length of the generators."
-            )
-
-        if latents is None:
-            if isinstance(generator, list):
-                if len(generator) != batch_size:
-                    raise ValueError(
-                        f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
-                        f" size of {batch_size}. Make sure the batch size matches the length of the generators."
-                    )
-
-                init_latents = [
-                    retrieve_latents(self.vae.encode(video[i].unsqueeze(0)), generator[i]) for i in range(batch_size)
-                ]
-            else:
-                init_latents = [retrieve_latents(self.vae.encode(vid.unsqueeze(0)), generator) for vid in video]
-
-            init_latents = torch.cat(init_latents, dim=0).to(dtype).permute(0, 2, 1, 3, 4)  # [B, F, C, H, W]
-            init_latents = self.vae.config.scaling_factor * init_latents
-
-            noise = randn_tensor(shape, generator=generator, device=device, dtype=dtype)
-            latents = self.scheduler.add_noise(init_latents, noise, timestep)
-        else:
-            latents = latents.to(device)
-
-        # scale the initial noise by the standard deviation required by the scheduler
-        latents = latents * self.scheduler.init_noise_sigma
-        return latents
-
-    # Copied from diffusers.pipelines.cogvideo.pipeline_cogvideox.CogVideoXPipeline.decode_latents
-    def decode_latents(self, latents: torch.Tensor) -> torch.Tensor:
-        latents = latents.permute(0, 2, 1, 3, 4)  # [batch_size, num_channels, num_frames, height, width]
-        latents = 1 / self.vae.config.scaling_factor * latents
-
-        frames = self.vae.decode(latents).sample
-        return frames
-
-    # Copied from diffusers.pipelines.animatediff.pipeline_animatediff_video2video.AnimateDiffVideoToVideoPipeline.get_timesteps
-    def get_timesteps(self, num_inference_steps, timesteps, strength, device):
-        # get the original timestep using init_timestep
-        init_timestep = min(int(num_inference_steps * strength), num_inference_steps)
-
-        t_start = max(num_inference_steps - init_timestep, 0)
-        timesteps = timesteps[t_start * self.scheduler.order :]
-
-        return timesteps, num_inference_steps - t_start
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_extra_step_kwargs
-    def prepare_extra_step_kwargs(self, generator, eta):
-        # prepare extra kwargs for the scheduler step, since not all schedulers have the same signature
-        # eta (η) is only used with the DDIMScheduler, it will be ignored for other schedulers.
-        # eta corresponds to η in DDIM paper: https://arxiv.org/abs/2010.02502
-        # and should be between [0, 1]
-
-        accepts_eta = "eta" in set(inspect.signature(self.scheduler.step).parameters.keys())
-        extra_step_kwargs = {}
-        if accepts_eta:
-            extra_step_kwargs["eta"] = eta
-
-        # check if the scheduler accepts generator
-        accepts_generator = "generator" in set(inspect.signature(self.scheduler.step).parameters.keys())
-        if accepts_generator:
-            extra_step_kwargs["generator"] = generator
-        return extra_step_kwargs
-
-    def check_inputs(
-        self,
-        prompt,
-        height,
-        width,
-        strength,
-        negative_prompt,
-        callback_on_step_end_tensor_inputs,
-        video=None,
-        latents=None,
-        prompt_embeds=None,
-        negative_prompt_embeds=None,
-    ):
-        if height % 8 != 0 or width % 8 != 0:
-            raise ValueError(f"`height` and `width` have to be divisible by 8 but are {height} and {width}.")
-
-        if strength < 0 or strength > 1:
-            raise ValueError(f"The value of strength should in [0.0, 1.0] but is {strength}")
-
-        if callback_on_step_end_tensor_inputs is not None and not all(
-            k in self._callback_tensor_inputs for k in callback_on_step_end_tensor_inputs
-        ):
-            raise ValueError(
-                f"`callback_on_step_end_tensor_inputs` has to be in {self._callback_tensor_inputs}, but found {[k for k in callback_on_step_end_tensor_inputs if k not in self._callback_tensor_inputs]}"
-            )
-        if prompt is not None and prompt_embeds is not None:
-            raise ValueError(
-                f"Cannot forward both `prompt`: {prompt} and `prompt_embeds`: {prompt_embeds}. Please make sure to"
-                " only forward one of the two."
-            )
-        elif prompt is None and prompt_embeds is None:
-            raise ValueError(
-                "Provide either `prompt` or `prompt_embeds`. Cannot leave both `prompt` and `prompt_embeds` undefined."
-            )
-        elif prompt is not None and (not isinstance(prompt, str) and not isinstance(prompt, list)):
-            raise ValueError(f"`prompt` has to be of type `str` or `list` but is {type(prompt)}")
-
-        if prompt is not None and negative_prompt_embeds is not None:
-            raise ValueError(
-                f"Cannot forward both `prompt`: {prompt} and `negative_prompt_embeds`:"
-                f" {negative_prompt_embeds}. Please make sure to only forward one of the two."
-            )
-
-        if negative_prompt is not None and negative_prompt_embeds is not None:
-            raise ValueError(
-                f"Cannot forward both `negative_prompt`: {negative_prompt} and `negative_prompt_embeds`:"
-                f" {negative_prompt_embeds}. Please make sure to only forward one of the two."
-            )
-
-        if prompt_embeds is not None and negative_prompt_embeds is not None:
-            if prompt_embeds.shape != negative_prompt_embeds.shape:
-                raise ValueError(
-                    "`prompt_embeds` and `negative_prompt_embeds` must have the same shape when passed directly, but"
-                    f" got: `prompt_embeds` {prompt_embeds.shape} != `negative_prompt_embeds`"
-                    f" {negative_prompt_embeds.shape}."
-                )
-
-        if video is not None and latents is not None:
-            raise ValueError("Only one of `video` or `latents` should be provided")
-
-    # Copied from diffusers.pipelines.cogvideo.pipeline_cogvideox.CogVideoXPipeline.fuse_qkv_projections
-    def fuse_qkv_projections(self) -> None:
-        r"""Enables fused QKV projections."""
-        self.fusing_transformer = True
-        self.transformer.fuse_qkv_projections()
-
-    # Copied from diffusers.pipelines.cogvideo.pipeline_cogvideox.CogVideoXPipeline.unfuse_qkv_projections
-    def unfuse_qkv_projections(self) -> None:
-        r"""Disable QKV projection fusion if enabled."""
-        if not self.fusing_transformer:
-            logger.warning("The Transformer was not initially fused for QKV projections. Doing nothing.")
-        else:
-            self.transformer.unfuse_qkv_projections()
-            self.fusing_transformer = False
-
-    # Copied from diffusers.pipelines.cogvideo.pipeline_cogvideox.CogVideoXPipeline._prepare_rotary_positional_embeddings
-    def _prepare_rotary_positional_embeddings(
-        self,
-        height: int,
-        width: int,
-        num_frames: int,
-        device: torch.device,
-    ) -> Tuple[torch.Tensor, torch.Tensor]:
-        grid_height = height // (self.vae_scale_factor_spatial * self.transformer.config.patch_size)
-        grid_width = width // (self.vae_scale_factor_spatial * self.transformer.config.patch_size)
-        base_size_width = 720 // (self.vae_scale_factor_spatial * self.transformer.config.patch_size)
-        base_size_height = 480 // (self.vae_scale_factor_spatial * self.transformer.config.patch_size)
-
-        grid_crops_coords = get_resize_crop_region_for_grid(
-            (grid_height, grid_width), base_size_width, base_size_height
-        )
-        freqs_cos, freqs_sin = get_3d_rotary_pos_embed(
-            embed_dim=self.transformer.config.attention_head_dim,
-            crops_coords=grid_crops_coords,
-            grid_size=(grid_height, grid_width),
-            temporal_size=num_frames,
-        )
-
-        freqs_cos = freqs_cos.to(device=device)
-        freqs_sin = freqs_sin.to(device=device)
-        return freqs_cos, freqs_sin
-
-    @property
-    def guidance_scale(self):
-        return self._guidance_scale
-
-    @property
-    def num_timesteps(self):
-        return self._num_timesteps
-
-    @property
-    def interrupt(self):
-        return self._interrupt
-
-    @torch.no_grad()
-    @replace_example_docstring(EXAMPLE_DOC_STRING)
-    def __call__(
-        self,
-        video: List[Image.Image] = None,
-        prompt: Optional[Union[str, List[str]]] = None,
-        negative_prompt: Optional[Union[str, List[str]]] = None,
-        height: int = 480,
-        width: int = 720,
-        num_inference_steps: int = 50,
-        timesteps: Optional[List[int]] = None,
-        strength: float = 0.8,
-        guidance_scale: float = 6,
-        use_dynamic_cfg: bool = False,
-        num_videos_per_prompt: int = 1,
-        eta: float = 0.0,
-        generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
-        latents: Optional[torch.FloatTensor] = None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
-        output_type: str = "pil",
-        return_dict: bool = True,
-        callback_on_step_end: Optional[
-            Union[Callable[[int, int, Dict], None], PipelineCallback, MultiPipelineCallbacks]
-        ] = None,
-        callback_on_step_end_tensor_inputs: List[str] = ["latents"],
-        max_sequence_length: int = 226,
-    ) -> Union[CogVideoXPipelineOutput, Tuple]:
-        """
-        Function invoked when calling the pipeline for generation.
-
-        Args:
-            video (`List[PIL.Image.Image]`):
-                The input video to condition the generation on. Must be a list of images/frames of the video.
-            prompt (`str` or `List[str]`, *optional*):
-                The prompt or prompts to guide the image generation. If not defined, one has to pass `prompt_embeds`.
-                instead.
-            negative_prompt (`str` or `List[str]`, *optional*):
-                The prompt or prompts not to guide the image generation. If not defined, one has to pass
-                `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
-                less than `1`).
-            height (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
-                The height in pixels of the generated image. This is set to 1024 by default for the best results.
-            width (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
-                The width in pixels of the generated image. This is set to 1024 by default for the best results.
-            num_inference_steps (`int`, *optional*, defaults to 50):
-                The number of denoising steps. More denoising steps usually lead to a higher quality image at the
-                expense of slower inference.
-            timesteps (`List[int]`, *optional*):
-                Custom timesteps to use for the denoising process with schedulers which support a `timesteps` argument
-                in their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is
-                passed will be used. Must be in descending order.
-            strength (`float`, *optional*, defaults to 0.8):
-                Higher strength leads to more differences between original video and generated video.
-            guidance_scale (`float`, *optional*, defaults to 7.0):
-                Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
-                `guidance_scale` is defined as `w` of equation 2. of [Imagen
-                Paper](https://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting `guidance_scale >
-                1`. Higher guidance scale encourages to generate images that are closely linked to the text `prompt`,
-                usually at the expense of lower image quality.
-            num_videos_per_prompt (`int`, *optional*, defaults to 1):
-                The number of videos to generate per prompt.
-            generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
-                One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
-                to make generation deterministic.
-            latents (`torch.FloatTensor`, *optional*):
-                Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
-                generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
-                tensor will ge generated by sampling using the supplied random `generator`.
-            prompt_embeds (`torch.FloatTensor`, *optional*):
-                Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
-                provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
-                Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
-                weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` 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`.
-            return_dict (`bool`, *optional*, defaults to `True`):
-                Whether or not to return a [`~pipelines.stable_diffusion_xl.StableDiffusionXLPipelineOutput`] instead
-                of a plain tuple.
-            callback_on_step_end (`Callable`, *optional*):
-                A function that calls at the end of each denoising steps during the inference. The function is called
-                with the following arguments: `callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int,
-                callback_kwargs: Dict)`. `callback_kwargs` will include a list of all tensors as specified by
-                `callback_on_step_end_tensor_inputs`.
-            callback_on_step_end_tensor_inputs (`List`, *optional*):
-                The list of tensor inputs for the `callback_on_step_end` function. The tensors specified in the list
-                will be passed as `callback_kwargs` argument. You will only be able to include variables listed in the
-                `._callback_tensor_inputs` attribute of your pipeline class.
-            max_sequence_length (`int`, defaults to `226`):
-                Maximum sequence length in encoded prompt. Must be consistent with
-                `self.transformer.config.max_text_seq_length` otherwise may lead to poor results.
-
-        Examples:
-
-        Returns:
-            [`~pipelines.cogvideo.pipeline_output.CogVideoXPipelineOutput`] or `tuple`:
-            [`~pipelines.cogvideo.pipeline_output.CogVideoXPipelineOutput`] if `return_dict` is True, otherwise a
-            `tuple`. When returning a tuple, the first element is a list with the generated images.
-        """
-
-        if isinstance(callback_on_step_end, (PipelineCallback, MultiPipelineCallbacks)):
-            callback_on_step_end_tensor_inputs = callback_on_step_end.tensor_inputs
-
-        height = height or self.transformer.config.sample_size * self.vae_scale_factor_spatial
-        width = width or self.transformer.config.sample_size * self.vae_scale_factor_spatial
-        num_videos_per_prompt = 1
-
-        # 1. Check inputs. Raise error if not correct
-        self.check_inputs(
-            prompt,
-            height,
-            width,
-            strength,
-            negative_prompt,
-            callback_on_step_end_tensor_inputs,
-            prompt_embeds,
-            negative_prompt_embeds,
-        )
-        self._guidance_scale = guidance_scale
-        self._interrupt = False
-
-        # 2. Default call parameters
-        if prompt is not None and isinstance(prompt, str):
-            batch_size = 1
-        elif prompt is not None and isinstance(prompt, list):
-            batch_size = len(prompt)
-        else:
-            batch_size = prompt_embeds.shape[0]
-
-        device = self._execution_device
-
-        # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
-        # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
-        # corresponds to doing no classifier free guidance.
-        do_classifier_free_guidance = guidance_scale > 1.0
-
-        # 3. Encode input prompt
-        prompt_embeds, negative_prompt_embeds = self.encode_prompt(
-            prompt,
-            negative_prompt,
-            do_classifier_free_guidance,
-            num_videos_per_prompt=num_videos_per_prompt,
-            prompt_embeds=prompt_embeds,
-            negative_prompt_embeds=negative_prompt_embeds,
-            max_sequence_length=max_sequence_length,
-            device=device,
-        )
-        if do_classifier_free_guidance:
-            prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds], dim=0)
-
-        # 4. Prepare timesteps
-        timesteps, num_inference_steps = retrieve_timesteps(self.scheduler, num_inference_steps, device, timesteps)
-        timesteps, num_inference_steps = self.get_timesteps(num_inference_steps, timesteps, strength, device)
-        latent_timestep = timesteps[:1].repeat(batch_size * num_videos_per_prompt)
-        self._num_timesteps = len(timesteps)
-
-        # 5. Prepare latents
-        if latents is None:
-            video = self.video_processor.preprocess_video(video, height=height, width=width)
-            video = video.to(device=device, dtype=prompt_embeds.dtype)
-
-        latent_channels = self.transformer.config.in_channels
-        latents = self.prepare_latents(
-            video,
-            batch_size * num_videos_per_prompt,
-            latent_channels,
-            height,
-            width,
-            prompt_embeds.dtype,
-            device,
-            generator,
-            latents,
-            latent_timestep,
-        )
-
-        # 6. Prepare extra step kwargs. TODO: Logic should ideally just be moved out of the pipeline
-        extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)
-
-        # 7. Create rotary embeds if required
-        image_rotary_emb = (
-            self._prepare_rotary_positional_embeddings(height, width, latents.size(1), device)
-            if self.transformer.config.use_rotary_positional_embeddings
-            else None
-        )
-
-        # 8. Denoising loop
-        num_warmup_steps = max(len(timesteps) - num_inference_steps * self.scheduler.order, 0)
-
-        with self.progress_bar(total=num_inference_steps) as progress_bar:
-            # for DPM-solver++
-            old_pred_original_sample = None
-            for i, t in enumerate(timesteps):
-                if self.interrupt:
-                    continue
-
-                latent_model_input = torch.cat([latents] * 2) if do_classifier_free_guidance else latents
-                latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)
-
-                # broadcast to batch dimension in a way that's compatible with ONNX/Core ML
-                timestep = t.expand(latent_model_input.shape[0])
-
-                # predict noise model_output
-                noise_pred = self.transformer(
-                    hidden_states=latent_model_input,
-                    encoder_hidden_states=prompt_embeds,
-                    timestep=timestep,
-                    image_rotary_emb=image_rotary_emb,
-                    return_dict=False,
-                )[0]
-                noise_pred = noise_pred.float()
-
-                # perform guidance
-                if use_dynamic_cfg:
-                    self._guidance_scale = 1 + guidance_scale * (
-                        (1 - math.cos(math.pi * ((num_inference_steps - t.item()) / num_inference_steps) ** 5.0)) / 2
-                    )
-                if do_classifier_free_guidance:
-                    noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
-                    noise_pred = noise_pred_uncond + self.guidance_scale * (noise_pred_text - noise_pred_uncond)
-
-                # compute the previous noisy sample x_t -> x_t-1
-                if not isinstance(self.scheduler, CogVideoXDPMScheduler):
-                    latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs, return_dict=False)[0]
-                else:
-                    latents, old_pred_original_sample = self.scheduler.step(
-                        noise_pred,
-                        old_pred_original_sample,
-                        t,
-                        timesteps[i - 1] if i > 0 else None,
-                        latents,
-                        **extra_step_kwargs,
-                        return_dict=False,
-                    )
-                latents = latents.to(prompt_embeds.dtype)
-
-                # call the callback, if provided
-                if callback_on_step_end is not None:
-                    callback_kwargs = {}
-                    for k in callback_on_step_end_tensor_inputs:
-                        callback_kwargs[k] = locals()[k]
-                    callback_outputs = callback_on_step_end(self, i, t, callback_kwargs)
-
-                    latents = callback_outputs.pop("latents", latents)
-                    prompt_embeds = callback_outputs.pop("prompt_embeds", prompt_embeds)
-                    negative_prompt_embeds = callback_outputs.pop("negative_prompt_embeds", negative_prompt_embeds)
-
-                if i == len(timesteps) - 1 or ((i + 1) > num_warmup_steps and (i + 1) % self.scheduler.order == 0):
-                    progress_bar.update()
-
-        if not output_type == "latent":
-            video = self.decode_latents(latents)
-            video = self.video_processor.postprocess_video(video=video, output_type=output_type)
-        else:
-            video = latents
-
-        # Offload all models
-        self.maybe_free_model_hooks()
-
-        if not return_dict:
-            return (video,)
-
-        return CogVideoXPipelineOutput(frames=video)

src/diffusers/pipelines/cogvideo/pipeline_output.py

@@ -1,20 +0,0 @@
-from dataclasses import dataclass
-
-import torch
-
-from diffusers.utils import BaseOutput
-
-
-@dataclass
-class CogVideoXPipelineOutput(BaseOutput):
-    r"""
-    Output class for CogVideo pipelines.
-
-    Args:
-        frames (`torch.Tensor`, `np.ndarray`, or List[List[PIL.Image.Image]]):
-            List of video outputs - It can be a nested list of length `batch_size,` with each sub-list containing
-            denoised PIL image sequences of length `num_frames.` It can also be a NumPy array or Torch tensor of shape
-            `(batch_size, num_frames, channels, height, width)`.
-    """
-
-    frames: torch.Tensor

src/diffusers/pipelines/controlnet/pipeline_controlnet_sd_xl_img2img.py

@@ -1538,6 +1538,7 @@ class StableDiffusionXLControlNetImg2ImgPipeline(
                     if isinstance(controlnet_cond_scale, list):
                         controlnet_cond_scale = controlnet_cond_scale[0]
                     cond_scale = controlnet_cond_scale * controlnet_keep[i]
+
                 down_block_res_samples, mid_block_res_sample = self.controlnet(
                     control_model_input,
                     t,

src/diffusers/pipelines/controlnet_sd3/__init__.py

@@ -23,9 +23,6 @@ except OptionalDependencyNotAvailable:
     _dummy_objects.update(get_objects_from_module(dummy_torch_and_transformers_objects))
 else:
     _import_structure["pipeline_stable_diffusion_3_controlnet"] = ["StableDiffusion3ControlNetPipeline"]
-    _import_structure["pipeline_stable_diffusion_3_controlnet_inpainting"] = [
-        "StableDiffusion3ControlNetInpaintingPipeline"
-    ]
 
 if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
     try:
@@ -36,7 +33,6 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
         from ...utils.dummy_torch_and_transformers_objects import *
     else:
         from .pipeline_stable_diffusion_3_controlnet import StableDiffusion3ControlNetPipeline
-        from .pipeline_stable_diffusion_3_controlnet_inpainting import StableDiffusion3ControlNetInpaintingPipeline
 
     try:
         if not (is_transformers_available() and is_flax_available()):