resolve conflicts

This reverts commit 65efbcead5.

.github/workflows/benchmark.yml

@@ -7,7 +7,7 @@ on:
 
 env:
   DIFFUSERS_IS_CI: yes
-  HF_XET_HIGH_PERFORMANCE: 1
+  HF_HUB_ENABLE_HF_TRANSFER: 1
   HF_HOME: /mnt/cache
   OMP_NUM_THREADS: 8
   MKL_NUM_THREADS: 8
@@ -38,8 +38,9 @@ jobs:
         run: |
           apt update
           apt install -y libpq-dev postgresql-client
-          uv pip install -e ".[quality]"
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          uv pip install -r benchmarks/requirements.txt
+          python -m uv pip install -e [quality,test]
+          python -m uv pip install -r benchmarks/requirements.txt
       - name: Environment
         run: |
           python utils/print_env.py

.github/workflows/build_docker_images.yml

@@ -42,39 +42,18 @@ jobs:
           CHANGED_FILES: ${{ steps.file_changes.outputs.all }}
         run: |
           echo "$CHANGED_FILES"
-          ALLOWED_IMAGES=(
+          for FILE in $CHANGED_FILES; do 
-            diffusers-pytorch-cpu
-            diffusers-pytorch-cuda
-            diffusers-pytorch-xformers-cuda
-            diffusers-pytorch-minimum-cuda
-            diffusers-doc-builder
-          )
-
-          declare -A IMAGES_TO_BUILD=()
-
-          for FILE in $CHANGED_FILES; do
             # skip anything that isn't still on disk
-            if [[ ! -e "$FILE" ]]; then
+            if [[ ! -f "$FILE" ]]; then
               echo "Skipping removed file $FILE"
               continue
+            fi           
+            if [[ "$FILE" == docker/*Dockerfile ]]; then
+              DOCKER_PATH="${FILE%/Dockerfile}"
+              DOCKER_TAG=$(basename "$DOCKER_PATH")
+              echo "Building Docker image for $DOCKER_TAG"
+              docker build -t "$DOCKER_TAG" "$DOCKER_PATH"
             fi
-
-            for IMAGE in "${ALLOWED_IMAGES[@]}"; do
-              if [[ "$FILE" == docker/${IMAGE}/* ]]; then
-                IMAGES_TO_BUILD["$IMAGE"]=1
-              fi
-            done
-          done
-
-          if [[ ${#IMAGES_TO_BUILD[@]} -eq 0 ]]; then
-            echo "No relevant Docker changes detected."
-            exit 0
-          fi
-
-          for IMAGE in "${!IMAGES_TO_BUILD[@]}"; do
-            DOCKER_PATH="docker/${IMAGE}"
-            echo "Building Docker image for $IMAGE"
-            docker build -t "$IMAGE" "$DOCKER_PATH"
           done
         if: steps.file_changes.outputs.all != ''
 
@@ -93,6 +72,7 @@ jobs:
         image-name:
           - diffusers-pytorch-cpu
           - diffusers-pytorch-cuda
+          - diffusers-pytorch-cuda
           - diffusers-pytorch-xformers-cuda
           - diffusers-pytorch-minimum-cuda
           - diffusers-doc-builder

.github/workflows/build_pr_documentation.yml

@@ -12,33 +12,7 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
-  check-links:
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: '3.10'
-
-      - name: Install uv
-        run: |
-          curl -LsSf https://astral.sh/uv/install.sh | sh
-          echo "$HOME/.cargo/bin" >> $GITHUB_PATH
-
-      - name: Install doc-builder
-        run: |
-          uv pip install --system git+https://github.com/huggingface/doc-builder.git@main
-
-      - name: Check documentation links
-        run: |
-          uv run doc-builder check-links docs/source/en
-
   build:
-    needs: check-links
     uses: huggingface/doc-builder/.github/workflows/build_pr_documentation.yml@main
     with:
       commit_sha: ${{ github.event.pull_request.head.sha }}

.github/workflows/mirror_community_pipeline.yml

@@ -74,7 +74,7 @@ jobs:
           python-version: "3.10"
       - name: Install dependencies
         run: |
-          pip install --upgrade pip
+          python -m pip install --upgrade pip
           pip install --upgrade huggingface_hub
 
       # Check secret is set

.github/workflows/nightly_tests.yml

@@ -7,7 +7,7 @@ on:
 
 env:
   DIFFUSERS_IS_CI: yes
-  HF_XET_HIGH_PERFORMANCE: 1
+  HF_HUB_ENABLE_HF_TRANSFER: 1
   OMP_NUM_THREADS: 8
   MKL_NUM_THREADS: 8
   PYTEST_TIMEOUT: 600
@@ -71,11 +71,10 @@ jobs:
         run: nvidia-smi
       - name: Install dependencies
         run: |
-          uv pip install -e ".[quality]"
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+          python -m uv pip install -e [quality,test]
-          #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+          pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-          uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1 
+          python -m uv pip install pytest-reportlog
-          uv pip install pytest-reportlog
       - name: Environment
         run: |
           python utils/print_env.py
@@ -85,8 +84,8 @@ jobs:
           # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
-          pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+          python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-             -k "not Flax and not Onnx" \
+            -s -v -k "not Flax and not Onnx" \
             --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
             --report-log=tests_pipeline_${{ matrix.module }}_cuda.log \
             tests/pipelines/${{ matrix.module }}
@@ -125,12 +124,11 @@ jobs:
 
     - name: Install dependencies
       run: |
-        uv pip install -e ".[quality]"
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        uv pip install peft@git+https://github.com/huggingface/peft.git
+        python -m uv pip install -e [quality,test]
-        uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+        python -m uv pip install peft@git+https://github.com/huggingface/peft.git
-        #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-        uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1 
+        python -m uv pip install pytest-reportlog
-        uv pip install pytest-reportlog
     - name: Environment
       run: python utils/print_env.py
 
@@ -141,8 +139,8 @@ jobs:
         # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -k "not Flax and not Onnx" \
+          -s -v -k "not Flax and not Onnx" \
           --make-reports=tests_torch_${{ matrix.module }}_cuda \
           --report-log=tests_torch_${{ matrix.module }}_cuda.log \
           tests/${{ matrix.module }}
@@ -154,8 +152,8 @@ jobs:
         # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          --make-reports=examples_torch_cuda \
+          -s -v --make-reports=examples_torch_cuda \
           --report-log=examples_torch_cuda.log \
           examples/
 
@@ -193,9 +191,8 @@ jobs:
         nvidia-smi
     - name: Install dependencies
       run: |
-        uv pip install -e ".[quality,training]"
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+        python -m uv pip install -e [quality,test,training]
-        uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1 
     - name: Environment
       run: |
         python utils/print_env.py
@@ -204,7 +201,7 @@ jobs:
         HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
         RUN_COMPILE: yes
       run: |
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile -k "compile" --make-reports=tests_torch_compile_cuda tests/
+        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: ${{ failure() }}
       run: cat reports/tests_torch_compile_cuda_failures_short.txt
@@ -235,12 +232,11 @@ jobs:
         run: nvidia-smi
       - name: Install dependencies
         run: |
-          uv pip install -e ".[quality]"
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          uv pip install peft@git+https://github.com/huggingface/peft.git
+          python -m uv pip install -e [quality,test]
-          uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+          python -m uv pip install peft@git+https://github.com/huggingface/peft.git
-          #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+          pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-          uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1 
+          python -m uv pip install pytest-reportlog
-          uv pip install pytest-reportlog
       - name: Environment
         run: |
           python utils/print_env.py
@@ -251,7 +247,7 @@ jobs:
           CUBLAS_WORKSPACE_CONFIG: :16:8
           BIG_GPU_MEMORY: 40
         run: |
-          pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+          python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
             -m "big_accelerator" \
             --make-reports=tests_big_gpu_torch_cuda \
             --report-log=tests_big_gpu_torch_cuda.log \
@@ -286,11 +282,10 @@ jobs:
 
       - name: Install dependencies
         run: |
-          uv pip install -e ".[quality]"
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          uv pip install peft@git+https://github.com/huggingface/peft.git
+          python -m uv pip install -e [quality,test]
-          uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+          python -m uv pip install peft@git+https://github.com/huggingface/peft.git
-          #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+          pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-          uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1 
 
       - name: Environment
         run: |
@@ -302,8 +297,8 @@ jobs:
           # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
-          pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+          python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            -k "not Flax and not Onnx" \
+            -s -v -k "not Flax and not Onnx" \
             --make-reports=tests_torch_minimum_version_cuda \
             tests/models/test_modeling_common.py \
             tests/pipelines/test_pipelines_common.py \
@@ -345,9 +340,6 @@ jobs:
           - backend: "optimum_quanto"
             test_location: "quanto"
             additional_deps: []
-          - backend: "nvidia_modelopt"
-            test_location: "modelopt"
-            additional_deps: []
     runs-on:
       group: aws-g6e-xlarge-plus
     container:
@@ -362,14 +354,13 @@ jobs:
         run: nvidia-smi
       - name: Install dependencies
         run: |
-          uv pip install -e ".[quality]"
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          uv pip install -U ${{ matrix.config.backend }}
+          python -m uv pip install -e [quality,test]
+          python -m uv pip install -U ${{ matrix.config.backend }}
           if [ "${{ join(matrix.config.additional_deps, ' ') }}" != "" ]; then
-              uv pip install ${{ join(matrix.config.additional_deps, ' ') }}
+              python -m uv pip install ${{ join(matrix.config.additional_deps, ' ') }}
           fi
-          uv pip install pytest-reportlog
+          python -m uv pip install pytest-reportlog
-          #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
-          uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1 
       - name: Environment
         run: |
           python utils/print_env.py
@@ -380,7 +371,7 @@ jobs:
           CUBLAS_WORKSPACE_CONFIG: :16:8
           BIG_GPU_MEMORY: 40
         run: |
-          pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+          python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
             --make-reports=tests_${{ matrix.config.backend }}_torch_cuda \
             --report-log=tests_${{ matrix.config.backend }}_torch_cuda.log \
             tests/quantization/${{ matrix.config.test_location }}
@@ -415,11 +406,10 @@ jobs:
         run: nvidia-smi
       - name: Install dependencies
         run: |
-          uv pip install -e ".[quality]"
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          uv pip install -U bitsandbytes optimum_quanto
+          python -m uv pip install -e [quality,test]
-          #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+          python -m uv pip install -U bitsandbytes optimum_quanto
-          uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1 
+          python -m uv pip install pytest-reportlog
-          uv pip install pytest-reportlog
       - name: Environment
         run: |
           python utils/print_env.py
@@ -430,7 +420,7 @@ jobs:
           CUBLAS_WORKSPACE_CONFIG: :16:8
           BIG_GPU_MEMORY: 40
         run: |
-          pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+          python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
             --make-reports=tests_pipeline_level_quant_torch_cuda \
             --report-log=tests_pipeline_level_quant_torch_cuda.log \
             tests/quantization/test_pipeline_level_quantization.py
@@ -530,11 +520,11 @@ jobs:
 #      - name: Install dependencies
 #        shell: arch -arch arm64 bash {0}
 #        run: |
-#          ${CONDA_RUN} pip install --upgrade pip uv
+#          ${CONDA_RUN} python -m pip install --upgrade pip uv
-#          ${CONDA_RUN} uv pip install -e ".[quality]"
+#          ${CONDA_RUN} python -m uv pip install -e [quality,test]
-#          ${CONDA_RUN} uv pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cpu
+#          ${CONDA_RUN} python -m uv pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cpu
-#          ${CONDA_RUN} uv pip install accelerate@git+https://github.com/huggingface/accelerate
+#          ${CONDA_RUN} python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate
-#          ${CONDA_RUN} uv pip install pytest-reportlog
+#          ${CONDA_RUN} python -m uv pip install pytest-reportlog
 #      - name: Environment
 #        shell: arch -arch arm64 bash {0}
 #        run: |
@@ -545,7 +535,7 @@ jobs:
 #          HF_HOME: /System/Volumes/Data/mnt/cache
 #          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
 #        run: |
-#          ${CONDA_RUN} pytest -n 1  --make-reports=tests_torch_mps \
+#          ${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
@@ -586,11 +576,11 @@ jobs:
 #      - name: Install dependencies
 #        shell: arch -arch arm64 bash {0}
 #        run: |
-#          ${CONDA_RUN} pip install --upgrade pip uv
+#          ${CONDA_RUN} python -m pip install --upgrade pip uv
-#          ${CONDA_RUN} uv pip install -e ".[quality]"
+#          ${CONDA_RUN} python -m uv pip install -e [quality,test]
-#          ${CONDA_RUN} uv pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cpu
+#          ${CONDA_RUN} python -m uv pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cpu
-#          ${CONDA_RUN} uv pip install accelerate@git+https://github.com/huggingface/accelerate
+#          ${CONDA_RUN} python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate
-#          ${CONDA_RUN} uv pip install pytest-reportlog
+#          ${CONDA_RUN} python -m uv pip install pytest-reportlog
 #      - name: Environment
 #        shell: arch -arch arm64 bash {0}
 #        run: |
@@ -601,7 +591,7 @@ jobs:
 #          HF_HOME: /System/Volumes/Data/mnt/cache
 #          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
 #        run: |
-#          ${CONDA_RUN} pytest -n 1  --make-reports=tests_torch_mps \
+#          ${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

.github/workflows/pr_dependency_test.yml

@@ -25,8 +25,11 @@ jobs:
           python-version: "3.8"
       - name: Install dependencies
         run: |
-          pip install -e .
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          pip install pytest
+          python -m pip install --upgrade pip uv
+          python -m uv pip install -e .
+          python -m uv pip install pytest
       - name: Check for soft dependencies
         run: |
-            pytest tests/others/test_dependencies.py
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+          pytest tests/others/test_dependencies.py

.github/workflows/pr_modular_tests.yml

@@ -26,7 +26,7 @@ concurrency:
 
 env:
   DIFFUSERS_IS_CI: yes
-  HF_XET_HIGH_PERFORMANCE: 1
+  HF_HUB_ENABLE_HF_TRANSFER: 1
   OMP_NUM_THREADS: 4
   MKL_NUM_THREADS: 4
   PYTEST_TIMEOUT: 60
@@ -42,7 +42,7 @@ jobs:
           python-version: "3.10"
       - name: Install dependencies
         run: |
-          pip install --upgrade pip
+          python -m pip install --upgrade pip
           pip install .[quality]
       - name: Check quality
         run: make quality
@@ -62,7 +62,7 @@ jobs:
           python-version: "3.10"
       - name: Install dependencies
         run: |
-          pip install --upgrade pip
+          python -m pip install --upgrade pip
           pip install .[quality]
       - name: Check repo consistency
         run: |
@@ -77,47 +77,65 @@ jobs:
 
   run_fast_tests:
     needs: [check_code_quality, check_repository_consistency]
-    name: Fast PyTorch Modular Pipeline CPU tests
+    strategy:
+      fail-fast: false
+      matrix:
+        config:
+          - name: Fast PyTorch Modular Pipeline CPU tests
+            framework: pytorch_pipelines
+            runner: aws-highmemory-32-plus
+            image: diffusers/diffusers-pytorch-cpu
+            report: torch_cpu_modular_pipelines
+
+    name: ${{ matrix.config.name }}
+
     runs-on:
-      group: aws-highmemory-32-plus
+      group: ${{ matrix.config.runner }}
+
     container:
-      image: diffusers/diffusers-pytorch-cpu
+      image: ${{ matrix.config.image }}
       options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
+
     defaults:
       run:
         shell: bash
 
     steps:
-      - name: Checkout diffusers
+    - name: Checkout diffusers
-        uses: actions/checkout@v3
+      uses: actions/checkout@v3
-        with:
+      with:
-          fetch-depth: 2
+        fetch-depth: 2
 
-      - name: Install dependencies
+    - name: Install dependencies
-        run: |
+      run: |
-          uv pip install -e ".[quality]"
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+        python -m uv pip install -e [quality,test]
-          uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
+        pip uninstall transformers -y && python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git --no-deps
-          uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git --no-deps
+        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git --no-deps
 
-      - name: Environment
+    - name: Environment
-        run: |
+      run: |
-          python utils/print_env.py
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python utils/print_env.py
 
-      - name: Run fast PyTorch Pipeline CPU tests
+    - name: Run fast PyTorch Pipeline CPU tests
-        run: |
+      if: ${{ matrix.config.framework == 'pytorch_pipelines' }}
-          pytest -n 8 --max-worker-restart=0 --dist=loadfile \
+      run: |
-            -s -v \
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-            --make-reports=tests_torch_cpu_modular_pipelines \
+        python -m pytest -n 8 --max-worker-restart=0 --dist=loadfile \
-            tests/modular_pipelines
+          -s -v -k "not Flax and not Onnx" \
+          --make-reports=tests_${{ matrix.config.report }} \
+          tests/modular_pipelines
+
+    - name: Failure short reports
+      if: ${{ failure() }}
+      run: cat reports/tests_${{ matrix.config.report }}_failures_short.txt
+
+    - name: Test suite reports artifacts
+      if: ${{ always() }}
+      uses: actions/upload-artifact@v4
+      with:
+        name: pr_${{ matrix.config.framework }}_${{ matrix.config.report }}_test_reports
+        path: reports
 
-      - name: Failure short reports
-        if: ${{ failure() }}
-        run: cat reports/tests_torch_cpu_modular_pipelines_failures_short.txt
 
-      - name: Test suite reports artifacts
-        if: ${{ always() }}
-        uses: actions/upload-artifact@v4
-        with:
-          name: pr_pytorch_pipelines_torch_cpu_modular_pipelines_test_reports
-          path: reports

.github/workflows/pr_test_fetcher.yml

@@ -33,7 +33,8 @@ jobs:
         fetch-depth: 0
     - name: Install dependencies
       run: |
-        uv pip install -e ".[quality]"
+        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
@@ -89,16 +90,19 @@ jobs:
 
     - name: Install dependencies
       run: |
-        uv pip install -e ".[quality]"
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        uv pip install accelerate
+        python -m pip install -e [quality,test]
+        python -m pip install accelerate
 
     - name: Environment
       run: |
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python utils/print_env.py
 
     - name: Run all selected tests on CPU
       run: |
-        pytest -n 2 --dist=loadfile -v --make-reports=${{ matrix.modules }}_tests_cpu ${{ fromJson(needs.setup_pr_tests.outputs.test_map)[matrix.modules] }}
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m pytest -n 2 --dist=loadfile -v --make-reports=${{ matrix.modules }}_tests_cpu ${{ fromJson(needs.setup_pr_tests.outputs.test_map)[matrix.modules] }}
 
     - name: Failure short reports
       if: ${{ failure() }}
@@ -144,16 +148,19 @@ jobs:
 
     - name: Install dependencies
       run: |
-        pip install -e [quality]
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m pip install -e [quality,test]
 
     - name: Environment
       run: |
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python utils/print_env.py
 
     - name: Run Hub tests for models, schedulers, and pipelines on a staging env
       if: ${{ matrix.config.framework == 'hub_tests_pytorch' }}
       run: |
-        HUGGINGFACE_CO_STAGING=true pytest \
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        HUGGINGFACE_CO_STAGING=true python -m pytest \
           -m "is_staging_test" \
           --make-reports=tests_${{ matrix.config.report }} \
           tests

.github/workflows/pr_tests.yml

@@ -22,7 +22,7 @@ concurrency:
 
 env:
   DIFFUSERS_IS_CI: yes
-  HF_XET_HIGH_PERFORMANCE: 1
+  HF_HUB_ENABLE_HF_TRANSFER: 1
   OMP_NUM_THREADS: 4
   MKL_NUM_THREADS: 4
   PYTEST_TIMEOUT: 60
@@ -38,7 +38,7 @@ jobs:
           python-version: "3.8"
       - name: Install dependencies
         run: |
-          pip install --upgrade pip
+          python -m pip install --upgrade pip
           pip install .[quality]
       - name: Check quality
         run: make quality
@@ -58,7 +58,7 @@ jobs:
           python-version: "3.8"
       - name: Install dependencies
         run: |
-          pip install --upgrade pip
+          python -m pip install --upgrade pip
           pip install .[quality]
       - name: Check repo consistency
         run: |
@@ -114,36 +114,40 @@ jobs:
 
     - name: Install dependencies
       run: |
-        uv pip install -e ".[quality]"
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+        python -m uv pip install -e [quality,test]
-        uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
+        pip uninstall transformers -y && python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git --no-deps
-        uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git --no-deps
+        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git --no-deps
 
     - name: Environment
       run: |
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python utils/print_env.py
 
     - name: Run fast PyTorch Pipeline CPU tests
       if: ${{ matrix.config.framework == 'pytorch_pipelines' }}
       run: |
-        pytest -n 8 --max-worker-restart=0 --dist=loadfile \
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          -k "not Flax and not Onnx" \
+        python -m pytest -n 8 --max-worker-restart=0 --dist=loadfile \
+          -s -v -k "not Flax and not Onnx" \
           --make-reports=tests_${{ matrix.config.report }} \
           tests/pipelines
 
     - name: Run fast PyTorch Model Scheduler CPU tests
       if: ${{ matrix.config.framework == 'pytorch_models' }}
       run: |
-        pytest -n 4 --max-worker-restart=0 --dist=loadfile \
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          -k "not Flax and not Onnx and not Dependency" \
+        python -m pytest -n 4 --max-worker-restart=0 --dist=loadfile \
+          -s -v -k "not Flax and not Onnx and not Dependency" \
           --make-reports=tests_${{ matrix.config.report }} \
           tests/models tests/schedulers tests/others
 
     - name: Run example PyTorch CPU tests
       if: ${{ matrix.config.framework == 'pytorch_examples' }}
       run: |
-        uv pip install ".[training]"
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        pytest -n 4 --max-worker-restart=0 --dist=loadfile \
+        python -m uv pip install peft timm
+        python -m pytest -n 4 --max-worker-restart=0 --dist=loadfile \
           --make-reports=tests_${{ matrix.config.report }} \
           examples
 
@@ -191,16 +195,19 @@ jobs:
 
     - name: Install dependencies
       run: |
-        uv pip install -e ".[quality]"
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m uv pip install -e [quality,test]
 
     - name: Environment
       run: |
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python utils/print_env.py
 
     - name: Run Hub tests for models, schedulers, and pipelines on a staging env
       if: ${{ matrix.config.framework == 'hub_tests_pytorch' }}
       run: |
-        HUGGINGFACE_CO_STAGING=true pytest \
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        HUGGINGFACE_CO_STAGING=true python -m pytest \
           -m "is_staging_test" \
           --make-reports=tests_${{ matrix.config.report }} \
           tests
@@ -242,26 +249,28 @@ jobs:
 
     - name: Install dependencies
       run: |
-        uv pip install -e ".[quality]"
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m uv pip install -e [quality,test]
         # TODO (sayakpaul, DN6): revisit `--no-deps`
-        uv pip install -U peft@git+https://github.com/huggingface/peft.git --no-deps
+        python -m pip install -U peft@git+https://github.com/huggingface/peft.git --no-deps
-        uv pip install -U tokenizers
+        python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git --no-deps
-        uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git --no-deps
+        python -m uv pip install -U tokenizers
-        #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git --no-deps
-        uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
 
     - name: Environment
       run: |
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python utils/print_env.py
 
     - name: Run fast PyTorch LoRA tests with PEFT
       run: |
-        pytest -n 4 --max-worker-restart=0 --dist=loadfile \
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          \
+        python -m pytest -n 4 --max-worker-restart=0 --dist=loadfile \
+          -s -v \
           --make-reports=tests_peft_main \
           tests/lora/
-        pytest -n 4 --max-worker-restart=0 --dist=loadfile \
+        python -m pytest -n 4 --max-worker-restart=0 --dist=loadfile \
-          \
+          -s -v \
           --make-reports=tests_models_lora_peft_main \
           tests/models/ -k "lora"
 

.github/workflows/pr_tests_gpu.yml

@@ -1,4 +1,4 @@
-name: Fast GPU Tests on PR
+name: Fast GPU Tests on PR 
 
 on:
   pull_request:
@@ -24,7 +24,7 @@ env:
   DIFFUSERS_IS_CI: yes
   OMP_NUM_THREADS: 8
   MKL_NUM_THREADS: 8
-  HF_XET_HIGH_PERFORMANCE: 1
+  HF_HUB_ENABLE_HF_TRANSFER: 1
   PYTEST_TIMEOUT: 600
   PIPELINE_USAGE_CUTOFF: 1000000000 # set high cutoff so that only always-test pipelines run
 
@@ -39,7 +39,7 @@ jobs:
           python-version: "3.8"
       - name: Install dependencies
         run: |
-          pip install --upgrade pip
+          python -m pip install --upgrade pip
           pip install .[quality]
       - name: Check quality
         run: make quality
@@ -59,7 +59,7 @@ jobs:
           python-version: "3.8"
       - name: Install dependencies
         run: |
-          pip install --upgrade pip
+          python -m pip install --upgrade pip
           pip install .[quality]
       - name: Check repo consistency
         run: |
@@ -71,7 +71,7 @@ jobs:
         if: ${{ failure() }}
         run: |
           echo "Repo consistency check failed. Please ensure the right dependency versions are installed with 'pip install -e .[quality]' and run 'make fix-copies'" >> $GITHUB_STEP_SUMMARY
-
+  
   setup_torch_cuda_pipeline_matrix:
     needs: [check_code_quality, check_repository_consistency]
     name: Setup Torch Pipelines CUDA Slow Tests Matrix
@@ -88,7 +88,8 @@ jobs:
           fetch-depth: 2
       - name: Install dependencies
         run: |
-          uv pip install -e ".[quality]"
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+          python -m uv pip install -e [quality,test]
       - name: Environment
         run: |
           python utils/print_env.py
@@ -129,10 +130,10 @@ jobs:
           nvidia-smi
       - name: Install dependencies
         run: |
-          uv pip install -e ".[quality]"
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+          python -m uv pip install -e [quality,test]
-          #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+          pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-          uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
+          pip uninstall transformers -y && python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git --no-deps
 
       - name: Environment
         run: |
@@ -150,18 +151,18 @@ jobs:
           # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
-          if [ "${{ matrix.module }}" = "ip_adapters" ]; then
+          if [ "${{ matrix.module }}" = "ip_adapters" ]; then 
-              pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+              python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-              -k "not Flax and not Onnx" \
+              -s -v -k "not Flax and not Onnx" \
               --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
               tests/pipelines/${{ matrix.module }}
-          else
+          else 
               pattern=$(cat ${{ steps.extract_tests.outputs.pattern_file }})
-              pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+              python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-              -k "not Flax and not Onnx and $pattern" \
+              -s -v -k "not Flax and not Onnx and $pattern" \
               --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
               tests/pipelines/${{ matrix.module }}
-          fi
+          fi 
 
       - name: Failure short reports
         if: ${{ failure() }}
@@ -199,11 +200,11 @@ jobs:
 
     - name: Install dependencies
       run: |
-        uv pip install -e ".[quality]"
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        uv pip install peft@git+https://github.com/huggingface/peft.git
+        python -m uv pip install -e [quality,test]
-        uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+        python -m uv pip install peft@git+https://github.com/huggingface/peft.git
-        #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-        uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
+        pip uninstall transformers -y && python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git --no-deps
 
     - name: Environment
       run: |
@@ -224,11 +225,11 @@ jobs:
       run: |
         pattern=$(cat ${{ steps.extract_tests.outputs.pattern_file }})
         if [ -z "$pattern" ]; then
-          pytest -n 1  --max-worker-restart=0 --dist=loadfile -k "not Flax and not Onnx" tests/${{ matrix.module }} \
+          python -m pytest -n 1 -sv --max-worker-restart=0 --dist=loadfile -k "not Flax and not Onnx" tests/${{ matrix.module }} \
-          --make-reports=tests_torch_cuda_${{ matrix.module }}
+          --make-reports=tests_torch_cuda_${{ matrix.module }}  
         else
-          pytest -n 1  --max-worker-restart=0 --dist=loadfile -k "not Flax and not Onnx and $pattern" tests/${{ matrix.module }} \
+          python -m pytest -n 1 -sv --max-worker-restart=0 --dist=loadfile -k "not Flax and not Onnx and $pattern" tests/${{ matrix.module }} \
-          --make-reports=tests_torch_cuda_${{ matrix.module }}
+          --make-reports=tests_torch_cuda_${{ matrix.module }}  
         fi
 
     - name: Failure short reports
@@ -264,20 +265,22 @@ jobs:
         nvidia-smi
     - name: Install dependencies
       run: |
-        #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
+        pip uninstall transformers -y && python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git --no-deps
-        uv pip install -e ".[quality,training]"
+        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: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
       run: |
-        uv pip install ".[training]"
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile --make-reports=examples_torch_cuda examples/
+        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() }}

.github/workflows/pr_torch_dependency_test.yml

@@ -25,8 +25,12 @@ jobs:
           python-version: "3.8"
       - name: Install dependencies
         run: |
-          pip install -e .
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          pip install torch torchvision torchaudio pytest
+          python -m pip install --upgrade pip uv
+          python -m uv pip install -e .
+          python -m uv pip install torch torchvision torchaudio
+          python -m uv pip install pytest
       - name: Check for soft dependencies
         run: |
-            pytest tests/others/test_dependencies.py
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+          pytest tests/others/test_dependencies.py

.github/workflows/push_tests.yml

@@ -14,7 +14,7 @@ env:
   DIFFUSERS_IS_CI: yes
   OMP_NUM_THREADS: 8
   MKL_NUM_THREADS: 8
-  HF_XET_HIGH_PERFORMANCE: 1
+  HF_HUB_ENABLE_HF_TRANSFER: 1
   PYTEST_TIMEOUT: 600
   PIPELINE_USAGE_CUTOFF: 50000
 
@@ -34,7 +34,8 @@ jobs:
           fetch-depth: 2
       - name: Install dependencies
         run: |
-          uv pip install -e ".[quality]"
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+          python -m uv pip install -e [quality,test]
       - name: Environment
         run: |
           python utils/print_env.py
@@ -74,10 +75,9 @@ jobs:
           nvidia-smi
       - name: Install dependencies
         run: |
-          uv pip install -e ".[quality]"
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+          python -m uv pip install -e [quality,test]
-          #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+          pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-          uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
       - name: Environment
         run: |
           python utils/print_env.py
@@ -87,8 +87,8 @@ jobs:
           # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
-          pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+          python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            -k "not Flax and not Onnx" \
+            -s -v -k "not Flax and not Onnx" \
             --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
             tests/pipelines/${{ matrix.module }}
       - name: Failure short reports
@@ -126,11 +126,10 @@ jobs:
 
     - name: Install dependencies
       run: |
-        uv pip install -e ".[quality]"
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        uv pip install peft@git+https://github.com/huggingface/peft.git
+        python -m uv pip install -e [quality,test]
-        uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+        python -m uv pip install peft@git+https://github.com/huggingface/peft.git
-        #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-        uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
 
     - name: Environment
       run: |
@@ -142,8 +141,8 @@ jobs:
         # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -k "not Flax and not Onnx" \
+          -s -v -k "not Flax and not Onnx" \
           --make-reports=tests_torch_cuda_${{ matrix.module }} \
           tests/${{ matrix.module }}
 
@@ -181,9 +180,8 @@ jobs:
         nvidia-smi
     - name: Install dependencies
       run: |
-        uv pip install -e ".[quality,training]"
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+        python -m uv pip install -e [quality,test,training]
-        uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
     - name: Environment
       run: |
         python utils/print_env.py
@@ -192,7 +190,7 @@ jobs:
         HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
         RUN_COMPILE: yes
       run: |
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile -k "compile" --make-reports=tests_torch_compile_cuda tests/
+        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: ${{ failure() }}
       run: cat reports/tests_torch_compile_cuda_failures_short.txt
@@ -225,7 +223,8 @@ jobs:
         nvidia-smi
     - name: Install dependencies
       run: |
-        uv pip install -e ".[quality,training]"
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m uv pip install -e [quality,test,training]
     - name: Environment
       run: |
         python utils/print_env.py
@@ -233,7 +232,7 @@ jobs:
       env:
         HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
       run: |
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile -k "xformers" --make-reports=tests_torch_xformers_cuda tests/
+        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: ${{ failure() }}
       run: cat reports/tests_torch_xformers_cuda_failures_short.txt
@@ -265,18 +264,21 @@ jobs:
         nvidia-smi
     - name: Install dependencies
       run: |
-        uv pip install -e ".[quality,training]"
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$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: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
       run: |
-        uv pip install ".[training]"
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile --make-reports=examples_torch_cuda examples/
+        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() }}

.github/workflows/push_tests_fast.yml

@@ -18,7 +18,7 @@ env:
   HF_HOME: /mnt/cache
   OMP_NUM_THREADS: 8
   MKL_NUM_THREADS: 8
-  HF_XET_HIGH_PERFORMANCE: 1
+  HF_HUB_ENABLE_HF_TRANSFER: 1
   PYTEST_TIMEOUT: 600
   RUN_SLOW: no
 
@@ -60,25 +60,29 @@ jobs:
 
     - name: Install dependencies
       run: |
-        uv pip install -e ".[quality]"
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m uv pip install -e [quality,test]
 
     - name: Environment
       run: |
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python utils/print_env.py
 
     - name: Run fast PyTorch CPU tests
       if: ${{ matrix.config.framework == 'pytorch' }}
       run: |
-        pytest -n 4 --max-worker-restart=0 --dist=loadfile \
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          -k "not Flax and not Onnx" \
+        python -m pytest -n 4 --max-worker-restart=0 --dist=loadfile \
+          -s -v -k "not Flax and not Onnx" \
           --make-reports=tests_${{ matrix.config.report }} \
           tests/
 
     - name: Run example PyTorch CPU tests
       if: ${{ matrix.config.framework == 'pytorch_examples' }}
       run: |
-        uv pip install ".[training]"
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        pytest -n 4 --max-worker-restart=0 --dist=loadfile \
+        python -m uv pip install peft timm
+        python -m pytest -n 4 --max-worker-restart=0 --dist=loadfile \
           --make-reports=tests_${{ matrix.config.report }} \
           examples
 

.github/workflows/push_tests_mps.yml

@@ -8,7 +8,7 @@ env:
   HF_HOME: /mnt/cache
   OMP_NUM_THREADS: 8
   MKL_NUM_THREADS: 8
-  HF_XET_HIGH_PERFORMANCE: 1
+  HF_HUB_ENABLE_HF_TRANSFER: 1
   PYTEST_TIMEOUT: 600
   RUN_SLOW: no
 
@@ -57,7 +57,7 @@ jobs:
         HF_HOME: /System/Volumes/Data/mnt/cache
         HF_TOKEN: ${{ secrets.HF_TOKEN }}
       run: |
-        ${CONDA_RUN} python -m pytest -n 0 --make-reports=tests_torch_mps tests/
+        ${CONDA_RUN} python -m pytest -n 0 -s -v --make-reports=tests_torch_mps tests/
 
     - name: Failure short reports
       if: ${{ failure() }}

.github/workflows/release_tests_fast.yml

@@ -32,7 +32,8 @@ jobs:
           fetch-depth: 2
       - name: Install dependencies
         run: |
-          uv pip install -e ".[quality]"
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+          python -m uv pip install -e [quality,test]
       - name: Environment
         run: |
           python utils/print_env.py
@@ -72,8 +73,9 @@ jobs:
           nvidia-smi
       - name: Install dependencies
         run: |
-          uv pip install -e ".[quality]"
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+          python -m uv pip install -e [quality,test]
+          pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
       - name: Environment
         run: |
           python utils/print_env.py
@@ -83,8 +85,8 @@ jobs:
           # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
-          pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+          python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            -k "not Flax and not Onnx" \
+            -s -v -k "not Flax and not Onnx" \
             --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
             tests/pipelines/${{ matrix.module }}
       - name: Failure short reports
@@ -122,9 +124,10 @@ jobs:
 
     - name: Install dependencies
       run: |
-        uv pip install -e ".[quality]"
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        uv pip install peft@git+https://github.com/huggingface/peft.git
+        python -m uv pip install -e [quality,test]
-        uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+        python -m uv pip install peft@git+https://github.com/huggingface/peft.git
+        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
 
     - name: Environment
       run: |
@@ -136,8 +139,8 @@ jobs:
         # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -k "not Flax and not Onnx" \
+          -s -v -k "not Flax and not Onnx" \
           --make-reports=tests_torch_${{ matrix.module }}_cuda \
           tests/${{ matrix.module }}
 
@@ -172,9 +175,10 @@ jobs:
 
       - name: Install dependencies
         run: |
-          uv pip install -e ".[quality]"
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          uv pip install peft@git+https://github.com/huggingface/peft.git
+          python -m uv pip install -e [quality,test]
-          uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+          python -m uv pip install peft@git+https://github.com/huggingface/peft.git
+          pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
 
       - name: Environment
         run: |
@@ -186,8 +190,8 @@ jobs:
           # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
-          pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+          python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            -k "not Flax and not Onnx" \
+            -s -v -k "not Flax and not Onnx" \
             --make-reports=tests_torch_minimum_cuda \
             tests/models/test_modeling_common.py \
             tests/pipelines/test_pipelines_common.py \
@@ -231,7 +235,8 @@ jobs:
         nvidia-smi
     - name: Install dependencies
       run: |
-        uv pip install -e ".[quality,training]"
+        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
@@ -240,7 +245,7 @@ jobs:
         HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
         RUN_COMPILE: yes
       run: |
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile -k "compile" --make-reports=tests_torch_compile_cuda tests/
+        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: ${{ failure() }}
       run: cat reports/tests_torch_compile_cuda_failures_short.txt
@@ -273,7 +278,8 @@ jobs:
         nvidia-smi
     - name: Install dependencies
       run: |
-        uv pip install -e ".[quality,training]"
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m uv pip install -e [quality,test,training]
     - name: Environment
       run: |
         python utils/print_env.py
@@ -281,7 +287,7 @@ jobs:
       env:
         HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
       run: |
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile -k "xformers" --make-reports=tests_torch_xformers_cuda tests/
+        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
@@ -315,18 +321,21 @@ jobs:
 
     - name: Install dependencies
       run: |
-        uv pip install -e ".[quality,training]"
+        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: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
       run: |
-        uv pip install ".[training]"
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile --make-reports=examples_torch_cuda examples/
+        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() }}

.github/workflows/run_tests_from_a_pr.yml

@@ -63,8 +63,9 @@ jobs:
 
       - name: Install pytest
         run: |
-          uv pip install -e ".[quality]"
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          uv pip install peft
+          python -m uv pip install -e [quality,test]
+          python -m uv pip install peft
 
       - name: Run tests
         env:

.gitignore

@@ -125,9 +125,6 @@ dmypy.json
 .vs
 .vscode
 
-# Cursor
-.cursor
-
 # Pycharm
 .idea
 

README.md

@@ -171,7 +171,7 @@ Also, say 👋 in our public Discord channel <a href="https://discord.gg/G7tWnz9
   <tr style="border-top: 2px solid black">
     <td>Text-guided Image Inpainting</td>
     <td><a href="https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/inpaint">Stable Diffusion Inpainting</a></td>
-      <td><a href="https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-inpainting"> stable-diffusion-v1-5/stable-diffusion-inpainting </a></td>
+      <td><a href="https://huggingface.co/runwayml/stable-diffusion-inpainting"> runwayml/stable-diffusion-inpainting </a></td>
   </tr>
   <tr style="border-top: 2px solid black">
     <td>Image Variation</td>

docker/diffusers-doc-builder/Dockerfile

@@ -1,45 +1,56 @@
-FROM python:3.10-slim
+FROM ubuntu:20.04
-ENV PYTHONDONTWRITEBYTECODE=1
 LABEL maintainer="Hugging Face"
 LABEL repository="diffusers"
 
 ENV DEBIAN_FRONTEND=noninteractive
 
-RUN apt-get -y update && apt-get install -y bash \
+RUN apt-get -y update \
-    build-essential \
+    && apt-get install -y software-properties-common \
-    git \
+    && add-apt-repository ppa:deadsnakes/ppa
-    git-lfs \
-    curl \
-    ca-certificates \
-    libglib2.0-0 \
-    libsndfile1-dev \
-    libgl1 \
-    zip \
-    wget
 
-ENV UV_PYTHON=/usr/local/bin/python
+RUN apt install -y bash \
+                   build-essential \
+                   git \
+                   git-lfs \
+                   curl \
+                   ca-certificates \
+                   libsndfile1-dev \
+                   python3.10 \
+                   python3-pip \
+                   libgl1 \
+                   zip \
+                   wget \
+                   python3.10-venv && \
+    rm -rf /var/lib/apt/lists
+
+# make sure to use venv
+RUN python3.10 -m venv /opt/venv
+ENV PATH="/opt/venv/bin:$PATH"
 
 # pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
-RUN pip install uv
+RUN python3.10 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
-RUN uv pip install --no-cache-dir \
+    python3.10 -m uv pip install --no-cache-dir \
-    torch \
+        torch \
-    torchvision \
+        torchvision \
-    torchaudio \
+        torchaudio \
-    --extra-index-url https://download.pytorch.org/whl/cpu
+        invisible_watermark \
-
+        --extra-index-url https://download.pytorch.org/whl/cpu && \
-RUN uv pip install --no-cache-dir "git+https://github.com/huggingface/diffusers.git@main#egg=diffusers[test]"
+    python3.10 -m uv pip install --no-cache-dir \
-
+        accelerate \
-# Extra dependencies
+        datasets \
-RUN uv pip install --no-cache-dir \
+        hf-doc-builder \
-    accelerate \
+        huggingface-hub \
-    numpy==1.26.4 \
+        Jinja2 \
-    hf_xet \
+        librosa \
-    setuptools==69.5.1 \
+        numpy==1.26.4 \
-    bitsandbytes \
+        scipy \
-    torchao \
+        tensorboard \
-    gguf \
+        transformers \
-    optimum-quanto
+        matplotlib \
-
+        setuptools==69.5.1 \
-RUN apt-get clean && rm -rf /var/lib/apt/lists/* && apt-get autoremove && apt-get autoclean
+        bitsandbytes \
+        torchao \
+        gguf \
+        optimum-quanto
 
 CMD ["/bin/bash"]

docker/diffusers-onnxruntime-cpu/Dockerfile

@@ -44,6 +44,6 @@ RUN python3 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
         scipy \
         tensorboard \
         transformers \
-        hf_xet
+        hf_transfer
 
 CMD ["/bin/bash"]

docker/diffusers-onnxruntime-cuda/Dockerfile

@@ -38,12 +38,13 @@ RUN python3.10 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
         datasets \
         hf-doc-builder \
         huggingface-hub \
-        hf_xet \
+        hf_transfer \
         Jinja2 \
         librosa \
         numpy==1.26.4 \
         scipy \
         tensorboard \
-        transformers
+        transformers \
+        hf_transfer
 
 CMD ["/bin/bash"]

docker/diffusers-pytorch-cpu/Dockerfile

@@ -1,38 +1,50 @@
-FROM python:3.10-slim
+FROM ubuntu:20.04
-ENV PYTHONDONTWRITEBYTECODE=1
 LABEL maintainer="Hugging Face"
 LABEL repository="diffusers"
 
 ENV DEBIAN_FRONTEND=noninteractive
 
-RUN apt-get -y update && apt-get install -y bash \
+RUN apt-get -y update \
-    build-essential \
+    && apt-get install -y software-properties-common \
-    git \
+    && add-apt-repository ppa:deadsnakes/ppa
-    git-lfs \
-    curl \
-    ca-certificates \
-    libglib2.0-0 \
-    libsndfile1-dev \
-    libgl1
 
-ENV UV_PYTHON=/usr/local/bin/python
+RUN apt install -y bash \
+                   build-essential \
+                   git \
+                   git-lfs \
+                   curl \
+                   ca-certificates \
+                   libsndfile1-dev \
+                   python3.10 \
+                   python3.10-dev \
+                   python3-pip \
+                   libgl1 \
+                   python3.10-venv && \
+    rm -rf /var/lib/apt/lists
+
+# make sure to use venv
+RUN python3.10 -m venv /opt/venv
+ENV PATH="/opt/venv/bin:$PATH"
 
 # pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
-RUN pip install uv
+RUN python3.10 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
-RUN uv pip install --no-cache-dir \
+    python3.10 -m uv pip install --no-cache-dir \
-    torch \
+        torch \
-    torchvision \
+        torchvision \
-    torchaudio \
+        torchaudio \
-    --extra-index-url https://download.pytorch.org/whl/cpu
+        invisible_watermark \
-
+        --extra-index-url https://download.pytorch.org/whl/cpu && \
-RUN uv pip install --no-cache-dir "git+https://github.com/huggingface/diffusers.git@main#egg=diffusers[test]"
+    python3.10 -m uv pip install --no-cache-dir \
-
+        accelerate \
-# Extra dependencies
+        datasets \
-RUN uv pip install --no-cache-dir \
+        hf-doc-builder \
-    accelerate \
+        huggingface-hub \
-    numpy==1.26.4 \
+        Jinja2 \
-    hf_xet
+        librosa \
-
+        numpy==1.26.4 \
-RUN apt-get clean && rm -rf /var/lib/apt/lists/* && apt-get autoremove && apt-get autoclean
+        scipy \
+        tensorboard \
+        transformers matplotlib  \
+        hf_transfer
 
 CMD ["/bin/bash"]

docker/diffusers-pytorch-cuda/Dockerfile

@@ -2,13 +2,11 @@ FROM nvidia/cuda:12.1.0-runtime-ubuntu20.04
 LABEL maintainer="Hugging Face"
 LABEL repository="diffusers"
 
-ARG PYTHON_VERSION=3.12
 ENV DEBIAN_FRONTEND=noninteractive
 
 RUN apt-get -y update \
     && apt-get install -y software-properties-common \
-    && add-apt-repository ppa:deadsnakes/ppa && \
+    && add-apt-repository ppa:deadsnakes/ppa
-    apt-get update
 
 RUN apt install -y bash \
     build-essential \
@@ -16,34 +14,38 @@ RUN apt install -y bash \
     git-lfs \
     curl \
     ca-certificates \
-    libglib2.0-0 \
     libsndfile1-dev \
     libgl1 \
-    python3 \
+    python3.10 \
+    python3.10-dev \
     python3-pip \
-    && apt-get clean \
+    python3.10-venv && \
-    && rm -rf /var/lib/apt/lists/*
+    rm -rf /var/lib/apt/lists
 
-RUN curl -LsSf https://astral.sh/uv/install.sh | sh
+# make sure to use venv
-ENV PATH="/root/.local/bin:$PATH"
+RUN python3.10 -m venv /opt/venv
-ENV VIRTUAL_ENV="/opt/venv"
+ENV PATH="/opt/venv/bin:$PATH"
-ENV UV_PYTHON_INSTALL_DIR=/opt/uv/python
-RUN uv venv --python ${PYTHON_VERSION} --seed ${VIRTUAL_ENV}
-ENV PATH="$VIRTUAL_ENV/bin:$PATH"
 
 # pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
-RUN uv pip install --no-cache-dir \
+RUN python3.10 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
+    python3.10 -m uv pip install --no-cache-dir \
     torch \
     torchvision \
-    torchaudio
+    torchaudio \
-
+    invisible_watermark && \
-RUN uv pip install --no-cache-dir "git+https://github.com/huggingface/diffusers.git@main#egg=diffusers[test]"
+    python3.10 -m pip install --no-cache-dir \
-
-# Extra dependencies
-RUN uv pip install --no-cache-dir \
     accelerate \
+    datasets \
+    hf-doc-builder \
+    huggingface-hub \
+    hf_transfer \
+    Jinja2 \
+    librosa \
     numpy==1.26.4 \
-    pytorch-lightning \
+    scipy \
-    hf_xet
+    tensorboard \
+    transformers \
+    pytorch-lightning  \
+    hf_transfer
 
 CMD ["/bin/bash"]

docker/diffusers-pytorch-minimum-cuda/Dockerfile

@@ -2,7 +2,6 @@ FROM nvidia/cuda:12.1.0-runtime-ubuntu20.04
 LABEL maintainer="Hugging Face"
 LABEL repository="diffusers"
 
-ARG PYTHON_VERSION=3.10
 ENV DEBIAN_FRONTEND=noninteractive
 ENV MINIMUM_SUPPORTED_TORCH_VERSION="2.1.0"
 ENV MINIMUM_SUPPORTED_TORCHVISION_VERSION="0.16.0"
@@ -10,8 +9,7 @@ ENV MINIMUM_SUPPORTED_TORCHAUDIO_VERSION="2.1.0"
 
 RUN apt-get -y update \
     && apt-get install -y software-properties-common \
-    && add-apt-repository ppa:deadsnakes/ppa && \
+    && add-apt-repository ppa:deadsnakes/ppa
-    apt-get update
 
 RUN apt install -y bash \
     build-essential \
@@ -19,34 +17,37 @@ RUN apt install -y bash \
     git-lfs \
     curl \
     ca-certificates \
-    libglib2.0-0 \
     libsndfile1-dev \
     libgl1 \
-    python3 \
+    python3.10 \
+    python3.10-dev \
     python3-pip \
-    && apt-get clean \
+    python3.10-venv && \
-    && rm -rf /var/lib/apt/lists/*
+    rm -rf /var/lib/apt/lists
 
-RUN curl -LsSf https://astral.sh/uv/install.sh | sh
+# make sure to use venv
-ENV PATH="/root/.local/bin:$PATH"
+RUN python3.10 -m venv /opt/venv
-ENV VIRTUAL_ENV="/opt/venv"
+ENV PATH="/opt/venv/bin:$PATH"
-ENV UV_PYTHON_INSTALL_DIR=/opt/uv/python
-RUN uv venv --python ${PYTHON_VERSION} --seed ${VIRTUAL_ENV}
-ENV PATH="$VIRTUAL_ENV/bin:$PATH"
 
 # pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
-RUN uv pip install --no-cache-dir \
+RUN python3.10 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
+    python3.10 -m uv pip install --no-cache-dir \
     torch==$MINIMUM_SUPPORTED_TORCH_VERSION \
     torchvision==$MINIMUM_SUPPORTED_TORCHVISION_VERSION \
-    torchaudio==$MINIMUM_SUPPORTED_TORCHAUDIO_VERSION
+    torchaudio==$MINIMUM_SUPPORTED_TORCHAUDIO_VERSION \
-
+    invisible_watermark && \
-RUN uv pip install --no-cache-dir "git+https://github.com/huggingface/diffusers.git@main#egg=diffusers[test]"
+    python3.10 -m pip install --no-cache-dir \
-
-# Extra dependencies
-RUN uv pip install --no-cache-dir \
     accelerate \
+    datasets \
+    hf-doc-builder \
+    huggingface-hub \
+    hf_transfer \
+    Jinja2 \
+    librosa \
     numpy==1.26.4 \
-    pytorch-lightning \
+    scipy \
-    hf_xet
+    tensorboard \
+    transformers \
+    hf_transfer
 
 CMD ["/bin/bash"]

docker/diffusers-pytorch-xformers-cuda/Dockerfile

@@ -2,49 +2,50 @@ FROM nvidia/cuda:12.1.0-runtime-ubuntu20.04
 LABEL maintainer="Hugging Face"
 LABEL repository="diffusers"
 
-ARG PYTHON_VERSION=3.12
 ENV DEBIAN_FRONTEND=noninteractive
 
 RUN apt-get -y update \
     && apt-get install -y software-properties-common \
-    && add-apt-repository ppa:deadsnakes/ppa && \
+    && add-apt-repository ppa:deadsnakes/ppa
-    apt-get update
 
 RUN apt install -y bash \
-    build-essential \
+                   build-essential \
-    git \
+                   git \
-    git-lfs \
+                   git-lfs \
-    curl \
+                   curl \
-    ca-certificates \
+                   ca-certificates \
-    libglib2.0-0 \
+                   libsndfile1-dev \
-    libsndfile1-dev \
+                   libgl1 \
-    libgl1 \
+                   python3.10 \
-    python3 \
+                   python3.10-dev \
-    python3-pip \
+                   python3-pip \
-    && apt-get clean \
+                   python3.10-venv && \
-    && rm -rf /var/lib/apt/lists/*
+    rm -rf /var/lib/apt/lists
 
-RUN curl -LsSf https://astral.sh/uv/install.sh | sh
+# make sure to use venv
-ENV PATH="/root/.local/bin:$PATH"
+RUN python3.10 -m venv /opt/venv
-ENV VIRTUAL_ENV="/opt/venv"
+ENV PATH="/opt/venv/bin:$PATH"
-ENV UV_PYTHON_INSTALL_DIR=/opt/uv/python
-RUN uv venv --python ${PYTHON_VERSION} --seed ${VIRTUAL_ENV}
-ENV PATH="$VIRTUAL_ENV/bin:$PATH"
 
 # pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
-RUN uv pip install --no-cache-dir \
+RUN python3.10 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
-    torch \
+    python3.10 -m pip install --no-cache-dir \
-    torchvision \
+        torch \
-    torchaudio
+        torchvision \
-
+        torchaudio \
-RUN uv pip install --no-cache-dir "git+https://github.com/huggingface/diffusers.git@main#egg=diffusers[test]"
+        invisible_watermark && \
-
+    python3.10 -m uv pip install --no-cache-dir \
-# Extra dependencies
+        accelerate \
-RUN uv pip install --no-cache-dir \
+        datasets \
-    accelerate \
+        hf-doc-builder \
-    numpy==1.26.4 \
+        huggingface-hub \
-    pytorch-lightning \
+        hf_transfer \
-    hf_xet \
+        Jinja2 \
-    xformers
+        librosa \
+        numpy==1.26.4 \
+        scipy \
+        tensorboard \
+        transformers \
+        xformers  \
+        hf_transfer
 
 CMD ["/bin/bash"]

docs/source/en/_toctree.yml

@@ -1,4 +1,5 @@
-- sections:
+- title: Get started
+  sections:
   - local: index
     title: Diffusers
   - local: installation
@@ -7,8 +8,9 @@
     title: Quickstart
   - local: stable_diffusion
     title: Basic performance
-  title: Get started
+
-- isExpanded: false
+- title: Pipelines
+  isExpanded: false
   sections:
   - local: using-diffusers/loading
     title: DiffusionPipeline
@@ -21,15 +23,16 @@
   - local: using-diffusers/reusing_seeds
     title: Reproducibility
   - local: using-diffusers/schedulers
-    title: Schedulers
+    title: Load schedulers and models
-  - local: using-diffusers/automodel
+  - local: using-diffusers/scheduler_features
-    title: AutoModel
+    title: Scheduler features
   - local: using-diffusers/other-formats
-    title: Model formats
+    title: Model files and layouts
   - local: using-diffusers/push_to_hub
-    title: Sharing pipelines and models
+    title: Push files to the Hub
-  title: Pipelines
+
-- isExpanded: false
+- title: Adapters
+  isExpanded: false
   sections:
   - local: tutorials/using_peft_for_inference
     title: LoRA
@@ -43,31 +46,38 @@
     title: DreamBooth
   - local: using-diffusers/textual_inversion_inference
     title: Textual inversion
-  title: Adapters
+
-- isExpanded: false
+- title: Inference
+  isExpanded: false
   sections:
   - local: using-diffusers/weighted_prompts
-    title: Prompting
+    title: Prompt techniques
   - local: using-diffusers/create_a_server
     title: Create a server
   - local: using-diffusers/batched_inference
     title: Batch inference
   - local: training/distributed_inference
     title: Distributed inference
-  title: Inference
+  - local: using-diffusers/scheduler_features
-- isExpanded: false
+    title: Scheduler features
+  - local: using-diffusers/callback
+    title: Pipeline callbacks
+  - local: using-diffusers/image_quality
+    title: Controlling image quality
+
+- title: Inference optimization
+  isExpanded: false
   sections:
   - local: optimization/fp16
     title: Accelerate inference
   - local: optimization/cache
     title: Caching
-  - local: optimization/attention_backends
-    title: Attention backends
   - local: optimization/memory
     title: Reduce memory usage
   - local: optimization/speed-memory-optims
     title: Compiling and offloading quantized models
-  - sections:
+  - title: Community optimizations
+    sections:
     - local: optimization/pruna
       title: Pruna
     - local: optimization/xformers
@@ -76,19 +86,15 @@
       title: Token merging
     - local: optimization/deepcache
       title: DeepCache
-    - local: optimization/cache_dit
-      title: CacheDiT
     - local: optimization/tgate
       title: TGATE
     - local: optimization/xdit
       title: xDiT
     - local: optimization/para_attn
       title: ParaAttention
-    - local: using-diffusers/image_quality
+
-      title: FreeU
+- title: Hybrid Inference
-    title: Community optimizations
+  isExpanded: false
-  title: Inference optimization
-- isExpanded: false
   sections:
   - local: hybrid_inference/overview
     title: Overview
@@ -98,8 +104,9 @@
     title: VAE Encode
   - local: hybrid_inference/api_reference
     title: API Reference
-  title: Hybrid Inference
+
-- isExpanded: false
+- title: Modular Diffusers
+  isExpanded: false
   sections:
   - local: modular_diffusers/overview
     title: Overview
@@ -121,10 +128,9 @@
     title: ComponentsManager
   - local: modular_diffusers/guiders
     title: Guiders
-  - local: modular_diffusers/custom_blocks
+
-    title: Building Custom Blocks
+- title: Training
-  title: Modular Diffusers
+  isExpanded: false
-- isExpanded: false
   sections:
   - local: training/overview
     title: Overview
@@ -134,7 +140,8 @@
     title: Adapt a model to a new task
   - local: tutorials/basic_training
     title: Train a diffusion model
-  - sections:
+  - title: Models
+    sections:
     - local: training/unconditional_training
       title: Unconditional image generation
     - local: training/text2image
@@ -153,8 +160,8 @@
       title: InstructPix2Pix
     - local: training/cogvideox
       title: CogVideoX
-    title: Models
+  - title: Methods
-  - sections:
+    sections:
     - local: training/text_inversion
       title: Textual Inversion
     - local: training/dreambooth
@@ -167,9 +174,9 @@
       title: Latent Consistency Distillation
     - local: training/ddpo
       title: Reinforcement learning training with DDPO
-    title: Methods
+
-  title: Training
+- title: Quantization
-- isExpanded: false
+  isExpanded: false
   sections:
   - local: quantization/overview
     title: Getting started
@@ -181,10 +188,9 @@
     title: torchao
   - local: quantization/quanto
     title: quanto
-  - local: quantization/modelopt
+
-    title: NVIDIA ModelOpt
+- title: Model accelerators and hardware
-  title: Quantization
+  isExpanded: false
-- isExpanded: false
   sections:
   - local: optimization/onnx
     title: ONNX
@@ -198,8 +204,9 @@
     title: Intel Gaudi
   - local: optimization/neuron
     title: AWS Neuron
-  title: Model accelerators and hardware
+
-- isExpanded: false
+- title: Specific pipeline examples
+  isExpanded: false
   sections:
   - local: using-diffusers/consisid
     title: ConsisID
@@ -225,10 +232,12 @@
     title: Stable Video Diffusion
   - local: using-diffusers/marigold_usage
     title: Marigold Computer Vision
-  title: Specific pipeline examples
+
-- isExpanded: false
+- title: Resources
+  isExpanded: false
   sections:
-  - sections:
+  - title: Task recipes
+    sections:
     - local: using-diffusers/unconditional_image_generation
       title: Unconditional image generation
     - local: using-diffusers/conditional_image_generation
@@ -243,7 +252,6 @@
       title: Video generation
     - local: using-diffusers/depth2img
       title: Depth-to-image
-    title: Task recipes
   - local: using-diffusers/write_own_pipeline
     title: Understanding pipelines, models and schedulers
   - local: community_projects
@@ -258,10 +266,12 @@
     title: Diffusers' Ethical Guidelines
   - local: conceptual/evaluation
     title: Evaluating Diffusion Models
-  title: Resources
+
-- isExpanded: false
+- title: API
+  isExpanded: false
   sections:
-  - sections:
+  - title: Main Classes
+    sections:
     - local: api/configuration
       title: Configuration
     - local: api/logging
@@ -270,10 +280,8 @@
       title: Outputs
     - local: api/quantization
       title: Quantization
-    - local: api/parallel
+  - title: Modular
-      title: Parallel inference
+    sections:
-    title: Main Classes
-  - sections:
     - local: api/modular_diffusers/pipeline
       title: Pipeline
     - local: api/modular_diffusers/pipeline_blocks
@@ -284,8 +292,8 @@
       title: Components and configs
     - local: api/modular_diffusers/guiders
       title: Guiders
-    title: Modular
+  - title: Loaders
-  - sections:
+    sections:
     - local: api/loaders/ip_adapter
       title: IP-Adapter
     - local: api/loaders/lora
@@ -300,13 +308,14 @@
       title: SD3Transformer2D
     - local: api/loaders/peft
       title: PEFT
-    title: Loaders
+  - title: Models
-  - sections:
+    sections:
     - local: api/models/overview
       title: Overview
     - local: api/models/auto_model
       title: AutoModel
-    - sections:
+    - title: ControlNets
+      sections:
       - local: api/models/controlnet
         title: ControlNetModel
       - local: api/models/controlnet_union
@@ -321,20 +330,16 @@
         title: SD3ControlNetModel
       - local: api/models/controlnet_sparsectrl
         title: SparseControlNetModel
-      title: ControlNets
+    - title: Transformers
-    - sections:
+      sections:
       - local: api/models/allegro_transformer3d
         title: AllegroTransformer3DModel
       - local: api/models/aura_flow_transformer2d
         title: AuraFlowTransformer2DModel
-      - local: api/models/transformer_bria_fibo
-        title: BriaFiboTransformer2DModel
       - local: api/models/bria_transformer
         title: BriaTransformer2DModel
       - local: api/models/chroma_transformer
         title: ChromaTransformer2DModel
-      - local: api/models/chronoedit_transformer_3d
-        title: ChronoEditTransformer3DModel
       - local: api/models/cogvideox_transformer3d
         title: CogVideoXTransformer3DModel
       - local: api/models/cogview3plus_transformer2d
@@ -349,18 +354,12 @@
         title: DiTTransformer2DModel
       - local: api/models/easyanimate_transformer3d
         title: EasyAnimateTransformer3DModel
-      - local: api/models/flux2_transformer
-        title: Flux2Transformer2DModel
       - local: api/models/flux_transformer
         title: FluxTransformer2DModel
       - local: api/models/hidream_image_transformer
         title: HiDreamImageTransformer2DModel
       - local: api/models/hunyuan_transformer2d
         title: HunyuanDiT2DModel
-      - local: api/models/hunyuanimage_transformer_2d
-        title: HunyuanImageTransformer2DModel
-      - local: api/models/hunyuan_video15_transformer_3d
-        title: HunyuanVideo15Transformer3DModel
       - local: api/models/hunyuan_video_transformer_3d
         title: HunyuanVideoTransformer3DModel
       - local: api/models/latte_transformer3d
@@ -375,8 +374,6 @@
         title: MochiTransformer3DModel
       - local: api/models/omnigen_transformer
         title: OmniGenTransformer2DModel
-      - local: api/models/ovisimage_transformer2d
-        title: OvisImageTransformer2DModel
       - local: api/models/pixart_transformer2d
         title: PixArtTransformer2DModel
       - local: api/models/prior_transformer
@@ -385,8 +382,6 @@
         title: QwenImageTransformer2DModel
       - local: api/models/sana_transformer2d
         title: SanaTransformer2DModel
-      - local: api/models/sana_video_transformer3d
-        title: SanaVideoTransformer3DModel
       - local: api/models/sd3_transformer2d
         title: SD3Transformer2DModel
       - local: api/models/skyreels_v2_transformer_3d
@@ -397,14 +392,10 @@
         title: Transformer2DModel
       - local: api/models/transformer_temporal
         title: TransformerTemporalModel
-      - local: api/models/wan_animate_transformer_3d
-        title: WanAnimateTransformer3DModel
       - local: api/models/wan_transformer_3d
         title: WanTransformer3DModel
-      - local: api/models/z_image_transformer2d
+    - title: UNets
-        title: ZImageTransformer2DModel        
+      sections:
-      title: Transformers
-    - sections:
       - local: api/models/stable_cascade_unet
         title: StableCascadeUNet
       - local: api/models/unet
@@ -419,8 +410,8 @@
         title: UNetMotionModel
       - local: api/models/uvit2d
         title: UViT2DModel
-      title: UNets
+    - title: VAEs
-    - sections:
+      sections:
       - local: api/models/asymmetricautoencoderkl
         title: AsymmetricAutoencoderKL
       - local: api/models/autoencoder_dc
@@ -433,14 +424,8 @@
         title: AutoencoderKLCogVideoX
       - local: api/models/autoencoderkl_cosmos
         title: AutoencoderKLCosmos
-      - local: api/models/autoencoder_kl_hunyuanimage
-        title: AutoencoderKLHunyuanImage
-      - local: api/models/autoencoder_kl_hunyuanimage_refiner
-        title: AutoencoderKLHunyuanImageRefiner
       - local: api/models/autoencoder_kl_hunyuan_video
         title: AutoencoderKLHunyuanVideo
-      - local: api/models/autoencoder_kl_hunyuan_video15
-        title: AutoencoderKLHunyuanVideo15
       - local: api/models/autoencoderkl_ltx_video
         title: AutoencoderKLLTXVideo
       - local: api/models/autoencoderkl_magvit
@@ -459,240 +444,210 @@
         title: Tiny AutoEncoder
       - local: api/models/vq
         title: VQModel
-      title: VAEs
+  - title: Pipelines
-    title: Models
+    sections:
-  - sections:
     - local: api/pipelines/overview
       title: Overview
+    - local: api/pipelines/allegro
+      title: Allegro
+    - local: api/pipelines/amused
+      title: aMUSEd
+    - local: api/pipelines/animatediff
+      title: AnimateDiff
+    - local: api/pipelines/attend_and_excite
+      title: Attend-and-Excite
+    - local: api/pipelines/audioldm
+      title: AudioLDM
+    - local: api/pipelines/audioldm2
+      title: AudioLDM 2
+    - local: api/pipelines/aura_flow
+      title: AuraFlow
     - local: api/pipelines/auto_pipeline
       title: AutoPipeline
-    - sections:
+    - local: api/pipelines/blip_diffusion
-      - local: api/pipelines/audioldm
+      title: BLIP-Diffusion
-        title: AudioLDM
+    - local: api/pipelines/bria_3_2
-      - local: api/pipelines/audioldm2
+      title: Bria 3.2
-        title: AudioLDM 2
+    - local: api/pipelines/chroma
-      - local: api/pipelines/dance_diffusion
+      title: Chroma
-        title: Dance Diffusion
+    - local: api/pipelines/cogvideox
-      - local: api/pipelines/musicldm
+      title: CogVideoX
-        title: MusicLDM
+    - local: api/pipelines/cogview3
-      - local: api/pipelines/stable_audio
+      title: CogView3
-        title: Stable Audio
+    - local: api/pipelines/cogview4
-      title: Audio
+      title: CogView4
-    - sections:
+    - local: api/pipelines/consisid
-      - local: api/pipelines/amused
+      title: ConsisID
-        title: aMUSEd
+    - local: api/pipelines/consistency_models
-      - local: api/pipelines/animatediff
+      title: Consistency Models
-        title: AnimateDiff
+    - local: api/pipelines/controlnet
-      - local: api/pipelines/attend_and_excite
+      title: ControlNet
-        title: Attend-and-Excite
+    - local: api/pipelines/controlnet_flux
-      - local: api/pipelines/aura_flow
+      title: ControlNet with Flux.1
-        title: AuraFlow
+    - local: api/pipelines/controlnet_hunyuandit
-      - local: api/pipelines/blip_diffusion
+      title: ControlNet with Hunyuan-DiT
-        title: BLIP-Diffusion
+    - local: api/pipelines/controlnet_sd3
-      - local: api/pipelines/bria_3_2
+      title: ControlNet with Stable Diffusion 3
-        title: Bria 3.2
+    - local: api/pipelines/controlnet_sdxl
-      - local: api/pipelines/bria_fibo
+      title: ControlNet with Stable Diffusion XL
-        title: Bria Fibo
+    - local: api/pipelines/controlnet_sana
-      - local: api/pipelines/chroma
+      title: ControlNet-Sana
-        title: Chroma
+    - local: api/pipelines/controlnetxs
-      - local: api/pipelines/cogview3
+      title: ControlNet-XS
-        title: CogView3
+    - local: api/pipelines/controlnetxs_sdxl
-      - local: api/pipelines/cogview4
+      title: ControlNet-XS with Stable Diffusion XL
-        title: CogView4
+    - local: api/pipelines/controlnet_union
-      - local: api/pipelines/consistency_models
+      title: ControlNetUnion
-        title: Consistency Models
+    - local: api/pipelines/cosmos
-      - local: api/pipelines/controlnet
+      title: Cosmos
-        title: ControlNet
+    - local: api/pipelines/dance_diffusion
-      - local: api/pipelines/controlnet_flux
+      title: Dance Diffusion
-        title: ControlNet with Flux.1
+    - local: api/pipelines/ddim
-      - local: api/pipelines/controlnet_hunyuandit
+      title: DDIM
-        title: ControlNet with Hunyuan-DiT
+    - local: api/pipelines/ddpm
-      - local: api/pipelines/controlnet_sd3
+      title: DDPM
-        title: ControlNet with Stable Diffusion 3
+    - local: api/pipelines/deepfloyd_if
-      - local: api/pipelines/controlnet_sdxl
+      title: DeepFloyd IF
-        title: ControlNet with Stable Diffusion XL
+    - local: api/pipelines/diffedit
-      - local: api/pipelines/controlnet_sana
+      title: DiffEdit
-        title: ControlNet-Sana
+    - local: api/pipelines/dit
-      - local: api/pipelines/controlnetxs
+      title: DiT
-        title: ControlNet-XS
+    - local: api/pipelines/easyanimate
-      - local: api/pipelines/controlnetxs_sdxl
+      title: EasyAnimate
-        title: ControlNet-XS with Stable Diffusion XL
+    - local: api/pipelines/flux
-      - local: api/pipelines/controlnet_union
+      title: Flux
-        title: ControlNetUnion
+    - local: api/pipelines/control_flux_inpaint
-      - local: api/pipelines/cosmos
+      title: FluxControlInpaint
-        title: Cosmos
+    - local: api/pipelines/framepack
-      - local: api/pipelines/ddim
+      title: Framepack
-        title: DDIM
+    - local: api/pipelines/hidream
-      - local: api/pipelines/ddpm
+      title: HiDream-I1
-        title: DDPM
+    - local: api/pipelines/hunyuandit
-      - local: api/pipelines/deepfloyd_if
+      title: Hunyuan-DiT
-        title: DeepFloyd IF
+    - local: api/pipelines/hunyuan_video
-      - local: api/pipelines/diffedit
+      title: HunyuanVideo
-        title: DiffEdit
+    - local: api/pipelines/i2vgenxl
-      - local: api/pipelines/dit
+      title: I2VGen-XL
-        title: DiT
+    - local: api/pipelines/pix2pix
-      - local: api/pipelines/easyanimate
+      title: InstructPix2Pix
-        title: EasyAnimate
+    - local: api/pipelines/kandinsky
-      - local: api/pipelines/flux
+      title: Kandinsky 2.1
-        title: Flux
+    - local: api/pipelines/kandinsky_v22
-      - local: api/pipelines/flux2
+      title: Kandinsky 2.2
-        title: Flux2
+    - local: api/pipelines/kandinsky3
-      - local: api/pipelines/control_flux_inpaint
+      title: Kandinsky 3
-        title: FluxControlInpaint
+    - local: api/pipelines/kolors
-      - local: api/pipelines/hidream
+      title: Kolors
-        title: HiDream-I1
+    - local: api/pipelines/latent_consistency_models
-      - local: api/pipelines/hunyuandit
+      title: Latent Consistency Models
-        title: Hunyuan-DiT
+    - local: api/pipelines/latent_diffusion
-      - local: api/pipelines/hunyuanimage21
+      title: Latent Diffusion
-        title: HunyuanImage2.1
+    - local: api/pipelines/latte
-      - local: api/pipelines/pix2pix
+      title: Latte
-        title: InstructPix2Pix
+    - local: api/pipelines/ledits_pp
-      - local: api/pipelines/kandinsky
+      title: LEDITS++
-        title: Kandinsky 2.1
+    - local: api/pipelines/ltx_video
-      - local: api/pipelines/kandinsky_v22
+      title: LTXVideo
-        title: Kandinsky 2.2
+    - local: api/pipelines/lumina2
-      - local: api/pipelines/kandinsky3
+      title: Lumina 2.0
-        title: Kandinsky 3
+    - local: api/pipelines/lumina
-      - local: api/pipelines/kandinsky5_image
+      title: Lumina-T2X
-        title: Kandinsky 5.0 Image
+    - local: api/pipelines/marigold
-      - local: api/pipelines/kolors
+      title: Marigold
-        title: Kolors
+    - local: api/pipelines/mochi
-      - local: api/pipelines/latent_consistency_models
+      title: Mochi
-        title: Latent Consistency Models
+    - local: api/pipelines/panorama
-      - local: api/pipelines/latent_diffusion
+      title: MultiDiffusion
-        title: Latent Diffusion
+    - local: api/pipelines/musicldm
-      - local: api/pipelines/ledits_pp
+      title: MusicLDM
-        title: LEDITS++
+    - local: api/pipelines/omnigen
-      - local: api/pipelines/lumina2
+      title: OmniGen
-        title: Lumina 2.0
+    - local: api/pipelines/pag
-      - local: api/pipelines/lumina
+      title: PAG
-        title: Lumina-T2X
+    - local: api/pipelines/paint_by_example
-      - local: api/pipelines/marigold
+      title: Paint by Example
-        title: Marigold
+    - local: api/pipelines/pia
-      - local: api/pipelines/panorama
+      title: Personalized Image Animator (PIA)
-        title: MultiDiffusion
+    - local: api/pipelines/pixart
-      - local: api/pipelines/omnigen
+      title: PixArt-α
-        title: OmniGen
+    - local: api/pipelines/pixart_sigma
-      - local: api/pipelines/ovis_image
+      title: PixArt-Σ
-        title: Ovis-Image
+    - local: api/pipelines/qwenimage
-      - local: api/pipelines/pag
+      title: QwenImage
-        title: PAG
+    - local: api/pipelines/sana
-      - local: api/pipelines/paint_by_example
+      title: Sana
-        title: Paint by Example
+    - local: api/pipelines/sana_sprint
-      - local: api/pipelines/pixart
+      title: Sana Sprint
-        title: PixArt-α
+    - local: api/pipelines/self_attention_guidance
-      - local: api/pipelines/pixart_sigma
+      title: Self-Attention Guidance
-        title: PixArt-Σ
+    - local: api/pipelines/semantic_stable_diffusion
-      - local: api/pipelines/prx
+      title: Semantic Guidance
-        title: PRX
+    - local: api/pipelines/shap_e
-      - local: api/pipelines/qwenimage
+      title: Shap-E
-        title: QwenImage
+    - local: api/pipelines/skyreels_v2
-      - local: api/pipelines/sana
+      title: SkyReels-V2
-        title: Sana
+    - local: api/pipelines/stable_audio
-      - local: api/pipelines/sana_sprint
+      title: Stable Audio
-        title: Sana Sprint
+    - local: api/pipelines/stable_cascade
-      - local: api/pipelines/sana_video
+      title: Stable Cascade
-        title: Sana Video
+    - title: Stable Diffusion
-      - local: api/pipelines/self_attention_guidance
+      sections:
-        title: Self-Attention Guidance
+      - local: api/pipelines/stable_diffusion/overview
-      - local: api/pipelines/semantic_stable_diffusion
+        title: Overview
-        title: Semantic Guidance
+      - local: api/pipelines/stable_diffusion/depth2img
-      - local: api/pipelines/shap_e
+        title: Depth-to-image
-        title: Shap-E
+      - local: api/pipelines/stable_diffusion/gligen
-      - local: api/pipelines/stable_cascade
+        title: GLIGEN (Grounded Language-to-Image Generation)
-        title: Stable Cascade
+      - local: api/pipelines/stable_diffusion/image_variation
-      - sections:
+        title: Image variation
-        - local: api/pipelines/stable_diffusion/overview
+      - local: api/pipelines/stable_diffusion/img2img
-          title: Overview
+        title: Image-to-image
-        - local: api/pipelines/stable_diffusion/depth2img
-          title: Depth-to-image
-        - local: api/pipelines/stable_diffusion/gligen
-          title: GLIGEN (Grounded Language-to-Image Generation)
-        - local: api/pipelines/stable_diffusion/image_variation
-          title: Image variation
-        - local: api/pipelines/stable_diffusion/img2img
-          title: Image-to-image
-        - local: api/pipelines/stable_diffusion/inpaint
-          title: Inpainting
-        - local: api/pipelines/stable_diffusion/k_diffusion
-          title: K-Diffusion
-        - local: api/pipelines/stable_diffusion/latent_upscale
-          title: Latent upscaler
-        - local: api/pipelines/stable_diffusion/ldm3d_diffusion
-          title: LDM3D Text-to-(RGB, Depth), Text-to-(RGB-pano, Depth-pano), LDM3D
-            Upscaler
-        - local: api/pipelines/stable_diffusion/stable_diffusion_safe
-          title: Safe Stable Diffusion
-        - local: api/pipelines/stable_diffusion/sdxl_turbo
-          title: SDXL Turbo
-        - local: api/pipelines/stable_diffusion/stable_diffusion_2
-          title: Stable Diffusion 2
-        - local: api/pipelines/stable_diffusion/stable_diffusion_3
-          title: Stable Diffusion 3
-        - local: api/pipelines/stable_diffusion/stable_diffusion_xl
-          title: Stable Diffusion XL
-        - local: api/pipelines/stable_diffusion/upscale
-          title: Super-resolution
-        - local: api/pipelines/stable_diffusion/adapter
-          title: T2I-Adapter
-        - local: api/pipelines/stable_diffusion/text2img
-          title: Text-to-image
-        title: Stable Diffusion
-      - local: api/pipelines/stable_unclip
-        title: Stable unCLIP
-      - local: api/pipelines/unclip
-        title: unCLIP
-      - local: api/pipelines/unidiffuser
-        title: UniDiffuser
-      - local: api/pipelines/value_guided_sampling
-        title: Value-guided sampling
-      - local: api/pipelines/visualcloze
-        title: VisualCloze
-      - local: api/pipelines/wuerstchen
-        title: Wuerstchen
-      - local: api/pipelines/z_image
-        title: Z-Image
-      title: Image
-    - sections:
-      - local: api/pipelines/allegro
-        title: Allegro
-      - local: api/pipelines/chronoedit
-        title: ChronoEdit
-      - local: api/pipelines/cogvideox
-        title: CogVideoX
-      - local: api/pipelines/consisid
-        title: ConsisID
-      - local: api/pipelines/framepack
-        title: Framepack
-      - local: api/pipelines/hunyuan_video
-        title: HunyuanVideo
-      - local: api/pipelines/hunyuan_video15
-        title: HunyuanVideo1.5
-      - local: api/pipelines/i2vgenxl
-        title: I2VGen-XL
-      - local: api/pipelines/kandinsky5_video
-        title: Kandinsky 5.0 Video
-      - local: api/pipelines/latte
-        title: Latte
-      - local: api/pipelines/ltx_video
-        title: LTXVideo
-      - local: api/pipelines/mochi
-        title: Mochi
-      - local: api/pipelines/pia
-        title: Personalized Image Animator (PIA)
-      - local: api/pipelines/skyreels_v2
-        title: SkyReels-V2
       - local: api/pipelines/stable_diffusion/svd
-        title: Stable Video Diffusion
+        title: Image-to-video
-      - local: api/pipelines/text_to_video
+      - local: api/pipelines/stable_diffusion/inpaint
-        title: Text-to-video
+        title: Inpainting
-      - local: api/pipelines/text_to_video_zero
+      - local: api/pipelines/stable_diffusion/k_diffusion
-        title: Text2Video-Zero
+        title: K-Diffusion
-      - local: api/pipelines/wan
+      - local: api/pipelines/stable_diffusion/latent_upscale
-        title: Wan
+        title: Latent upscaler
-      title: Video
+      - local: api/pipelines/stable_diffusion/ldm3d_diffusion
-    title: Pipelines
+        title: LDM3D Text-to-(RGB, Depth), Text-to-(RGB-pano, Depth-pano), LDM3D Upscaler
-  - sections:
+      - local: api/pipelines/stable_diffusion/stable_diffusion_safe
+        title: Safe Stable Diffusion
+      - local: api/pipelines/stable_diffusion/sdxl_turbo
+        title: SDXL Turbo
+      - local: api/pipelines/stable_diffusion/stable_diffusion_2
+        title: Stable Diffusion 2
+      - local: api/pipelines/stable_diffusion/stable_diffusion_3
+        title: Stable Diffusion 3
+      - local: api/pipelines/stable_diffusion/stable_diffusion_xl
+        title: Stable Diffusion XL
+      - local: api/pipelines/stable_diffusion/upscale
+        title: Super-resolution
+      - local: api/pipelines/stable_diffusion/adapter
+        title: T2I-Adapter
+      - local: api/pipelines/stable_diffusion/text2img
+        title: Text-to-image
+    - local: api/pipelines/stable_unclip
+      title: Stable unCLIP
+    - local: api/pipelines/text_to_video
+      title: Text-to-video
+    - local: api/pipelines/text_to_video_zero
+      title: Text2Video-Zero
+    - local: api/pipelines/unclip
+      title: unCLIP
+    - local: api/pipelines/unidiffuser
+      title: UniDiffuser
+    - local: api/pipelines/value_guided_sampling
+      title: Value-guided sampling
+    - local: api/pipelines/visualcloze
+      title: VisualCloze
+    - local: api/pipelines/wan
+      title: Wan
+    - local: api/pipelines/wuerstchen
+      title: Wuerstchen
+  - title: Schedulers
+    sections:
     - local: api/schedulers/overview
       title: Overview
     - local: api/schedulers/cm_stochastic_iterative
@@ -761,8 +716,8 @@
       title: UniPCMultistepScheduler
     - local: api/schedulers/vq_diffusion
       title: VQDiffusionScheduler
-    title: Schedulers
+  - title: Internal classes
-  - sections:
+    sections:
     - local: api/internal_classes_overview
       title: Overview
     - local: api/attnprocessor
@@ -779,5 +734,3 @@
       title: VAE Image Processor
     - local: api/video_processor
       title: Video Processor
-    title: Internal classes
-  title: API

docs/source/en/api/cache.md

@@ -34,9 +34,3 @@ Cache methods speedup diffusion transformers by storing and reusing intermediate
 [[autodoc]] FirstBlockCacheConfig
 
 [[autodoc]] apply_first_block_cache
-
-### TaylorSeerCacheConfig
-
-[[autodoc]] TaylorSeerCacheConfig
-
-[[autodoc]] apply_taylorseer_cache

docs/source/en/api/configuration.md

@@ -14,8 +14,11 @@ specific language governing permissions and limitations under the License.
 
 Schedulers from [`~schedulers.scheduling_utils.SchedulerMixin`] and models from [`ModelMixin`] inherit from [`ConfigMixin`] which stores all the parameters that are passed to their respective `__init__` methods in a JSON-configuration file.
 
-> [!TIP]
+<Tip>
-> To use private or [gated](https://huggingface.co/docs/hub/models-gated#gated-models) models, log-in with `hf auth login`.
+
+To use private or [gated](https://huggingface.co/docs/hub/models-gated#gated-models) models, log-in with `hf auth login`.
+
+</Tip>
 
 ## ConfigMixin
 

docs/source/en/api/image_processor.md

@@ -20,12 +20,6 @@ All pipelines with [`VaeImageProcessor`] accept PIL Image, PyTorch tensor, or Nu
 
 [[autodoc]] image_processor.VaeImageProcessor
 
-## InpaintProcessor
-
-The [`InpaintProcessor`] accepts `mask` and `image` inputs and process them together. Optionally, it can accept padding_mask_crop and apply mask overlay.
-
-[[autodoc]] image_processor.InpaintProcessor
-
 ## VaeImageProcessorLDM3D
 
 The [`VaeImageProcessorLDM3D`] accepts RGB and depth inputs and returns RGB and depth outputs.

docs/source/en/api/loaders/ip_adapter.md

@@ -14,8 +14,11 @@ specific language governing permissions and limitations under the License.
 
 [IP-Adapter](https://hf.co/papers/2308.06721) is a lightweight adapter that enables prompting a diffusion model with an image. This method decouples the cross-attention layers of the image and text features. The image features are generated from an image encoder.
 
-> [!TIP]
+<Tip>
-> Learn how to load and use an IP-Adapter checkpoint and image in the [IP-Adapter](../../using-diffusers/ip_adapter) guide,.
+
+Learn how to load an IP-Adapter checkpoint and image in the IP-Adapter [loading](../../using-diffusers/loading_adapters#ip-adapter) guide, and you can see how to use it in the [usage](../../using-diffusers/ip_adapter) guide.
+
+</Tip>
 
 ## IPAdapterMixin
 

docs/source/en/api/loaders/lora.md

@@ -30,13 +30,14 @@ LoRA is a fast and lightweight training method that inserts and trains a signifi
 - [`CogView4LoraLoaderMixin`] provides similar functions for [CogView4](https://huggingface.co/docs/diffusers/main/en/api/pipelines/cogview4).
 - [`AmusedLoraLoaderMixin`] is for the [`AmusedPipeline`].
 - [`HiDreamImageLoraLoaderMixin`] provides similar functions for [HiDream Image](https://huggingface.co/docs/diffusers/main/en/api/pipelines/hidream)
-- [`QwenImageLoraLoaderMixin`] provides similar functions for [Qwen Image](https://huggingface.co/docs/diffusers/main/en/api/pipelines/qwen).
+- [`QwenImageLoraLoaderMixin`] provides similar functions for [Qwen Image](https://huggingface.co/docs/diffusers/main/en/api/pipelines/qwen)
-- [`ZImageLoraLoaderMixin`] provides similar functions for [Z-Image](https://huggingface.co/docs/diffusers/main/en/api/pipelines/zimage).
-- [`Flux2LoraLoaderMixin`] provides similar functions for [Flux2](https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux2).
 - [`LoraBaseMixin`] provides a base class with several utility methods to fuse, unfuse, unload, LoRAs and more.
 
-> [!TIP]
+<Tip>
-> To learn more about how to load LoRA weights, see the [LoRA](../../tutorials/using_peft_for_inference) loading guide.
+
+To learn more about how to load LoRA weights, see the [LoRA](../../using-diffusers/loading_adapters#lora) loading guide.
+
+</Tip>
 
 ## LoraBaseMixin
 
@@ -58,10 +59,6 @@ LoRA is a fast and lightweight training method that inserts and trains a signifi
 
 [[autodoc]] loaders.lora_pipeline.FluxLoraLoaderMixin
 
-## Flux2LoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.Flux2LoraLoaderMixin
-
 ## CogVideoXLoraLoaderMixin
 
 [[autodoc]] loaders.lora_pipeline.CogVideoXLoraLoaderMixin
@@ -113,13 +110,6 @@ LoRA is a fast and lightweight training method that inserts and trains a signifi
 
 [[autodoc]] loaders.lora_pipeline.QwenImageLoraLoaderMixin
 
-## ZImageLoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.ZImageLoraLoaderMixin
-
-## KandinskyLoraLoaderMixin
-[[autodoc]] loaders.lora_pipeline.KandinskyLoraLoaderMixin
-
 ## LoraBaseMixin
 
 [[autodoc]] loaders.lora_base.LoraBaseMixin

docs/source/en/api/loaders/peft.md

@@ -12,10 +12,13 @@ specific language governing permissions and limitations under the License.
 
 # PEFT
 
-Diffusers supports loading adapters such as [LoRA](../../tutorials/using_peft_for_inference) with the [PEFT](https://huggingface.co/docs/peft/index) library with the [`~loaders.peft.PeftAdapterMixin`] class. This allows modeling classes in Diffusers like [`UNet2DConditionModel`], [`SD3Transformer2DModel`] to operate with an adapter.
+Diffusers supports loading adapters such as [LoRA](../../using-diffusers/loading_adapters) with the [PEFT](https://huggingface.co/docs/peft/index) library with the [`~loaders.peft.PeftAdapterMixin`] class. This allows modeling classes in Diffusers like [`UNet2DConditionModel`], [`SD3Transformer2DModel`] to operate with an adapter.
 
-> [!TIP]
+<Tip>
-> Refer to the [Inference with PEFT](../../tutorials/using_peft_for_inference.md) tutorial for an overview of how to use PEFT in Diffusers for inference.
+
+Refer to the [Inference with PEFT](../../tutorials/using_peft_for_inference.md) tutorial for an overview of how to use PEFT in Diffusers for inference.
+
+</Tip>
 
 ## PeftAdapterMixin
 

docs/source/en/api/loaders/textual_inversion.md

@@ -16,8 +16,11 @@ Textual Inversion is a training method for personalizing models by learning new
 
 [`TextualInversionLoaderMixin`] provides a function for loading Textual Inversion embeddings from Diffusers and Automatic1111 into the text encoder and loading a special token to activate the embeddings.
 
-> [!TIP]
+<Tip>
-> To learn more about how to load Textual Inversion embeddings, see the [Textual Inversion](../../using-diffusers/textual_inversion_inference) loading guide.
+
+To learn more about how to load Textual Inversion embeddings, see the [Textual Inversion](../../using-diffusers/loading_adapters#textual-inversion) loading guide.
+
+</Tip>
 
 ## TextualInversionLoaderMixin
 

docs/source/en/api/loaders/transformer_sd3.md

@@ -16,8 +16,11 @@ This class is useful when *only* loading weights into a [`SD3Transformer2DModel`
 
 The [`SD3Transformer2DLoadersMixin`] class currently only loads IP-Adapter weights, but will be used in the future to save weights and load LoRAs.
 
-> [!TIP]
+<Tip>
-> To learn more about how to load LoRA weights, see the [LoRA](../../tutorials/using_peft_for_inference) loading guide.
+
+To learn more about how to load LoRA weights, see the [LoRA](../../using-diffusers/loading_adapters#lora) loading guide.
+
+</Tip>
 
 ## SD3Transformer2DLoadersMixin
 

docs/source/en/api/loaders/unet.md

@@ -16,8 +16,11 @@ Some training methods - like LoRA and Custom Diffusion - typically target the UN
 
 The [`UNet2DConditionLoadersMixin`] class provides functions for loading and saving weights, fusing and unfusing LoRAs, disabling and enabling LoRAs, and setting and deleting adapters.
 
-> [!TIP]
+<Tip>
-> To learn more about how to load LoRA weights, see the [LoRA](../../tutorials/using_peft_for_inference) guide.
+
+To learn more about how to load LoRA weights, see the [LoRA](../../using-diffusers/loading_adapters#lora) loading guide.
+
+</Tip>
 
 ## UNet2DConditionLoadersMixin
 

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

@@ -39,7 +39,7 @@ mask_url = "https://huggingface.co/datasets/hf-internal-testing/diffusers-images
 original_image = load_image(img_url).resize((512, 512))
 mask_image = load_image(mask_url).resize((512, 512))
 
-pipe = StableDiffusionInpaintPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-inpainting")
+pipe = StableDiffusionInpaintPipeline.from_pretrained("runwayml/stable-diffusion-inpainting")
 pipe.vae = AsymmetricAutoencoderKL.from_pretrained("cross-attention/asymmetric-autoencoder-kl-x-1-5")
 pipe.to("cuda")
 

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

@@ -12,7 +12,15 @@ specific language governing permissions and limitations under the License.
 
 # AutoModel
 
-[`AutoModel`] automatically retrieves the correct model class from the checkpoint `config.json` file.
+The `AutoModel` is designed to make it easy to load a checkpoint without needing to know the specific model class. `AutoModel` automatically retrieves the correct model class from the checkpoint `config.json` file.
+
+```python
+from diffusers import AutoModel, AutoPipelineForText2Image
+
+unet = AutoModel.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", subfolder="unet")
+pipe = AutoPipelineForText2Image.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", unet=unet)
+```
+
 
 ## AutoModel
 

docs/source/en/api/models/autoencoder_kl_hunyuan_video15.md

@@ -1,36 +0,0 @@
-<!-- Copyright 2025 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. -->
-
-# AutoencoderKLHunyuanVideo15
-
-The 3D variational autoencoder (VAE) model with KL loss used in [HunyuanVideo1.5](https://github.com/Tencent/HunyuanVideo1-1.5) by Tencent.
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import AutoencoderKLHunyuanVideo15
-
-vae = AutoencoderKLHunyuanVideo15.from_pretrained("hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v", subfolder="vae", torch_dtype=torch.float32)
-
-# make sure to enable tiling to avoid OOM
-vae.enable_tiling()
-```
-
-## AutoencoderKLHunyuanVideo15
-
-[[autodoc]] AutoencoderKLHunyuanVideo15
-  - decode
-  - encode
-  - all
-
-## DecoderOutput
-
-[[autodoc]] models.autoencoders.vae.DecoderOutput

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

@@ -1,32 +0,0 @@
-<!-- Copyright 2025 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. -->
-
-# AutoencoderKLHunyuanImage
-
-The 2D variational autoencoder (VAE) model with KL loss used in [HunyuanImage2.1].
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import AutoencoderKLHunyuanImage
-
-vae = AutoencoderKLHunyuanImage.from_pretrained("hunyuanvideo-community/HunyuanImage-2.1-Diffusers", subfolder="vae", torch_dtype=torch.bfloat16)
-```
-
-## AutoencoderKLHunyuanImage
-
-[[autodoc]] AutoencoderKLHunyuanImage
-  - decode
-  - all
-
-## DecoderOutput
-
-[[autodoc]] models.autoencoders.vae.DecoderOutput

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

@@ -1,32 +0,0 @@
-<!-- Copyright 2025 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. -->
-
-# AutoencoderKLHunyuanImageRefiner
-
-The 3D variational autoencoder (VAE) model with KL loss used in [HunyuanImage2.1](https://github.com/Tencent-Hunyuan/HunyuanImage-2.1) for its refiner pipeline.
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import AutoencoderKLHunyuanImageRefiner
-
-vae = AutoencoderKLHunyuanImageRefiner.from_pretrained("hunyuanvideo-community/HunyuanImage-2.1-Refiner-Diffusers", subfolder="vae", torch_dtype=torch.bfloat16)
-```
-
-## AutoencoderKLHunyuanImageRefiner
-
-[[autodoc]] AutoencoderKLHunyuanImageRefiner
-  - decode
-  - all
-
-## DecoderOutput
-
-[[autodoc]] models.autoencoders.vae.DecoderOutput

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

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # ChromaTransformer2DModel
 
-A modified flux Transformer model from [Chroma](https://huggingface.co/lodestones/Chroma1-HD)
+A modified flux Transformer model from [Chroma](https://huggingface.co/lodestones/Chroma)
 
 ## ChromaTransformer2DModel
 

docs/source/en/api/models/chronoedit_transformer_3d.md

@@ -1,32 +0,0 @@
-<!-- Copyright 2025 The ChronoEdit Team and 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. -->
-
-# ChronoEditTransformer3DModel
-
-A Diffusion Transformer model for 3D video-like data from [ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation](https://huggingface.co/papers/2510.04290) from NVIDIA and University of Toronto, by Jay Zhangjie Wu, Xuanchi Ren, Tianchang Shen, Tianshi Cao, Kai He, Yifan Lu, Ruiyuan Gao, Enze Xie, Shiyi Lan, Jose M. Alvarez, Jun Gao, Sanja Fidler, Zian Wang, Huan Ling.
-
-> **TL;DR:** ChronoEdit reframes image editing as a video generation task, using input and edited images as start/end frames to leverage pretrained video models with temporal consistency. A temporal reasoning stage introduces reasoning tokens to ensure physically plausible edits and visualize the editing trajectory.
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import ChronoEditTransformer3DModel
-
-transformer = ChronoEditTransformer3DModel.from_pretrained("nvidia/ChronoEdit-14B-Diffusers", subfolder="transformer", torch_dtype=torch.bfloat16)
-```
-
-## ChronoEditTransformer3DModel
-
-[[autodoc]] ChronoEditTransformer3DModel
-
-## Transformer2DModelOutput
-
-[[autodoc]] models.modeling_outputs.Transformer2DModelOutput

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

@@ -16,8 +16,11 @@ Consistency decoder can be used to decode the latents from the denoising UNet in
 
 The original codebase can be found at [openai/consistencydecoder](https://github.com/openai/consistencydecoder).
 
-> [!WARNING]
+<Tip warning={true}>
-> Inference is only supported for 2 iterations as of now.
+
+Inference is only supported for 2 iterations as of now.
+
+</Tip>
 
 The pipeline could not have been contributed without the help of [madebyollin](https://github.com/madebyollin) and [mrsteyk](https://github.com/mrsteyk) from [this issue](https://github.com/openai/consistencydecoder/issues/1).
 

docs/source/en/api/models/flux2_transformer.md

@@ -1,19 +0,0 @@
-<!--Copyright 2025 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.
--->
-
-# Flux2Transformer2DModel
-
-A Transformer model for image-like data from [Flux2](https://hf.co/black-forest-labs/FLUX.2-dev).
-
-## Flux2Transformer2DModel
-
-[[autodoc]] Flux2Transformer2DModel

docs/source/en/api/models/hunyuan_video15_transformer_3d.md

@@ -1,30 +0,0 @@
-<!-- Copyright 2025 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. -->
-
-# HunyuanVideo15Transformer3DModel
-
-A Diffusion Transformer model for 3D video-like data used in [HunyuanVideo1.5](https://github.com/Tencent/HunyuanVideo1-1.5).
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import HunyuanVideo15Transformer3DModel
-
-transformer = HunyuanVideo15Transformer3DModel.from_pretrained("hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v" subfolder="transformer", torch_dtype=torch.bfloat16)
-```
-
-## HunyuanVideo15Transformer3DModel
-
-[[autodoc]] HunyuanVideo15Transformer3DModel
-
-## Transformer2DModelOutput
-
-[[autodoc]] models.modeling_outputs.Transformer2DModelOutput

docs/source/en/api/models/hunyuanimage_transformer_2d.md

@@ -1,30 +0,0 @@
-<!-- Copyright 2025 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. -->
-
-# HunyuanImageTransformer2DModel
-
-A Diffusion Transformer model for [HunyuanImage2.1](https://github.com/Tencent-Hunyuan/HunyuanImage-2.1).
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import HunyuanImageTransformer2DModel
-
-transformer = HunyuanImageTransformer2DModel.from_pretrained("hunyuanvideo-community/HunyuanImage-2.1-Diffusers", subfolder="transformer", torch_dtype=torch.bfloat16)
-```
-
-## HunyuanImageTransformer2DModel
-
-[[autodoc]] HunyuanImageTransformer2DModel
-
-## Transformer2DModelOutput
-
-[[autodoc]] models.modeling_outputs.Transformer2DModelOutput

docs/source/en/api/models/ovisimage_transformer2d.md

@@ -1,24 +0,0 @@
-<!-- Copyright 2025 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. -->
-
-# OvisImageTransformer2DModel
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import OvisImageTransformer2DModel
-
-transformer = OvisImageTransformer2DModel.from_pretrained("AIDC-AI/Ovis-Image-7B", subfolder="transformer", torch_dtype=torch.bfloat16)
-```
-
-## OvisImageTransformer2DModel
-
-[[autodoc]] OvisImageTransformer2DModel

docs/source/en/api/models/sana_video_transformer3d.md

@@ -1,36 +0,0 @@
-<!-- Copyright 2025 The SANA-Video Authors and 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. -->
-
-# SanaVideoTransformer3DModel
-
-A Diffusion Transformer model for 3D data (video) from [SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer](https://huggingface.co/papers/2509.24695) from NVIDIA and MIT HAN Lab, by Junsong Chen, Yuyang Zhao, Jincheng Yu, Ruihang Chu, Junyu Chen, Shuai Yang, Xianbang Wang, Yicheng Pan, Daquan Zhou, Huan Ling, Haozhe Liu, Hongwei Yi, Hao Zhang, Muyang Li, Yukang Chen, Han Cai, Sanja Fidler, Ping Luo, Song Han, Enze Xie.
-
-The abstract from the paper is:
-
-*We introduce SANA-Video, a small diffusion model that can efficiently generate videos up to 720x1280 resolution and minute-length duration. SANA-Video synthesizes high-resolution, high-quality and long videos with strong text-video alignment at a remarkably fast speed, deployable on RTX 5090 GPU. Two core designs ensure our efficient, effective and long video generation: (1) Linear DiT: We leverage linear attention as the core operation, which is more efficient than vanilla attention given the large number of tokens processed in video generation. (2) Constant-Memory KV cache for Block Linear Attention: we design block-wise autoregressive approach for long video generation by employing a constant-memory state, derived from the cumulative properties of linear attention. This KV cache provides the Linear DiT with global context at a fixed memory cost, eliminating the need for a traditional KV cache and enabling efficient, minute-long video generation. In addition, we explore effective data filters and model training strategies, narrowing the training cost to 12 days on 64 H100 GPUs, which is only 1% of the cost of MovieGen. Given its low cost, SANA-Video achieves competitive performance compared to modern state-of-the-art small diffusion models (e.g., Wan 2.1-1.3B and SkyReel-V2-1.3B) while being 16x faster in measured latency. Moreover, SANA-Video can be deployed on RTX 5090 GPUs with NVFP4 precision, accelerating the inference speed of generating a 5-second 720p video from 71s to 29s (2.4x speedup). In summary, SANA-Video enables low-cost, high-quality video generation.*
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import SanaVideoTransformer3DModel
-import torch
-
-transformer = SanaVideoTransformer3DModel.from_pretrained("Efficient-Large-Model/SANA-Video_2B_480p_diffusers", subfolder="transformer", torch_dtype=torch.bfloat16)
-```
-
-## SanaVideoTransformer3DModel
-
-[[autodoc]] SanaVideoTransformer3DModel
-
-## Transformer2DModelOutput
-
-[[autodoc]] models.modeling_outputs.Transformer2DModelOutput
-

docs/source/en/api/models/transformer2d.md

@@ -22,8 +22,11 @@ When the input is **continuous**:
 
 When the input is **discrete**:
 
-> [!TIP]
+<Tip>
-> It is assumed one of the input classes is the masked latent pixel. The predicted classes of the unnoised image don't contain a prediction for the masked pixel because the unnoised image cannot be masked.
+
+It is assumed one of the input classes is the masked latent pixel. The predicted classes of the unnoised image don't contain a prediction for the masked pixel because the unnoised image cannot be masked.
+
+</Tip>
 
 1. Convert input (classes of latent pixels) to embeddings and apply positional embeddings.
 2. Apply the Transformer blocks in the standard way.

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

@@ -1,19 +0,0 @@
-<!--Copyright 2025 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.
--->
-
-# BriaFiboTransformer2DModel
-
-A modified flux Transformer model from [Bria](https://huggingface.co/briaai/FIBO)
-
-## BriaFiboTransformer2DModel
-
-[[autodoc]] BriaFiboTransformer2DModel

docs/source/en/api/models/wan_animate_transformer_3d.md

@@ -1,30 +0,0 @@
-<!-- Copyright 2025 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. -->
-
-# WanAnimateTransformer3DModel
-
-A Diffusion Transformer model for 3D video-like data was introduced in [Wan Animate](https://github.com/Wan-Video/Wan2.2) by the Alibaba Wan Team.
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import WanAnimateTransformer3DModel
-
-transformer = WanAnimateTransformer3DModel.from_pretrained("Wan-AI/Wan2.2-Animate-14B-Diffusers", subfolder="transformer", torch_dtype=torch.bfloat16)
-```
-
-## WanAnimateTransformer3DModel
-
-[[autodoc]] WanAnimateTransformer3DModel
-
-## Transformer2DModelOutput
-
-[[autodoc]] models.modeling_outputs.Transformer2DModelOutput

docs/source/en/api/models/z_image_transformer2d.md

@@ -1,19 +0,0 @@
-<!--Copyright 2025 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.
--->
-
-# ZImageTransformer2DModel
-
-A Transformer model for image-like data from [Z-Image](https://huggingface.co/Tongyi-MAI/Z-Image-Turbo).
-
-## ZImageTransformer2DModel
-
-[[autodoc]] ZImageTransformer2DModel

docs/source/en/api/outputs.md

@@ -39,8 +39,11 @@ For instance, retrieving an image by indexing into it returns the tuple `(output
 outputs[:1]
 ```
 
-> [!TIP]
+<Tip>
-> To check a specific pipeline or model output, refer to its corresponding API documentation.
+
+To check a specific pipeline or model output, refer to its corresponding API documentation.
+
+</Tip>
 
 ## BaseOutput
 

docs/source/en/api/parallel.md

@@ -1,24 +0,0 @@
-<!-- Copyright 2025 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. -->
-
-# Parallelism
-
-Parallelism strategies help speed up diffusion transformers by distributing computations across multiple devices, allowing for faster inference/training times. Refer to the [Distributed inferece](../training/distributed_inference) guide to learn more.
-
-## ParallelConfig
-
-[[autodoc]] ParallelConfig
-
-## ContextParallelConfig
-
-[[autodoc]] ContextParallelConfig
-
-[[autodoc]] hooks.apply_context_parallel

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

@@ -17,8 +17,11 @@ The abstract from the paper is:
 
 *Significant advancements have been made in the field of video generation, with the open-source community contributing a wealth of research papers and tools for training high-quality models. However, despite these efforts, the available information and resources remain insufficient for achieving commercial-level performance. In this report, we open the black box and introduce Allegro, an advanced video generation model that excels in both quality and temporal consistency. We also highlight the current limitations in the field and present a comprehensive methodology for training high-performance, commercial-level video generation models, addressing key aspects such as data, model architecture, training pipeline, and evaluation. Our user study shows that Allegro surpasses existing open-source models and most commercial models, ranking just behind Hailuo and Kling. Code: https://github.com/rhymes-ai/Allegro , Model: https://huggingface.co/rhymes-ai/Allegro , Gallery: https://rhymes.ai/allegro_gallery .*
 
-> [!TIP]
+<Tip>
-> Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
 
 ## Quantization
 

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

@@ -102,8 +102,11 @@ Here are some sample outputs:
     </tr>
 </table>
 
-> [!TIP]
+<Tip>
-> AnimateDiff tends to work better with finetuned Stable Diffusion models. If you plan on using a scheduler that can clip samples, make sure to disable it by setting `clip_sample=False` in the scheduler as this can also have an adverse effect on generated samples. Additionally, the AnimateDiff checkpoints can be sensitive to the beta schedule of the scheduler. We recommend setting this to `linear`.
+
+AnimateDiff tends to work better with finetuned Stable Diffusion models. If you plan on using a scheduler that can clip samples, make sure to disable it by setting `clip_sample=False` in the scheduler as this can also have an adverse effect on generated samples. Additionally, the AnimateDiff checkpoints can be sensitive to the beta schedule of the scheduler. We recommend setting this to `linear`.
+
+</Tip>
 
 ### AnimateDiffControlNetPipeline
 
@@ -796,11 +799,17 @@ frames = output.frames[0]
 export_to_gif(frames, "animation.gif")
 ```
 
-> [!WARNING]
+<Tip warning={true}>
-> FreeInit is not really free - the improved quality comes at the cost of extra computation. It requires sampling a few extra times depending on the `num_iters` parameter that is set when enabling it. Setting the `use_fast_sampling` parameter to `True` can improve the overall performance (at the cost of lower quality compared to when `use_fast_sampling=False` but still better results than vanilla video generation models).
 
-> [!TIP]
+FreeInit is not really free - the improved quality comes at the cost of extra computation. It requires sampling a few extra times depending on the `num_iters` parameter that is set when enabling it. Setting the `use_fast_sampling` parameter to `True` can improve the overall performance (at the cost of lower quality compared to when `use_fast_sampling=False` but still better results than vanilla video generation models).
-> Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
+
+<Tip>
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
 
 <table>
     <tr>

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

@@ -23,8 +23,11 @@ The abstract from the paper is:
 
 You can find additional information about Attend-and-Excite on the [project page](https://attendandexcite.github.io/Attend-and-Excite/), the [original codebase](https://github.com/AttendAndExcite/Attend-and-Excite), or try it out in a [demo](https://huggingface.co/spaces/AttendAndExcite/Attend-and-Excite).
 
-> [!TIP]
+<Tip>
-> Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
 
 ## StableDiffusionAttendAndExcitePipeline
 

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

@@ -38,8 +38,11 @@ During inference:
 * The _quality_ of the predicted audio sample can be controlled by the `num_inference_steps` argument; higher steps give higher quality audio at the expense of slower inference.
 * The _length_ of the predicted audio sample can be controlled by varying the `audio_length_in_s` argument.
 
-> [!TIP]
+<Tip>
-> Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
 
 ## AudioLDMPipeline
 [[autodoc]] AudioLDMPipeline

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

@@ -58,8 +58,11 @@ See table below for details on the three checkpoints:
 
 The following example demonstrates how to construct good music and speech generation using the aforementioned tips: [example](https://huggingface.co/docs/diffusers/main/en/api/pipelines/audioldm2#diffusers.AudioLDM2Pipeline.__call__.example).
 
-> [!TIP]
+<Tip>
-> Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
 
 ## AudioLDM2Pipeline
 [[autodoc]] AudioLDM2Pipeline

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

@@ -16,8 +16,11 @@ AuraFlow is inspired by [Stable Diffusion 3](../pipelines/stable_diffusion/stabl
 
 It was developed by the Fal team and more details about it can be found in [this blog post](https://blog.fal.ai/auraflow/).
 
-> [!TIP]
+<Tip>
-> AuraFlow can be quite expensive to run on consumer hardware devices. However, you can perform a suite of optimizations to run it faster and in a more memory-friendly manner. Check out [this section](https://huggingface.co/blog/sd3#memory-optimizations-for-sd3) for more details.
+
+AuraFlow can be quite expensive to run on consumer hardware devices. However, you can perform a suite of optimizations to run it faster and in a more memory-friendly manner. Check out [this section](https://huggingface.co/blog/sd3#memory-optimizations-for-sd3) for more details.
+
+</Tip>
 
 ## Quantization
 

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

@@ -26,8 +26,11 @@ The original codebase can be found at [salesforce/LAVIS](https://github.com/sale
 
 `BlipDiffusionPipeline` and `BlipDiffusionControlNetPipeline` were contributed by [`ayushtues`](https://github.com/ayushtues/).
 
-> [!TIP]
+<Tip>
-> Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
 
 
 ## BlipDiffusionPipeline

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

@@ -1,45 +0,0 @@
-<!--Copyright 2025 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.
--->
-
-# Bria Fibo
-
-Text-to-image models have mastered imagination - but not control. FIBO changes that.
-
-FIBO is trained on structured JSON captions up to 1,000+ words and designed to understand and control different visual parameters such as lighting, composition, color, and camera settings, enabling precise and reproducible outputs.
-
-With only 8 billion parameters, FIBO provides a new level of image quality, prompt adherence and proffesional control.
-
-FIBO is trained exclusively on a structured prompt and will not work with freeform text prompts.
-you can use the [FIBO-VLM-prompt-to-JSON](https://huggingface.co/briaai/FIBO-VLM-prompt-to-JSON) model or the [FIBO-gemini-prompt-to-JSON](https://huggingface.co/briaai/FIBO-gemini-prompt-to-JSON)  to convert your freeform text prompt to a structured JSON prompt.
-
-> [!NOTE]
-> Avoid using freeform text prompts directly with FIBO because it does not produce the best results.
-
-Refer to the Bria Fibo Hugging Face [page](https://huggingface.co/briaai/FIBO) to learn more.
-
-
-## Usage
-
-_As the model is gated, before using it with diffusers you first need to go to the [Bria Fibo Hugging Face page](https://huggingface.co/briaai/FIBO), fill in the form and accept the gate. Once you are in, you need to login so that your system knows you’ve accepted the gate._
-
-Use the command below to log in:
-
-```bash
-hf auth login
-```
-
-
-## BriaFiboPipeline
-
-[[autodoc]] BriaFiboPipeline
-	- all
-	- __call__

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

@@ -19,21 +19,23 @@ specific language governing permissions and limitations under the License.
 
 Chroma is a text to image generation model based on Flux.
 
-Original model checkpoints for Chroma can be found here:
+Original model checkpoints for Chroma can be found [here](https://huggingface.co/lodestones/Chroma).
-* High-resolution finetune: [lodestones/Chroma1-HD](https://huggingface.co/lodestones/Chroma1-HD)
-* Base model: [lodestones/Chroma1-Base](https://huggingface.co/lodestones/Chroma1-Base)
-* Original repo with progress checkpoints: [lodestones/Chroma](https://huggingface.co/lodestones/Chroma) (loading this repo with `from_pretrained` will load a Diffusers-compatible version of the `unlocked-v37` checkpoint)
 
-> [!TIP]
+<Tip>
-> Chroma can use all the same optimizations as Flux.
+
+Chroma can use all the same optimizations as Flux.
+
+</Tip>
 
 ## Inference
 
+The Diffusers version of Chroma is based on the [`unlocked-v37`](https://huggingface.co/lodestones/Chroma/blob/main/chroma-unlocked-v37.safetensors) version of the original model, which is available in the [Chroma repository](https://huggingface.co/lodestones/Chroma).
+
 ```python
 import torch
 from diffusers import ChromaPipeline
 
-pipe = ChromaPipeline.from_pretrained("lodestones/Chroma1-HD", torch_dtype=torch.bfloat16)
+pipe = ChromaPipeline.from_pretrained("lodestones/Chroma", torch_dtype=torch.bfloat16)
 pipe.enable_model_cpu_offload()
 
 prompt = [
@@ -64,10 +66,10 @@ Then run the following example
 import torch
 from diffusers import ChromaTransformer2DModel, ChromaPipeline
 
-model_id = "lodestones/Chroma1-HD"
+model_id = "lodestones/Chroma"
 dtype = torch.bfloat16
 
-transformer = ChromaTransformer2DModel.from_single_file("https://huggingface.co/lodestones/Chroma1-HD/blob/main/Chroma1-HD.safetensors", torch_dtype=dtype)
+transformer = ChromaTransformer2DModel.from_single_file("https://huggingface.co/lodestones/Chroma/blob/main/chroma-unlocked-v37.safetensors", torch_dtype=dtype)
 
 pipe = ChromaPipeline.from_pretrained(model_id, transformer=transformer, torch_dtype=dtype)
 pipe.enable_model_cpu_offload()

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

@@ -1,156 +0,0 @@
-<!-- Copyright 2025 The ChronoEdit Team and 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. -->
-
-<div style="float: right;">
-  <div class="flex flex-wrap space-x-1">
-    <a href="https://huggingface.co/docs/diffusers/main/en/tutorials/using_peft_for_inference" target="_blank" rel="noopener">
-      <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
-    </a>
-  </div>
-</div>
-
-# ChronoEdit
-
-[ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation](https://huggingface.co/papers/2510.04290) from NVIDIA and University of Toronto, by Jay Zhangjie Wu, Xuanchi Ren, Tianchang Shen, Tianshi Cao, Kai He, Yifan Lu, Ruiyuan Gao, Enze Xie, Shiyi Lan, Jose M. Alvarez, Jun Gao, Sanja Fidler, Zian Wang, Huan Ling.
-
-> **TL;DR:** ChronoEdit reframes image editing as a video generation task, using input and edited images as start/end frames to leverage pretrained video models with temporal consistency. A temporal reasoning stage introduces reasoning tokens to ensure physically plausible edits and visualize the editing trajectory.
-
-*Recent advances in large generative models have greatly enhanced both image editing and in-context image generation, yet a critical gap remains in ensuring physical consistency, where edited objects must remain coherent. This capability is especially vital for world simulation related tasks. In this paper, we present ChronoEdit, a framework that reframes image editing as a video generation problem. First, ChronoEdit treats the input and edited images as the first and last frames of a video, allowing it to leverage large pretrained video generative models that capture not only object appearance but also the implicit physics of motion and interaction through learned temporal consistency. Second, ChronoEdit introduces a temporal reasoning stage that explicitly performs editing at inference time. Under this setting, target frame is jointly denoised with reasoning tokens to imagine a plausible editing trajectory that constrains the solution space to physically viable transformations. The reasoning tokens are then dropped after a few steps to avoid the high computational cost of rendering a full video. To validate ChronoEdit, we introduce PBench-Edit, a new benchmark of image-prompt pairs for contexts that require physical consistency, and demonstrate that ChronoEdit surpasses state-of-the-art baselines in both visual fidelity and physical plausibility. Project page for code and models: [this https URL](https://research.nvidia.com/labs/toronto-ai/chronoedit).*
-
-The ChronoEdit pipeline is developed by the ChronoEdit Team. The original code is available on [GitHub](https://github.com/nv-tlabs/ChronoEdit), and pretrained models can be found in the [nvidia/ChronoEdit](https://huggingface.co/collections/nvidia/chronoedit) collection on Hugging Face.
-
-
-### Image Editing
-
-```py
-import torch
-import numpy as np
-from diffusers import AutoencoderKLWan, ChronoEditTransformer3DModel, ChronoEditPipeline
-from diffusers.utils import export_to_video, load_image
-from transformers import CLIPVisionModel
-from PIL import Image
-
-model_id = "nvidia/ChronoEdit-14B-Diffusers"
-image_encoder = CLIPVisionModel.from_pretrained(model_id, subfolder="image_encoder", torch_dtype=torch.float32)
-vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
-transformer = ChronoEditTransformer3DModel.from_pretrained(model_id, subfolder="transformer", torch_dtype=torch.bfloat16)
-pipe = ChronoEditPipeline.from_pretrained(model_id, image_encoder=image_encoder, transformer=transformer, vae=vae, torch_dtype=torch.bfloat16)
-pipe.to("cuda")
-
-image = load_image(
-    "https://huggingface.co/spaces/nvidia/ChronoEdit/resolve/main/examples/3.png"
-)
-max_area = 720 * 1280
-aspect_ratio = image.height / image.width
-mod_value = pipe.vae_scale_factor_spatial * pipe.transformer.config.patch_size[1]
-height = round(np.sqrt(max_area * aspect_ratio)) // mod_value * mod_value
-width = round(np.sqrt(max_area / aspect_ratio)) // mod_value * mod_value
-print("width", width, "height", height)
-image = image.resize((width, height))
-prompt = (
-    "The user wants to transform the image by adding a small, cute mouse sitting inside the floral teacup, enjoying a spa bath. The mouse should appear relaxed and cheerful, with a tiny white bath towel draped over its head like a turban. It should be positioned comfortably in the cup’s liquid, with gentle steam rising around it to blend with the cozy atmosphere. "
-    "The mouse’s pose should be natural—perhaps sitting upright with paws resting lightly on the rim or submerged in the tea. The teacup’s floral design, gold trim, and warm lighting must remain unchanged to preserve the original aesthetic. The steam should softly swirl around the mouse, enhancing the spa-like, whimsical mood."
-)
-
-output = pipe(
-    image=image,
-    prompt=prompt,
-    height=height,
-    width=width,
-    num_frames=5,
-    num_inference_steps=50,
-    guidance_scale=5.0,
-    enable_temporal_reasoning=False,
-    num_temporal_reasoning_steps=0,
-).frames[0]
-Image.fromarray((output[-1] * 255).clip(0, 255).astype("uint8")).save("output.png")
-```
-
-Optionally, enable **temporal reasoning** for improved physical consistency:
-```py
-output = pipe(
-    image=image,
-    prompt=prompt,
-    height=height,
-    width=width,
-    num_frames=29,
-    num_inference_steps=50,
-    guidance_scale=5.0,
-    enable_temporal_reasoning=True,
-    num_temporal_reasoning_steps=50,
-).frames[0]
-export_to_video(output, "output.mp4", fps=16)
-Image.fromarray((output[-1] * 255).clip(0, 255).astype("uint8")).save("output.png")
-```
-
-### Inference with 8-Step Distillation Lora
-
-```py
-import torch
-import numpy as np
-from diffusers import AutoencoderKLWan, ChronoEditTransformer3DModel, ChronoEditPipeline
-from diffusers.utils import export_to_video, load_image
-from transformers import CLIPVisionModel
-from PIL import Image
-
-model_id = "nvidia/ChronoEdit-14B-Diffusers"
-image_encoder = CLIPVisionModel.from_pretrained(model_id, subfolder="image_encoder", torch_dtype=torch.float32)
-vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
-transformer = ChronoEditTransformer3DModel.from_pretrained(model_id, subfolder="transformer", torch_dtype=torch.bfloat16)
-pipe = ChronoEditPipeline.from_pretrained(model_id, image_encoder=image_encoder, transformer=transformer, vae=vae, torch_dtype=torch.bfloat16)
-lora_path = hf_hub_download(repo_id=model_id, filename="lora/chronoedit_distill_lora.safetensors")
-pipe.load_lora_weights(lora_path)
-pipe.fuse_lora(lora_scale=1.0)
-pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config, flow_shift=2.0)
-pipe.to("cuda")
-
-image = load_image(
-    "https://huggingface.co/spaces/nvidia/ChronoEdit/resolve/main/examples/3.png"
-)
-max_area = 720 * 1280
-aspect_ratio = image.height / image.width
-mod_value = pipe.vae_scale_factor_spatial * pipe.transformer.config.patch_size[1]
-height = round(np.sqrt(max_area * aspect_ratio)) // mod_value * mod_value
-width = round(np.sqrt(max_area / aspect_ratio)) // mod_value * mod_value
-print("width", width, "height", height)
-image = image.resize((width, height))
-prompt = (
-    "The user wants to transform the image by adding a small, cute mouse sitting inside the floral teacup, enjoying a spa bath. The mouse should appear relaxed and cheerful, with a tiny white bath towel draped over its head like a turban. It should be positioned comfortably in the cup’s liquid, with gentle steam rising around it to blend with the cozy atmosphere. "
-    "The mouse’s pose should be natural—perhaps sitting upright with paws resting lightly on the rim or submerged in the tea. The teacup’s floral design, gold trim, and warm lighting must remain unchanged to preserve the original aesthetic. The steam should softly swirl around the mouse, enhancing the spa-like, whimsical mood."
-)
-
-output = pipe(
-    image=image,
-    prompt=prompt,
-    height=height,
-    width=width,
-    num_frames=5,
-    num_inference_steps=8,
-    guidance_scale=1.0,
-    enable_temporal_reasoning=False,
-    num_temporal_reasoning_steps=0,
-).frames[0]
-export_to_video(output, "output.mp4", fps=16)
-Image.fromarray((output[-1] * 255).clip(0, 255).astype("uint8")).save("output.png")
-```
-
-## ChronoEditPipeline
-
-[[autodoc]] ChronoEditPipeline
-  - all
-  - __call__
-
-## ChronoEditPipelineOutput
-
-[[autodoc]] pipelines.chronoedit.pipeline_output.ChronoEditPipelineOutput

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

@@ -50,7 +50,7 @@ from diffusers.utils import export_to_video
 pipeline_quant_config = PipelineQuantizationConfig(
   quant_backend="torchao",
   quant_kwargs={"quant_type": "int8wo"},
-  components_to_quantize="transformer"
+  components_to_quantize=["transformer"]
 )
 
 # fp8 layerwise weight-casting

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

@@ -21,8 +21,11 @@ The abstract from the paper is:
 
 *Recent advancements in text-to-image generative systems have been largely driven by diffusion models. However, single-stage text-to-image diffusion models still face challenges, in terms of computational efficiency and the refinement of image details. To tackle the issue, we propose CogView3, an innovative cascaded framework that enhances the performance of text-to-image diffusion. CogView3 is the first model implementing relay diffusion in the realm of text-to-image generation, executing the task by first creating low-resolution images and subsequently applying relay-based super-resolution. This methodology not only results in competitive text-to-image outputs but also greatly reduces both training and inference costs. Our experimental results demonstrate that CogView3 outperforms SDXL, the current state-of-the-art open-source text-to-image diffusion model, by 77.0% in human evaluations, all while requiring only about 1/2 of the inference time. The distilled variant of CogView3 achieves comparable performance while only utilizing 1/10 of the inference time by SDXL.*
 
-> [!TIP]
+<Tip>
-> Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
 
 This pipeline was contributed by [zRzRzRzRzRzRzR](https://github.com/zRzRzRzRzRzRzR). The original codebase can be found [here](https://huggingface.co/THUDM). The original weights can be found under [hf.co/THUDM](https://huggingface.co/THUDM).
 

docs/source/en/api/pipelines/cogview4.md

@@ -15,8 +15,11 @@
 
 # CogView4
 
-> [!TIP]
+<Tip>
-> Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
 
 This pipeline was contributed by [zRzRzRzRzRzRzR](https://github.com/zRzRzRzRzRzRzR). The original codebase can be found [here](https://huggingface.co/THUDM). The original weights can be found under [hf.co/THUDM](https://huggingface.co/THUDM).
 

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

@@ -25,8 +25,11 @@ The abstract from the paper is:
 
 *Identity-preserving text-to-video (IPT2V) generation aims to create high-fidelity videos with consistent human identity. It is an important task in video generation but remains an open problem for generative models. This paper pushes the technical frontier of IPT2V in two directions that have not been resolved in the literature: (1) A tuning-free pipeline without tedious case-by-case finetuning, and (2) A frequency-aware heuristic identity-preserving Diffusion Transformer (DiT)-based control scheme. To achieve these goals, we propose **ConsisID**, a tuning-free DiT-based controllable IPT2V model to keep human-**id**entity **consis**tent in the generated video. Inspired by prior findings in frequency analysis of vision/diffusion transformers, it employs identity-control signals in the frequency domain, where facial features can be decomposed into low-frequency global features (e.g., profile, proportions) and high-frequency intrinsic features (e.g., identity markers that remain unaffected by pose changes). First, from a low-frequency perspective, we introduce a global facial extractor, which encodes the reference image and facial key points into a latent space, generating features enriched with low-frequency information. These features are then integrated into the shallow layers of the network to alleviate training challenges associated with DiT. Second, from a high-frequency perspective, we design a local facial extractor to capture high-frequency details and inject them into the transformer blocks, enhancing the model's ability to preserve fine-grained features. To leverage the frequency information for identity preservation, we propose a hierarchical training strategy, transforming a vanilla pre-trained video generation model into an IPT2V model. Extensive experiments demonstrate that our frequency-aware heuristic scheme provides an optimal control solution for DiT-based models. Thanks to this scheme, our **ConsisID** achieves excellent results in generating high-quality, identity-preserving videos, making strides towards more effective IPT2V. The model weight of ConsID is publicly available at https://github.com/PKU-YuanGroup/ConsisID.*
 
-> [!TIP]
+<Tip>
-> Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers.md) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading.md#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers.md) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading.md#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
 
 This pipeline was contributed by [SHYuanBest](https://github.com/SHYuanBest). The original codebase can be found [here](https://github.com/PKU-YuanGroup/ConsisID). The original weights can be found under [hf.co/BestWishYsh](https://huggingface.co/BestWishYsh).
 

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

@@ -26,8 +26,11 @@ FLUX.1 Depth and Canny [dev] is a 12 billion parameter rectified flow transforme
 | Canny | [Black Forest Labs](https://huggingface.co/black-forest-labs) | [Link](https://huggingface.co/black-forest-labs/FLUX.1-Canny-dev) |
 
 
-> [!TIP]
+<Tip>
-> Flux can be quite expensive to run on consumer hardware devices. However, you can perform a suite of optimizations to run it faster and in a more memory-friendly manner. Check out [this section](https://huggingface.co/blog/sd3#memory-optimizations-for-sd3) for more details. Additionally, Flux can benefit from quantization for memory efficiency with a trade-off in inference latency. Refer to [this blog post](https://huggingface.co/blog/quanto-diffusers) to learn more. For an exhaustive list of resources, check out [this gist](https://gist.github.com/sayakpaul/b664605caf0aa3bf8585ab109dd5ac9c).
+
+Flux can be quite expensive to run on consumer hardware devices. However, you can perform a suite of optimizations to run it faster and in a more memory-friendly manner. Check out [this section](https://huggingface.co/blog/sd3#memory-optimizations-for-sd3) for more details. Additionally, Flux can benefit from quantization for memory efficiency with a trade-off in inference latency. Refer to [this blog post](https://huggingface.co/blog/quanto-diffusers) to learn more. For an exhaustive list of resources, check out [this gist](https://gist.github.com/sayakpaul/b664605caf0aa3bf8585ab109dd5ac9c).
+
+</Tip>
 
 ```python
 import torch

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

@@ -28,8 +28,11 @@ This model was contributed by [takuma104](https://huggingface.co/takuma104). ❤
 
 The original codebase can be found at [lllyasviel/ControlNet](https://github.com/lllyasviel/ControlNet), and you can find official ControlNet checkpoints on [lllyasviel's](https://huggingface.co/lllyasviel) Hub profile.
 
-> [!TIP]
+<Tip>
-> Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
 
 ## StableDiffusionControlNetPipeline
 [[autodoc]] StableDiffusionControlNetPipeline

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

@@ -44,8 +44,11 @@ XLabs ControlNets are also supported, which was contributed by the [XLabs team](
 | HED | [The XLabs Team](https://huggingface.co/XLabs-AI) | [Link](https://huggingface.co/XLabs-AI/flux-controlnet-hed-diffusers) |
 
 
-> [!TIP]
+<Tip>
-> Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
 
 ## FluxControlNetPipeline
 [[autodoc]] FluxControlNetPipeline

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

@@ -24,8 +24,11 @@ The abstract from the paper is:
 
 This code is implemented by Tencent Hunyuan Team. You can find pre-trained checkpoints for Hunyuan-DiT ControlNets on [Tencent Hunyuan](https://huggingface.co/Tencent-Hunyuan).
 
-> [!TIP]
+<Tip>
-> Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
 
 ## HunyuanDiTControlNetPipeline
 [[autodoc]] HunyuanDiTControlNetPipeline

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

@@ -38,8 +38,11 @@ This controlnet code is mainly implemented by [The InstantX Team](https://huggin
 | Inpainting | [The AlimamaCreative Team](https://huggingface.co/alimama-creative) | [link](https://huggingface.co/alimama-creative/SD3-Controlnet-Inpainting) |
 
 
-> [!TIP]
+<Tip>
-> Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
 
 ## StableDiffusion3ControlNetPipeline
 [[autodoc]] StableDiffusion3ControlNetPipeline

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

@@ -26,13 +26,19 @@ The abstract from the paper is:
 
 You can find additional smaller Stable Diffusion XL (SDXL) ControlNet checkpoints from the 🤗 [Diffusers](https://huggingface.co/diffusers) Hub organization, and browse [community-trained](https://huggingface.co/models?other=stable-diffusion-xl&other=controlnet) checkpoints on the Hub.
 
-> [!WARNING]
+<Tip warning={true}>
-> 🧪 Many of the SDXL ControlNet checkpoints are experimental, and there is a lot of room for improvement. Feel free to open an [Issue](https://github.com/huggingface/diffusers/issues/new/choose) and leave us feedback on how we can improve!
+
+🧪 Many of the SDXL ControlNet checkpoints are experimental, and there is a lot of room for improvement. Feel free to open an [Issue](https://github.com/huggingface/diffusers/issues/new/choose) and leave us feedback on how we can improve!
+
+</Tip>
 
 If you don't see a checkpoint you're interested in, you can train your own SDXL ControlNet with our [training script](../../../../../examples/controlnet/README_sdxl).
 
-> [!TIP]
+<Tip>
-> Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
 
 ## StableDiffusionXLControlNetPipeline
 [[autodoc]] StableDiffusionXLControlNetPipeline

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

@@ -31,8 +31,11 @@ Here's the overview from the [project page](https://vislearn.github.io/ControlNe
 
 This model was contributed by [UmerHA](https://twitter.com/UmerHAdil). ❤️
 
-> [!TIP]
+<Tip>
-> Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
 
 ## StableDiffusionControlNetXSPipeline
 [[autodoc]] StableDiffusionControlNetXSPipeline

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

@@ -27,11 +27,17 @@ Here's the overview from the [project page](https://vislearn.github.io/ControlNe
 
 This model was contributed by [UmerHA](https://twitter.com/UmerHAdil). ❤️
 
-> [!WARNING]
+<Tip warning={true}>
-> 🧪 Many of the SDXL ControlNet checkpoints are experimental, and there is a lot of room for improvement. Feel free to open an [Issue](https://github.com/huggingface/diffusers/issues/new/choose) and leave us feedback on how we can improve!
 
-> [!TIP]
+🧪 Many of the SDXL ControlNet checkpoints are experimental, and there is a lot of room for improvement. Feel free to open an [Issue](https://github.com/huggingface/diffusers/issues/new/choose) and leave us feedback on how we can improve!
-> Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
+
+<Tip>
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
 
 ## StableDiffusionXLControlNetXSPipeline
 [[autodoc]] StableDiffusionXLControlNetXSPipeline

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

@@ -18,8 +18,11 @@
 
 *Physical AI needs to be trained digitally first. It needs a digital twin of itself, the policy model, and a digital twin of the world, the world model. In this paper, we present the Cosmos World Foundation Model Platform to help developers build customized world models for their Physical AI setups. We position a world foundation model as a general-purpose world model that can be fine-tuned into customized world models for downstream applications. Our platform covers a video curation pipeline, pre-trained world foundation models, examples of post-training of pre-trained world foundation models, and video tokenizers. To help Physical AI builders solve the most critical problems of our society, we make our platform open-source and our models open-weight with permissive licenses available via https://github.com/NVIDIA/Cosmos.*
 
-> [!TIP]
+<Tip>
-> Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
 
 ## Loading original format checkpoints
 

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

@@ -20,8 +20,11 @@ specific language governing permissions and limitations under the License.
 Dance Diffusion is the first in a suite of generative audio tools for producers and musicians released by [Harmonai](https://github.com/Harmonai-org).
 
 
-> [!TIP]
+<Tip>
-> Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
 
 ## DanceDiffusionPipeline
 [[autodoc]] DanceDiffusionPipeline

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

@@ -20,8 +20,11 @@ The abstract from the paper is:
 
 The original codebase can be found at [hohonathanho/diffusion](https://github.com/hojonathanho/diffusion).
 
-> [!TIP]
+<Tip>
-> Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
 
 # DDPMPipeline
 [[autodoc]] DDPMPipeline

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

@@ -20,8 +20,11 @@ The abstract from the paper is:
 
 The original codebase can be found at [facebookresearch/dit](https://github.com/facebookresearch/dit).
 
-> [!TIP]
+<Tip>
-> Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
 
 ## DiTPipeline
 [[autodoc]] DiTPipeline

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

@@ -21,10 +21,13 @@ Flux is a series of text-to-image generation models based on diffusion transform
 
 Original model checkpoints for Flux can be found [here](https://huggingface.co/black-forest-labs). Original inference code can be found [here](https://github.com/black-forest-labs/flux).
 
-> [!TIP]
+<Tip>
-> Flux can be quite expensive to run on consumer hardware devices. However, you can perform a suite of optimizations to run it faster and in a more memory-friendly manner. Check out [this section](https://huggingface.co/blog/sd3#memory-optimizations-for-sd3) for more details. Additionally, Flux can benefit from quantization for memory efficiency with a trade-off in inference latency. Refer to [this blog post](https://huggingface.co/blog/quanto-diffusers) to learn more.  For an exhaustive list of resources, check out [this gist](https://gist.github.com/sayakpaul/b664605caf0aa3bf8585ab109dd5ac9c).
+
->
+Flux can be quite expensive to run on consumer hardware devices. However, you can perform a suite of optimizations to run it faster and in a more memory-friendly manner. Check out [this section](https://huggingface.co/blog/sd3#memory-optimizations-for-sd3) for more details. Additionally, Flux can benefit from quantization for memory efficiency with a trade-off in inference latency. Refer to [this blog post](https://huggingface.co/blog/quanto-diffusers) to learn more.  For an exhaustive list of resources, check out [this gist](https://gist.github.com/sayakpaul/b664605caf0aa3bf8585ab109dd5ac9c).
-> [Caching](../../optimization/cache) may also speed up inference by storing and reusing intermediate outputs.
+
+[Caching](../../optimization/cache) may also speed up inference by storing and reusing intermediate outputs.
+
+</Tip>
 
 Flux comes in the following variants:
 
@@ -417,8 +420,11 @@ When unloading the Control LoRA weights, call `pipe.unload_lora_weights(reset_to
 
 ## IP-Adapter
 
-> [!TIP]
+<Tip>
-> Check out [IP-Adapter](../../using-diffusers/ip_adapter) to learn more about how IP-Adapters work.
+
+Check out [IP-Adapter](../../../using-diffusers/ip_adapter) to learn more about how IP-Adapters work.
+
+</Tip>
 
 An IP-Adapter lets you prompt Flux with images, in addition to the text prompt. This is especially useful when describing complex concepts that are difficult to articulate through text alone and you have reference images.
 
@@ -598,8 +604,9 @@ image.save("flux.png")
 
 The `FluxTransformer2DModel` supports loading checkpoints in the original format shipped by Black Forest Labs. This is also useful when trying to load finetunes or quantized versions of the models that have been published by the community.
 
-> [!TIP]
+<Tip>
-> `FP8` inference can be brittle depending on the GPU type, CUDA version, and `torch` version that you are using. It is recommended that you use the `optimum-quanto` library in order to run FP8 inference on your machine.
+`FP8` inference can be brittle depending on the GPU type, CUDA version, and `torch` version that you are using. It is recommended that you use the `optimum-quanto` library in order to run FP8 inference on your machine.
+</Tip>
 
 The following example demonstrates how to run Flux with less than 16GB of VRAM.
 

docs/source/en/api/pipelines/flux2.md

@@ -1,39 +0,0 @@
-<!--Copyright 2025 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.
--->
-
-# Flux2
-
-<div class="flex flex-wrap space-x-1">
-  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
-  <img alt="MPS" src="https://img.shields.io/badge/MPS-000000?style=flat&logo=apple&logoColor=white%22">
-</div>
-
-Flux.2 is the recent series of image generation models from Black Forest Labs, preceded by the [Flux.1](./flux.md) series. It is an entirely new model with a new architecture and pre-training done from scratch!
-
-Original model checkpoints for Flux can be found [here](https://huggingface.co/black-forest-labs). Original inference code can be found [here](https://github.com/black-forest-labs/flux2).
-
-> [!TIP]
-> Flux2 can be quite expensive to run on consumer hardware devices. However, you can perform a suite of optimizations to run it faster and in a more memory-friendly manner. Check out [this section](https://huggingface.co/blog/sd3#memory-optimizations-for-sd3) for more details. Additionally, Flux can benefit from quantization for memory efficiency with a trade-off in inference latency. Refer to [this blog post](https://huggingface.co/blog/quanto-diffusers) to learn more.
->
-> [Caching](../../optimization/cache) may also speed up inference by storing and reusing intermediate outputs.
-
-## Caption upsampling
-
-Flux.2 can potentially generate better better outputs with better prompts. We can "upsample"
-an input prompt by setting the `caption_upsample_temperature` argument in the pipeline call arguments.
-The [official implementation](https://github.com/black-forest-labs/flux2/blob/5a5d316b1b42f6b59a8c9194b77c8256be848432/src/flux2/text_encoder.py#L140) recommends this value to be 0.15.
-
-## Flux2Pipeline
-
-[[autodoc]] Flux2Pipeline
-	- all
-	- __call__

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

@@ -22,8 +22,11 @@
 
 *We present a neural network structure, FramePack, to train next-frame (or next-frame-section) prediction models for video generation. The FramePack compresses input frames to make the transformer context length a fixed number regardless of the video length. As a result, we are able to process a large number of frames using video diffusion with computation bottleneck similar to image diffusion. This also makes the training video batch sizes significantly higher (batch sizes become comparable to image diffusion training). We also propose an anti-drifting sampling method that generates frames in inverted temporal order with early-established endpoints to avoid exposure bias (error accumulation over iterations). Finally, we show that existing video diffusion models can be finetuned with FramePack, and their visual quality may be improved because the next-frame prediction supports more balanced diffusion schedulers with less extreme flow shift timesteps.*
 
-> [!TIP]
+<Tip>
-> Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
 
 ## Available models
 

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

@@ -16,12 +16,15 @@
 
 [HiDream-I1](https://huggingface.co/HiDream-ai) by HiDream.ai
 
-> [!TIP]
+<Tip>
-> [Caching](../../optimization/cache) may also speed up inference by storing and reusing intermediate outputs.
+
+[Caching](../../optimization/cache) may also speed up inference by storing and reusing intermediate outputs.
+
+</Tip>
 
 ## Available models
 
-The following models are available for the [`HiDreamImagePipeline`] pipeline:
+The following models are available for the [`HiDreamImagePipeline`](text-to-image) pipeline:
 
 | Model name | Description |
 |:---|:---|

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

@@ -54,7 +54,7 @@ pipeline_quant_config = PipelineQuantizationConfig(
       "bnb_4bit_quant_type": "nf4",
       "bnb_4bit_compute_dtype": torch.bfloat16
       },
-    components_to_quantize="transformer"
+    components_to_quantize=["transformer"]
 )
 
 pipeline = HunyuanVideoPipeline.from_pretrained(
@@ -91,7 +91,7 @@ pipeline_quant_config = PipelineQuantizationConfig(
       "bnb_4bit_quant_type": "nf4",
       "bnb_4bit_compute_dtype": torch.bfloat16
       },
-    components_to_quantize="transformer"
+    components_to_quantize=["transformer"]
 )
 
 pipeline = HunyuanVideoPipeline.from_pretrained(
@@ -139,7 +139,7 @@ export_to_video(video, "output.mp4", fps=15)
         "bnb_4bit_quant_type": "nf4",
         "bnb_4bit_compute_dtype": torch.bfloat16
         },
-      components_to_quantize="transformer"
+      components_to_quantize=["transformer"]
   )
 
   pipeline = HunyuanVideoPipeline.from_pretrained(

docs/source/en/api/pipelines/hunyuan_video15.md

@@ -1,120 +0,0 @@
-<!-- Copyright 2025 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. -->
-
-
-# HunyuanVideo-1.5
-
-HunyuanVideo-1.5 is a lightweight yet powerful video generation model that achieves state-of-the-art visual quality and motion coherence with only 8.3 billion parameters, enabling efficient inference on consumer-grade GPUs. This achievement is built upon several key components, including meticulous data curation, an advanced DiT architecture with selective and sliding tile attention (SSTA), enhanced bilingual understanding through glyph-aware text encoding, progressive pre-training and post-training, and an efficient video super-resolution network. Leveraging these designs, we developed a unified framework capable of high-quality text-to-video and image-to-video generation across multiple durations and resolutions. Extensive experiments demonstrate that this compact and proficient model establishes a new state-of-the-art among open-source models.
-
-You can find all the original HunyuanVideo checkpoints under the [Tencent](https://huggingface.co/tencent) organization.
-
-> [!TIP]
-> Click on the HunyuanVideo models in the right sidebar for more examples of video generation tasks.
->
-> The examples below use a checkpoint from [hunyuanvideo-community](https://huggingface.co/hunyuanvideo-community) because the weights are stored in a layout compatible with Diffusers.
-
-The example below demonstrates how to generate a video optimized for memory or inference speed.
-
-<hfoptions id="usage">
-<hfoption id="memory">
-
-Refer to the [Reduce memory usage](../../optimization/memory) guide for more details about the various memory saving techniques.
-
-
-```py
-import torch
-from diffusers import AutoModel, HunyuanVideo15Pipeline
-from diffusers.utils import export_to_video
-
-
-pipeline = HunyuanVideo15Pipeline.from_pretrained(
-    "HunyuanVideo-1.5-Diffusers-480p_t2v",
-    torch_dtype=torch.bfloat16,
-)
-
-# model-offloading and tiling
-pipeline.enable_model_cpu_offload()
-pipeline.vae.enable_tiling()
-
-prompt = "A fluffy teddy bear sits on a bed of soft pillows surrounded by children's toys."
-video = pipeline(prompt=prompt, num_frames=61, num_inference_steps=30).frames[0]
-export_to_video(video, "output.mp4", fps=15)
-```
-
-## Notes
-
-- HunyuanVideo1.5 use attention masks with variable-length sequences. For best performance, we recommend using an attention backend that handles padding efficiently.
-
-    - **H100/H800:** `_flash_3_hub` or `_flash_3_varlen_hub`
-    - **A100/A800/RTX 4090:** `flash_hub` or `flash_varlen_hub`
-    - **Other GPUs:** `sage_hub`
-
-Refer to the [Attention backends](../../optimization/attention_backends) guide for more details about using a different backend.
-
-
-```py
-pipe.transformer.set_attention_backend("flash_hub")  # or your preferred backend
-```
-
-- [`HunyuanVideo15Pipeline`] use guider and does not take `guidance_scale` parameter at runtime. 
-
-You can check the default guider configuration using `pipe.guider`:
-
-```py
->>> pipe.guider 
-ClassifierFreeGuidance {
-  "_class_name": "ClassifierFreeGuidance",
-  "_diffusers_version": "0.36.0.dev0",
-  "enabled": true,
-  "guidance_rescale": 0.0,
-  "guidance_scale": 6.0,
-  "start": 0.0,
-  "stop": 1.0,
-  "use_original_formulation": false
-}
-
-State:
-  step: None
-  num_inference_steps: None
-  timestep: None
-  count_prepared: 0
-  enabled: True
-  num_conditions: 2
-```
-
-To update guider configuration, you can run `pipe.guider = pipe.guider.new(...)`
-
-```py
-pipe.guider = pipe.guider.new(guidance_scale=5.0)
-```
-
-Read more on Guider [here](../../modular_diffusers/guiders).
-
-
-
-## HunyuanVideo15Pipeline
-
-[[autodoc]] HunyuanVideo15Pipeline
-  - all
-  - __call__
-
-## HunyuanVideo15ImageToVideoPipeline
-
-[[autodoc]] HunyuanVideo15ImageToVideoPipeline
-  - all
-  - __call__
-
-## HunyuanVideo15PipelineOutput
-
-[[autodoc]] pipelines.hunyuan_video1_5.pipeline_output.HunyuanVideo15PipelineOutput

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

@@ -28,11 +28,17 @@ HunyuanDiT has the following components:
 * It uses a diffusion transformer as the backbone
 * It combines two text encoders, a bilingual CLIP and a multilingual T5 encoder
 
-> [!TIP]
+<Tip>
-> Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
 
-> [!TIP]
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
-> You can further improve generation quality by passing the generated image from [`HungyuanDiTPipeline`] to the [SDXL refiner](../../using-diffusers/sdxl#base-to-refiner-model) model.
+
+</Tip>
+
+<Tip>
+
+You can further improve generation quality by passing the generated image from [`HungyuanDiTPipeline`] to the [SDXL refiner](../../using-diffusers/sdxl#base-to-refiner-model) model.
+
+</Tip>
 
 ## Optimization
 

docs/source/en/api/pipelines/hunyuanimage21.md

@@ -1,152 +0,0 @@
-<!-- Copyright 2025 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. -->
-
-# HunyuanImage2.1
-
-
-HunyuanImage-2.1 is a 17B text-to-image model that is capable of generating 2K (2048 x 2048) resolution images
-
-HunyuanImage-2.1 comes in the following variants:
-
-| model type | model id |
-|:----------:|:--------:|
-| HunyuanImage-2.1 | [hunyuanvideo-community/HunyuanImage-2.1-Diffusers](https://huggingface.co/hunyuanvideo-community/HunyuanImage-2.1-Diffusers) |
-| HunyuanImage-2.1-Distilled | [hunyuanvideo-community/HunyuanImage-2.1-Distilled-Diffusers](https://huggingface.co/hunyuanvideo-community/HunyuanImage-2.1-Distilled-Diffusers) |
-| HunyuanImage-2.1-Refiner | [hunyuanvideo-community/HunyuanImage-2.1-Refiner-Diffusers](https://huggingface.co/hunyuanvideo-community/HunyuanImage-2.1-Refiner-Diffusers) |
-
-> [!TIP]
-> [Caching](../../optimization/cache) may also speed up inference by storing and reusing intermediate outputs.
-
-## HunyuanImage-2.1
-
-HunyuanImage-2.1 applies [Adaptive Projected Guidance (APG)](https://huggingface.co/papers/2410.02416) combined with Classifier-Free Guidance (CFG) in the denoising loop. `HunyuanImagePipeline` has a `guider` component (read more about [Guider](../modular_diffusers/guiders.md)) and does not take a `guidance_scale` parameter at runtime. To change guider-related parameters, e.g., `guidance_scale`, you can update the `guider` configuration instead.
-
-```python
-import torch
-from diffusers import HunyuanImagePipeline
-
-pipe = HunyuanImagePipeline.from_pretrained(
-    "hunyuanvideo-community/HunyuanImage-2.1-Diffusers", 
-    torch_dtype=torch.bfloat16
-)
-pipe = pipe.to("cuda")
-``` 
-
-You can inspect the `guider` object:
-
-```py
->>> pipe.guider
-AdaptiveProjectedMixGuidance {
-  "_class_name": "AdaptiveProjectedMixGuidance",
-  "_diffusers_version": "0.36.0.dev0",
-  "adaptive_projected_guidance_momentum": -0.5,
-  "adaptive_projected_guidance_rescale": 10.0,
-  "adaptive_projected_guidance_scale": 10.0,
-  "adaptive_projected_guidance_start_step": 5,
-  "enabled": true,
-  "eta": 0.0,
-  "guidance_rescale": 0.0,
-  "guidance_scale": 3.5,
-  "start": 0.0,
-  "stop": 1.0,
-  "use_original_formulation": false
-}
-
-State:
-  step: None
-  num_inference_steps: None
-  timestep: None
-  count_prepared: 0
-  enabled: True
-  num_conditions: 2
-  momentum_buffer: None
-  is_apg_enabled: False
-  is_cfg_enabled: True
-```
-
-To update the guider with a different configuration, use the `new()` method. For example, to generate an image with `guidance_scale=5.0` while keeping all other default guidance parameters:
-
-```py
-import torch
-from diffusers import HunyuanImagePipeline
-
-pipe = HunyuanImagePipeline.from_pretrained(
-    "hunyuanvideo-community/HunyuanImage-2.1-Diffusers", 
-    torch_dtype=torch.bfloat16
-)
-pipe = pipe.to("cuda")
-
-# Update the guider configuration
-pipe.guider = pipe.guider.new(guidance_scale=5.0)
-
-prompt = (
-    "A cute, cartoon-style anthropomorphic penguin plush toy with fluffy fur, standing in a painting studio, "
-    "wearing a red knitted scarf and a red beret with the word 'Tencent' on it, holding a paintbrush with a "
-    "focused expression as it paints an oil painting of the Mona Lisa, rendered in a photorealistic photographic style."
-)
-
-image = pipe(
-    prompt=prompt, 
-    num_inference_steps=50, 
-    height=2048, 
-    width=2048,
-).images[0]
-image.save("image.png")
-```
-
-
-## HunyuanImage-2.1-Distilled
-
-use `distilled_guidance_scale` with the guidance-distilled checkpoint, 
-
-```py
-import torch
-from diffusers import HunyuanImagePipeline
-pipe = HunyuanImagePipeline.from_pretrained("hunyuanvideo-community/HunyuanImage-2.1-Distilled-Diffusers", torch_dtype=torch.bfloat16)
-pipe = pipe.to("cuda")
-
-prompt = (
-    "A cute, cartoon-style anthropomorphic penguin plush toy with fluffy fur, standing in a painting studio, "
-    "wearing a red knitted scarf and a red beret with the word 'Tencent' on it, holding a paintbrush with a "
-    "focused expression as it paints an oil painting of the Mona Lisa, rendered in a photorealistic photographic style."
-)
-
-out = pipe(
-    prompt,
-    num_inference_steps=8,
-    distilled_guidance_scale=3.25,
-    height=2048,
-    width=2048,
-    generator=generator,
-).images[0]
-
-```
-
-
-## HunyuanImagePipeline
-
-[[autodoc]] HunyuanImagePipeline
-  - all
-  - __call__
-
-## HunyuanImageRefinerPipeline
-
-[[autodoc]] HunyuanImageRefinerPipeline
-  - all
-  - __call__
-
-
-## HunyuanImagePipelineOutput
-
-[[autodoc]] pipelines.hunyuan_image.pipeline_output.HunyuanImagePipelineOutput

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

@@ -23,8 +23,11 @@ The abstract from the paper is:
 
 The original codebase can be found [here](https://github.com/ali-vilab/i2vgen-xl/). The model checkpoints can be found [here](https://huggingface.co/ali-vilab/).
 
-> [!TIP]
+<Tip>
-> Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines. Also, to know more about reducing the memory usage of this pipeline, refer to the ["Reduce memory usage"] section [here](../../using-diffusers/svd#reduce-memory-usage).
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines. Also, to know more about reducing the memory usage of this pipeline, refer to the ["Reduce memory usage"] section [here](../../using-diffusers/svd#reduce-memory-usage).
+
+</Tip>
 
 Sample output with I2VGenXL:
 

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

@@ -17,11 +17,17 @@ The description from it's GitHub page is:
 
 The original codebase can be found at [ai-forever/Kandinsky-2](https://github.com/ai-forever/Kandinsky-2).
 
-> [!TIP]
+<Tip>
-> Check out the [Kandinsky Community](https://huggingface.co/kandinsky-community) organization on the Hub for the official model checkpoints for tasks like text-to-image, image-to-image, and inpainting.
 
-> [!TIP]
+Check out the [Kandinsky Community](https://huggingface.co/kandinsky-community) organization on the Hub for the official model checkpoints for tasks like text-to-image, image-to-image, and inpainting.
-> Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
+
+<Tip>
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
 
 ## KandinskyPriorPipeline
 

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

@@ -28,11 +28,17 @@ Its architecture includes 3 main components:
 
 The original codebase can be found at [ai-forever/Kandinsky-3](https://github.com/ai-forever/Kandinsky-3).
 
-> [!TIP]
+<Tip>
-> Check out the [Kandinsky Community](https://huggingface.co/kandinsky-community) organization on the Hub for the official model checkpoints for tasks like text-to-image, image-to-image, and inpainting.
 
-> [!TIP]
+Check out the [Kandinsky Community](https://huggingface.co/kandinsky-community) organization on the Hub for the official model checkpoints for tasks like text-to-image, image-to-image, and inpainting.
-> Make sure to check out the schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
+
+<Tip>
+
+Make sure to check out the schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
 
 ## Kandinsky3Pipeline
 

docs/source/en/api/pipelines/kandinsky5_image.md

@@ -1,116 +0,0 @@
-<!--Copyright 2025 The HuggingFace Team and Kandinsky Lab 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.
--->
-
-# Kandinsky 5.0 Image
-
-[Kandinsky 5.0](https://arxiv.org/abs/2511.14993) is a family of diffusion models for Video & Image generation. 
-
-Kandinsky 5.0 Image Lite is a lightweight image generation model (6B parameters).
-
-The model introduces several key innovations:
-- **Latent diffusion pipeline** with **Flow Matching** for improved training stability
-- **Diffusion Transformer (DiT)** as the main generative backbone with cross-attention to text embeddings
-- Dual text encoding using **Qwen2.5-VL** and **CLIP** for comprehensive text understanding
-- **Flux VAE** for efficient image encoding and decoding
-
-The original codebase can be found at [kandinskylab/Kandinsky-5](https://github.com/kandinskylab/Kandinsky-5).
-
-> [!TIP]
-> Check out the [Kandinsky Lab](https://huggingface.co/kandinskylab) organization on the Hub for the official model checkpoints for text-to-video generation, including pretrained, SFT, no-CFG, and distilled variants.
-
-
-## Available Models
-
-Kandinsky 5.0 Image Lite:
-
-| model_id | Description | Use Cases |
-|------------|-------------|-----------|
-| [**kandinskylab/Kandinsky-5.0-T2I-Lite-sft-Diffusers**](https://huggingface.co/kandinskylab/Kandinsky-5.0-T2I-Lite-sft-Diffusers) | 6B image Supervised Fine-Tuned model | Highest generation quality |
-| [**kandinskylab/Kandinsky-5.0-I2I-Lite-sft-Diffusers**](https://huggingface.co/kandinskylab/Kandinsky-5.0-I2I-Lite-sft-Diffusers) | 6B image editing Supervised Fine-Tuned model | Highest generation quality |
-| [**kandinskylab/Kandinsky-5.0-T2I-Lite-pretrain-Diffusers**](https://huggingface.co/kandinskylab/Kandinsky-5.0-T2I-Lite-pretrain-Diffusers) | 6B image Base pretrained model | Research and fine-tuning |
-| [**kandinskylab/Kandinsky-5.0-I2I-Lite-pretrain-Diffusers**](https://huggingface.co/kandinskylab/Kandinsky-5.0-I2I-Lite-pretrain-Diffusers) | 6B image editing Base pretrained model | Research and fine-tuning |
-
-## Usage Examples
-
-### Basic Text-to-Image Generation
-
-```python
-import torch
-from diffusers import Kandinsky5T2IPipeline
-
-# Load the pipeline
-model_id = "kandinskylab/Kandinsky-5.0-T2I-Lite-sft-Diffusers"
-pipe = Kandinsky5T2IPipeline.from_pretrained(model_id)
-_ = pipe.to(device='cuda',dtype=torch.bfloat16)
-
-# Generate image
-prompt = "A fluffy, expressive cat wearing a bright red hat with a soft, slightly textured fabric. The hat should look cozy and well-fitted on the cat’s head. On the front of the hat, add clean, bold white text that reads “SWEET”, clearly visible and neatly centered. Ensure the overall lighting highlights the hat’s color and the cat’s fur details."
-
-output = pipe(
-    prompt=prompt,
-    negative_prompt="",
-    height=1024,
-    width=1024,
-    num_inference_steps=50,
-    guidance_scale=3.5,
-).image[0]
-```
-
-### Basic Image-to-Image Generation
-
-```python
-import torch
-from diffusers import Kandinsky5I2IPipeline
-from diffusers.utils import load_image 
-# Load the pipeline
-model_id = "kandinskylab/Kandinsky-5.0-I2I-Lite-sft-Diffusers"
-pipe = Kandinsky5I2IPipeline.from_pretrained(model_id)
-
-_ = pipe.to(device='cuda',dtype=torch.bfloat16)
-pipe.enable_model_cpu_offload()                                               # <--- Enable CPU offloading for single GPU inference
-
-# Edit the input image
-image = load_image(
-    "https://huggingface.co/kandinsky-community/kandinsky-3/resolve/main/assets/title.jpg?download=true"
-)
-
-prompt = "Change the background from a winter night scene to a bright summer day. Place the character on a sandy beach with clear blue sky, soft sunlight, and gentle waves in the distance. Replace the winter clothing with a light short-sleeved T-shirt (in soft pastel colors) and casual shorts. Ensure the character’s fur reflects warm daylight instead of cold winter tones. Add small beach details such as seashells, footprints in the sand, and a few scattered beach toys nearby. Keep the oranges in the scene, but place them naturally on the sand."
-negative_prompt = ""
-
-output = pipe(
-    image=image,
-    prompt=prompt,
-    negative_prompt=negative_prompt,
-    guidance_scale=3.5,
-).image[0]
-```
-
-
-## Kandinsky5T2IPipeline
-
-[[autodoc]] Kandinsky5T2IPipeline
-    - all
-    - __call__
-
-## Kandinsky5I2IPipeline
-
-[[autodoc]] Kandinsky5I2IPipeline
-    - all
-    - __call__
-
-
-## Citation
-```bibtex
-@misc{kandinsky2025,
-    author = {Alexander Belykh and Alexander Varlamov and Alexey Letunovskiy and Anastasia Aliaskina and Anastasia Maltseva and Anastasiia Kargapoltseva and Andrey Shutkin and Anna Averchenkova and Anna Dmitrienko and Bulat Akhmatov and Denis Dimitrov and Denis Koposov and Denis Parkhomenko and Dmitrii and Ilya Vasiliev and Ivan Kirillov and Julia Agafonova and Kirill Chernyshev and Kormilitsyn Semen and Lev Novitskiy and Maria Kovaleva and Mikhail Mamaev and Mikhailov and Nikita Kiselev and Nikita Osterov and Nikolai Gerasimenko and Nikolai Vaulin and Olga Kim and Olga Vdovchenko and Polina Gavrilova and Polina Mikhailova and Tatiana Nikulina and Viacheslav Vasilev and Vladimir Arkhipkin and Vladimir Korviakov and Vladimir Polovnikov and Yury Kolabushin},
-    title = {Kandinsky 5.0: A family of diffusion models for Video & Image generation},
-    howpublished = {\url{https://github.com/kandinskylab/Kandinsky-5}},
-    year = 2025
-}
-```

docs/source/en/api/pipelines/kandinsky5_video.md

@@ -1,310 +0,0 @@
-<!--Copyright 2025 The HuggingFace Team Kandinsky Lab 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.
--->
-
-# Kandinsky 5.0 Video
-
-[Kandinsky 5.0](https://arxiv.org/abs/2511.14993) is a family of diffusion models for Video & Image generation.
-
-Kandinsky 5.0 Lite line-up of lightweight video generation models (2B parameters) that ranks #1 among open-source models in its class. It outperforms larger models and offers the best understanding of Russian concepts in the open-source ecosystem.
-
-Kandinsky 5.0 Pro line-up of large high quality video generation models (19B parameters). It offers high qualty generation in HD and more generation formats like I2V.
-
-The model introduces several key innovations:
-- **Latent diffusion pipeline** with **Flow Matching** for improved training stability
-- **Diffusion Transformer (DiT)** as the main generative backbone with cross-attention to text embeddings
-- Dual text encoding using **Qwen2.5-VL** and **CLIP** for comprehensive text understanding
-- **HunyuanVideo 3D VAE** for efficient video encoding and decoding
-- **Sparse attention mechanisms** (NABLA) for efficient long-sequence processing
-
-The original codebase can be found at [kandinskylab/Kandinsky-5](https://github.com/kandinskylab/Kandinsky-5).
-
-> [!TIP]
-> Check out the [Kandinsky Lab](https://huggingface.co/kandinskylab) organization on the Hub for the official model checkpoints for text-to-video generation, including pretrained, SFT, no-CFG, and distilled variants.
-
-## Available Models
-
-Kandinsky 5.0 T2V Pro:
-
-| model_id | Description | Use Cases |
-|------------|-------------|-----------|
-| **kandinskylab/Kandinsky-5.0-T2V-Pro-sft-5s-Diffusers** | 5 second Text-to-Video Pro model | High-quality text-to-video generation |
-| **kandinskylab/Kandinsky-5.0-I2V-Pro-sft-5s-Diffusers** | 5 second Image-to-Video Pro model | High-quality image-to-video generation |
-
-Kandinsky 5.0 T2V Lite:
-| model_id | Description | Use Cases |
-|------------|-------------|-----------|
-| **kandinskylab/Kandinsky-5.0-T2V-Lite-sft-5s-Diffusers** | 5 second Supervised Fine-Tuned model | Highest generation quality |
-| **kandinskylab/Kandinsky-5.0-T2V-Lite-sft-10s-Diffusers** | 10 second Supervised Fine-Tuned model | Highest generation quality |
-| **kandinskylab/Kandinsky-5.0-T2V-Lite-nocfg-5s-Diffusers** | 5 second Classifier-Free Guidance distilled | 2× faster inference |
-| **kandinskylab/Kandinsky-5.0-T2V-Lite-nocfg-10s-Diffusers** | 10 second Classifier-Free Guidance distilled | 2× faster inference |
-| **kandinskylab/Kandinsky-5.0-T2V-Lite-distilled16steps-5s-Diffusers** | 5 second Diffusion distilled to 16 steps | 6× faster inference, minimal quality loss |
-| **kandinskylab/Kandinsky-5.0-T2V-Lite-distilled16steps-10s-Diffusers** | 10 second Diffusion distilled to 16 steps | 6× faster inference, minimal quality loss |
-| **kandinskylab/Kandinsky-5.0-T2V-Lite-pretrain-5s-Diffusers** | 5 second Base pretrained model | Research and fine-tuning |
-| **kandinskylab/Kandinsky-5.0-T2V-Lite-pretrain-10s-Diffusers** | 10 second Base pretrained model | Research and fine-tuning |
-
-
-## Usage Examples
-
-### Basic Text-to-Video Generation
-
-#### Pro
-**⚠️ Warning!** all Pro models should be infered with pipeline.enable_model_cpu_offload()  
-```python
-import torch
-from diffusers import Kandinsky5T2VPipeline
-from diffusers.utils import export_to_video
-
-# Load the pipeline
-model_id = "kandinskylab/Kandinsky-5.0-T2V-Pro-sft-5s-Diffusers"
-pipe = Kandinsky5T2VPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
-
-pipe = pipe.to("cuda")
-pipeline.transformer.set_attention_backend("flex")                            # <--- Set attention bakend to Flex
-pipeline.enable_model_cpu_offload()                                           # <--- Enable cpu offloading for single GPU inference
-pipeline.transformer.compile(mode="max-autotune-no-cudagraphs", dynamic=True) # <--- Compile with max-autotune-no-cudagraphs
-
-# Generate video
-prompt = "A cat and a dog baking a cake together in a kitchen."
-negative_prompt = "Static, 2D cartoon, cartoon, 2d animation, paintings, images, worst quality, low quality, ugly, deformed, walking backwards"
-
-output = pipe(
-    prompt=prompt,
-    negative_prompt=negative_prompt,
-    height=768,
-    width=1024,
-    num_frames=121,  # ~5 seconds at 24fps
-    num_inference_steps=50,
-    guidance_scale=5.0,
-).frames[0]
-
-export_to_video(output, "output.mp4", fps=24, quality=9)
-```
-
-#### Lite
-```python
-import torch
-from diffusers import Kandinsky5T2VPipeline
-from diffusers.utils import export_to_video
-
-# Load the pipeline
-model_id = "kandinskylab/Kandinsky-5.0-T2V-Lite-sft-5s-Diffusers"
-pipe = Kandinsky5T2VPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
-pipe = pipe.to("cuda")
-
-# Generate video
-prompt = "A cat and a dog baking a cake together in a kitchen."
-negative_prompt = "Static, 2D cartoon, cartoon, 2d animation, paintings, images, worst quality, low quality, ugly, deformed, walking backwards"
-
-output = pipe(
-    prompt=prompt,
-    negative_prompt=negative_prompt,
-    height=512,
-    width=768,
-    num_frames=121,  # ~5 seconds at 24fps
-    num_inference_steps=50,
-    guidance_scale=5.0,
-).frames[0]
-
-export_to_video(output, "output.mp4", fps=24, quality=9)
-```
-
-### 10 second Models
-**⚠️ Warning!** all 10 second models should be used with Flex attention and max-autotune-no-cudagraphs compilation:
-
-```python
-pipe = Kandinsky5T2VPipeline.from_pretrained(
-    "kandinskylab/Kandinsky-5.0-T2V-Lite-sft-10s-Diffusers", 
-    torch_dtype=torch.bfloat16
-)
-pipe = pipe.to("cuda")
-
-pipe.transformer.set_attention_backend(
-    "flex"
-)                                       # <--- Set attention bakend to Flex
-pipe.transformer.compile(
-    mode="max-autotune-no-cudagraphs", 
-    dynamic=True
-)                                       # <--- Compile with max-autotune-no-cudagraphs
-
-prompt = "A cat and a dog baking a cake together in a kitchen."
-negative_prompt = "Static, 2D cartoon, cartoon, 2d animation, paintings, images, worst quality, low quality, ugly, deformed, walking backwards"
-
-output = pipe(
-    prompt=prompt,
-    negative_prompt=negative_prompt,
-    height=512,
-    width=768,
-    num_frames=241,
-    num_inference_steps=50,
-    guidance_scale=5.0,
-).frames[0]
-
-export_to_video(output, "output.mp4", fps=24, quality=9)
-```
-
-### Diffusion Distilled model
-**⚠️ Warning!** all nocfg and diffusion distilled models should be infered wothout CFG (```guidance_scale=1.0```):
-
-```python
-model_id = "kandinskylab/Kandinsky-5.0-T2V-Lite-distilled16steps-5s-Diffusers"
-pipe = Kandinsky5T2VPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
-pipe = pipe.to("cuda")
-
-output = pipe(
-    prompt="A beautiful sunset over mountains",
-    num_inference_steps=16,  # <--- Model is distilled in 16 steps
-    guidance_scale=1.0,      # <--- no CFG
-).frames[0]
-
-export_to_video(output, "output.mp4", fps=24, quality=9)
-```
-
-
-### Basic Image-to-Video Generation
-**⚠️ Warning!** all Pro models should be infered with pipeline.enable_model_cpu_offload()  
-```python
-import torch
-from diffusers import Kandinsky5T2VPipeline
-from diffusers.utils import export_to_video
-
-# Load the pipeline
-model_id = "kandinskylab/Kandinsky-5.0-I2V-Pro-sft-5s-Diffusers"
-pipe = Kandinsky5T2VPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
-
-pipe = pipe.to("cuda")
-pipeline.transformer.set_attention_backend("flex")                            # <--- Set attention bakend to Flex
-pipeline.enable_model_cpu_offload()                                           # <--- Enable cpu offloading for single GPU inference
-pipeline.transformer.compile(mode="max-autotune-no-cudagraphs", dynamic=True) # <--- Compile with max-autotune-no-cudagraphs
-
-# Generate video
-image = load_image(
-    "https://huggingface.co/kandinsky-community/kandinsky-3/resolve/main/assets/title.jpg?download=true"
-)
-height = 896
-width = 896
-image = image.resize((width, height))
-
-prompt = "An funny furry creture smiles happily and holds a sign that says 'Kandinsky'"
-negative_prompt = ""
-
-output = pipe(
-    prompt=prompt,
-    negative_prompt=negative_prompt,
-    height=height,
-    width=width,
-    num_frames=121,  # ~5 seconds at 24fps
-    num_inference_steps=50,
-    guidance_scale=5.0,
-).frames[0]
-
-export_to_video(output, "output.mp4", fps=24, quality=9)
-```
-
-
-
-## Kandinsky 5.0 Pro Side-by-Side evaluation
-
-<table border="0" style="width: 200; text-align: left; margin-top: 20px;">
-  <tr>
-      <td>
-          <img width="200" alt="image" src="https://github.com/user-attachments/assets/73e5ff00-2735-40fd-8f01-767de9181918" />
-      </td>
-      <td>
-         <img width="200" alt="image" src="https://github.com/user-attachments/assets/f449a9e7-74b7-481d-82da-02723e396acd" />
-      </td>
-
-  <tr>
-      <td>
-          Comparison with Veo 3 
-      </td>
-      <td>
-          Comparison with Veo 3 fast
-      </td>
-  <tr>
-      <td>
-          <img width="200" alt="image" src="https://github.com/user-attachments/assets/a6902fb6-b5e8-4093-adad-aa4caab79c6d" />
-      </td>
-      <td>
-          <img width="200" alt="image" src="https://github.com/user-attachments/assets/09986015-3d07-4de8-b942-c145039b9b2d" />
-      </td>
-  <tr>
-      <td>
-          Comparison with Wan 2.2 A14B Text-to-Video mode
-      </td>
-      <td>
-          Comparison with Wan 2.2 A14B Image-to-Video mode
-      </td>
-
-</table>
-
-
-## Kandinsky 5.0 Lite Side-by-Side evaluation
-
-The evaluation is based on the expanded prompts from the [Movie Gen benchmark](https://github.com/facebookresearch/MovieGenBench), which are available in the expanded_prompt column of the benchmark/moviegen_bench.csv file.
-
-<table border="0" style="width: 400; text-align: left; margin-top: 20px;">
-  <tr>
-      <td>
-          <img src="https://github.com/kandinskylab/kandinsky-5/raw/main/assets/sbs/kandinsky_5_video_lite_vs_sora.jpg" width=400 >
-      </td>
-      <td>
-          <img src="https://github.com/kandinskylab/kandinsky-5/raw/main/assets/sbs/kandinsky_5_video_lite_vs_wan_2.1_14B.jpg" width=400 >
-      </td>
-  <tr>
-      <td>
-          <img src="https://github.com/kandinskylab/kandinsky-5/raw/main/assets/sbs/kandinsky_5_video_lite_vs_wan_2.2_5B.jpg" width=400 >
-      </td>
-      <td>
-          <img src="https://github.com/kandinskylab/kandinsky-5/raw/main/assets/sbs/kandinsky_5_video_lite_vs_wan_2.2_A14B.jpg" width=400 >
-      </td>
-  <tr>
-      <td>
-          <img src="https://github.com/kandinskylab/kandinsky-5/raw/main/assets/sbs/kandinsky_5_video_lite_vs_wan_2.1_1.3B.jpg" width=400 >
-      </td>
-
-</table>
-
-
-
-
-## Kandinsky 5.0 Lite Distill Side-by-Side evaluation
-
-<table border="0" style="width: 400; text-align: left; margin-top: 20px;">
-  <tr>
-      <td>
-          <img src="https://github.com/kandinskylab/kandinsky-5/raw/main/assets/sbs/kandinsky_5_video_lite_5s_vs_kandinsky_5_video_lite_distill_5s.jpg" width=400 >
-      </td>
-      <td>
-          <img src="https://github.com/kandinskylab/kandinsky-5/raw/main/assets/sbs/kandinsky_5_video_lite_10s_vs_kandinsky_5_video_lite_distill_10s.jpg" width=400 >
-      </td>
-
-</table>
-
-## Kandinsky5T2VPipeline
-
-[[autodoc]] Kandinsky5T2VPipeline
-    - all
-    - __call__
-
-## Kandinsky5I2VPipeline
-
-[[autodoc]] Kandinsky5I2VPipeline
-    - all
-    - __call__
-
-
-## Citation
-```bibtex
-@misc{kandinsky2025,
-    author = {Alexander Belykh and Alexander Varlamov and Alexey Letunovskiy and Anastasia Aliaskina and Anastasia Maltseva and Anastasiia Kargapoltseva and Andrey Shutkin and Anna Averchenkova and Anna Dmitrienko and Bulat Akhmatov and Denis Dimitrov and Denis Koposov and Denis Parkhomenko and Dmitrii and Ilya Vasiliev and Ivan Kirillov and Julia Agafonova and Kirill Chernyshev and Kormilitsyn Semen and Lev Novitskiy and Maria Kovaleva and Mikhail Mamaev and Mikhailov and Nikita Kiselev and Nikita Osterov and Nikolai Gerasimenko and Nikolai Vaulin and Olga Kim and Olga Vdovchenko and Polina Gavrilova and Polina Mikhailova and Tatiana Nikulina and Viacheslav Vasilev and Vladimir Arkhipkin and Vladimir Korviakov and Vladimir Polovnikov and Yury Kolabushin},
-    title = {Kandinsky 5.0: A family of diffusion models for Video & Image generation},
-    howpublished = {\url{https://github.com/kandinskylab/Kandinsky-5}},
-    year = 2025
-}
-```

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

@@ -17,11 +17,17 @@ The description from it's GitHub page is:
 
 The original codebase can be found at [ai-forever/Kandinsky-2](https://github.com/ai-forever/Kandinsky-2).
 
-> [!TIP]
+<Tip>
-> Check out the [Kandinsky Community](https://huggingface.co/kandinsky-community) organization on the Hub for the official model checkpoints for tasks like text-to-image, image-to-image, and inpainting.
 
-> [!TIP]
+Check out the [Kandinsky Community](https://huggingface.co/kandinsky-community) organization on the Hub for the official model checkpoints for tasks like text-to-image, image-to-image, and inpainting.
-> Make sure to check out the schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
+
+<Tip>
+
+Make sure to check out the schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
 
 ## KandinskyV22PriorPipeline
 

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

@@ -50,11 +50,17 @@ image.save("kolors_sample.png")
 
 Kolors needs a different IP Adapter to work, and it uses [Openai-CLIP-336](https://huggingface.co/openai/clip-vit-large-patch14-336) as an image encoder.
 
-> [!TIP]
+<Tip>
-> Using an IP Adapter with Kolors requires more than 24GB of VRAM. To use it, we recommend using [`~DiffusionPipeline.enable_model_cpu_offload`] on consumer GPUs.
 
-> [!TIP]
+Using an IP Adapter with Kolors requires more than 24GB of VRAM. To use it, we recommend using [`~DiffusionPipeline.enable_model_cpu_offload`] on consumer GPUs.
-> While Kolors is integrated in Diffusers, you need to load the image encoder from a revision to use the safetensor files. You can still use the main branch of the original repository if you're comfortable loading pickle checkpoints.
+
+</Tip>
+
+<Tip>
+
+While Kolors is integrated in Diffusers, you need to load the image encoder from a revision to use the safetensor files. You can still use the main branch of the original repository if you're comfortable loading pickle checkpoints.
+
+</Tip>
 
 ```python
 import torch

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

@@ -20,8 +20,11 @@ The abstract from the paper is:
 
 The original codebase can be found at [CompVis/latent-diffusion](https://github.com/CompVis/latent-diffusion).
 
-> [!TIP]
+<Tip>
-> Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
 
 ## LDMTextToImagePipeline
 [[autodoc]] LDMTextToImagePipeline

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

@@ -26,8 +26,11 @@ The abstract from the paper is:
 
 This pipeline was contributed by [maxin-cn](https://github.com/maxin-cn). The original codebase can be found [here](https://github.com/Vchitect/Latte). The original weights can be found under [hf.co/maxin-cn](https://huggingface.co/maxin-cn).
 
-> [!TIP]
+<Tip>
-> Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
 
 ### Inference
 

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

@@ -22,12 +22,16 @@ The abstract from the paper is:
 
 *Text-to-image diffusion models have recently received increasing interest for their astonishing ability to produce high-fidelity images from solely text inputs. Subsequent research efforts aim to exploit and apply their capabilities to real image editing. However, existing image-to-image methods are often inefficient, imprecise, and of limited versatility. They either require time-consuming fine-tuning, deviate unnecessarily strongly from the input image, and/or lack support for multiple, simultaneous edits. To address these issues, we introduce LEDITS++, an efficient yet versatile and precise textual image manipulation technique. LEDITS++'s novel inversion approach requires no tuning nor optimization and produces high-fidelity results with a few diffusion steps. Second, our methodology supports multiple simultaneous edits and is architecture-agnostic. Third, we use a novel implicit masking technique that limits changes to relevant image regions. We propose the novel TEdBench++ benchmark as part of our exhaustive evaluation. Our results demonstrate the capabilities of LEDITS++ and its improvements over previous methods. The project page is available at https://leditsplusplus-project.static.hf.space .*
 
-> [!TIP]
+<Tip>
-> You can find additional information about LEDITS++ on the [project page](https://leditsplusplus-project.static.hf.space/index.html) and try it out in a [demo](https://huggingface.co/spaces/editing-images/leditsplusplus).
 
-> [!WARNING]
+You can find additional information about LEDITS++ on the [project page](https://leditsplusplus-project.static.hf.space/index.html) and try it out in a [demo](https://huggingface.co/spaces/editing-images/leditsplusplus).
-> Due to some backward compatibility issues with the current diffusers implementation of [`~schedulers.DPMSolverMultistepScheduler`] this implementation of LEdits++ can no longer guarantee perfect inversion.
+
-> This issue is unlikely to have any noticeable effects on applied use-cases. However, we provide an alternative implementation that guarantees perfect inversion in a dedicated [GitHub repo](https://github.com/ml-research/ledits_pp).
+</Tip>
+
+<Tip warning={true}>
+Due to some backward compatibility issues with the current diffusers implementation of [`~schedulers.DPMSolverMultistepScheduler`] this implementation of LEdits++ can no longer guarantee perfect inversion.
+This issue is unlikely to have any noticeable effects on applied use-cases. However, we provide an alternative implementation that guarantees perfect inversion in a dedicated [GitHub repo](https://github.com/ml-research/ledits_pp).
+</Tip>
 
 We provide two distinct pipelines based on different pre-trained models.
 

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

@@ -254,8 +254,8 @@ export_to_video(video, "output.mp4", fps=24)
   pipeline.vae.enable_tiling()
 
   def round_to_nearest_resolution_acceptable_by_vae(height, width):
-      height = height - (height % pipeline.vae_spatial_compression_ratio)
+      height = height - (height % pipeline.vae_temporal_compression_ratio)
-      width = width - (width % pipeline.vae_spatial_compression_ratio)
+      width = width - (width % pipeline.vae_temporal_compression_ratio)
       return height, width
 
   prompt = """
@@ -325,95 +325,6 @@ export_to_video(video, "output.mp4", fps=24)
 
   </details>
 
-- LTX-Video 0.9.8 distilled model is similar to the 0.9.7 variant. It is guidance and timestep-distilled, and similar inference code can be used as above. An improvement of this version is that it supports generating very long videos. Additionally, it supports using tone mapping to improve the quality of the generated video using the `tone_map_compression_ratio` parameter. The default value of `0.6` is recommended.
-
-  <details>
-  <summary>Show example code</summary>
-  
-  ```python
-  import torch
-  from diffusers import LTXConditionPipeline, LTXLatentUpsamplePipeline
-  from diffusers.pipelines.ltx.pipeline_ltx_condition import LTXVideoCondition
-  from diffusers.pipelines.ltx.modeling_latent_upsampler import LTXLatentUpsamplerModel
-  from diffusers.utils import export_to_video, load_video
-
-  pipeline = LTXConditionPipeline.from_pretrained("Lightricks/LTX-Video-0.9.8-13B-distilled", torch_dtype=torch.bfloat16)
-  # TODO: Update the checkpoint here once updated in LTX org
-  upsampler = LTXLatentUpsamplerModel.from_pretrained("a-r-r-o-w/LTX-0.9.8-Latent-Upsampler", torch_dtype=torch.bfloat16)
-  pipe_upsample = LTXLatentUpsamplePipeline(vae=pipeline.vae, latent_upsampler=upsampler).to(torch.bfloat16)
-  pipeline.to("cuda")
-  pipe_upsample.to("cuda")
-  pipeline.vae.enable_tiling()
-
-  def round_to_nearest_resolution_acceptable_by_vae(height, width):
-      height = height - (height % pipeline.vae_spatial_compression_ratio)
-      width = width - (width % pipeline.vae_spatial_compression_ratio)
-      return height, width
-
-  prompt = """The camera pans over a snow-covered mountain range, revealing a vast expanse of snow-capped peaks and valleys.The mountains are covered in a thick layer of snow, with some areas appearing almost white while others have a slightly darker, almost grayish hue. The peaks are jagged and irregular, with some rising sharply into the sky while others are more rounded. The valleys are deep and narrow, with steep slopes that are also covered in snow. The trees in the foreground are mostly bare, with only a few leaves remaining on their branches. The sky is overcast, with thick clouds obscuring the sun. The overall impression is one of peace and tranquility, with the snow-covered mountains standing as a testament to the power and beauty of nature."""
-  # prompt = """A woman walks away from a white Jeep parked on a city street at night, then ascends a staircase and knocks on a door. The woman, wearing a dark jacket and jeans, walks away from the Jeep parked on the left side of the street, her back to the camera; she walks at a steady pace, her arms swinging slightly by her sides; the street is dimly lit, with streetlights casting pools of light on the wet pavement; a man in a dark jacket and jeans walks past the Jeep in the opposite direction; the camera follows the woman from behind as she walks up a set of stairs towards a building with a green door; she reaches the top of the stairs and turns left, continuing to walk towards the building; she reaches the door and knocks on it with her right hand; the camera remains stationary, focused on the doorway; the scene is captured in real-life footage."""
-  negative_prompt = "bright colors, symbols, graffiti, watermarks, worst quality, inconsistent motion, blurry, jittery, distorted"
-  expected_height, expected_width = 480, 832
-  downscale_factor = 2 / 3
-  # num_frames = 161
-  num_frames = 361
-
-  # 1. Generate video at smaller resolution
-  downscaled_height, downscaled_width = int(expected_height * downscale_factor), int(expected_width * downscale_factor)
-  downscaled_height, downscaled_width = round_to_nearest_resolution_acceptable_by_vae(downscaled_height, downscaled_width)
-  latents = pipeline(
-      prompt=prompt,
-      negative_prompt=negative_prompt,
-      width=downscaled_width,
-      height=downscaled_height,
-      num_frames=num_frames,
-      timesteps=[1000, 993, 987, 981, 975, 909, 725, 0.03],
-      decode_timestep=0.05,
-      decode_noise_scale=0.025,
-      image_cond_noise_scale=0.0,
-      guidance_scale=1.0,
-      guidance_rescale=0.7,
-      generator=torch.Generator().manual_seed(0),
-      output_type="latent",
-  ).frames
-
-  # 2. Upscale generated video using latent upsampler with fewer inference steps
-  # The available latent upsampler upscales the height/width by 2x
-  upscaled_height, upscaled_width = downscaled_height * 2, downscaled_width * 2
-  upscaled_latents = pipe_upsample(
-      latents=latents,
-      adain_factor=1.0,
-      tone_map_compression_ratio=0.6,
-      output_type="latent"
-  ).frames
-
-  # 3. Denoise the upscaled video with few steps to improve texture (optional, but recommended)
-  video = pipeline(
-      prompt=prompt,
-      negative_prompt=negative_prompt,
-      width=upscaled_width,
-      height=upscaled_height,
-      num_frames=num_frames,
-      denoise_strength=0.999,  # Effectively, 4 inference steps out of 5
-      timesteps=[1000, 909, 725, 421, 0],
-      latents=upscaled_latents,
-      decode_timestep=0.05,
-      decode_noise_scale=0.025,
-      image_cond_noise_scale=0.0,
-      guidance_scale=1.0,
-      guidance_rescale=0.7,
-      generator=torch.Generator().manual_seed(0),
-      output_type="pil",
-  ).frames[0]
-
-  # 4. Downscale the video to the expected resolution
-  video = [frame.resize((expected_width, expected_height)) for frame in video]
-
-  export_to_video(video, "output.mp4", fps=24)
-  ```
-
-  </details>
-
 - LTX-Video supports LoRAs with [`~loaders.LTXVideoLoraLoaderMixin.load_lora_weights`].
 
   <details>

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

@@ -45,8 +45,11 @@ Lumina-T2X has the following components:
 
 This pipeline was contributed by [PommesPeter](https://github.com/PommesPeter). The original codebase can be found [here](https://github.com/Alpha-VLLM/Lumina-T2X). The original weights can be found under [hf.co/Alpha-VLLM](https://huggingface.co/Alpha-VLLM).
 
-> [!TIP]
+<Tip>
-> Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
 
 ### Inference (Text-to-Image)