remove torch.save from remnant code.

* fix links

* up

.github/workflows/benchmark.yml

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

.github/workflows/build_docker_images.yml

@@ -42,18 +42,39 @@ jobs:
           CHANGED_FILES: ${{ steps.file_changes.outputs.all }}
         run: |
           echo "$CHANGED_FILES"
-          for FILE in $CHANGED_FILES; do 
+          ALLOWED_IMAGES=(
+            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 $CHANGED_FILES; do
             # skip anything that isn't still on disk
-            if [[ ! -f "$FILE" ]]; then
+            if [[ ! -e "$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 != ''
 
@@ -72,7 +93,6 @@ 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

@@ -12,7 +12,33 @@ 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: |
-          python -m pip install --upgrade pip
+          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_HUB_ENABLE_HF_TRANSFER: 1
+  HF_XET_HIGH_PERFORMANCE: 1
   OMP_NUM_THREADS: 8
   MKL_NUM_THREADS: 8
   PYTEST_TIMEOUT: 600
@@ -71,10 +71,11 @@ jobs:
         run: nvidia-smi
       - name: Install dependencies
         run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          python -m uv pip install -e [quality,test]
-          pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-          python -m uv pip install pytest-reportlog
+          uv pip install -e ".[quality]"
+          uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+          #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+          uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1 
+          uv pip install pytest-reportlog
       - name: Environment
         run: |
           python utils/print_env.py
@@ -84,8 +85,8 @@ jobs:
           # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
-          python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            -s -v -k "not Flax and not Onnx" \
+          pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+             -k "not Flax and not Onnx" \
             --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
             --report-log=tests_pipeline_${{ matrix.module }}_cuda.log \
             tests/pipelines/${{ matrix.module }}
@@ -124,11 +125,12 @@ jobs:
 
     - name: Install dependencies
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
-        python -m uv pip install peft@git+https://github.com/huggingface/peft.git
-        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-        python -m uv pip install pytest-reportlog
+        uv pip install -e ".[quality]"
+        uv pip install peft@git+https://github.com/huggingface/peft.git
+        uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+        #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 
+        uv pip install pytest-reportlog
     - name: Environment
       run: python utils/print_env.py
 
@@ -139,8 +141,8 @@ jobs:
         # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
-        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "not Flax and not Onnx" \
+        pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+          -k "not Flax and not Onnx" \
           --make-reports=tests_torch_${{ matrix.module }}_cuda \
           --report-log=tests_torch_${{ matrix.module }}_cuda.log \
           tests/${{ matrix.module }}
@@ -152,8 +154,8 @@ jobs:
         # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
-        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -s -v --make-reports=examples_torch_cuda \
+        pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+          --make-reports=examples_torch_cuda \
           --report-log=examples_torch_cuda.log \
           examples/
 
@@ -191,8 +193,9 @@ jobs:
         nvidia-smi
     - name: Install dependencies
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test,training]
+        uv pip install -e ".[quality,training]"
+        #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
@@ -201,7 +204,7 @@ jobs:
         HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
         RUN_COMPILE: yes
       run: |
-        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v -k "compile" --make-reports=tests_torch_compile_cuda tests/
+        pytest -n 1 --max-worker-restart=0 --dist=loadfile -k "compile" --make-reports=tests_torch_compile_cuda tests/
     - name: Failure short reports
       if: ${{ failure() }}
       run: cat reports/tests_torch_compile_cuda_failures_short.txt
@@ -232,11 +235,12 @@ jobs:
         run: nvidia-smi
       - name: Install dependencies
         run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          python -m uv pip install -e [quality,test]
-          python -m uv pip install 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
-          python -m uv pip install pytest-reportlog
+          uv pip install -e ".[quality]"
+          uv pip install peft@git+https://github.com/huggingface/peft.git
+          uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+          #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 
+          uv pip install pytest-reportlog
       - name: Environment
         run: |
           python utils/print_env.py
@@ -247,7 +251,7 @@ jobs:
           CUBLAS_WORKSPACE_CONFIG: :16:8
           BIG_GPU_MEMORY: 40
         run: |
-          python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+          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 \
@@ -282,10 +286,11 @@ jobs:
 
       - name: Install dependencies
         run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          python -m uv pip install -e [quality,test]
-          python -m uv pip install peft@git+https://github.com/huggingface/peft.git
-          pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+          uv pip install -e ".[quality]"
+          uv pip install peft@git+https://github.com/huggingface/peft.git
+          uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+          #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: |
@@ -297,8 +302,8 @@ jobs:
           # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
-          python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            -s -v -k "not Flax and not Onnx" \
+          pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+            -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 \
@@ -357,13 +362,14 @@ jobs:
         run: nvidia-smi
       - name: Install dependencies
         run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          python -m uv pip install -e [quality,test]
-          python -m uv pip install -U ${{ matrix.config.backend }}
+          uv pip install -e ".[quality]"
+          uv pip install -U ${{ matrix.config.backend }}
           if [ "${{ join(matrix.config.additional_deps, ' ') }}" != "" ]; then
-              python -m uv pip install ${{ join(matrix.config.additional_deps, ' ') }}
+              uv pip install ${{ join(matrix.config.additional_deps, ' ') }}
           fi
-          python -m uv pip install pytest-reportlog
+          uv pip install pytest-reportlog
+          #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+          uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1 
       - name: Environment
         run: |
           python utils/print_env.py
@@ -374,7 +380,7 @@ jobs:
           CUBLAS_WORKSPACE_CONFIG: :16:8
           BIG_GPU_MEMORY: 40
         run: |
-          python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+          pytest -n 1 --max-worker-restart=0 --dist=loadfile \
             --make-reports=tests_${{ matrix.config.backend }}_torch_cuda \
             --report-log=tests_${{ matrix.config.backend }}_torch_cuda.log \
             tests/quantization/${{ matrix.config.test_location }}
@@ -409,10 +415,11 @@ jobs:
         run: nvidia-smi
       - name: Install dependencies
         run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          python -m uv pip install -e [quality,test]
-          python -m uv pip install -U bitsandbytes optimum_quanto
-          python -m uv pip install pytest-reportlog
+          uv pip install -e ".[quality]"
+          uv pip install -U bitsandbytes optimum_quanto
+          #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 
+          uv pip install pytest-reportlog
       - name: Environment
         run: |
           python utils/print_env.py
@@ -423,7 +430,7 @@ jobs:
           CUBLAS_WORKSPACE_CONFIG: :16:8
           BIG_GPU_MEMORY: 40
         run: |
-          python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+          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
@@ -523,11 +530,11 @@ jobs:
 #      - name: Install dependencies
 #        shell: arch -arch arm64 bash {0}
 #        run: |
-#          ${CONDA_RUN} python -m pip install --upgrade pip uv
-#          ${CONDA_RUN} python -m uv pip install -e [quality,test]
-#          ${CONDA_RUN} python -m uv pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cpu
-#          ${CONDA_RUN} python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate
-#          ${CONDA_RUN} python -m uv pip install pytest-reportlog
+#          ${CONDA_RUN} pip install --upgrade pip uv
+#          ${CONDA_RUN} uv pip install -e ".[quality]"
+#          ${CONDA_RUN} 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} uv pip install pytest-reportlog
 #      - name: Environment
 #        shell: arch -arch arm64 bash {0}
 #        run: |
@@ -538,7 +545,7 @@ jobs:
 #          HF_HOME: /System/Volumes/Data/mnt/cache
 #          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
 #        run: |
-#          ${CONDA_RUN} python -m pytest -n 1 -s -v --make-reports=tests_torch_mps \
+#          ${CONDA_RUN} pytest -n 1  --make-reports=tests_torch_mps \
 #            --report-log=tests_torch_mps.log \
 #            tests/
 #      - name: Failure short reports
@@ -579,11 +586,11 @@ jobs:
 #      - name: Install dependencies
 #        shell: arch -arch arm64 bash {0}
 #        run: |
-#          ${CONDA_RUN} python -m pip install --upgrade pip uv
-#          ${CONDA_RUN} python -m uv pip install -e [quality,test]
-#          ${CONDA_RUN} python -m uv pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cpu
-#          ${CONDA_RUN} python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate
-#          ${CONDA_RUN} python -m uv pip install pytest-reportlog
+#          ${CONDA_RUN} pip install --upgrade pip uv
+#          ${CONDA_RUN} uv pip install -e ".[quality]"
+#          ${CONDA_RUN} 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} uv pip install pytest-reportlog
 #      - name: Environment
 #        shell: arch -arch arm64 bash {0}
 #        run: |
@@ -594,7 +601,7 @@ jobs:
 #          HF_HOME: /System/Volumes/Data/mnt/cache
 #          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
 #        run: |
-#          ${CONDA_RUN} python -m pytest -n 1 -s -v --make-reports=tests_torch_mps \
+#          ${CONDA_RUN} pytest -n 1  --make-reports=tests_torch_mps \
 #            --report-log=tests_torch_mps.log \
 #            tests/
 #      - name: Failure short reports

.github/workflows/pr_dependency_test.yml

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

.github/workflows/pr_modular_tests.yml

@@ -26,7 +26,7 @@ concurrency:
 
 env:
   DIFFUSERS_IS_CI: yes
-  HF_HUB_ENABLE_HF_TRANSFER: 1
+  HF_XET_HIGH_PERFORMANCE: 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: |
-          python -m pip install --upgrade pip
+          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: |
-          python -m pip install --upgrade pip
+          pip install --upgrade pip
           pip install .[quality]
       - name: Check repo consistency
         run: |
@@ -108,22 +108,20 @@ jobs:
 
     - name: Install dependencies
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
-        pip uninstall transformers -y && pip uninstall huggingface_hub -y && python -m 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 install -e ".[quality]"
+        #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
+        uv pip uninstall accelerate && 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: ${{ matrix.config.framework == 'pytorch_pipelines' }}
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m pytest -n 8 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "not Flax and not Onnx" \
+        pytest -n 8 --max-worker-restart=0 --dist=loadfile \
+          -k "not Flax and not Onnx" \
           --make-reports=tests_${{ matrix.config.report }} \
           tests/modular_pipelines
 

.github/workflows/pr_test_fetcher.yml

@@ -33,8 +33,7 @@ jobs:
         fetch-depth: 0
     - name: Install dependencies
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
+        uv pip install -e ".[quality]"
     - name: Environment
       run: |
         python utils/print_env.py
@@ -90,19 +89,16 @@ jobs:
 
     - name: Install dependencies
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m pip install -e [quality,test]
-        python -m pip install accelerate
+        uv pip install -e ".[quality]"
+        uv 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: |
-        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 ${{ fromJson(needs.setup_pr_tests.outputs.test_map)[matrix.modules] }}
+        pytest -n 2 --dist=loadfile -v --make-reports=${{ matrix.modules }}_tests_cpu ${{ fromJson(needs.setup_pr_tests.outputs.test_map)[matrix.modules] }}
 
     - name: Failure short reports
       if: ${{ failure() }}
@@ -148,19 +144,16 @@ jobs:
 
     - name: Install dependencies
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m pip install -e [quality,test]
+        pip install -e [quality]
 
     - 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: ${{ matrix.config.framework == 'hub_tests_pytorch' }}
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        HUGGINGFACE_CO_STAGING=true python -m pytest \
+        HUGGINGFACE_CO_STAGING=true 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_HUB_ENABLE_HF_TRANSFER: 1
+  HF_XET_HIGH_PERFORMANCE: 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: |
-          python -m pip install --upgrade pip
+          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: |
-          python -m pip install --upgrade pip
+          pip install --upgrade pip
           pip install .[quality]
       - name: Check repo consistency
         run: |
@@ -114,40 +114,36 @@ jobs:
 
     - name: Install dependencies
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
-        pip uninstall transformers -y && pip uninstall huggingface_hub -y && python -m 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 install -e ".[quality]"
+        #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
+        uv pip uninstall accelerate && 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: ${{ matrix.config.framework == 'pytorch_pipelines' }}
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m pytest -n 8 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "not Flax and not Onnx" \
+        pytest -n 8 --max-worker-restart=0 --dist=loadfile \
+          -k "not Flax and not Onnx" \
           --make-reports=tests_${{ matrix.config.report }} \
           tests/pipelines
 
     - name: Run fast PyTorch Model Scheduler CPU tests
       if: ${{ matrix.config.framework == 'pytorch_models' }}
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m pytest -n 4 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "not Flax and not Onnx and not Dependency" \
+        pytest -n 4 --max-worker-restart=0 --dist=loadfile \
+          -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: ${{ matrix.config.framework == 'pytorch_examples' }}
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install peft timm
-        python -m pytest -n 4 --max-worker-restart=0 --dist=loadfile \
+        uv pip install ".[training]"
+        pytest -n 4 --max-worker-restart=0 --dist=loadfile \
           --make-reports=tests_${{ matrix.config.report }} \
           examples
 
@@ -195,19 +191,16 @@ jobs:
 
     - name: Install dependencies
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
+        uv pip install -e ".[quality]"
 
     - 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: ${{ matrix.config.framework == 'hub_tests_pytorch' }}
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        HUGGINGFACE_CO_STAGING=true python -m pytest \
+        HUGGINGFACE_CO_STAGING=true pytest \
           -m "is_staging_test" \
           --make-reports=tests_${{ matrix.config.report }} \
           tests
@@ -249,28 +242,26 @@ jobs:
 
     - name: Install dependencies
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
+        uv pip install -e ".[quality]"
         # TODO (sayakpaul, DN6): revisit `--no-deps`
-        python -m pip install -U peft@git+https://github.com/huggingface/peft.git --no-deps
-        python -m uv pip install -U tokenizers
-        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git --no-deps
-        pip uninstall transformers -y && pip uninstall huggingface_hub -y && python -m uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+        uv pip install -U peft@git+https://github.com/huggingface/peft.git --no-deps
+        uv pip install -U tokenizers
+        uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git --no-deps
+        #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 -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python utils/print_env.py
 
     - name: Run fast PyTorch LoRA tests with PEFT
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m pytest -n 4 --max-worker-restart=0 --dist=loadfile \
-          -s -v \
+        pytest -n 4 --max-worker-restart=0 --dist=loadfile \
+          \
           --make-reports=tests_peft_main \
           tests/lora/
-        python -m pytest -n 4 --max-worker-restart=0 --dist=loadfile \
-          -s -v \
+        pytest -n 4 --max-worker-restart=0 --dist=loadfile \
+          \
           --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_HUB_ENABLE_HF_TRANSFER: 1
+  HF_XET_HIGH_PERFORMANCE: 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: |
-          python -m pip install --upgrade pip
+          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: |
-          python -m pip install --upgrade pip
+          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'" >> $GITHUB_STEP_SUMMARY
-  
+
   setup_torch_cuda_pipeline_matrix:
     needs: [check_code_quality, check_repository_consistency]
     name: Setup Torch Pipelines CUDA Slow Tests Matrix
@@ -88,8 +88,7 @@ jobs:
           fetch-depth: 2
       - name: Install dependencies
         run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          python -m uv pip install -e [quality,test]
+          uv pip install -e ".[quality]"
       - name: Environment
         run: |
           python utils/print_env.py
@@ -130,10 +129,10 @@ jobs:
           nvidia-smi
       - name: Install dependencies
         run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          python -m uv pip install -e [quality,test]
-          pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-          pip uninstall transformers -y && pip uninstall huggingface_hub -y && python -m uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+          uv pip install -e ".[quality]"
+          uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+          #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: |
@@ -151,18 +150,18 @@ jobs:
           # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
-          if [ "${{ matrix.module }}" = "ip_adapters" ]; then 
-              python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-              -s -v -k "not Flax and not Onnx" \
+          if [ "${{ matrix.module }}" = "ip_adapters" ]; then
+              pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+              -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 }})
-              python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-              -s -v -k "not Flax and not Onnx and $pattern" \
+              pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+              -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() }}
@@ -200,11 +199,11 @@ jobs:
 
     - name: Install dependencies
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
-        python -m uv pip install peft@git+https://github.com/huggingface/peft.git
-        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-        pip uninstall transformers -y && pip uninstall huggingface_hub -y && python -m uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+        uv pip install -e ".[quality]"
+        uv pip install peft@git+https://github.com/huggingface/peft.git
+        uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+        #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: |
@@ -225,11 +224,11 @@ jobs:
       run: |
         pattern=$(cat ${{ steps.extract_tests.outputs.pattern_file }})
         if [ -z "$pattern" ]; then
-          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 }}  
+          pytest -n 1  --max-worker-restart=0 --dist=loadfile -k "not Flax and not Onnx" tests/${{ matrix.module }} \
+          --make-reports=tests_torch_cuda_${{ matrix.module }}
         else
-          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 }}  
+          pytest -n 1  --max-worker-restart=0 --dist=loadfile -k "not Flax and not Onnx and $pattern" tests/${{ matrix.module }} \
+          --make-reports=tests_torch_cuda_${{ matrix.module }}
         fi
 
     - name: Failure short reports
@@ -265,22 +264,20 @@ jobs:
         nvidia-smi
     - name: Install dependencies
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        pip uninstall transformers -y && pip uninstall huggingface_hub -y && python -m 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 --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+        uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
+        uv pip install -e ".[quality,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: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install timm
-        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v --make-reports=examples_torch_cuda examples/
+        uv pip install ".[training]"
+        pytest -n 1 --max-worker-restart=0 --dist=loadfile --make-reports=examples_torch_cuda examples/
 
     - name: Failure short reports
       if: ${{ failure() }}

.github/workflows/pr_torch_dependency_test.yml

@@ -25,12 +25,8 @@ jobs:
           python-version: "3.8"
       - name: Install dependencies
         run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          python -m pip install --upgrade pip uv
-          python -m uv pip install -e .
-          python -m uv pip install torch torchvision torchaudio
-          python -m uv pip install pytest
+          pip install -e .
+          pip install torch torchvision torchaudio pytest
       - name: Check for soft dependencies
         run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          pytest tests/others/test_dependencies.py
+            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_HUB_ENABLE_HF_TRANSFER: 1
+  HF_XET_HIGH_PERFORMANCE: 1
   PYTEST_TIMEOUT: 600
   PIPELINE_USAGE_CUTOFF: 50000
 
@@ -34,8 +34,7 @@ jobs:
           fetch-depth: 2
       - name: Install dependencies
         run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          python -m uv pip install -e [quality,test]
+          uv pip install -e ".[quality]"
       - name: Environment
         run: |
           python utils/print_env.py
@@ -75,9 +74,10 @@ jobs:
           nvidia-smi
       - name: Install dependencies
         run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          python -m uv pip install -e [quality,test]
-          pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+          uv pip install -e ".[quality]"
+          uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+          #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
@@ -87,8 +87,8 @@ jobs:
           # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
-          python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            -s -v -k "not Flax and not Onnx" \
+          pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+            -k "not Flax and not Onnx" \
             --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
             tests/pipelines/${{ matrix.module }}
       - name: Failure short reports
@@ -126,10 +126,11 @@ jobs:
 
     - name: Install dependencies
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
-        python -m uv pip install peft@git+https://github.com/huggingface/peft.git
-        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+        uv pip install -e ".[quality]"
+        uv pip install peft@git+https://github.com/huggingface/peft.git
+        uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+        #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: |
@@ -141,8 +142,8 @@ jobs:
         # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
-        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "not Flax and not Onnx" \
+        pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+          -k "not Flax and not Onnx" \
           --make-reports=tests_torch_cuda_${{ matrix.module }} \
           tests/${{ matrix.module }}
 
@@ -180,8 +181,9 @@ jobs:
         nvidia-smi
     - name: Install dependencies
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test,training]
+        uv pip install -e ".[quality,training]"
+        #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
@@ -190,7 +192,7 @@ jobs:
         HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
         RUN_COMPILE: yes
       run: |
-        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v -k "compile" --make-reports=tests_torch_compile_cuda tests/
+        pytest -n 1 --max-worker-restart=0 --dist=loadfile -k "compile" --make-reports=tests_torch_compile_cuda tests/
     - name: Failure short reports
       if: ${{ failure() }}
       run: cat reports/tests_torch_compile_cuda_failures_short.txt
@@ -223,8 +225,7 @@ jobs:
         nvidia-smi
     - name: Install dependencies
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test,training]
+        uv pip install -e ".[quality,training]"
     - name: Environment
       run: |
         python utils/print_env.py
@@ -232,7 +233,7 @@ jobs:
       env:
         HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
       run: |
-        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v -k "xformers" --make-reports=tests_torch_xformers_cuda tests/
+        pytest -n 1 --max-worker-restart=0 --dist=loadfile -k "xformers" --make-reports=tests_torch_xformers_cuda tests/
     - name: Failure short reports
       if: ${{ failure() }}
       run: cat reports/tests_torch_xformers_cuda_failures_short.txt
@@ -264,21 +265,18 @@ jobs:
         nvidia-smi
     - name: Install dependencies
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test,training]
+        uv pip install -e ".[quality,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: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install timm
-        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v --make-reports=examples_torch_cuda examples/
+        uv pip install ".[training]"
+        pytest -n 1 --max-worker-restart=0 --dist=loadfile --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_HUB_ENABLE_HF_TRANSFER: 1
+  HF_XET_HIGH_PERFORMANCE: 1
   PYTEST_TIMEOUT: 600
   RUN_SLOW: no
 
@@ -60,29 +60,25 @@ jobs:
 
     - name: Install dependencies
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
+        uv pip install -e ".[quality]"
 
     - 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: ${{ matrix.config.framework == 'pytorch' }}
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m pytest -n 4 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "not Flax and not Onnx" \
+        pytest -n 4 --max-worker-restart=0 --dist=loadfile \
+          -k "not Flax and not Onnx" \
           --make-reports=tests_${{ matrix.config.report }} \
           tests/
 
     - name: Run example PyTorch CPU tests
       if: ${{ matrix.config.framework == 'pytorch_examples' }}
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install peft timm
-        python -m pytest -n 4 --max-worker-restart=0 --dist=loadfile \
+        uv pip install ".[training]"
+        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_HUB_ENABLE_HF_TRANSFER: 1
+  HF_XET_HIGH_PERFORMANCE: 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 -s -v --make-reports=tests_torch_mps tests/
+        ${CONDA_RUN} python -m pytest -n 0 --make-reports=tests_torch_mps tests/
 
     - name: Failure short reports
       if: ${{ failure() }}

.github/workflows/release_tests_fast.yml

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

.github/workflows/run_tests_from_a_pr.yml

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

.gitignore

@@ -125,6 +125,9 @@ 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/runwayml/stable-diffusion-inpainting"> runwayml/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>
   </tr>
   <tr style="border-top: 2px solid black">
     <td>Image Variation</td>

docker/diffusers-doc-builder/Dockerfile

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

docker/diffusers-onnxruntime-cuda/Dockerfile

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

docker/diffusers-pytorch-cpu/Dockerfile

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

docker/diffusers-pytorch-cuda/Dockerfile

@@ -2,11 +2,13 @@ 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 \
@@ -14,38 +16,34 @@ RUN apt install -y bash \
     git-lfs \
     curl \
     ca-certificates \
+    libglib2.0-0 \
     libsndfile1-dev \
     libgl1 \
-    python3.10 \
-    python3.10-dev \
+    python3 \
     python3-pip \
-    python3.10-venv && \
-    rm -rf /var/lib/apt/lists
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/*
 
-# make sure to use venv
-RUN python3.10 -m venv /opt/venv
-ENV PATH="/opt/venv/bin:$PATH"
+RUN curl -LsSf https://astral.sh/uv/install.sh | sh
+ENV PATH="/root/.local/bin:$PATH"
+ENV VIRTUAL_ENV="/opt/venv"
+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 python3.10 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
-    python3.10 -m uv pip install --no-cache-dir \
+RUN uv pip install --no-cache-dir \
     torch \
     torchvision \
-    torchaudio \
-    invisible_watermark && \
-    python3.10 -m pip install --no-cache-dir \
+    torchaudio
+
+RUN uv pip install --no-cache-dir "git+https://github.com/huggingface/diffusers.git@main#egg=diffusers[test]"
+
+# Extra dependencies
+RUN uv pip install --no-cache-dir \
     accelerate \
-    datasets \
-    hf-doc-builder \
-    huggingface-hub \
-    hf_transfer \
-    Jinja2 \
-    librosa \
     numpy==1.26.4 \
-    scipy \
-    tensorboard \
-    transformers \
-    pytorch-lightning  \
-    hf_transfer
+    pytorch-lightning \
+    hf_xet
 
 CMD ["/bin/bash"]

docker/diffusers-pytorch-minimum-cuda/Dockerfile

@@ -2,6 +2,7 @@ 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"
@@ -9,7 +10,8 @@ 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 \
@@ -17,37 +19,34 @@ RUN apt install -y bash \
     git-lfs \
     curl \
     ca-certificates \
+    libglib2.0-0 \
     libsndfile1-dev \
     libgl1 \
-    python3.10 \
-    python3.10-dev \
+    python3 \
     python3-pip \
-    python3.10-venv && \
-    rm -rf /var/lib/apt/lists
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/*
 
-# make sure to use venv
-RUN python3.10 -m venv /opt/venv
-ENV PATH="/opt/venv/bin:$PATH"
+RUN curl -LsSf https://astral.sh/uv/install.sh | sh
+ENV PATH="/root/.local/bin:$PATH"
+ENV VIRTUAL_ENV="/opt/venv"
+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 python3.10 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
-    python3.10 -m uv pip install --no-cache-dir \
+RUN uv pip install --no-cache-dir \
     torch==$MINIMUM_SUPPORTED_TORCH_VERSION \
     torchvision==$MINIMUM_SUPPORTED_TORCHVISION_VERSION \
-    torchaudio==$MINIMUM_SUPPORTED_TORCHAUDIO_VERSION \
-    invisible_watermark && \
-    python3.10 -m pip install --no-cache-dir \
+    torchaudio==$MINIMUM_SUPPORTED_TORCHAUDIO_VERSION
+
+RUN uv pip install --no-cache-dir "git+https://github.com/huggingface/diffusers.git@main#egg=diffusers[test]"
+
+# Extra dependencies
+RUN uv pip install --no-cache-dir \
     accelerate \
-    datasets \
-    hf-doc-builder \
-    huggingface-hub \
-    hf_transfer \
-    Jinja2 \
-    librosa \
     numpy==1.26.4 \
-    scipy \
-    tensorboard \
-    transformers \
-    hf_transfer
+    pytorch-lightning \
+    hf_xet
 
 CMD ["/bin/bash"]

docker/diffusers-pytorch-xformers-cuda/Dockerfile

@@ -2,50 +2,49 @@ 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 \
-                   git \
-                   git-lfs \
-                   curl \
-                   ca-certificates \
-                   libsndfile1-dev \
-                   libgl1 \
-                   python3.10 \
-                   python3.10-dev \
-                   python3-pip \
-                   python3.10-venv && \
-    rm -rf /var/lib/apt/lists
+    build-essential \
+    git \
+    git-lfs \
+    curl \
+    ca-certificates \
+    libglib2.0-0 \
+    libsndfile1-dev \
+    libgl1 \
+    python3 \
+    python3-pip \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/*
 
-# make sure to use venv
-RUN python3.10 -m venv /opt/venv
-ENV PATH="/opt/venv/bin:$PATH"
+RUN curl -LsSf https://astral.sh/uv/install.sh | sh
+ENV PATH="/root/.local/bin:$PATH"
+ENV VIRTUAL_ENV="/opt/venv"
+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 python3.10 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
-    python3.10 -m pip install --no-cache-dir \
-        torch \
-        torchvision \
-        torchaudio \
-        invisible_watermark && \
-    python3.10 -m uv pip install --no-cache-dir \
-        accelerate \
-        datasets \
-        hf-doc-builder \
-        huggingface-hub \
-        hf_transfer \
-        Jinja2 \
-        librosa \
-        numpy==1.26.4 \
-        scipy \
-        tensorboard \
-        transformers \
-        xformers  \
-        hf_transfer
+RUN uv pip install --no-cache-dir \
+    torch \
+    torchvision \
+    torchaudio
+
+RUN uv pip install --no-cache-dir "git+https://github.com/huggingface/diffusers.git@main#egg=diffusers[test]"
+
+# Extra dependencies
+RUN uv pip install --no-cache-dir \
+    accelerate \
+    numpy==1.26.4 \
+    pytorch-lightning \
+    hf_xet \
+    xformers
 
 CMD ["/bin/bash"]

docs/source/en/_toctree.yml

@@ -1,5 +1,4 @@
-- title: Get started
-  sections:
+- sections:
   - local: index
     title: Diffusers
   - local: installation
@@ -8,9 +7,8 @@
     title: Quickstart
   - local: stable_diffusion
     title: Basic performance
-
-- title: Pipelines
-  isExpanded: false
+  title: Get started
+- isExpanded: false
   sections:
   - local: using-diffusers/loading
     title: DiffusionPipeline
@@ -24,13 +22,14 @@
     title: Reproducibility
   - local: using-diffusers/schedulers
     title: Schedulers
+  - local: using-diffusers/automodel
+    title: AutoModel
   - local: using-diffusers/other-formats
     title: Model formats
   - local: using-diffusers/push_to_hub
     title: Sharing pipelines and models
-
-- title: Adapters
-  isExpanded: false
+  title: Pipelines
+- isExpanded: false
   sections:
   - local: tutorials/using_peft_for_inference
     title: LoRA
@@ -44,21 +43,19 @@
     title: DreamBooth
   - local: using-diffusers/textual_inversion_inference
     title: Textual inversion
-
-- title: Inference
-  isExpanded: false
+  title: Adapters
+- isExpanded: false
   sections:
   - local: using-diffusers/weighted_prompts
-    title: Prompt techniques
+    title: Prompting
   - 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 optimization
-  isExpanded: false
+  title: Inference
+- isExpanded: false
   sections:
   - local: optimization/fp16
     title: Accelerate inference
@@ -70,8 +67,7 @@
     title: Reduce memory usage
   - local: optimization/speed-memory-optims
     title: Compiling and offloading quantized models
-  - title: Community optimizations
-    sections:
+  - sections:
     - local: optimization/pruna
       title: Pruna
     - local: optimization/xformers
@@ -90,9 +86,9 @@
       title: ParaAttention
     - local: using-diffusers/image_quality
       title: FreeU
-
-- title: Hybrid Inference
-  isExpanded: false
+    title: Community optimizations
+  title: Inference optimization
+- isExpanded: false
   sections:
   - local: hybrid_inference/overview
     title: Overview
@@ -102,9 +98,8 @@
     title: VAE Encode
   - local: hybrid_inference/api_reference
     title: API Reference
-
-- title: Modular Diffusers
-  isExpanded: false
+  title: Hybrid Inference
+- isExpanded: false
   sections:
   - local: modular_diffusers/overview
     title: Overview
@@ -126,9 +121,10 @@
     title: ComponentsManager
   - local: modular_diffusers/guiders
     title: Guiders
-
-- title: Training
-  isExpanded: false
+  - local: modular_diffusers/custom_blocks
+    title: Building Custom Blocks
+  title: Modular Diffusers
+- isExpanded: false
   sections:
   - local: training/overview
     title: Overview
@@ -138,8 +134,7 @@
     title: Adapt a model to a new task
   - local: tutorials/basic_training
     title: Train a diffusion model
-  - title: Models
-    sections:
+  - sections:
     - local: training/unconditional_training
       title: Unconditional image generation
     - local: training/text2image
@@ -158,8 +153,8 @@
       title: InstructPix2Pix
     - local: training/cogvideox
       title: CogVideoX
-  - title: Methods
-    sections:
+    title: Models
+  - sections:
     - local: training/text_inversion
       title: Textual Inversion
     - local: training/dreambooth
@@ -172,9 +167,9 @@
       title: Latent Consistency Distillation
     - local: training/ddpo
       title: Reinforcement learning training with DDPO
-
-- title: Quantization
-  isExpanded: false
+    title: Methods
+  title: Training
+- isExpanded: false
   sections:
   - local: quantization/overview
     title: Getting started
@@ -188,9 +183,8 @@
     title: quanto
   - local: quantization/modelopt
     title: NVIDIA ModelOpt
-
-- title: Model accelerators and hardware
-  isExpanded: false
+  title: Quantization
+- isExpanded: false
   sections:
   - local: optimization/onnx
     title: ONNX
@@ -204,9 +198,8 @@
     title: Intel Gaudi
   - local: optimization/neuron
     title: AWS Neuron
-
-- title: Specific pipeline examples
-  isExpanded: false
+  title: Model accelerators and hardware
+- isExpanded: false
   sections:
   - local: using-diffusers/consisid
     title: ConsisID
@@ -232,12 +225,10 @@
     title: Stable Video Diffusion
   - local: using-diffusers/marigold_usage
     title: Marigold Computer Vision
-
-- title: Resources
-  isExpanded: false
+  title: Specific pipeline examples
+- isExpanded: false
   sections:
-  - title: Task recipes
-    sections:
+  - sections:
     - local: using-diffusers/unconditional_image_generation
       title: Unconditional image generation
     - local: using-diffusers/conditional_image_generation
@@ -252,6 +243,7 @@
       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
@@ -266,12 +258,10 @@
     title: Diffusers' Ethical Guidelines
   - local: conceptual/evaluation
     title: Evaluating Diffusion Models
-
-- title: API
-  isExpanded: false
+  title: Resources
+- isExpanded: false
   sections:
-  - title: Main Classes
-    sections:
+  - sections:
     - local: api/configuration
       title: Configuration
     - local: api/logging
@@ -282,8 +272,8 @@
       title: Quantization
     - local: api/parallel
       title: Parallel inference
-  - title: Modular
-    sections:
+    title: Main Classes
+  - sections:
     - local: api/modular_diffusers/pipeline
       title: Pipeline
     - local: api/modular_diffusers/pipeline_blocks
@@ -294,8 +284,8 @@
       title: Components and configs
     - local: api/modular_diffusers/guiders
       title: Guiders
-  - title: Loaders
-    sections:
+    title: Modular
+  - sections:
     - local: api/loaders/ip_adapter
       title: IP-Adapter
     - local: api/loaders/lora
@@ -310,14 +300,13 @@
       title: SD3Transformer2D
     - local: api/loaders/peft
       title: PEFT
-  - title: Models
-    sections:
+    title: Loaders
+  - sections:
     - local: api/models/overview
       title: Overview
     - local: api/models/auto_model
       title: AutoModel
-    - title: ControlNets
-      sections:
+    - sections:
       - local: api/models/controlnet
         title: ControlNetModel
       - local: api/models/controlnet_union
@@ -332,16 +321,20 @@
         title: SD3ControlNetModel
       - local: api/models/controlnet_sparsectrl
         title: SparseControlNetModel
-    - title: Transformers
-      sections:
+      title: ControlNets
+    - 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
@@ -356,12 +349,16 @@
         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_video_transformer_3d
         title: HunyuanVideoTransformer3DModel
       - local: api/models/latte_transformer3d
@@ -384,6 +381,8 @@
         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
@@ -394,10 +393,12 @@
         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
-    - title: UNets
-      sections:
+      title: Transformers
+    - sections:
       - local: api/models/stable_cascade_unet
         title: StableCascadeUNet
       - local: api/models/unet
@@ -412,8 +413,8 @@
         title: UNetMotionModel
       - local: api/models/uvit2d
         title: UViT2DModel
-    - title: VAEs
-      sections:
+      title: UNets
+    - sections:
       - local: api/models/asymmetricautoencoderkl
         title: AsymmetricAutoencoderKL
       - local: api/models/autoencoder_dc
@@ -426,6 +427,10 @@
         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/autoencoderkl_ltx_video
@@ -446,210 +451,232 @@
         title: Tiny AutoEncoder
       - local: api/models/vq
         title: VQModel
-  - title: Pipelines
-    sections:
+      title: VAEs
+    title: Models
+  - 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
-    - local: api/pipelines/blip_diffusion
-      title: BLIP-Diffusion
-    - local: api/pipelines/bria_3_2
-      title: Bria 3.2
-    - local: api/pipelines/chroma
-      title: Chroma
-    - local: api/pipelines/cogvideox
-      title: CogVideoX
-    - local: api/pipelines/cogview3
-      title: CogView3
-    - local: api/pipelines/cogview4
-      title: CogView4
-    - local: api/pipelines/consisid
-      title: ConsisID
-    - local: api/pipelines/consistency_models
-      title: Consistency Models
-    - local: api/pipelines/controlnet
-      title: ControlNet
-    - local: api/pipelines/controlnet_flux
-      title: ControlNet with Flux.1
-    - local: api/pipelines/controlnet_hunyuandit
-      title: ControlNet with Hunyuan-DiT
-    - local: api/pipelines/controlnet_sd3
-      title: ControlNet with Stable Diffusion 3
-    - local: api/pipelines/controlnet_sdxl
-      title: ControlNet with Stable Diffusion XL
-    - local: api/pipelines/controlnet_sana
-      title: ControlNet-Sana
-    - local: api/pipelines/controlnetxs
-      title: ControlNet-XS
-    - local: api/pipelines/controlnetxs_sdxl
-      title: ControlNet-XS with Stable Diffusion XL
-    - local: api/pipelines/controlnet_union
-      title: ControlNetUnion
-    - local: api/pipelines/cosmos
-      title: Cosmos
-    - local: api/pipelines/dance_diffusion
-      title: Dance Diffusion
-    - local: api/pipelines/ddim
-      title: DDIM
-    - local: api/pipelines/ddpm
-      title: DDPM
-    - local: api/pipelines/deepfloyd_if
-      title: DeepFloyd IF
-    - local: api/pipelines/diffedit
-      title: DiffEdit
-    - local: api/pipelines/dit
-      title: DiT
-    - local: api/pipelines/easyanimate
-      title: EasyAnimate
-    - local: api/pipelines/flux
-      title: Flux
-    - local: api/pipelines/control_flux_inpaint
-      title: FluxControlInpaint
-    - local: api/pipelines/framepack
-      title: Framepack
-    - local: api/pipelines/hidream
-      title: HiDream-I1
-    - local: api/pipelines/hunyuandit
-      title: Hunyuan-DiT
-    - local: api/pipelines/hunyuan_video
-      title: HunyuanVideo
-    - local: api/pipelines/i2vgenxl
-      title: I2VGen-XL
-    - local: api/pipelines/pix2pix
-      title: InstructPix2Pix
-    - local: api/pipelines/kandinsky
-      title: Kandinsky 2.1
-    - local: api/pipelines/kandinsky_v22
-      title: Kandinsky 2.2
-    - local: api/pipelines/kandinsky3
-      title: Kandinsky 3
-    - local: api/pipelines/kolors
-      title: Kolors
-    - local: api/pipelines/latent_consistency_models
-      title: Latent Consistency Models
-    - local: api/pipelines/latent_diffusion
-      title: Latent Diffusion
-    - local: api/pipelines/latte
-      title: Latte
-    - local: api/pipelines/ledits_pp
-      title: LEDITS++
-    - local: api/pipelines/ltx_video
-      title: LTXVideo
-    - local: api/pipelines/lumina2
-      title: Lumina 2.0
-    - local: api/pipelines/lumina
-      title: Lumina-T2X
-    - local: api/pipelines/marigold
-      title: Marigold
-    - local: api/pipelines/mochi
-      title: Mochi
-    - local: api/pipelines/panorama
-      title: MultiDiffusion
-    - local: api/pipelines/musicldm
-      title: MusicLDM
-    - local: api/pipelines/omnigen
-      title: OmniGen
-    - local: api/pipelines/pag
-      title: PAG
-    - local: api/pipelines/paint_by_example
-      title: Paint by Example
-    - local: api/pipelines/pia
-      title: Personalized Image Animator (PIA)
-    - local: api/pipelines/pixart
-      title: PixArt-α
-    - local: api/pipelines/pixart_sigma
-      title: PixArt-Σ
-    - local: api/pipelines/qwenimage
-      title: QwenImage
-    - local: api/pipelines/sana
-      title: Sana
-    - local: api/pipelines/sana_sprint
-      title: Sana Sprint
-    - local: api/pipelines/self_attention_guidance
-      title: Self-Attention Guidance
-    - local: api/pipelines/semantic_stable_diffusion
-      title: Semantic Guidance
-    - local: api/pipelines/shap_e
-      title: Shap-E
-    - local: api/pipelines/skyreels_v2
-      title: SkyReels-V2
-    - local: api/pipelines/stable_audio
-      title: Stable Audio
-    - local: api/pipelines/stable_cascade
-      title: Stable Cascade
-    - title: Stable Diffusion
-      sections:
-      - local: api/pipelines/stable_diffusion/overview
-        title: Overview
-      - 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
+    - sections:
+      - local: api/pipelines/audioldm
+        title: AudioLDM
+      - local: api/pipelines/audioldm2
+        title: AudioLDM 2
+      - local: api/pipelines/dance_diffusion
+        title: Dance Diffusion
+      - local: api/pipelines/musicldm
+        title: MusicLDM
+      - local: api/pipelines/stable_audio
+        title: Stable Audio
+      title: Audio
+    - sections:
+      - 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/aura_flow
+        title: AuraFlow
+      - local: api/pipelines/blip_diffusion
+        title: BLIP-Diffusion
+      - local: api/pipelines/bria_3_2
+        title: Bria 3.2
+      - local: api/pipelines/bria_fibo
+        title: Bria Fibo
+      - local: api/pipelines/chroma
+        title: Chroma
+      - local: api/pipelines/cogview3
+        title: CogView3
+      - local: api/pipelines/cogview4
+        title: CogView4
+      - local: api/pipelines/consistency_models
+        title: Consistency Models
+      - local: api/pipelines/controlnet
+        title: ControlNet
+      - local: api/pipelines/controlnet_flux
+        title: ControlNet with Flux.1
+      - local: api/pipelines/controlnet_hunyuandit
+        title: ControlNet with Hunyuan-DiT
+      - local: api/pipelines/controlnet_sd3
+        title: ControlNet with Stable Diffusion 3
+      - local: api/pipelines/controlnet_sdxl
+        title: ControlNet with Stable Diffusion XL
+      - local: api/pipelines/controlnet_sana
+        title: ControlNet-Sana
+      - local: api/pipelines/controlnetxs
+        title: ControlNet-XS
+      - local: api/pipelines/controlnetxs_sdxl
+        title: ControlNet-XS with Stable Diffusion XL
+      - local: api/pipelines/controlnet_union
+        title: ControlNetUnion
+      - local: api/pipelines/cosmos
+        title: Cosmos
+      - local: api/pipelines/ddim
+        title: DDIM
+      - local: api/pipelines/ddpm
+        title: DDPM
+      - local: api/pipelines/deepfloyd_if
+        title: DeepFloyd IF
+      - local: api/pipelines/diffedit
+        title: DiffEdit
+      - local: api/pipelines/dit
+        title: DiT
+      - local: api/pipelines/easyanimate
+        title: EasyAnimate
+      - local: api/pipelines/flux
+        title: Flux
+      - local: api/pipelines/flux2
+        title: Flux2
+      - local: api/pipelines/control_flux_inpaint
+        title: FluxControlInpaint
+      - local: api/pipelines/hidream
+        title: HiDream-I1
+      - local: api/pipelines/hunyuandit
+        title: Hunyuan-DiT
+      - local: api/pipelines/hunyuanimage21
+        title: HunyuanImage2.1
+      - local: api/pipelines/pix2pix
+        title: InstructPix2Pix
+      - local: api/pipelines/kandinsky
+        title: Kandinsky 2.1
+      - local: api/pipelines/kandinsky_v22
+        title: Kandinsky 2.2
+      - local: api/pipelines/kandinsky3
+        title: Kandinsky 3
+      - local: api/pipelines/kolors
+        title: Kolors
+      - local: api/pipelines/latent_consistency_models
+        title: Latent Consistency Models
+      - local: api/pipelines/latent_diffusion
+        title: Latent Diffusion
+      - local: api/pipelines/ledits_pp
+        title: LEDITS++
+      - local: api/pipelines/lumina2
+        title: Lumina 2.0
+      - local: api/pipelines/lumina
+        title: Lumina-T2X
+      - local: api/pipelines/marigold
+        title: Marigold
+      - local: api/pipelines/panorama
+        title: MultiDiffusion
+      - local: api/pipelines/omnigen
+        title: OmniGen
+      - local: api/pipelines/pag
+        title: PAG
+      - local: api/pipelines/paint_by_example
+        title: Paint by Example
+      - local: api/pipelines/pixart
+        title: PixArt-α
+      - local: api/pipelines/pixart_sigma
+        title: PixArt-Σ
+      - local: api/pipelines/prx
+        title: PRX
+      - local: api/pipelines/qwenimage
+        title: QwenImage
+      - local: api/pipelines/sana
+        title: Sana
+      - local: api/pipelines/sana_sprint
+        title: Sana Sprint
+      - local: api/pipelines/sana_video
+        title: Sana Video
+      - local: api/pipelines/self_attention_guidance
+        title: Self-Attention Guidance
+      - local: api/pipelines/semantic_stable_diffusion
+        title: Semantic Guidance
+      - local: api/pipelines/shap_e
+        title: Shap-E
+      - local: api/pipelines/stable_cascade
+        title: Stable Cascade
+      - sections:
+        - local: api/pipelines/stable_diffusion/overview
+          title: Overview
+        - 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
+      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/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: Image-to-video
-      - 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
-    - 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:
+        title: Stable Video Diffusion
+      - local: api/pipelines/text_to_video
+        title: Text-to-video
+      - local: api/pipelines/text_to_video_zero
+        title: Text2Video-Zero
+      - local: api/pipelines/wan
+        title: Wan
+      title: Video
+    title: Pipelines
+  - sections:
     - local: api/schedulers/overview
       title: Overview
     - local: api/schedulers/cm_stochastic_iterative
@@ -718,8 +745,8 @@
       title: UniPCMultistepScheduler
     - local: api/schedulers/vq_diffusion
       title: VQDiffusionScheduler
-  - title: Internal classes
-    sections:
+    title: Schedulers
+  - sections:
     - local: api/internal_classes_overview
       title: Overview
     - local: api/attnprocessor
@@ -736,3 +763,5 @@
       title: VAE Image Processor
     - local: api/video_processor
       title: Video Processor
+    title: Internal classes
+  title: API

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

@@ -15,7 +15,7 @@ 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]
-> 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.
+> Learn how to load and use an IP-Adapter checkpoint and image in the [IP-Adapter](../../using-diffusers/ip_adapter) guide,.
 
 ## IPAdapterMixin
 

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

@@ -30,11 +30,12 @@ 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).
+- [`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]
-> To learn more about how to load LoRA weights, see the [LoRA](../../using-diffusers/loading_adapters#lora) loading guide.
+> To learn more about how to load LoRA weights, see the [LoRA](../../tutorials/using_peft_for_inference) loading guide.
 
 ## LoraBaseMixin
 
@@ -56,6 +57,10 @@ 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
@@ -107,6 +112,9 @@ LoRA is a fast and lightweight training method that inserts and trains a signifi
 
 [[autodoc]] loaders.lora_pipeline.QwenImageLoraLoaderMixin
 
+## KandinskyLoraLoaderMixin
+[[autodoc]] loaders.lora_pipeline.KandinskyLoraLoaderMixin
+
 ## LoraBaseMixin
 
 [[autodoc]] loaders.lora_base.LoraBaseMixin

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

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # PEFT
 
-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.
+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.
 
 > [!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.

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

@@ -17,7 +17,7 @@ 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]
-> To learn more about how to load Textual Inversion embeddings, see the [Textual Inversion](../../using-diffusers/loading_adapters#textual-inversion) loading guide.
+> To learn more about how to load Textual Inversion embeddings, see the [Textual Inversion](../../using-diffusers/textual_inversion_inference) loading guide.
 
 ## TextualInversionLoaderMixin
 

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

@@ -17,7 +17,7 @@ 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]
-> To learn more about how to load LoRA weights, see the [LoRA](../../using-diffusers/loading_adapters#lora) loading guide.
+> To learn more about how to load LoRA weights, see the [LoRA](../../tutorials/using_peft_for_inference) loading guide.
 
 ## SD3Transformer2DLoadersMixin
 

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

@@ -17,7 +17,7 @@ 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]
-> To learn more about how to load LoRA weights, see the [LoRA](../../using-diffusers/loading_adapters#lora) loading guide.
+> To learn more about how to load LoRA weights, see the [LoRA](../../tutorials/using_peft_for_inference) guide.
 
 ## 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("runwayml/stable-diffusion-inpainting")
+pipe = StableDiffusionInpaintPipeline.from_pretrained("stable-diffusion-v1-5/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

@@ -12,15 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # AutoModel
 
-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`] automatically retrieves the correct model class from the checkpoint `config.json` file.
 
 ## AutoModel
 

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

@@ -0,0 +1,32 @@
+<!-- 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

@@ -0,0 +1,32 @@
+<!-- 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/Chroma)
+A modified flux Transformer model from [Chroma](https://huggingface.co/lodestones/Chroma1-HD)
 
 ## ChromaTransformer2DModel
 

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

@@ -0,0 +1,32 @@
+<!-- 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/flux2_transformer.md

@@ -0,0 +1,19 @@
+<!--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/hunyuanimage_transformer_2d.md

@@ -0,0 +1,30 @@
+<!-- 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/sana_video_transformer3d.md

@@ -0,0 +1,36 @@
+<!-- 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/transformer_bria_fibo.md

@@ -0,0 +1,19 @@
+<!--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

@@ -0,0 +1,30 @@
+<!-- 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/pipelines/bria_fibo.md

@@ -0,0 +1,45 @@
+<!--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.
+
+its not recommended to use freeform text prompts directly with FIBO, as it will not produce the best results.
+
+you can learn more about FIBO in  [Bria Fibo Hugging Face page](https://huggingface.co/briaai/FIBO).
+
+
+## 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
+```
+
+
+## BriaPipeline
+
+[[autodoc]] BriaPipeline
+	- all
+	- __call__
+

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

@@ -19,20 +19,21 @@ 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](https://huggingface.co/lodestones/Chroma).
+Original model checkpoints for Chroma can be found here:
+* 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]
 > Chroma can use all the same optimizations as Flux.
 
 ## 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/Chroma", torch_dtype=torch.bfloat16)
+pipe = ChromaPipeline.from_pretrained("lodestones/Chroma1-HD", torch_dtype=torch.bfloat16)
 pipe.enable_model_cpu_offload()
 
 prompt = [
@@ -63,10 +64,10 @@ Then run the following example
 import torch
 from diffusers import ChromaTransformer2DModel, ChromaPipeline
 
-model_id = "lodestones/Chroma"
+model_id = "lodestones/Chroma1-HD"
 dtype = torch.bfloat16
 
-transformer = ChromaTransformer2DModel.from_single_file("https://huggingface.co/lodestones/Chroma/blob/main/chroma-unlocked-v37.safetensors", torch_dtype=dtype)
+transformer = ChromaTransformer2DModel.from_single_file("https://huggingface.co/lodestones/Chroma1-HD/blob/main/Chroma1-HD.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

@@ -0,0 +1,156 @@
+<!-- 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/flux.md

@@ -418,7 +418,7 @@ When unloading the Control LoRA weights, call `pipe.unload_lora_weights(reset_to
 ## IP-Adapter
 
 > [!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.
 
 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.
 

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

@@ -0,0 +1,33 @@
+<!--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.
+
+## Flux2Pipeline
+
+[[autodoc]] Flux2Pipeline
+	- all
+	- __call__

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

@@ -21,7 +21,7 @@
 
 ## Available models
 
-The following models are available for the [`HiDreamImagePipeline`](text-to-image) pipeline:
+The following models are available for the [`HiDreamImagePipeline`] pipeline:
 
 | Model name | Description |
 |:---|:---|

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

@@ -0,0 +1,152 @@
+<!-- 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/kandinsky5_video.md

@@ -0,0 +1,149 @@
+<!--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.
+-->
+
+# Kandinsky 5.0 Video
+
+Kandinsky 5.0 Video is created by the Kandinsky team: Alexey Letunovskiy, Maria Kovaleva, Ivan Kirillov, Lev Novitskiy, Denis Koposov, Dmitrii Mikhailov, Anna Averchenkova, Andrey Shutkin, Julia Agafonova, Olga Kim, Anastasiia Kargapoltseva, Nikita Kiselev, Anna Dmitrienko,  Anastasia Maltseva, Kirill Chernyshev, Ilia Vasiliev, Viacheslav Vasilev, Vladimir Polovnikov, Yury Kolabushin, Alexander Belykh, Mikhail Mamaev, Anastasia Aliaskina, Tatiana Nikulina, Polina Gavrilova, Vladimir Arkhipkin, Vladimir Korviakov, Nikolai Gerasimenko, Denis Parkhomenko, Denis Dimitrov
+
+
+Kandinsky 5.0 is a family of diffusion models for Video & Image generation. Kandinsky 5.0 T2V Lite is a lightweight video generation model (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.
+
+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 [ai-forever/Kandinsky-5](https://github.com/ai-forever/Kandinsky-5).
+
+> [!TIP]
+> Check out the [AI Forever](https://huggingface.co/ai-forever) 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 Lite comes in several variants optimized for different use cases:
+
+| model_id | Description | Use Cases |
+|------------|-------------|-----------|
+| **ai-forever/Kandinsky-5.0-T2V-Lite-sft-5s-Diffusers** | 5 second Supervised Fine-Tuned model | Highest generation quality |
+| **ai-forever/Kandinsky-5.0-T2V-Lite-sft-10s-Diffusers** | 10 second Supervised Fine-Tuned model | Highest generation quality |
+| **ai-forever/Kandinsky-5.0-T2V-Lite-nocfg-5s-Diffusers** | 5 second Classifier-Free Guidance distilled | 2× faster inference |
+| **ai-forever/Kandinsky-5.0-T2V-Lite-nocfg-10s-Diffusers** | 10 second Classifier-Free Guidance distilled | 2× faster inference |
+| **ai-forever/Kandinsky-5.0-T2V-Lite-distilled16steps-5s-Diffusers** | 5 second Diffusion distilled to 16 steps | 6× faster inference, minimal quality loss |
+| **ai-forever/Kandinsky-5.0-T2V-Lite-distilled16steps-10s-Diffusers** | 10 second Diffusion distilled to 16 steps | 6× faster inference, minimal quality loss |
+| **ai-forever/Kandinsky-5.0-T2V-Lite-pretrain-5s-Diffusers** | 5 second Base pretrained model | Research and fine-tuning |
+| **ai-forever/Kandinsky-5.0-T2V-Lite-pretrain-10s-Diffusers** | 10 second Base pretrained model | Research and fine-tuning |
+
+All models are available in 5-second and 10-second video generation versions.
+
+## Kandinsky5T2VPipeline
+
+[[autodoc]] Kandinsky5T2VPipeline
+    - all
+    - __call__
+
+## Usage Examples
+
+### Basic Text-to-Video Generation
+
+```python
+import torch
+from diffusers import Kandinsky5T2VPipeline
+from diffusers.utils import export_to_video
+
+# Load the pipeline
+model_id = "ai-forever/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(
+    "ai-forever/Kandinsky-5.0-T2V-Lite-sft-10s-Diffusers", 
+    torch_dtype=torch.bfloat16
+)
+pipe = pipe.to("cuda")
+
+pipe.transformer.set_attention_backend(
+    "flex"
+)                                       # <--- Sett 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 = "ai-forever/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)
+```
+
+
+## Citation
+```bibtex
+@misc{kandinsky2025,
+    author = {Alexey Letunovskiy and Maria Kovaleva and Ivan Kirillov and Lev Novitskiy and Denis Koposov and
+              Dmitrii Mikhailov and Anna Averchenkova and Andrey Shutkin and Julia Agafonova and Olga Kim and
+              Anastasiia Kargapoltseva and Nikita Kiselev and Vladimir Arkhipkin and Vladimir Korviakov and
+              Nikolai Gerasimenko and Denis Parkhomenko and Anna Dmitrienko and Anastasia Maltseva and
+              Kirill Chernyshev and Ilia Vasiliev and Viacheslav Vasilev and Vladimir Polovnikov and
+              Yury Kolabushin and Alexander Belykh and Mikhail Mamaev and Anastasia Aliaskina and
+              Tatiana Nikulina and Polina Gavrilova and Denis Dimitrov},
+    title = {Kandinsky 5.0: A family of diffusion models for Video & Image generation},
+    howpublished = {\url{https://github.com/ai-forever/Kandinsky-5}},
+    year = 2025
+}
+```

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_temporal_compression_ratio)
-      width = width - (width % pipeline.vae_temporal_compression_ratio)
+      height = height - (height % pipeline.vae_spatial_compression_ratio)
+      width = width - (width % pipeline.vae_spatial_compression_ratio)
       return height, width
 
   prompt = """
@@ -325,6 +325,95 @@ 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/marigold.md

@@ -75,7 +75,7 @@ The following is a summary of the recommended checkpoints, all of which produce
 | [prs-eth/marigold-depth-v1-1](https://huggingface.co/prs-eth/marigold-depth-v1-1)                   | Depth        | Affine-invariant depth prediction assigns each pixel a value between 0 (near plane) and 1 (far plane), with both planes determined by the model during inference.                    |
 | [prs-eth/marigold-normals-v0-1](https://huggingface.co/prs-eth/marigold-normals-v0-1)               | Normals      | The surface normals predictions are unit-length 3D vectors in the screen space camera, with values in the range from -1 to 1.                                                        |
 | [prs-eth/marigold-iid-appearance-v1-1](https://huggingface.co/prs-eth/marigold-iid-appearance-v1-1) | Intrinsics   | InteriorVerse decomposition is comprised of Albedo and two BRDF material properties: Roughness and Metallicity.                                                                      | 
-| [prs-eth/marigold-iid-lighting-v1-1](https://huggingface.co/prs-eth/marigold-iid-lighting-v1-1)     | Intrinsics   | HyperSim decomposition of an image &nbsp\\(I\\)&nbsp is comprised of Albedo &nbsp\\(A\\), Diffuse shading &nbsp\\(S\\), and Non-diffuse residual &nbsp\\(R\\): &nbsp\\(I = A*S+R\\). |
+| [prs-eth/marigold-iid-lighting-v1-1](https://huggingface.co/prs-eth/marigold-iid-lighting-v1-1)     | Intrinsics   | HyperSim decomposition of an image $I$ is comprised of Albedo $A$, Diffuse shading $S$, and Non-diffuse residual $R$: $I = A*S+R$. |
 
 > [!TIP]
 > Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff 

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

@@ -32,7 +32,7 @@ The table below lists all the pipelines currently available in 🤗 Diffusers an
 | [Attend-and-Excite](attend_and_excite) | text2image |
 | [AudioLDM](audioldm) | text2audio |
 | [AudioLDM2](audioldm2) | text2audio |
-| [AuraFlow](auraflow) | text2image |
+| [AuraFlow](aura_flow) | text2image |
 | [BLIP Diffusion](blip_diffusion) | text2image |
 | [Bria 3.2](bria_3_2) | text2image |
 | [CogVideoX](cogvideox) | text2video |

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

@@ -0,0 +1,131 @@
+<!-- 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. -->
+
+# PRX
+
+
+PRX generates high-quality images from text using a simplified MMDIT architecture where text tokens don't update through transformer blocks. It employs flow matching with discrete scheduling for efficient sampling and uses Google's T5Gemma-2B-2B-UL2 model for multi-language text encoding. The ~1.3B parameter transformer delivers fast inference without sacrificing quality. You can choose between Flux VAE (8x compression, 16 latent channels) for balanced quality and speed or DC-AE (32x compression, 32 latent channels) for latent compression and faster processing.
+
+## Available models
+
+PRX offers multiple variants with different VAE configurations, each optimized for specific resolutions. Base models excel with detailed prompts, capturing complex compositions and subtle details. Fine-tuned models trained on the [Alchemist dataset](https://huggingface.co/datasets/yandex/alchemist) improve aesthetic quality, especially with simpler prompts.
+
+
+| Model | Resolution | Fine-tuned | Distilled | Description | Suggested prompts | Suggested parameters | Recommended dtype |
+|:-----:|:-----------------:|:----------:|:----------:|:----------:|:----------:|:----------:|:----------:|
+| [`Photoroom/prx-256-t2i`](https://huggingface.co/Photoroom/prx-256-t2i)| 256 | No | No | Base model pre-trained at 256 with Flux VAE|Works best with detailed prompts in natural language|28 steps, cfg=5.0| `torch.bfloat16` |
+| [`Photoroom/prx-256-t2i-sft`](https://huggingface.co/Photoroom/prx-256-t2i-sft)| 512 | Yes | No | Fine-tuned on the [Alchemist dataset](https://huggingface.co/datasets/yandex/alchemist) dataset with Flux VAE | Can handle less detailed prompts|28 steps, cfg=5.0| `torch.bfloat16` |
+| [`Photoroom/prx-512-t2i`](https://huggingface.co/Photoroom/prx-512-t2i)| 512 | No | No | Base model pre-trained at 512 with Flux VAE |Works best with detailed prompts in natural language|28 steps, cfg=5.0| `torch.bfloat16` |
+| [`Photoroom/prx-512-t2i-sft`](https://huggingface.co/Photoroom/prx-512-t2i-sft)| 512 | Yes | No | Fine-tuned on the [Alchemist dataset](https://huggingface.co/datasets/yandex/alchemist) dataset with Flux VAE | Can handle less detailed prompts in natural language|28 steps, cfg=5.0| `torch.bfloat16` |
+| [`Photoroom/prx-512-t2i-sft-distilled`](https://huggingface.co/Photoroom/prx-512-t2i-sft-distilled)| 512 | Yes | Yes | 8-step distilled model from [`Photoroom/prx-512-t2i-sft`](https://huggingface.co/Photoroom/prx-512-t2i-sft) | Can handle less detailed prompts in natural language|8 steps, cfg=1.0| `torch.bfloat16` |
+| [`Photoroom/prx-512-t2i-dc-ae`](https://huggingface.co/Photoroom/prx-512-t2i-dc-ae)| 512 | No | No | Base model pre-trained at 512 with [Deep Compression Autoencoder (DC-AE)](https://hanlab.mit.edu/projects/dc-ae)|Works best with detailed prompts in natural language|28 steps, cfg=5.0| `torch.bfloat16` |
+| [`Photoroom/prx-512-t2i-dc-ae-sft`](https://huggingface.co/Photoroom/prx-512-t2i-dc-ae-sft)| 512 | Yes | No | Fine-tuned on the [Alchemist dataset](https://huggingface.co/datasets/yandex/alchemist) dataset with [Deep Compression Autoencoder (DC-AE)](https://hanlab.mit.edu/projects/dc-ae) | Can handle less detailed prompts in natural language|28 steps, cfg=5.0| `torch.bfloat16` |
+| [`Photoroom/prx-512-t2i-dc-ae-sft-distilled`](https://huggingface.co/Photoroom/prx-512-t2i-dc-ae-sft-distilled)| 512 | Yes | Yes | 8-step distilled model from [`Photoroom/prx-512-t2i-dc-ae-sft-distilled`](https://huggingface.co/Photoroom/prx-512-t2i-dc-ae-sft-distilled) | Can handle less detailed prompts in natural language|8 steps, cfg=1.0| `torch.bfloat16` |s
+
+Refer to [this](https://huggingface.co/collections/Photoroom/prx-models-68e66254c202ebfab99ad38e) collection for more information.
+
+## Loading the pipeline
+
+Load the pipeline with [`~DiffusionPipeline.from_pretrained`].
+
+```py
+from diffusers.pipelines.prx import PRXPipeline
+
+# Load pipeline - VAE and text encoder will be loaded from HuggingFace
+pipe = PRXPipeline.from_pretrained("Photoroom/prx-512-t2i-sft", torch_dtype=torch.bfloat16)
+pipe.to("cuda")
+
+prompt = "A front-facing portrait of a lion the golden savanna at sunset."
+image = pipe(prompt, num_inference_steps=28, guidance_scale=5.0).images[0]
+image.save("prx_output.png")
+```
+
+### Manual Component Loading
+
+Load components individually to customize the pipeline for instance to use quantized models.
+
+```py
+import torch
+from diffusers.pipelines.prx import PRXPipeline
+from diffusers.models import AutoencoderKL, AutoencoderDC
+from diffusers.models.transformers.transformer_prx import PRXTransformer2DModel
+from diffusers.schedulers import FlowMatchEulerDiscreteScheduler
+from transformers import T5GemmaModel, GemmaTokenizerFast
+from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig
+from transformers import BitsAndBytesConfig as BitsAndBytesConfig
+
+quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
+# Load transformer
+transformer = PRXTransformer2DModel.from_pretrained(
+    "checkpoints/prx-512-t2i-sft",
+    subfolder="transformer",
+    quantization_config=quant_config,
+    torch_dtype=torch.bfloat16,
+)
+
+# Load scheduler
+scheduler = FlowMatchEulerDiscreteScheduler.from_pretrained(
+    "checkpoints/prx-512-t2i-sft", subfolder="scheduler"
+)
+
+# Load T5Gemma text encoder
+t5gemma_model = T5GemmaModel.from_pretrained("google/t5gemma-2b-2b-ul2",
+                                            quantization_config=quant_config,
+                                            torch_dtype=torch.bfloat16)
+text_encoder = t5gemma_model.encoder.to(dtype=torch.bfloat16)
+tokenizer = GemmaTokenizerFast.from_pretrained("google/t5gemma-2b-2b-ul2")
+tokenizer.model_max_length = 256
+
+# Load VAE - choose either Flux VAE or DC-AE
+# Flux VAE
+vae = AutoencoderKL.from_pretrained("black-forest-labs/FLUX.1-dev",
+                                    subfolder="vae",
+                                    quantization_config=quant_config,
+                                    torch_dtype=torch.bfloat16)
+
+pipe = PRXPipeline(
+    transformer=transformer,
+    scheduler=scheduler,
+    text_encoder=text_encoder,
+    tokenizer=tokenizer,
+    vae=vae
+)
+pipe.to("cuda")
+```
+
+
+## Memory Optimization
+
+For memory-constrained environments:
+
+```py
+import torch
+from diffusers.pipelines.prx import PRXPipeline
+
+pipe = PRXPipeline.from_pretrained("Photoroom/prx-512-t2i-sft", torch_dtype=torch.bfloat16)
+pipe.enable_model_cpu_offload()  # Offload components to CPU when not in use
+
+# Or use sequential CPU offload for even lower memory
+pipe.enable_sequential_cpu_offload()
+```
+
+## PRXPipeline
+
+[[autodoc]] PRXPipeline
+  - all
+  - __call__
+
+## PRXPipelineOutput
+
+[[autodoc]] pipelines.prx.pipeline_output.PRXPipelineOutput

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

@@ -109,7 +109,7 @@ image_1 = load_image("https://huggingface.co/datasets/huggingface/documentation-
 image_2 = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/peng.png")
 image = pipe(
     image=[image_1, image_2], 
-    prompt="put the penguin and the cat at a game show called "Qwen Edit Plus Games"", 
+    prompt='''put the penguin and the cat at a game show called "Qwen Edit Plus Games"''', 
     num_inference_steps=50
 ).images[0]
 ```

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

@@ -24,9 +24,6 @@ The abstract from the paper is:
 
 *This paper presents SANA-Sprint, an efficient diffusion model for ultra-fast text-to-image (T2I) generation. SANA-Sprint is built on a pre-trained foundation model and augmented with hybrid distillation, dramatically reducing inference steps from 20 to 1-4. We introduce three key innovations: (1) We propose a training-free approach that transforms a pre-trained flow-matching model for continuous-time consistency distillation (sCM), eliminating costly training from scratch and achieving high training efficiency. Our hybrid distillation strategy combines sCM with latent adversarial distillation (LADD): sCM ensures alignment with the teacher model, while LADD enhances single-step generation fidelity. (2) SANA-Sprint is a unified step-adaptive model that achieves high-quality generation in 1-4 steps, eliminating step-specific training and improving efficiency. (3) We integrate ControlNet with SANA-Sprint for real-time interactive image generation, enabling instant visual feedback for user interaction. SANA-Sprint establishes a new Pareto frontier in speed-quality tradeoffs, achieving state-of-the-art performance with 7.59 FID and 0.74 GenEval in only 1 step — outperforming FLUX-schnell (7.94 FID / 0.71 GenEval) while being 10× faster (0.1s vs 1.1s on H100). It also achieves 0.1s (T2I) and 0.25s (ControlNet) latency for 1024×1024 images on H100, and 0.31s (T2I) on an RTX 4090, showcasing its exceptional efficiency and potential for AI-powered consumer applications (AIPC). Code and pre-trained models will be open-sourced.*
 
-> [!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.
-
 This pipeline was contributed by [lawrence-cj](https://github.com/lawrence-cj), [shuchen Xue](https://github.com/scxue) and [Enze Xie](https://github.com/xieenze). The original codebase can be found [here](https://github.com/NVlabs/Sana). The original weights can be found under [hf.co/Efficient-Large-Model](https://huggingface.co/Efficient-Large-Model/).
 
 Available models:

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

@@ -0,0 +1,189 @@
+<!-- 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. -->
+
+# Sana-Video
+
+<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>
+
+[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. [this https URL](https://github.com/NVlabs/SANA).*
+
+This pipeline was contributed by SANA Team. The original codebase can be found [here](https://github.com/NVlabs/Sana). The original weights can be found under [hf.co/Efficient-Large-Model](https://hf.co/collections/Efficient-Large-Model/sana-video).
+
+Available models:
+
+| Model | Recommended dtype |
+|:-----:|:-----------------:|
+| [`Efficient-Large-Model/SANA-Video_2B_480p_diffusers`](https://huggingface.co/Efficient-Large-Model/ANA-Video_2B_480p_diffusers) | `torch.bfloat16` |
+
+Refer to [this](https://huggingface.co/collections/Efficient-Large-Model/sana-video) collection for more information.
+
+Note: The recommended dtype mentioned is for the transformer weights. The text encoder and VAE weights must stay in `torch.bfloat16` or `torch.float32` for the model to work correctly. Please refer to the inference example below to see how to load the model with the recommended dtype. 
+
+
+## Generation Pipelines
+
+<hfoptions id="generation pipelines">`
+<hfoption id="Text-to-Video">
+
+The example below demonstrates how to use the text-to-video pipeline to generate a video using a text description.
+
+```python
+pipe = SanaVideoPipeline.from_pretrained(
+    "Efficient-Large-Model/SANA-Video_2B_480p_diffusers", 
+    torch_dtype=torch.bfloat16,
+)
+pipe.text_encoder.to(torch.bfloat16)
+pipe.vae.to(torch.float32)
+pipe.to("cuda")
+
+prompt = "A cat and a dog baking a cake together in a kitchen. The cat is carefully measuring flour, while the dog is stirring the batter with a wooden spoon. The kitchen is cozy, with sunlight streaming through the window."
+negative_prompt = "A chaotic sequence with misshapen, deformed limbs in heavy motion blur, sudden disappearance, jump cuts, jerky movements, rapid shot changes, frames out of sync, inconsistent character shapes, temporal artifacts, jitter, and ghosting effects, creating a disorienting visual experience."
+motion_scale = 30
+motion_prompt = f" motion score: {motion_scale}."
+prompt = prompt + motion_prompt
+
+video = pipe(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    height=480,
+    width=832,
+    frames=81,
+    guidance_scale=6,
+    num_inference_steps=50,
+    generator=torch.Generator(device="cuda").manual_seed(0),
+).frames[0]
+
+export_to_video(video, "sana_video.mp4", fps=16)
+```
+
+</hfoption>
+<hfoption id="Image-to-Video">
+
+The example below demonstrates how to use the image-to-video pipeline to generate a video using a text description and a starting frame.
+
+```python
+pipe = SanaImageToVideoPipeline.from_pretrained(
+    "Efficient-Large-Model/SANA-Video_2B_480p_diffusers",
+    torch_dtype=torch.bfloat16,
+)
+pipe.scheduler = FlowMatchEulerDiscreteScheduler.from_config(pipe.scheduler.config, flow_shift=8.0)
+pipe.vae.to(torch.float32)
+pipe.text_encoder.to(torch.bfloat16)
+pipe.to("cuda")
+
+image = load_image("https://raw.githubusercontent.com/NVlabs/Sana/refs/heads/main/asset/samples/i2v-1.png")
+prompt = "A woman stands against a stunning sunset backdrop, her long, wavy brown hair gently blowing in the breeze. She wears a sleeveless, light-colored blouse with a deep V-neckline, which accentuates her graceful posture. The warm hues of the setting sun cast a golden glow across her face and hair, creating a serene and ethereal atmosphere. The background features a blurred landscape with soft, rolling hills and scattered clouds, adding depth to the scene. The camera remains steady, capturing the tranquil moment from a medium close-up angle."
+negative_prompt = "A chaotic sequence with misshapen, deformed limbs in heavy motion blur, sudden disappearance, jump cuts, jerky movements, rapid shot changes, frames out of sync, inconsistent character shapes, temporal artifacts, jitter, and ghosting effects, creating a disorienting visual experience."
+motion_scale = 30
+motion_prompt = f" motion score: {motion_scale}."
+prompt = prompt + motion_prompt
+
+motion_scale = 30.0
+
+video = pipe(
+    image=image,
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    height=480,
+    width=832,
+    frames=81,
+    guidance_scale=6,
+    num_inference_steps=50,
+    generator=torch.Generator(device="cuda").manual_seed(0),
+).frames[0]
+
+export_to_video(video, "sana-i2v.mp4", fps=16)
+```
+
+</hfoption>
+</hfoptions>
+
+
+## Quantization
+
+Quantization helps reduce the memory requirements of very large models by storing model weights in a lower precision data type. However, quantization may have varying impact on video quality depending on the video model.
+
+Refer to the [Quantization](../../quantization/overview) overview to learn more about supported quantization backends and selecting a quantization backend that supports your use case. The example below demonstrates how to load a quantized [`SanaVideoPipeline`] for inference with bitsandbytes.
+
+```py
+import torch
+from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, SanaVideoTransformer3DModel, SanaVideoPipeline
+from transformers import BitsAndBytesConfig as BitsAndBytesConfig, AutoModel
+
+quant_config = BitsAndBytesConfig(load_in_8bit=True)
+text_encoder_8bit = AutoModel.from_pretrained(
+    "Efficient-Large-Model/SANA-Video_2B_480p_diffusers",
+    subfolder="text_encoder",
+    quantization_config=quant_config,
+    torch_dtype=torch.float16,
+)
+
+quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
+transformer_8bit = SanaVideoTransformer3DModel.from_pretrained(
+    "Efficient-Large-Model/SANA-Video_2B_480p_diffusers",
+    subfolder="transformer",
+    quantization_config=quant_config,
+    torch_dtype=torch.float16,
+)
+
+pipeline = SanaVideoPipeline.from_pretrained(
+    "Efficient-Large-Model/SANA-Video_2B_480p_diffusers",
+    text_encoder=text_encoder_8bit,
+    transformer=transformer_8bit,
+    torch_dtype=torch.float16,
+    device_map="balanced",
+)
+
+model_score = 30
+prompt = "Evening, backlight, side lighting, soft light, high contrast, mid-shot, centered composition, clean solo shot, warm color. A young Caucasian man stands in a forest, golden light glimmers on his hair as sunlight filters through the leaves. He wears a light shirt, wind gently blowing his hair and collar, light dances across his face with his movements. The background is blurred, with dappled light and soft tree shadows in the distance. The camera focuses on his lifted gaze, clear and emotional."
+negative_prompt = "A chaotic sequence with misshapen, deformed limbs in heavy motion blur, sudden disappearance, jump cuts, jerky movements, rapid shot changes, frames out of sync, inconsistent character shapes, temporal artifacts, jitter, and ghosting effects, creating a disorienting visual experience."
+motion_prompt = f" motion score: {model_score}."
+prompt = prompt + motion_prompt
+
+output = pipeline(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    height=480,
+    width=832,
+    num_frames=81,
+    guidance_scale=6.0,
+    num_inference_steps=50
+).frames[0]
+export_to_video(output, "sana-video-output.mp4", fps=16)
+```
+
+## SanaVideoPipeline
+
+[[autodoc]] SanaVideoPipeline
+  - all
+  - __call__
+
+
+## SanaImageToVideoPipeline
+
+[[autodoc]] SanaImageToVideoPipeline
+  - all
+  - __call__
+
+
+## SanaVideoPipelineOutput
+
+[[autodoc]] pipelines.sana_video.pipeline_sana_video.SanaVideoPipelineOutput

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

@@ -21,7 +21,7 @@ The Stable Diffusion model can also infer depth based on an image using [MiDaS](
 > [!TIP]
 > Make sure to check out the Stable Diffusion [Tips](overview#tips) section to learn how to explore the tradeoff between scheduler speed and quality, and how to reuse pipeline components efficiently!
 >
-> If you're interested in using one of the official checkpoints for a task, explore the [CompVis](https://huggingface.co/CompVis), [Runway](https://huggingface.co/runwayml), and [Stability AI](https://huggingface.co/stabilityai) Hub organizations!
+> If you're interested in using one of the official checkpoints for a task, explore the [CompVis](https://huggingface.co/CompVis) and [Stability AI](https://huggingface.co/stabilityai) Hub organizations!
 
 ## StableDiffusionDepth2ImgPipeline
 

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

@@ -21,14 +21,14 @@ The Stable Diffusion model can also be applied to inpainting which lets you edit
 ## Tips
 
 It is recommended to use this pipeline with checkpoints that have been specifically fine-tuned for inpainting, such
-as [runwayml/stable-diffusion-inpainting](https://huggingface.co/runwayml/stable-diffusion-inpainting). Default
+as [stable-diffusion-v1-5/stable-diffusion-inpainting](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-inpainting). Default
 text-to-image Stable Diffusion checkpoints, such as
 [stable-diffusion-v1-5/stable-diffusion-v1-5](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) are also compatible but they might be less performant.
 
 > [!TIP]
 > Make sure to check out the Stable Diffusion [Tips](overview#tips) section to learn how to explore the tradeoff between scheduler speed and quality, and how to reuse pipeline components efficiently!
 >
-> If you're interested in using one of the official checkpoints for a task, explore the [CompVis](https://huggingface.co/CompVis), [Runway](https://huggingface.co/runwayml), and [Stability AI](https://huggingface.co/stabilityai) Hub organizations!
+> If you're interested in using one of the official checkpoints for a task, explore the [CompVis](https://huggingface.co/CompVis) and [Stability AI](https://huggingface.co/stabilityai) Hub organizations!
 
 ## StableDiffusionInpaintPipeline
 

docs/source/en/api/pipelines/stable_diffusion/latent_upscale.md

@@ -17,7 +17,7 @@ The Stable Diffusion latent upscaler model was created by [Katherine Crowson](ht
 > [!TIP]
 > Make sure to check out the Stable Diffusion [Tips](overview#tips) section to learn how to explore the tradeoff between scheduler speed and quality, and how to reuse pipeline components efficiently!
 >
-> If you're interested in using one of the official checkpoints for a task, explore the [CompVis](https://huggingface.co/CompVis), [Runway](https://huggingface.co/runwayml), and [Stability AI](https://huggingface.co/stabilityai) Hub organizations!
+> If you're interested in using one of the official checkpoints for a task, explore the [CompVis](https://huggingface.co/CompVis) and [Stability AI](https://huggingface.co/stabilityai) Hub organizations!
 
 ## StableDiffusionLatentUpscalePipeline
 

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

@@ -22,7 +22,7 @@ Stable Diffusion is trained on 512x512 images from a subset of the LAION-5B data
 
 For more details about how Stable Diffusion works and how it differs from the base latent diffusion model, take a look at the Stability AI [announcement](https://stability.ai/blog/stable-diffusion-announcement) and our own [blog post](https://huggingface.co/blog/stable_diffusion#how-does-stable-diffusion-work) for more technical details.
 
-You can find the original codebase for Stable Diffusion v1.0 at [CompVis/stable-diffusion](https://github.com/CompVis/stable-diffusion) and Stable Diffusion v2.0 at [Stability-AI/stablediffusion](https://github.com/Stability-AI/stablediffusion) as well as their original scripts for various tasks. Additional official checkpoints for the different Stable Diffusion versions and tasks can be found on the [CompVis](https://huggingface.co/CompVis), [Runway](https://huggingface.co/runwayml), and [Stability AI](https://huggingface.co/stabilityai) Hub organizations. Explore these organizations to find the best checkpoint for your use-case!
+You can find the original codebase for Stable Diffusion v1.0 at [CompVis/stable-diffusion](https://github.com/CompVis/stable-diffusion) and Stable Diffusion v2.0 at [Stability-AI/stablediffusion](https://github.com/Stability-AI/stablediffusion) as well as their original scripts for various tasks. Additional official checkpoints for the different Stable Diffusion versions and tasks can be found on the [CompVis](https://huggingface.co/CompVis) and [Stability AI](https://huggingface.co/stabilityai) Hub organizations. Explore these organizations to find the best checkpoint for your use-case!
 
 The table below summarizes the available Stable Diffusion pipelines, their supported tasks, and an interactive demo:
 
@@ -64,7 +64,7 @@ The table below summarizes the available Stable Diffusion pipelines, their suppo
             <a href="./inpaint">StableDiffusionInpaint</a>
             </td>
             <td class="px-4 py-2 text-gray-700">inpainting</td>
-            <td class="px-4 py-2"><a href="https://huggingface.co/spaces/runwayml/stable-diffusion-inpainting"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue"/></a>
+            <td class="px-4 py-2"><a href="https://huggingface.co/spaces/stable-diffusion-v1-5/stable-diffusion-inpainting"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue"/></a>
             </td>
         </tr>
         <tr>

docs/source/en/api/pipelines/stable_diffusion/stable_diffusion_2.md

@@ -36,7 +36,7 @@ Here are some examples for how to use Stable Diffusion 2 for each task:
 > [!TIP]
 > Make sure to check out the Stable Diffusion [Tips](overview#tips) section to learn how to explore the tradeoff between scheduler speed and quality, and how to reuse pipeline components efficiently!
 >
-> If you're interested in using one of the official checkpoints for a task, explore the [CompVis](https://huggingface.co/CompVis), [Runway](https://huggingface.co/runwayml), and [Stability AI](https://huggingface.co/stabilityai) Hub organizations!
+> If you're interested in using one of the official checkpoints for a task, explore the [CompVis](https://huggingface.co/CompVis) and [Stability AI](https://huggingface.co/stabilityai) Hub organizations!
 
 ## Text-to-image
 

docs/source/en/api/pipelines/stable_diffusion/stable_diffusion_3.md

@@ -271,7 +271,7 @@ Check out the full script [here](https://gist.github.com/sayakpaul/508d89d7aad4f
 
 Quantization helps reduce the memory requirements of very large models by storing model weights in a lower precision data type. However, quantization may have varying impact on video quality depending on the video model.
 
-Refer to the [Quantization](../../quantization/overview) overview to learn more about supported quantization backends and selecting a quantization backend that supports your use case. The example below demonstrates how to load a quantized [`StableDiffusion3Pipeline`] for inference with bitsandbytes.
+Refer to the [Quantization](../../../quantization/overview) overview to learn more about supported quantization backends and selecting a quantization backend that supports your use case. The example below demonstrates how to load a quantized [`StableDiffusion3Pipeline`] for inference with bitsandbytes.
 
 ```py
 import torch

docs/source/en/api/pipelines/stable_diffusion/svd.md

@@ -29,7 +29,7 @@ The abstract from the paper is:
 
 Video generation is memory-intensive and one way to reduce your memory usage is to set `enable_forward_chunking` on the pipeline's UNet so you don't run the entire feedforward layer at once. Breaking it up into chunks in a loop is more efficient.
 
-Check out the [Text or image-to-video](text-img2vid) guide for more details about how certain parameters can affect video generation and how to optimize inference by reducing memory usage.
+Check out the [Text or image-to-video](../../../using-diffusers/text-img2vid) guide for more details about how certain parameters can affect video generation and how to optimize inference by reducing memory usage.
 
 ## StableVideoDiffusionPipeline
 

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

@@ -25,7 +25,7 @@ The abstract from the paper is:
 > [!TIP]
 > Make sure to check out the Stable Diffusion [Tips](overview#tips) section to learn how to explore the tradeoff between scheduler speed and quality, and how to reuse pipeline components efficiently!
 >
-> If you're interested in using one of the official checkpoints for a task, explore the [CompVis](https://huggingface.co/CompVis), [Runway](https://huggingface.co/runwayml), and [Stability AI](https://huggingface.co/stabilityai) Hub organizations!
+> If you're interested in using one of the official checkpoints for a task, explore the [CompVis](https://huggingface.co/CompVis) and [Stability AI](https://huggingface.co/stabilityai) Hub organizations!
 
 ## StableDiffusionPipeline
 

docs/source/en/api/pipelines/stable_diffusion/upscale.md

@@ -21,7 +21,7 @@ The Stable Diffusion upscaler diffusion model was created by the researchers and
 > [!TIP]
 > Make sure to check out the Stable Diffusion [Tips](overview#tips) section to learn how to explore the tradeoff between scheduler speed and quality, and how to reuse pipeline components efficiently!
 >
-> If you're interested in using one of the official checkpoints for a task, explore the [CompVis](https://huggingface.co/CompVis), [Runway](https://huggingface.co/runwayml), and [Stability AI](https://huggingface.co/stabilityai) Hub organizations!
+> If you're interested in using one of the official checkpoints for a task, explore the [CompVis](https://huggingface.co/CompVis) and [Stability AI](https://huggingface.co/stabilityai) Hub organizations!
 
 ## StableDiffusionUpscalePipeline
 

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

@@ -172,7 +172,7 @@ Here are some sample outputs:
 
 Video generation is memory-intensive and one way to reduce your memory usage is to set `enable_forward_chunking` on the pipeline's UNet so you don't run the entire feedforward layer at once. Breaking it up into chunks in a loop is more efficient.
 
-Check out the [Text or image-to-video](text-img2vid) guide for more details about how certain parameters can affect video generation and how to optimize inference by reducing memory usage.
+Check out the [Text or image-to-video](../../using-diffusers/text-img2vid) guide for more details about how certain parameters can affect video generation and how to optimize inference by reducing memory usage.
 
 > [!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.

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

@@ -40,6 +40,7 @@ The following Wan models are supported in Diffusers:
 - [Wan 2.2 T2V 14B](https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B-Diffusers)
 - [Wan 2.2 I2V 14B](https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B-Diffusers)
 - [Wan 2.2 TI2V 5B](https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B-Diffusers)
+- [Wan 2.2 Animate 14B](https://huggingface.co/Wan-AI/Wan2.2-Animate-14B-Diffusers)
 
 > [!TIP]
 > Click on the Wan models in the right sidebar for more examples of video generation.
@@ -95,15 +96,15 @@ pipeline = WanPipeline.from_pretrained(
 pipeline.to("cuda")
 
 prompt = """
-The camera rushes from far to near in a low-angle shot, 
-revealing a white ferret on a log. It plays, leaps into the water, and emerges, as the camera zooms in 
-for a close-up. Water splashes berry bushes nearby, while moss, snow, and leaves blanket the ground. 
-Birch trees and a light blue sky frame the scene, with ferns in the foreground. Side lighting casts dynamic 
+The camera rushes from far to near in a low-angle shot,
+revealing a white ferret on a log. It plays, leaps into the water, and emerges, as the camera zooms in
+for a close-up. Water splashes berry bushes nearby, while moss, snow, and leaves blanket the ground.
+Birch trees and a light blue sky frame the scene, with ferns in the foreground. Side lighting casts dynamic
 shadows and warm highlights. Medium composition, front view, low angle, with depth of field.
 """
 negative_prompt = """
-Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, 
-low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, 
+Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality,
+low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured,
 misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards
 """
 
@@ -150,15 +151,15 @@ pipeline.transformer = torch.compile(
 )
 
 prompt = """
-The camera rushes from far to near in a low-angle shot, 
-revealing a white ferret on a log. It plays, leaps into the water, and emerges, as the camera zooms in 
-for a close-up. Water splashes berry bushes nearby, while moss, snow, and leaves blanket the ground. 
-Birch trees and a light blue sky frame the scene, with ferns in the foreground. Side lighting casts dynamic 
+The camera rushes from far to near in a low-angle shot,
+revealing a white ferret on a log. It plays, leaps into the water, and emerges, as the camera zooms in
+for a close-up. Water splashes berry bushes nearby, while moss, snow, and leaves blanket the ground.
+Birch trees and a light blue sky frame the scene, with ferns in the foreground. Side lighting casts dynamic
 shadows and warm highlights. Medium composition, front view, low angle, with depth of field.
 """
 negative_prompt = """
-Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, 
-low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, 
+Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality,
+low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured,
 misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards
 """
 
@@ -249,6 +250,208 @@ The code snippets available in [this](https://github.com/huggingface/diffusers/p
 
 The general rule of thumb to keep in mind when preparing inputs for the VACE pipeline is that the input images, or frames of a video that you want to use for conditioning, should have a corresponding mask that is black in color. The black mask signifies that the model will not generate new content for that area, and only use those parts for conditioning the generation process. For parts/frames that should be generated by the model, the mask should be white in color.
 
+</hfoption>
+</hfoptions>
+
+### Wan-Animate: Unified Character Animation and Replacement with Holistic Replication
+
+[Wan-Animate](https://huggingface.co/papers/2509.14055) by the Wan Team.
+
+*We introduce Wan-Animate, a unified framework for character animation and replacement. Given a character image and a reference video, Wan-Animate can animate the character by precisely replicating the expressions and movements of the character in the video to generate high-fidelity character videos. Alternatively, it can integrate the animated character into the reference video to replace the original character, replicating the scene's lighting and color tone to achieve seamless environmental integration. Wan-Animate is built upon the Wan model. To adapt it for character animation tasks, we employ a modified input paradigm to differentiate between reference conditions and regions for generation. This design unifies multiple tasks into a common symbolic representation. We use spatially-aligned skeleton signals to replicate body motion and implicit facial features extracted from source images to reenact expressions, enabling the generation of character videos with high controllability and expressiveness. Furthermore, to enhance environmental integration during character replacement, we develop an auxiliary Relighting LoRA. This module preserves the character's appearance consistency while applying the appropriate environmental lighting and color tone. Experimental results demonstrate that Wan-Animate achieves state-of-the-art performance. We are committed to open-sourcing the model weights and its source code.*
+
+The project page: https://humanaigc.github.io/wan-animate
+
+This model was mostly contributed by [M. Tolga Cangöz](https://github.com/tolgacangoz).
+
+#### Usage
+
+The Wan-Animate pipeline supports two modes of operation:
+
+1. **Animation Mode** (default): Animates a character image based on motion and expression from reference videos
+2. **Replacement Mode**: Replaces a character in a background video with a new character while preserving the scene
+
+##### Prerequisites
+
+Before using the pipeline, you need to preprocess your reference video to extract:
+- **Pose video**: Contains skeletal keypoints representing body motion
+- **Face video**: Contains facial feature representations for expression control
+
+For replacement mode, you additionally need:
+- **Background video**: The original video containing the scene
+- **Mask video**: A mask indicating where to generate content (white) vs. preserve original (black)
+
+> [!NOTE]
+> Raw videos should not be used for inputs such as `pose_video`, which the pipeline expects to be preprocessed to extract the proper information. Preprocessing scripts to prepare these inputs are available in the [original Wan-Animate repository](https://github.com/Wan-Video/Wan2.2?tab=readme-ov-file#1-preprocessing). Integration of these preprocessing steps into Diffusers is planned for a future release.
+
+The example below demonstrates how to use the Wan-Animate pipeline:
+
+<hfoptions id="Animate usage">
+<hfoption id="Animation mode">
+
+```python
+import numpy as np
+import torch
+from diffusers import AutoencoderKLWan, WanAnimatePipeline
+from diffusers.utils import export_to_video, load_image, load_video
+
+model_id = "Wan-AI/Wan2.2-Animate-14B-Diffusers"
+vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
+pipe = WanAnimatePipeline.from_pretrained(model_id, vae=vae, torch_dtype=torch.bfloat16)
+pipe.to("cuda")
+
+# Load character image and preprocessed videos
+image = load_image("path/to/character.jpg")
+pose_video = load_video("path/to/pose_video.mp4")  # Preprocessed skeletal keypoints
+face_video = load_video("path/to/face_video.mp4")  # Preprocessed facial features
+
+# Resize image to match VAE constraints
+def aspect_ratio_resize(image, pipe, 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
+    image = image.resize((width, height))
+    return image, height, width
+
+image, height, width = aspect_ratio_resize(image, pipe)
+
+prompt = "A person dancing energetically in a studio with dynamic lighting and professional camera work"
+negative_prompt = "blurry, low quality, distorted, deformed, static, poorly drawn"
+
+# Generate animated video
+output = pipe(
+    image=image,
+    pose_video=pose_video,
+    face_video=face_video,
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    height=height,
+    width=width,
+    segment_frame_length=77,
+    guidance_scale=1.0,
+    mode="animate",  # Animation mode (default)
+).frames[0]
+export_to_video(output, "animated_character.mp4", fps=30)
+```
+
+</hfoption>
+<hfoption id="Replacement mode">
+
+```python
+import numpy as np
+import torch
+from diffusers import AutoencoderKLWan, WanAnimatePipeline
+from diffusers.utils import export_to_video, load_image, load_video
+
+model_id = "Wan-AI/Wan2.2-Animate-14B-Diffusers"
+vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
+pipe = WanAnimatePipeline.from_pretrained(model_id, vae=vae, torch_dtype=torch.bfloat16)
+pipe.to("cuda")
+
+# Load all required inputs for replacement mode
+image = load_image("path/to/new_character.jpg")
+pose_video = load_video("path/to/pose_video.mp4")  # Preprocessed skeletal keypoints
+face_video = load_video("path/to/face_video.mp4")  # Preprocessed facial features
+background_video = load_video("path/to/background_video.mp4")  # Original scene
+mask_video = load_video("path/to/mask_video.mp4")  # Black: preserve, White: generate
+
+# Resize image to match video dimensions
+def aspect_ratio_resize(image, pipe, 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
+    image = image.resize((width, height))
+    return image, height, width
+
+image, height, width = aspect_ratio_resize(image, pipe)
+
+prompt = "A person seamlessly integrated into the scene with consistent lighting and environment"
+negative_prompt = "blurry, low quality, inconsistent lighting, floating, disconnected from scene"
+
+# Replace character in background video
+output = pipe(
+    image=image,
+    pose_video=pose_video,
+    face_video=face_video,
+    background_video=background_video,
+    mask_video=mask_video,
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    height=height,
+    width=width,
+    segment_frame_lengths=77,
+    guidance_scale=1.0,
+    mode="replace",  # Replacement mode
+).frames[0]
+export_to_video(output, "character_replaced.mp4", fps=30)
+```
+
+</hfoption>
+<hfoption id="Advanced options">
+
+```python
+import numpy as np
+import torch
+from diffusers import AutoencoderKLWan, WanAnimatePipeline
+from diffusers.utils import export_to_video, load_image, load_video
+
+model_id = "Wan-AI/Wan2.2-Animate-14B-Diffusers"
+vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
+pipe = WanAnimatePipeline.from_pretrained(model_id, vae=vae, torch_dtype=torch.bfloat16)
+pipe.to("cuda")
+
+image = load_image("path/to/character.jpg")
+pose_video = load_video("path/to/pose_video.mp4")
+face_video = load_video("path/to/face_video.mp4")
+
+def aspect_ratio_resize(image, pipe, 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
+    image = image.resize((width, height))
+    return image, height, width
+
+image, height, width = aspect_ratio_resize(image, pipe)
+
+prompt = "A person dancing energetically in a studio"
+negative_prompt = "blurry, low quality"
+
+# Advanced: Use temporal guidance and custom callback
+def callback_fn(pipe, step_index, timestep, callback_kwargs):
+    # You can modify latents or other tensors here
+    print(f"Step {step_index}, Timestep {timestep}")
+    return callback_kwargs
+
+output = pipe(
+    image=image,
+    pose_video=pose_video,
+    face_video=face_video,
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    height=height,
+    width=width,
+    segment_frame_length=77,
+    num_inference_steps=50,
+    guidance_scale=5.0,
+    prev_segment_conditioning_frames=5,  # Use 5 frames for temporal guidance (1 or 5 recommended)
+    callback_on_step_end=callback_fn,
+    callback_on_step_end_tensor_inputs=["latents"],
+).frames[0]
+export_to_video(output, "animated_advanced.mp4", fps=30)
+```
+
+</hfoption>
+</hfoptions>
+
+#### Key Parameters
+
+- **mode**: Choose between `"animate"` (default) or `"replace"`
+- **prev_segment_conditioning_frames**: Number of frames for temporal guidance (1 or 5 recommended). Using 5 provides better temporal consistency but requires more memory
+- **guidance_scale**: Controls how closely the output follows the text prompt. Higher values (5-7) produce results more aligned with the prompt. For Wan-Animate, CFG is disabled by default (`guidance_scale=1.0`) but can be enabled to support negative prompts and finer control over facial expressions. (Note that CFG will only target the text prompt and face conditioning.)
+
+
 ## Notes
 
 - Wan2.1 supports LoRAs with [`~loaders.WanLoraLoaderMixin.load_lora_weights`].
@@ -281,10 +484,10 @@ The general rule of thumb to keep in mind when preparing inputs for the VACE pip
 
   # use "steamboat willie style" to trigger the LoRA
   prompt = """
-  steamboat willie style, golden era animation, The camera rushes from far to near in a low-angle shot, 
-  revealing a white ferret on a log. It plays, leaps into the water, and emerges, as the camera zooms in 
-  for a close-up. Water splashes berry bushes nearby, while moss, snow, and leaves blanket the ground. 
-  Birch trees and a light blue sky frame the scene, with ferns in the foreground. Side lighting casts dynamic 
+  steamboat willie style, golden era animation, The camera rushes from far to near in a low-angle shot,
+  revealing a white ferret on a log. It plays, leaps into the water, and emerges, as the camera zooms in
+  for a close-up. Water splashes berry bushes nearby, while moss, snow, and leaves blanket the ground.
+  Birch trees and a light blue sky frame the scene, with ferns in the foreground. Side lighting casts dynamic
   shadows and warm highlights. Medium composition, front view, low angle, with depth of field.
   """
 
@@ -359,6 +562,12 @@ The general rule of thumb to keep in mind when preparing inputs for the VACE pip
   - all
   - __call__
 
+## WanAnimatePipeline
+
+[[autodoc]] WanAnimatePipeline
+  - all
+  - __call__
+
 ## WanPipelineOutput
 
-[[autodoc]] pipelines.wan.pipeline_output.WanPipelineOutput
+[[autodoc]] pipelines.wan.pipeline_output.WanPipelineOutput

docs/source/en/api/utilities.md

@@ -26,6 +26,10 @@ Utility and helper functions for working with 🤗 Diffusers.
 
 [[autodoc]] utils.load_image
 
+## load_video
+
+[[autodoc]] utils.load_video
+
 ## export_to_gif
 
 [[autodoc]] utils.export_to_gif

docs/source/en/modular_diffusers/custom_blocks.md

@@ -0,0 +1,492 @@
+<!--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.
+-->
+
+
+# Building Custom Blocks
+
+[ModularPipelineBlocks](./pipeline_block) are the fundamental building blocks of a [`ModularPipeline`]. You can create custom blocks by defining their inputs, outputs, and computation logic. This guide demonstrates how to create and use a custom block.
+
+> [!TIP]
+> Explore the [Modular Diffusers Custom Blocks](https://huggingface.co/collections/diffusers/modular-diffusers-custom-blocks) collection for official custom modular blocks like Nano Banana.
+
+## Project Structure
+
+Your custom block project should use the following structure:
+
+```shell
+.
+├── block.py
+└── modular_config.json
+```
+
+- `block.py` contains the custom block implementation
+- `modular_config.json` contains the metadata needed to load the block
+
+## Example: Florence 2 Inpainting Block
+
+In this example we will create a custom block that uses the [Florence 2](https://huggingface.co/docs/transformers/model_doc/florence2) model to process an input image and generate a mask for inpainting.
+
+The first step is to define the components that the block will use. In this case, we will need to use the `Florence2ForConditionalGeneration` model and its corresponding processor `AutoProcessor`. When defining components, we must specify the name of the component within our pipeline, model class via `type_hint`, and provide a `pretrained_model_name_or_path` for the component if we intend to load the model weights from a specific repository on the Hub.
+
+```py
+# Inside block.py
+from diffusers.modular_pipelines import (
+    ModularPipelineBlocks,
+    ComponentSpec,
+)
+from transformers import AutoProcessor, Florence2ForConditionalGeneration
+
+
+class Florence2ImageAnnotatorBlock(ModularPipelineBlocks):
+
+    @property
+    def expected_components(self):
+        return [
+            ComponentSpec(
+                name="image_annotator",
+                type_hint=Florence2ForConditionalGeneration,
+                pretrained_model_name_or_path="florence-community/Florence-2-base-ft",
+            ),
+            ComponentSpec(
+                name="image_annotator_processor",
+                type_hint=AutoProcessor,
+                pretrained_model_name_or_path="florence-community/Florence-2-base-ft",
+            ),
+        ]
+```
+
+Next, we define the inputs and outputs of the block. The inputs include the image to be annotated, the annotation task, and the annotation prompt. The outputs include the generated mask image and annotations.
+
+```py
+from typing import List, Union
+from PIL import Image, ImageDraw
+import torch
+import numpy as np
+
+from diffusers.modular_pipelines import (
+    PipelineState,
+    ModularPipelineBlocks,
+    InputParam,
+    ComponentSpec,
+    OutputParam,
+)
+from transformers import AutoProcessor, Florence2ForConditionalGeneration
+
+
+class Florence2ImageAnnotatorBlock(ModularPipelineBlocks):
+
+    @property
+    def expected_components(self):
+        return [
+            ComponentSpec(
+                name="image_annotator",
+                type_hint=Florence2ForConditionalGeneration,
+                pretrained_model_name_or_path="florence-community/Florence-2-base-ft",
+            ),
+            ComponentSpec(
+                name="image_annotator_processor",
+                type_hint=AutoProcessor,
+                pretrained_model_name_or_path="florence-community/Florence-2-base-ft",
+            ),
+        ]
+
+    @property
+    def inputs(self) -> List[InputParam]:
+        return [
+            InputParam(
+                "image",
+                type_hint=Union[Image.Image, List[Image.Image]],
+                required=True,
+                description="Image(s) to annotate",
+            ),
+            InputParam(
+                "annotation_task",
+                type_hint=Union[str, List[str]],
+                required=True,
+                default="<REFERRING_EXPRESSION_SEGMENTATION>",
+                description="""Annotation Task to perform on the image.
+                Supported Tasks:
+
+                <OD>
+                <REFERRING_EXPRESSION_SEGMENTATION>
+                <CAPTION>
+                <DETAILED_CAPTION>
+                <MORE_DETAILED_CAPTION>
+                <DENSE_REGION_CAPTION>
+                <CAPTION_TO_PHRASE_GROUNDING>
+                <OPEN_VOCABULARY_DETECTION>
+
+                """,
+            ),
+            InputParam(
+                "annotation_prompt",
+                type_hint=Union[str, List[str]],
+                required=True,
+                description="""Annotation Prompt to provide more context to the task.
+                Can be used to detect or segment out specific elements in the image
+                """,
+            ),
+            InputParam(
+                "annotation_output_type",
+                type_hint=str,
+                required=True,
+                default="mask_image",
+                description="""Output type from annotation predictions. Availabe options are
+                mask_image:
+                    -black and white mask image for the given image based on the task type
+                mask_overlay:
+                    - mask overlayed on the original image
+                bounding_box:
+                    - bounding boxes drawn on the original image
+                """,
+            ),
+            InputParam(
+                "annotation_overlay",
+                type_hint=bool,
+                required=True,
+                default=False,
+                description="",
+            ),
+        ]
+
+    @property
+    def intermediate_outputs(self) -> List[OutputParam]:
+        return [
+            OutputParam(
+                "mask_image",
+                type_hint=Image,
+                description="Inpainting Mask for input Image(s)",
+            ),
+            OutputParam(
+                "annotations",
+                type_hint=dict,
+                description="Annotations Predictions for input Image(s)",
+            ),
+            OutputParam(
+                "image",
+                type_hint=Image,
+                description="Annotated input Image(s)",
+            ),
+        ]
+
+```
+
+Now we implement the `__call__` method, which contains the logic for processing the input image and generating the mask.
+
+```py
+from typing import List, Union
+from PIL import Image, ImageDraw
+import torch
+import numpy as np
+
+from diffusers.modular_pipelines import (
+    PipelineState,
+    ModularPipelineBlocks,
+    InputParam,
+    ComponentSpec,
+    OutputParam,
+)
+from transformers import AutoProcessor, Florence2ForConditionalGeneration
+
+
+class Florence2ImageAnnotatorBlock(ModularPipelineBlocks):
+
+    @property
+    def expected_components(self):
+        return [
+            ComponentSpec(
+                name="image_annotator",
+                type_hint=Florence2ForConditionalGeneration,
+                pretrained_model_name_or_path="florence-community/Florence-2-base-ft",
+            ),
+            ComponentSpec(
+                name="image_annotator_processor",
+                type_hint=AutoProcessor,
+                pretrained_model_name_or_path="florence-community/Florence-2-base-ft",
+            ),
+        ]
+
+    @property
+    def inputs(self) -> List[InputParam]:
+        return [
+            InputParam(
+                "image",
+                type_hint=Union[Image.Image, List[Image.Image]],
+                required=True,
+                description="Image(s) to annotate",
+            ),
+            InputParam(
+                "annotation_task",
+                type_hint=Union[str, List[str]],
+                required=True,
+                default="<REFERRING_EXPRESSION_SEGMENTATION>",
+                description="""Annotation Task to perform on the image.
+                Supported Tasks:
+
+                <OD>
+                <REFERRING_EXPRESSION_SEGMENTATION>
+                <CAPTION>
+                <DETAILED_CAPTION>
+                <MORE_DETAILED_CAPTION>
+                <DENSE_REGION_CAPTION>
+                <CAPTION_TO_PHRASE_GROUNDING>
+                <OPEN_VOCABULARY_DETECTION>
+
+                """,
+            ),
+            InputParam(
+                "annotation_prompt",
+                type_hint=Union[str, List[str]],
+                required=True,
+                description="""Annotation Prompt to provide more context to the task.
+                Can be used to detect or segment out specific elements in the image
+                """,
+            ),
+            InputParam(
+                "annotation_output_type",
+                type_hint=str,
+                required=True,
+                default="mask_image",
+                description="""Output type from annotation predictions. Availabe options are
+                mask_image:
+                    -black and white mask image for the given image based on the task type
+                mask_overlay:
+                    - mask overlayed on the original image
+                bounding_box:
+                    - bounding boxes drawn on the original image
+                """,
+            ),
+            InputParam(
+                "annotation_overlay",
+                type_hint=bool,
+                required=True,
+                default=False,
+                description="",
+            ),
+        ]
+
+    @property
+    def intermediate_outputs(self) -> List[OutputParam]:
+        return [
+            OutputParam(
+                "mask_image",
+                type_hint=Image,
+                description="Inpainting Mask for input Image(s)",
+            ),
+            OutputParam(
+                "annotations",
+                type_hint=dict,
+                description="Annotations Predictions for input Image(s)",
+            ),
+            OutputParam(
+                "image",
+                type_hint=Image,
+                description="Annotated input Image(s)",
+            ),
+        ]
+
+    def get_annotations(self, components, images, prompts, task):
+        task_prompts = [task + prompt for prompt in prompts]
+
+        inputs = components.image_annotator_processor(
+            text=task_prompts, images=images, return_tensors="pt"
+        ).to(components.image_annotator.device, components.image_annotator.dtype)
+
+        generated_ids = components.image_annotator.generate(
+            input_ids=inputs["input_ids"],
+            pixel_values=inputs["pixel_values"],
+            max_new_tokens=1024,
+            early_stopping=False,
+            do_sample=False,
+            num_beams=3,
+        )
+        annotations = components.image_annotator_processor.batch_decode(
+            generated_ids, skip_special_tokens=False
+        )
+        outputs = []
+        for image, annotation in zip(images, annotations):
+            outputs.append(
+                components.image_annotator_processor.post_process_generation(
+                    annotation, task=task, image_size=(image.width, image.height)
+                )
+            )
+        return outputs
+
+    def prepare_mask(self, images, annotations, overlay=False, fill="white"):
+        masks = []
+        for image, annotation in zip(images, annotations):
+            mask_image = image.copy() if overlay else Image.new("L", image.size, 0)
+            draw = ImageDraw.Draw(mask_image)
+
+            for _, _annotation in annotation.items():
+                if "polygons" in _annotation:
+                    for polygon in _annotation["polygons"]:
+                        polygon = np.array(polygon).reshape(-1, 2)
+                        if len(polygon) < 3:
+                            continue
+                        polygon = polygon.reshape(-1).tolist()
+                        draw.polygon(polygon, fill=fill)
+
+                elif "bbox" in _annotation:
+                    bbox = _annotation["bbox"]
+                    draw.rectangle(bbox, fill="white")
+
+            masks.append(mask_image)
+
+        return masks
+
+    def prepare_bounding_boxes(self, images, annotations):
+        outputs = []
+        for image, annotation in zip(images, annotations):
+            image_copy = image.copy()
+            draw = ImageDraw.Draw(image_copy)
+            for _, _annotation in annotation.items():
+                bbox = _annotation["bbox"]
+                label = _annotation["label"]
+
+                draw.rectangle(bbox, outline="red", width=3)
+                draw.text((bbox[0], bbox[1] - 20), label, fill="red")
+
+            outputs.append(image_copy)
+
+        return outputs
+
+    def prepare_inputs(self, images, prompts):
+        prompts = prompts or ""
+
+        if isinstance(images, Image.Image):
+            images = [images]
+        if isinstance(prompts, str):
+            prompts = [prompts]
+
+        if len(images) != len(prompts):
+            raise ValueError("Number of images and annotation prompts must match.")
+
+        return images, prompts
+
+    @torch.no_grad()
+    def __call__(self, components, state: PipelineState) -> PipelineState:
+        block_state = self.get_block_state(state)
+        images, annotation_task_prompt = self.prepare_inputs(
+            block_state.image, block_state.annotation_prompt
+        )
+        task = block_state.annotation_task
+        fill = block_state.fill
+
+        annotations = self.get_annotations(
+            components, images, annotation_task_prompt, task
+        )
+        block_state.annotations = annotations
+        if block_state.annotation_output_type == "mask_image":
+            block_state.mask_image = self.prepare_mask(images, annotations)
+        else:
+            block_state.mask_image = None
+
+        if block_state.annotation_output_type == "mask_overlay":
+            block_state.image = self.prepare_mask(images, annotations, overlay=True, fill=fill)
+
+        elif block_state.annotation_output_type == "bounding_box":
+            block_state.image = self.prepare_bounding_boxes(images, annotations)
+
+        self.set_block_state(state, block_state)
+
+        return components, state
+
+```
+
+Once we have defined our custom block, we can save it to the Hub, using either the CLI or the [`push_to_hub`] method. This will make it easy to share and reuse our custom block with other pipelines.
+
+<hfoptions id="share">
+<hfoption id="hf CLI">
+
+```shell
+# In the folder with the `block.py` file, run:
+diffusers-cli custom_block
+```
+
+Then upload the block to the Hub:
+
+```shell
+hf upload <your repo id> . .
+```
+</hfoption>
+<hfoption id="push_to_hub">
+
+```py
+from block import Florence2ImageAnnotatorBlock
+block = Florence2ImageAnnotatorBlock()
+block.push_to_hub("<your repo id>")
+```
+
+</hfoption>
+</hfoptions>
+
+## Using Custom Blocks
+
+Load the custom block with [`~ModularPipelineBlocks.from_pretrained`] and set `trust_remote_code=True`.
+
+```py
+import torch
+from diffusers.modular_pipelines import ModularPipelineBlocks, SequentialPipelineBlocks
+from diffusers.modular_pipelines.stable_diffusion_xl import INPAINT_BLOCKS
+from diffusers.utils import load_image
+
+# Fetch the Florence2 image annotator block that will create our mask
+image_annotator_block = ModularPipelineBlocks.from_pretrained("diffusers/florence-2-custom-block", trust_remote_code=True)
+
+my_blocks = INPAINT_BLOCKS.copy()
+# insert the annotation block before the image encoding step
+my_blocks.insert("image_annotator", image_annotator_block, 1)
+
+# Create our initial set of inpainting blocks
+blocks = SequentialPipelineBlocks.from_blocks_dict(my_blocks)
+
+repo_id = "diffusers/modular-stable-diffusion-xl-base-1.0"
+pipe = blocks.init_pipeline(repo_id)
+pipe.load_components(torch_dtype=torch.float16, device_map="cuda", trust_remote_code=True)
+
+image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg?download=true")
+image = image.resize((1024, 1024))
+
+prompt = ["A red car"]
+annotation_task = "<REFERRING_EXPRESSION_SEGMENTATION>"
+annotation_prompt = ["the car"]
+
+output = pipe(
+    prompt=prompt,
+    image=image,
+    annotation_task=annotation_task,
+    annotation_prompt=annotation_prompt,
+    annotation_output_type="mask_image",
+    num_inference_steps=35,
+    guidance_scale=7.5,
+    strength=0.95,
+    output="images"
+)
+output[0].save("florence-inpainting.png")
+```
+
+## Editing Custom Blocks
+
+By default, custom blocks are saved in your cache directory. Use the `local_dir` argument to download and edit a custom block in a specific folder.
+
+```py
+import torch
+from diffusers.modular_pipelines import ModularPipelineBlocks, SequentialPipelineBlocks
+from diffusers.modular_pipelines.stable_diffusion_xl import INPAINT_BLOCKS
+from diffusers.utils import load_image
+
+# Fetch the Florence2 image annotator block that will create our mask
+image_annotator_block = ModularPipelineBlocks.from_pretrained("diffusers/florence-2-custom-block", trust_remote_code=True, local_dir="/my-local-folder")
+```
+
+Any changes made to the block files in this folder will be reflected when you load the block again.

docs/source/en/modular_diffusers/loop_sequential_pipeline_blocks.md

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # LoopSequentialPipelineBlocks
 
-[`~modular_pipelines.LoopSequentialPipelineBlocks`] are a multi-block type that composes other [`~modular_pipelines.ModularPipelineBlocks`] together in a loop. Data flows circularly, using `intermediate_inputs` and `intermediate_outputs`, and each block is run iteratively. This is typically used to create a denoising loop which is iterative by default.
+[`~modular_pipelines.LoopSequentialPipelineBlocks`] are a multi-block type that composes other [`~modular_pipelines.ModularPipelineBlocks`] together in a loop. Data flows circularly, using `inputs` and `intermediate_outputs`, and each block is run iteratively. This is typically used to create a denoising loop which is iterative by default.
 
 This guide shows you how to create [`~modular_pipelines.LoopSequentialPipelineBlocks`].
 
@@ -21,7 +21,6 @@ This guide shows you how to create [`~modular_pipelines.LoopSequentialPipelineBl
 [`~modular_pipelines.LoopSequentialPipelineBlocks`], is also known as the *loop wrapper* because it defines the loop structure, iteration variables, and configuration. Within the loop wrapper, you need the following variables.
 
 - `loop_inputs` are user provided values and equivalent to [`~modular_pipelines.ModularPipelineBlocks.inputs`].
-- `loop_intermediate_inputs` are intermediate variables from the [`~modular_pipelines.PipelineState`] and equivalent to [`~modular_pipelines.ModularPipelineBlocks.intermediate_inputs`].
 - `loop_intermediate_outputs` are new intermediate variables created by the block and added to the [`~modular_pipelines.PipelineState`]. It is equivalent to [`~modular_pipelines.ModularPipelineBlocks.intermediate_outputs`].
 - `__call__` method defines the loop structure and iteration logic.
 
@@ -90,4 +89,4 @@ Add more loop blocks to run within each iteration with [`~modular_pipelines.Loop
 
 ```py
 loop = LoopWrapper.from_blocks_dict({"block1": LoopBlock(), "block2": LoopBlock})
-```
+```

docs/source/en/modular_diffusers/pipeline_block.md

@@ -37,17 +37,7 @@ A [`~modular_pipelines.ModularPipelineBlocks`] requires `inputs`, and `intermedi
     ]
     ```
 
-- `intermediate_inputs` are values typically created from a previous block but it can also be directly provided if no preceding block generates them. Unlike `inputs`, `intermediate_inputs` can be modified.
-
-    Use `InputParam` to define `intermediate_inputs`.
-
-    ```py
-    user_intermediate_inputs = [
-        InputParam(name="processed_image", type_hint="torch.Tensor", description="image that has been preprocessed and normalized"),
-    ]
-    ```
-
-- `intermediate_outputs` are new values created by a block and added to the [`~modular_pipelines.PipelineState`]. The `intermediate_outputs` are available as `intermediate_inputs` for subsequent blocks or available as the final output from running the pipeline.
+- `intermediate_outputs` are new values created by a block and added to the [`~modular_pipelines.PipelineState`]. The `intermediate_outputs` are available as `inputs` for subsequent blocks or available as the final output from running the pipeline.
 
     Use `OutputParam` to define `intermediate_outputs`.
 
@@ -65,8 +55,8 @@ The intermediate inputs and outputs share data to connect blocks. They are acces
 
 The computation a block performs is defined in the `__call__` method and it follows a specific structure.
 
-1. Retrieve the [`~modular_pipelines.BlockState`] to get a local view of the `inputs` and `intermediate_inputs`.
-2. Implement the computation logic on the `inputs` and `intermediate_inputs`.
+1. Retrieve the [`~modular_pipelines.BlockState`] to get a local view of the `inputs`
+2. Implement the computation logic on the `inputs`.
 3. Update [`~modular_pipelines.PipelineState`] to push changes from the local [`~modular_pipelines.BlockState`] back to the global [`~modular_pipelines.PipelineState`].
 4. Return the components and state which becomes available to the next block.
 
@@ -76,7 +66,7 @@ def __call__(self, components, state):
     block_state = self.get_block_state(state)
 
     # Your computation logic here
-    # block_state contains all your inputs and intermediate_inputs
+    # block_state contains all your inputs
     # Access them like: block_state.image, block_state.processed_image
 
     # Update the pipeline state with your updated block_states
@@ -112,4 +102,4 @@ def __call__(self, components, state):
     unet = components.unet
     vae = components.vae
     scheduler = components.scheduler
-```
+```

docs/source/en/modular_diffusers/quickstart.md

@@ -183,7 +183,7 @@ from diffusers.modular_pipelines import ComponentsManager
 components = ComponentManager()
 
 dd_pipeline = dd_blocks.init_pipeline("YiYiXu/modular-demo-auto", components_manager=components, collection="diffdiff")
-dd_pipeline.load_default_componenets(torch_dtype=torch.float16)
+dd_pipeline.load_componenets(torch_dtype=torch.float16)
 dd_pipeline.to("cuda")
 ```
 

docs/source/en/modular_diffusers/sequential_pipeline_blocks.md

@@ -12,11 +12,11 @@ specific language governing permissions and limitations under the License.
 
 # SequentialPipelineBlocks
 
-[`~modular_pipelines.SequentialPipelineBlocks`] are a multi-block type that composes other [`~modular_pipelines.ModularPipelineBlocks`] together in a sequence. Data flows linearly from one block to the next using `intermediate_inputs` and `intermediate_outputs`. Each block in [`~modular_pipelines.SequentialPipelineBlocks`] usually represents a step in the pipeline, and by combining them, you gradually build a pipeline.
+[`~modular_pipelines.SequentialPipelineBlocks`] are a multi-block type that composes other [`~modular_pipelines.ModularPipelineBlocks`] together in a sequence. Data flows linearly from one block to the next using `inputs` and `intermediate_outputs`. Each block in [`~modular_pipelines.SequentialPipelineBlocks`] usually represents a step in the pipeline, and by combining them, you gradually build a pipeline.
 
 This guide shows you how to connect two blocks into a [`~modular_pipelines.SequentialPipelineBlocks`].
 
-Create two [`~modular_pipelines.ModularPipelineBlocks`]. The first block, `InputBlock`, outputs a `batch_size` value and the second block, `ImageEncoderBlock` uses `batch_size` as `intermediate_inputs`.
+Create two [`~modular_pipelines.ModularPipelineBlocks`]. The first block, `InputBlock`, outputs a `batch_size` value and the second block, `ImageEncoderBlock` uses `batch_size` as `inputs`.
 
 <hfoptions id="sequential">
 <hfoption id="InputBlock">
@@ -110,4 +110,4 @@ Inspect the sub-blocks in [`~modular_pipelines.SequentialPipelineBlocks`] by cal
 ```py
 print(blocks)
 print(blocks.doc)
-```
+```

docs/source/en/optimization/attention_backends.md

@@ -21,6 +21,7 @@ Refer to the table below for an overview of the available attention families and
 | attention family | main feature |
 |---|---|
 | FlashAttention | minimizes memory reads/writes through tiling and recomputation |
+| AI Tensor Engine for ROCm | FlashAttention implementation optimized for AMD ROCm accelerators |
 | SageAttention | quantizes attention to int8 |
 | PyTorch native | built-in PyTorch implementation using [scaled_dot_product_attention](./fp16#scaled-dot-product-attention) |
 | xFormers | memory-efficient attention with support for various attention kernels |
@@ -81,6 +82,45 @@ with attention_backend("_flash_3_hub"):
 > [!TIP]
 > Most attention backends support `torch.compile` without graph breaks and can be used to further speed up inference.
 
+## Checks
+
+The attention dispatcher includes debugging checks that catch common errors before they cause problems.
+
+1. Device checks verify that query, key, and value tensors live on the same device.
+2. Data type checks confirm tensors have matching dtypes and use either bfloat16 or float16.
+3. Shape checks validate tensor dimensions and prevent mixing attention masks with causal flags.
+
+Enable these checks by setting the `DIFFUSERS_ATTN_CHECKS` environment variable. Checks add overhead to every attention operation, so they're disabled by default. 
+
+```bash
+export DIFFUSERS_ATTN_CHECKS=yes
+```
+
+The checks are run now before every attention operation.
+
+```py
+import torch
+
+query = torch.randn(1, 10, 8, 64, dtype=torch.bfloat16, device="cuda")
+key = torch.randn(1, 10, 8, 64, dtype=torch.bfloat16, device="cuda")
+value = torch.randn(1, 10, 8, 64, dtype=torch.bfloat16, device="cuda")
+
+try:
+    with attention_backend("flash"):
+        output = dispatch_attention_fn(query, key, value)
+        print("✓ Flash Attention works with checks enabled")
+except Exception as e:
+    print(f"✗ Flash Attention failed: {e}")
+```
+
+You can also configure the registry directly.
+
+```py
+from diffusers.models.attention_dispatch import _AttentionBackendRegistry
+
+_AttentionBackendRegistry._checks_enabled = True
+```
+
 ## Available backends
 
 Refer to the table below for a complete list of available attention backends and their variants.
@@ -99,11 +139,14 @@ Refer to the table below for a complete list of available attention backends and
 | `_native_npu` | [PyTorch native](https://docs.pytorch.org/docs/stable/generated/torch.nn.attention.SDPBackend.html#torch.nn.attention.SDPBackend) | NPU-optimized attention |
 | `_native_xla` | [PyTorch native](https://docs.pytorch.org/docs/stable/generated/torch.nn.attention.SDPBackend.html#torch.nn.attention.SDPBackend) | XLA-optimized attention |
 | `flash` | [FlashAttention](https://github.com/Dao-AILab/flash-attention) | FlashAttention-2 |
+| `flash_hub` | [FlashAttention](https://github.com/Dao-AILab/flash-attention) | FlashAttention-2 from kernels |
 | `flash_varlen` | [FlashAttention](https://github.com/Dao-AILab/flash-attention) | Variable length FlashAttention |
+| `aiter` | [AI Tensor Engine for ROCm](https://github.com/ROCm/aiter) | FlashAttention for AMD ROCm |
 | `_flash_3` | [FlashAttention](https://github.com/Dao-AILab/flash-attention) | FlashAttention-3 |
 | `_flash_varlen_3` | [FlashAttention](https://github.com/Dao-AILab/flash-attention) | Variable length FlashAttention-3 |
 | `_flash_3_hub` | [FlashAttention](https://github.com/Dao-AILab/flash-attention) | FlashAttention-3 from kernels |
 | `sage` | [SageAttention](https://github.com/thu-ml/SageAttention) | Quantized attention (INT8 QK) |
+| `sage_hub` | [SageAttention](https://github.com/thu-ml/SageAttention) | Quantized attention (INT8 QK) from kernels |
 | `sage_varlen` | [SageAttention](https://github.com/thu-ml/SageAttention) | Variable length SageAttention |
 | `_sage_qk_int8_pv_fp8_cuda` | [SageAttention](https://github.com/thu-ml/SageAttention) | INT8 QK + FP8 PV (CUDA) |
 | `_sage_qk_int8_pv_fp8_cuda_sm90` | [SageAttention](https://github.com/thu-ml/SageAttention) | INT8 QK + FP8 PV (SM90) |

docs/source/en/training/adapt_a_model.md

@@ -16,12 +16,12 @@ pipeline.unet.config["in_channels"]
 4
 ```
 
-Inpainting requires 9 channels in the input sample. You can check this value in a pretrained inpainting model like [`runwayml/stable-diffusion-inpainting`](https://huggingface.co/runwayml/stable-diffusion-inpainting):
+Inpainting requires 9 channels in the input sample. You can check this value in a pretrained inpainting model like [`stable-diffusion-v1-5/stable-diffusion-inpainting`](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-inpainting):
 
 ```py
 from diffusers import StableDiffusionPipeline
 
-pipeline = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-inpainting", use_safetensors=True)
+pipeline = StableDiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-inpainting", use_safetensors=True)
 pipeline.unet.config["in_channels"]
 9
 ```

docs/source/en/training/dreambooth.md

@@ -548,4 +548,4 @@ Training the DeepFloyd IF model can be challenging, but here are some tips that
 
 Congratulations on training your DreamBooth model! To learn more about how to use your new model, the following guide may be helpful:
 
-- Learn how to [load a DreamBooth](../using-diffusers/loading_adapters) model for inference if you trained your model with LoRA.
+- Learn how to [load a DreamBooth](../using-diffusers/dreambooth) model for inference if you trained your model with LoRA.

docs/source/en/training/lcm_distill.md

@@ -75,7 +75,7 @@ accelerate launch train_lcm_distill_sd_wds.py \
 Most of the parameters are identical to the parameters in the [Text-to-image](text2image#script-parameters) training guide, so you'll focus on the parameters that are relevant to latent consistency distillation in this guide.
 
 - `--pretrained_teacher_model`: the path to a pretrained latent diffusion model to use as the teacher model
-- `--pretrained_vae_model_name_or_path`: path to a pretrained VAE; the SDXL VAE is known to suffer from numerical instability, so this parameter allows you to specify an alternative VAE (like this [VAE]((https://huggingface.co/madebyollin/sdxl-vae-fp16-fix)) by madebyollin which works in fp16)
+- `--pretrained_vae_model_name_or_path`: path to a pretrained VAE; the SDXL VAE is known to suffer from numerical instability, so this parameter allows you to specify an alternative VAE (like this [VAE](https://huggingface.co/madebyollin/sdxl-vae-fp16-fix)) by madebyollin which works in fp16)
 - `--w_min` and `--w_max`: the minimum and maximum guidance scale values for guidance scale sampling
 - `--num_ddim_timesteps`: the number of timesteps for DDIM sampling
 - `--loss_type`: the type of loss (L2 or Huber) to calculate for latent consistency distillation; Huber loss is generally preferred because it's more robust to outliers
@@ -245,5 +245,5 @@ The SDXL training script is discussed in more detail in the [SDXL training](sdxl
 
 Congratulations on distilling a LCM model! To learn more about LCM, the following may be helpful:
 
-- Learn how to use [LCMs for inference](../using-diffusers/lcm) for text-to-image, image-to-image, and with LoRA checkpoints.
+- Learn how to use [LCMs for inference](../using-diffusers/inference_with_lcm) for text-to-image, image-to-image, and with LoRA checkpoints.
 - Read the [SDXL in 4 steps with Latent Consistency LoRAs](https://huggingface.co/blog/lcm_lora) blog post to learn more about SDXL LCM-LoRA's for super fast inference, quality comparisons, benchmarks, and more.

docs/source/en/training/lora.md

@@ -198,5 +198,5 @@ image = pipeline("A naruto with blue eyes").images[0]
 
 Congratulations on training a new model with LoRA! To learn more about how to use your new model, the following guides may be helpful:
 
-- Learn how to [load different LoRA formats](../using-diffusers/loading_adapters#LoRA) trained using community trainers like Kohya and TheLastBen.
+- Learn how to [load different LoRA formats](../tutorials/using_peft_for_inference) trained using community trainers like Kohya and TheLastBen.
 - Learn how to use and [combine multiple LoRA's](../tutorials/using_peft_for_inference) with PEFT for inference.

docs/source/en/training/text2image.md

@@ -178,5 +178,5 @@ image.save("yoda-naruto.png")
 
 Congratulations on training your own text-to-image model! To learn more about how to use your new model, the following guides may be helpful:
 
-- Learn how to [load LoRA weights](../using-diffusers/loading_adapters#LoRA) for inference if you trained your model with LoRA.
+- Learn how to [load LoRA weights](../tutorials/using_peft_for_inference) for inference if you trained your model with LoRA.
 - Learn more about how certain parameters like guidance scale or techniques such as prompt weighting can help you control inference in the [Text-to-image](../using-diffusers/conditional_image_generation) task guide.

docs/source/en/training/text_inversion.md

@@ -203,5 +203,4 @@ image.save("cat-train.png")
 
 Congratulations on training your own Textual Inversion model! 🎉 To learn more about how to use your new model, the following guides may be helpful:
 
-- Learn how to [load Textual Inversion embeddings](../using-diffusers/loading_adapters) and also use them as negative embeddings.
-- Learn how to use [Textual Inversion](textual_inversion_inference) for inference with Stable Diffusion 1/2 and Stable Diffusion XL.
+- Learn how to [load Textual Inversion embeddings](../using-diffusers/textual_inversion_inference) and also use them as negative embeddings.

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

@@ -0,0 +1,46 @@
+<!--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.
+-->
+
+# AutoModel
+
+The [`AutoModel`] class automatically detects and loads the correct model class (UNet, transformer, VAE) from a `config.json` file. You don't need to know the specific model class name ahead of time. It supports data types and device placement, and works across model types and libraries.
+
+The example below loads a transformer from Diffusers and a text encoder from Transformers. Use the `subfolder` parameter to specify where to load the `config.json` file from.
+
+```py
+import torch
+from diffusers import AutoModel, DiffusionPipeline
+
+transformer = AutoModel.from_pretrained(
+    "Qwen/Qwen-Image", subfolder="transformer", torch_dtype=torch.bfloat16, device_map="cuda"
+)
+
+text_encoder = AutoModel.from_pretrained(
+    "Qwen/Qwen-Image", subfolder="text_encoder", torch_dtype=torch.bfloat16, device_map="cuda"
+)
+```
+
+[`AutoModel`] also loads models from the [Hub](https://huggingface.co/models) that aren't included in Diffusers. Set `trust_remote_code=True` in [`AutoModel.from_pretrained`] to load custom models.
+
+```py
+import torch
+from diffusers import AutoModel
+
+transformer = AutoModel.from_pretrained(
+    "custom/custom-transformer-model", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map="cuda"
+)
+```
+
+If the custom model inherits from the [`ModelMixin`] class, it gets access to the same features as Diffusers model classes, like [regional compilation](../optimization/fp16#regional-compilation) and [group offloading](../optimization/memory#group-offloading).
+
+> [!NOTE]
+> Learn more about implementing custom models in the [Community components](../using-diffusers/custom_pipeline_overview#community-components) guide.

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

@@ -16,24 +16,24 @@ Batch inference processes multiple prompts at a time to increase throughput. It
 
 The downside is increased latency because you must wait for the entire batch to complete, and more GPU memory is required for large batches.
 
-<hfoptions id="usage">
-<hfoption id="text-to-image">
-
-For text-to-image, pass a list of prompts to the pipeline.
+For text-to-image, pass a list of prompts to the pipeline and for image-to-image, pass a list of images and prompts to the pipeline. The example below demonstrates batched text-to-image inference.
 
 ```py
 import torch
+import matplotlib.pyplot as plt
 from diffusers import DiffusionPipeline
 
 pipeline = DiffusionPipeline.from_pretrained(
     "stabilityai/stable-diffusion-xl-base-1.0",
-    torch_dtype=torch.float16
-).to("cuda")
+    torch_dtype=torch.float16,
+    device_map="cuda"
+)
 
 prompts = [
-    "cinematic photo of A beautiful sunset over mountains, 35mm photograph, film, professional, 4k, highly detailed",
-    "cinematic film still of a cat basking in the sun on a roof in Turkey, highly detailed, high budget hollywood movie, cinemascope, moody, epic, gorgeous, film grain",
-    "pixel-art a cozy coffee shop interior, low-res, blocky, pixel art style, 8-bit graphics"
+    "Cinematic shot of a cozy coffee shop interior, warm pastel light streaming through a window where a cat rests. Shallow depth of field, glowing cups in soft focus, dreamy lofi-inspired mood, nostalgic tones, framed like a quiet film scene.",
+    "Polaroid-style photograph of a cozy coffee shop interior, bathed in warm pastel light. A cat sits on the windowsill near steaming mugs. Soft, slightly faded tones and dreamy blur evoke nostalgia, a lofi mood, and the intimate, imperfect charm of instant film.",
+    "Soft watercolor illustration of a cozy coffee shop interior, pastel washes of color filling the space. A cat rests peacefully on the windowsill as warm light glows through. Gentle brushstrokes create a dreamy, lofi-inspired atmosphere with whimsical textures and nostalgic calm.",
+    "Isometric pixel-art illustration of a cozy coffee shop interior in detailed 8-bit style. Warm pastel light fills the space as a cat rests on the windowsill. Blocky furniture and tiny mugs add charm, low-res retro graphics enhance the nostalgic, lofi-inspired game aesthetic."
 ]
 
 images = pipeline(
@@ -52,6 +52,10 @@ plt.tight_layout()
 plt.show()
 ```
 
+<div class="flex justify-center">
+    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/batch-inference.png"/>
+</div>
+
 To generate multiple variations of one prompt, use the `num_images_per_prompt` argument.
 
 ```py
@@ -61,11 +65,18 @@ from diffusers import DiffusionPipeline
 
 pipeline = DiffusionPipeline.from_pretrained(
     "stabilityai/stable-diffusion-xl-base-1.0",
-    torch_dtype=torch.float16
-).to("cuda")
+    torch_dtype=torch.float16,
+    device_map="cuda"
+)
+
+prompt="""
+Isometric pixel-art illustration of a cozy coffee shop interior in detailed 8-bit style. Warm pastel light fills the
+space as a cat rests on the windowsill. Blocky furniture and tiny mugs add charm, low-res retro graphics enhance the
+nostalgic, lofi-inspired game aesthetic.
+"""
 
 images = pipeline(
-    prompt="pixel-art a cozy coffee shop interior, low-res, blocky, pixel art style, 8-bit graphics",
+    prompt=prompt,
     num_images_per_prompt=4
 ).images
 
@@ -81,6 +92,10 @@ plt.tight_layout()
 plt.show()
 ```
 
+<div class="flex justify-center">
+    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/batch-inference-2.png"/>
+</div>
+
 Combine both approaches to generate different variations of different prompts.
 
 ```py
@@ -89,7 +104,7 @@ images = pipeline(
     num_images_per_prompt=2,
 ).images
 
-fig, axes = plt.subplots(2, 2, figsize=(12, 12))
+fig, axes = plt.subplots(2, 4, figsize=(12, 12))
 axes = axes.flatten()
 
 for i, image in enumerate(images):
@@ -101,126 +116,18 @@ plt.tight_layout()
 plt.show()
 ```
 
-</hfoption>
-<hfoption id="image-to-image">
-
-For image-to-image, pass a list of input images and prompts to the pipeline.
-
-```py
-import torch
-from diffusers.utils import load_image
-from diffusers import DiffusionPipeline
-
-pipeline = DiffusionPipeline.from_pretrained(
-    "stabilityai/stable-diffusion-xl-base-1.0",
-    torch_dtype=torch.float16
-).to("cuda")
-
-input_images = [
-    load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint.png"),
-    load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png"),
-    load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/detail-prompt.png")
-]
-
-prompts = [
-    "cinematic photo of a beautiful sunset over mountains, 35mm photograph, film, professional, 4k, highly detailed",
-    "cinematic film still of a cat basking in the sun on a roof in Turkey, highly detailed, high budget hollywood movie, cinemascope, moody, epic, gorgeous, film grain",
-    "pixel-art a cozy coffee shop interior, low-res, blocky, pixel art style, 8-bit graphics"
-]
-
-images = pipeline(
-    prompt=prompts,
-    image=input_images,
-    guidance_scale=8.0,
-    strength=0.5
-).images
-
-fig, axes = plt.subplots(2, 2, figsize=(12, 12))
-axes = axes.flatten()
-
-for i, image in enumerate(images):
-    axes[i].imshow(image)
-    axes[i].set_title(f"Image {i+1}")
-    axes[i].axis('off')
-
-plt.tight_layout()
-plt.show()
-```
-
-To generate multiple variations of one prompt, use the `num_images_per_prompt` argument.
-
-```py
-import torch
-import matplotlib.pyplot as plt
-from diffusers.utils import load_image
-from diffusers import DiffusionPipeline
-
-pipeline = DiffusionPipeline.from_pretrained(
-    "stabilityai/stable-diffusion-xl-base-1.0",
-    torch_dtype=torch.float16
-).to("cuda")
-
-input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/detail-prompt.png")
-
-images = pipeline(
-    prompt="pixel-art a cozy coffee shop interior, low-res, blocky, pixel art style, 8-bit graphics",
-    image=input_image,
-    num_images_per_prompt=4
-).images
-
-fig, axes = plt.subplots(2, 2, figsize=(12, 12))
-axes = axes.flatten()
-
-for i, image in enumerate(images):
-    axes[i].imshow(image)
-    axes[i].set_title(f"Image {i+1}")
-    axes[i].axis('off')
-
-plt.tight_layout()
-plt.show()
-```
-
-Combine both approaches to generate different variations of different prompts.
-
-```py
-input_images = [
-    load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png"),
-    load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/detail-prompt.png")
-]
-
-prompts = [
-    "cinematic film still of a cat basking in the sun on a roof in Turkey, highly detailed, high budget hollywood movie, cinemascope, moody, epic, gorgeous, film grain",
-    "pixel-art a cozy coffee shop interior, low-res, blocky, pixel art style, 8-bit graphics"
-]
-
-images = pipeline(
-    prompt=prompts,
-    image=input_images,
-    num_images_per_prompt=2,
-).images
-
-fig, axes = plt.subplots(2, 2, figsize=(12, 12))
-axes = axes.flatten()
-
-for i, image in enumerate(images):
-    axes[i].imshow(image)
-    axes[i].set_title(f"Image {i+1}")
-    axes[i].axis('off')
-
-plt.tight_layout()
-plt.show()
-```
-
-</hfoption>
-</hfoptions>
+<div class="flex justify-center">
+    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/batch-inference-3.png"/>
+</div>
 
 ## Deterministic generation
 
 Enable reproducible batch generation by passing a list of [Generator’s](https://pytorch.org/docs/stable/generated/torch.Generator.html) to the pipeline and tie each `Generator` to a seed to reuse it.
 
-Use a list comprehension to iterate over the batch size specified in `range()` to create a unique `Generator` object for each image in the batch.
+> [!TIP]
+> Refer to the [Reproducibility](./reusing_seeds) docs to learn more about deterministic algorithms and the `Generator` object.
 
-Don't multiply the `Generator` by the batch size because that only creates one `Generator` object that is used sequentially for each image in the batch.
+Use a list comprehension to iterate over the batch size specified in `range()` to create a unique `Generator` object for each image in the batch. Don't multiply the `Generator` by the batch size because that only creates one `Generator` object that is used sequentially for each image in the batch.
 
 ```py
 generator = [torch.Generator(device="cuda").manual_seed(0)] * 3
@@ -234,14 +141,16 @@ from diffusers import DiffusionPipeline
 
 pipeline = DiffusionPipeline.from_pretrained(
     "stabilityai/stable-diffusion-xl-base-1.0",
-    torch_dtype=torch.float16
-).to("cuda")
+    torch_dtype=torch.float16,
+    device_map="cuda"
+)
 
 generator = [torch.Generator(device="cuda").manual_seed(i) for i in range(3)]
 prompts = [
-    "cinematic photo of A beautiful sunset over mountains, 35mm photograph, film, professional, 4k, highly detailed",
-    "cinematic film still of a cat basking in the sun on a roof in Turkey, highly detailed, high budget hollywood movie, cinemascope, moody, epic, gorgeous, film grain",
-    "pixel-art a cozy coffee shop interior, low-res, blocky, pixel art style, 8-bit graphics"
+    "Cinematic shot of a cozy coffee shop interior, warm pastel light streaming through a window where a cat rests. Shallow depth of field, glowing cups in soft focus, dreamy lofi-inspired mood, nostalgic tones, framed like a quiet film scene.",
+    "Polaroid-style photograph of a cozy coffee shop interior, bathed in warm pastel light. A cat sits on the windowsill near steaming mugs. Soft, slightly faded tones and dreamy blur evoke nostalgia, a lofi mood, and the intimate, imperfect charm of instant film.",
+    "Soft watercolor illustration of a cozy coffee shop interior, pastel washes of color filling the space. A cat rests peacefully on the windowsill as warm light glows through. Gentle brushstrokes create a dreamy, lofi-inspired atmosphere with whimsical textures and nostalgic calm.",
+    "Isometric pixel-art illustration of a cozy coffee shop interior in detailed 8-bit style. Warm pastel light fills the space as a cat rests on the windowsill. Blocky furniture and tiny mugs add charm, low-res retro graphics enhance the nostalgic, lofi-inspired game aesthetic."
 ]
 
 images = pipeline(
@@ -261,4 +170,4 @@ plt.tight_layout()
 plt.show()
 ```
 
-You can use this to iteratively select an image associated with a seed and then improve on it by crafting a more detailed prompt.
+You can use this to select an image associated with a seed and iteratively improve on it by crafting a more detailed prompt.

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

@@ -70,32 +70,6 @@ For convenience, we provide a table to denote which methods are inference-only a
 [InstructPix2Pix](../api/pipelines/pix2pix) is fine-tuned from Stable Diffusion to support editing input images. It takes as inputs an image and a prompt describing an edit, and it outputs the edited image.
 InstructPix2Pix has been explicitly trained to work well with [InstructGPT](https://openai.com/blog/instruction-following/)-like prompts.
 
-## Pix2Pix Zero
-
-[Paper](https://huggingface.co/papers/2302.03027)
-
-[Pix2Pix Zero](../api/pipelines/pix2pix_zero) allows modifying an image so that one concept or subject is translated to another one while preserving general image semantics.
-
-The denoising process is guided from one conceptual embedding towards another conceptual embedding. The intermediate latents are optimized during the denoising process to push the attention maps towards reference attention maps. The reference attention maps are from the denoising process of the input image and are used to encourage semantic preservation.
-
-Pix2Pix Zero can be used both to edit synthetic images as well as real images.
-
-- To edit synthetic images, one first generates an image given a caption.
-  Next, we generate image captions for the concept that shall be edited and for the new target concept. We can use a model like [Flan-T5](https://huggingface.co/docs/transformers/model_doc/flan-t5) for this purpose. Then, "mean" prompt embeddings for both the source and target concepts are created via the text encoder. Finally, the pix2pix-zero algorithm is used to edit the synthetic image.
-- To edit a real image, one first generates an image caption using a model like [BLIP](https://huggingface.co/docs/transformers/model_doc/blip). Then one applies DDIM inversion on the prompt and image to generate "inverse" latents. Similar to before, "mean" prompt embeddings for both source and target concepts are created and finally the pix2pix-zero algorithm in combination with the "inverse" latents is used to edit the image.
-
-> [!TIP]
-> Pix2Pix Zero is the first model that allows "zero-shot" image editing. This means that the model
-> can edit an image in less than a minute on a consumer GPU as shown [here](../api/pipelines/pix2pix_zero#usage-example).
-
-As mentioned above, Pix2Pix Zero includes optimizing the latents (and not any of the UNet, VAE, or the text encoder) to steer the generation toward a specific concept. This means that the overall
-pipeline might require more memory than a standard [StableDiffusionPipeline](../api/pipelines/stable_diffusion/text2img).
-
-> [!TIP]
-> An important distinction between methods like InstructPix2Pix and Pix2Pix Zero is that the former
-> involves fine-tuning the pre-trained weights while the latter does not. This means that you can
-> apply Pix2Pix Zero to any of the available Stable Diffusion models.
-
 ## Attend and Excite
 
 [Paper](https://huggingface.co/papers/2301.13826)
@@ -178,14 +152,6 @@ multi-concept training by design. Like DreamBooth and Textual Inversion, Custom
 teach a pre-trained text-to-image diffusion model about new concepts to generate outputs involving the
 concept(s) of interest.
 
-## Model Editing
-
-[Paper](https://huggingface.co/papers/2303.08084)
-
-The [text-to-image model editing pipeline](../api/pipelines/model_editing) helps you mitigate some of the incorrect implicit assumptions a pre-trained text-to-image
-diffusion model might make about the subjects present in the input prompt. For example, if you prompt Stable Diffusion to generate images for "A pack of roses", the roses in the generated images
-are more likely to be red. This pipeline helps you change that assumption.
-
 ## DiffEdit
 
 [Paper](https://huggingface.co/papers/2210.11427)

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

@@ -215,7 +215,7 @@ from diffusers import AutoPipelineForInpainting, LCMScheduler
 from diffusers.utils import load_image, make_image_grid
 
 pipe = AutoPipelineForInpainting.from_pretrained(
-    "runwayml/stable-diffusion-inpainting",
+    "stable-diffusion-v1-5/stable-diffusion-inpainting",
     torch_dtype=torch.float16,
     variant="fp16",
 ).to("cuda")
@@ -257,7 +257,7 @@ LCMs are compatible with adapters like LoRA, ControlNet, T2I-Adapter, and Animat
 
 ### LoRA
 
-[LoRA](../using-diffusers/loading_adapters#lora) adapters can be rapidly finetuned to learn a new style from just a few images and plugged into a pretrained model to generate images in that style.
+[LoRA](../tutorials/using_peft_for_inference) adapters can be rapidly finetuned to learn a new style from just a few images and plugged into a pretrained model to generate images in that style.
 
 <hfoptions id="lcm-lora">
 <hfoption id="LCM">

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

@@ -18,7 +18,7 @@ Trajectory Consistency Distillation (TCD) enables a model to generate higher qua
 
 The major advantages of TCD are:
 
-- Better than Teacher: TCD demonstrates superior generative quality at both small and large inference steps and exceeds the performance of [DPM-Solver++(2S)](../../api/schedulers/multistep_dpm_solver) with Stable Diffusion XL (SDXL). There is no additional discriminator or LPIPS supervision included during TCD training.
+- Better than Teacher: TCD demonstrates superior generative quality at both small and large inference steps and exceeds the performance of [DPM-Solver++(2S)](../api/schedulers/multistep_dpm_solver) with Stable Diffusion XL (SDXL). There is no additional discriminator or LPIPS supervision included during TCD training.
 
 - Flexible Inference Steps: The inference steps for TCD sampling can be freely adjusted without adversely affecting the image quality.
 
@@ -166,7 +166,7 @@ image = pipe(
 TCD-LoRA also supports other LoRAs trained on different styles. For example, let's load the [TheLastBen/Papercut_SDXL](https://huggingface.co/TheLastBen/Papercut_SDXL) LoRA and fuse it with the TCD-LoRA with the [`~loaders.UNet2DConditionLoadersMixin.set_adapters`] method.
 
 > [!TIP]
-> Check out the [Merge LoRAs](merge_loras) guide to learn more about efficient merging methods.
+> Check out the [Merge LoRAs](../tutorials/using_peft_for_inference#merge) guide to learn more about efficient merging methods.
 
 ```python
 import torch

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

@@ -112,7 +112,7 @@ blurred_mask
 
 ## Popular models
 
-[Stable Diffusion Inpainting](https://huggingface.co/runwayml/stable-diffusion-inpainting), [Stable Diffusion XL (SDXL) Inpainting](https://huggingface.co/diffusers/stable-diffusion-xl-1.0-inpainting-0.1), and [Kandinsky 2.2 Inpainting](https://huggingface.co/kandinsky-community/kandinsky-2-2-decoder-inpaint) are among the most popular models for inpainting. SDXL typically produces higher resolution images than Stable Diffusion v1.5, and Kandinsky 2.2 is also capable of generating high-quality images.
+[Stable Diffusion Inpainting](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-inpainting), [Stable Diffusion XL (SDXL) Inpainting](https://huggingface.co/diffusers/stable-diffusion-xl-1.0-inpainting-0.1), and [Kandinsky 2.2 Inpainting](https://huggingface.co/kandinsky-community/kandinsky-2-2-decoder-inpaint) are among the most popular models for inpainting. SDXL typically produces higher resolution images than Stable Diffusion v1.5, and Kandinsky 2.2 is also capable of generating high-quality images.
 
 ### Stable Diffusion Inpainting
 
@@ -124,7 +124,7 @@ from diffusers import AutoPipelineForInpainting
 from diffusers.utils import load_image, make_image_grid
 
 pipeline = AutoPipelineForInpainting.from_pretrained(
-    "runwayml/stable-diffusion-inpainting", torch_dtype=torch.float16, variant="fp16"
+    "stable-diffusion-v1-5/stable-diffusion-inpainting", torch_dtype=torch.float16, variant="fp16"
 )
 pipeline.enable_model_cpu_offload()
 # remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
@@ -244,7 +244,7 @@ make_image_grid([init_image, image], rows=1, cols=2)
 ```
 
 </hfoption>
-<hfoption id="runwayml/stable-diffusion-inpainting">
+<hfoption id="stable-diffusion-v1-5/stable-diffusion-inpainting">
 
 ```py
 import torch
@@ -252,7 +252,7 @@ from diffusers import AutoPipelineForInpainting
 from diffusers.utils import load_image, make_image_grid
 
 pipeline = AutoPipelineForInpainting.from_pretrained(
-    "runwayml/stable-diffusion-inpainting", torch_dtype=torch.float16, variant="fp16"
+    "stable-diffusion-v1-5/stable-diffusion-inpainting", torch_dtype=torch.float16, variant="fp16"
 )
 pipeline.enable_model_cpu_offload()
 # remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
@@ -278,7 +278,7 @@ make_image_grid([init_image, image], rows=1, cols=2)
   </div>
   <div>
     <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint-specific.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">runwayml/stable-diffusion-inpainting</figcaption>
+    <figcaption class="mt-2 text-center text-sm text-gray-500">stable-diffusion-v1-5/stable-diffusion-inpainting</figcaption>
   </div>
 </div>
 
@@ -308,7 +308,7 @@ make_image_grid([init_image, image], rows=1, cols=2)
 ```
 
 </hfoption>
-<hfoption id="runwayml/stable-diffusion-inpaint">
+<hfoption id="stable-diffusion-v1-5/stable-diffusion-inpaint">
 
 ```py
 import torch
@@ -316,7 +316,7 @@ from diffusers import AutoPipelineForInpainting
 from diffusers.utils import load_image, make_image_grid
 
 pipeline = AutoPipelineForInpainting.from_pretrained(
-    "runwayml/stable-diffusion-inpainting", torch_dtype=torch.float16, variant="fp16"
+    "stable-diffusion-v1-5/stable-diffusion-inpainting", torch_dtype=torch.float16, variant="fp16"
 )
 pipeline.enable_model_cpu_offload()
 # remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
@@ -340,7 +340,7 @@ make_image_grid([init_image, image], rows=1, cols=2)
   </div>
   <div>
     <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/specific-inpaint-basic.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">runwayml/stable-diffusion-inpainting</figcaption>
+    <figcaption class="mt-2 text-center text-sm text-gray-500">stable-diffusion-v1-5/stable-diffusion-inpainting</figcaption>
   </div>
 </div>
 
@@ -358,7 +358,7 @@ from diffusers.utils import load_image, make_image_grid
 
 device = "cuda"
 pipeline = AutoPipelineForInpainting.from_pretrained(
-    "runwayml/stable-diffusion-inpainting",
+    "stable-diffusion-v1-5/stable-diffusion-inpainting",
     torch_dtype=torch.float16,
     variant="fp16"
 )
@@ -396,7 +396,7 @@ from diffusers import AutoPipelineForInpainting
 from diffusers.utils import load_image, make_image_grid
 
 pipeline = AutoPipelineForInpainting.from_pretrained(
-    "runwayml/stable-diffusion-inpainting", torch_dtype=torch.float16, variant="fp16"
+    "stable-diffusion-v1-5/stable-diffusion-inpainting", torch_dtype=torch.float16, variant="fp16"
 )
 pipeline.enable_model_cpu_offload()
 # remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
@@ -441,7 +441,7 @@ from diffusers import AutoPipelineForInpainting
 from diffusers.utils import load_image, make_image_grid
 
 pipeline = AutoPipelineForInpainting.from_pretrained(
-    "runwayml/stable-diffusion-inpainting", torch_dtype=torch.float16, variant="fp16"
+    "stable-diffusion-v1-5/stable-diffusion-inpainting", torch_dtype=torch.float16, variant="fp16"
 )
 pipeline.enable_model_cpu_offload()
 # remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
@@ -481,7 +481,7 @@ from diffusers import AutoPipelineForInpainting
 from diffusers.utils import load_image, make_image_grid
 
 pipeline = AutoPipelineForInpainting.from_pretrained(
-    "runwayml/stable-diffusion-inpainting", torch_dtype=torch.float16, variant="fp16"
+    "stable-diffusion-v1-5/stable-diffusion-inpainting", torch_dtype=torch.float16, variant="fp16"
 )
 pipeline.enable_model_cpu_offload()
 # remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
@@ -606,7 +606,7 @@ from diffusers import AutoPipelineForInpainting, AutoPipelineForImage2Image
 from diffusers.utils import load_image, make_image_grid
 
 pipeline = AutoPipelineForInpainting.from_pretrained(
-    "runwayml/stable-diffusion-inpainting", torch_dtype=torch.float16, variant="fp16"
+    "stable-diffusion-v1-5/stable-diffusion-inpainting", torch_dtype=torch.float16, variant="fp16"
 )
 pipeline.enable_model_cpu_offload()
 # remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
@@ -683,7 +683,7 @@ from diffusers import AutoPipelineForInpainting
 from diffusers.utils import make_image_grid
 
 pipeline = AutoPipelineForInpainting.from_pretrained(
-    "runwayml/stable-diffusion-inpainting", torch_dtype=torch.float16,
+    "stable-diffusion-v1-5/stable-diffusion-inpainting", torch_dtype=torch.float16,
 )
 pipeline.enable_model_cpu_offload()
 # remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
@@ -714,7 +714,7 @@ controlnet = ControlNetModel.from_pretrained("lllyasviel/control_v11p_sd15_inpai
 
 # pass ControlNet to the pipeline
 pipeline = StableDiffusionControlNetInpaintPipeline.from_pretrained(
-    "runwayml/stable-diffusion-inpainting", controlnet=controlnet, torch_dtype=torch.float16, variant="fp16"
+    "stable-diffusion-v1-5/stable-diffusion-inpainting", controlnet=controlnet, torch_dtype=torch.float16, variant="fp16"
 )
 pipeline.enable_model_cpu_offload()
 # remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed

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

@@ -280,7 +280,7 @@ refiner = DiffusionPipeline.from_pretrained(
 ```
 
 > [!WARNING]
-> You can use SDXL refiner with a different base model. For example, you can use the [Hunyuan-DiT](../../api/pipelines/hunyuandit) or [PixArt-Sigma](../../api/pipelines/pixart_sigma) pipelines to generate images with better prompt adherence. Once you have generated an image, you can pass it to the SDXL refiner model to enhance final generation quality.
+> You can use SDXL refiner with a different base model. For example, you can use the [Hunyuan-DiT](../api/pipelines/hunyuandit) or [PixArt-Sigma](../api/pipelines/pixart_sigma) pipelines to generate images with better prompt adherence. Once you have generated an image, you can pass it to the SDXL refiner model to enhance final generation quality.
 
 Generate an image from the base model, and set the model output to **latent** space:
 

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

@@ -10,423 +10,96 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
 specific language governing permissions and limitations under the License.
 -->
 
-# Prompt techniques
-
 [[open-in-colab]]
 
-Prompts are important because they describe what you want a diffusion model to generate. The best prompts are detailed, specific, and well-structured to help the model realize your vision. But crafting a great prompt takes time and effort and sometimes it may not be enough because language and words can be imprecise. This is where you need to boost your prompt with other techniques, such as prompt enhancing and prompt weighting, to get the results you want.
+# Prompting
 
-This guide will show you how you can use these prompt techniques to generate high-quality images with lower effort and adjust the weight of certain keywords in a prompt.
+Prompts describes what a model should generate. Good prompts are detailed, specific, and structured and they generate better images and videos.
 
-## Prompt engineering
+This guide shows you how to write effective prompts and introduces techniques that make them stronger.
 
-> [!TIP]
-> This is not an exhaustive guide on prompt engineering, but it will help you understand the necessary parts of a good prompt. We encourage you to continue experimenting with different prompts and combine them in new ways to see what works best. As you write more prompts, you'll develop an intuition for what works and what doesn't!
+## Writing good prompts
 
-New diffusion models do a pretty good job of generating high-quality images from a basic prompt, but it is still important to create a well-written prompt to get the best results. Here are a few tips for writing a good prompt:
+Every effective prompt needs three core elements.
 
-1. What is the image *medium*? Is it a photo, a painting, a 3D illustration, or something else?
-2. What is the image *subject*? Is it a person, animal, object, or scene?
-3. What *details* would you like to see in the image? This is where you can get really creative and have a lot of fun experimenting with different words to bring your image to life. For example, what is the lighting like? What is the vibe and aesthetic? What kind of art or illustration style are you looking for? The more specific and precise words you use, the better the model will understand what you want to generate.
+1. <span class="underline decoration-sky-500 decoration-2 underline-offset-4">Subject</span> - what you want to generate. Start your prompt here.
+2. <span class="underline decoration-pink-500 decoration-2 underline-offset-4">Style</span> - the medium or aesthetic. How should it look?
+3. <span class="underline decoration-green-500 decoration-2 underline-offset-4">Context</span> - details about actions, setting, and mood.
+
+Use these elements as a structured narrative, not a keyword list. Modern models understand language better than keyword matching. Start simple, then add details.
+
+Context is especially important for creating better prompts. Try adding lighting, artistic details, and mood.
 
 <div class="flex gap-4">
-  <div>
-    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/plain-prompt.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">"A photo of a banana-shaped couch in a living room"</figcaption>
+  <div class="flex-1 text-center">
+    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/ok-prompt.png" class="w-full h-auto object-cover rounded-lg">
+    <figcaption class="mt-2 text-sm text-gray-500">A <span class="underline decoration-sky-500 decoration-2 underline-offset-1">cute cat</span> <span class="underline decoration-pink-500 decoration-2 underline-offset-1">lounges on a leaf in a pool during a peaceful summer afternoon</span>, in <span class="underline decoration-green-500 decoration-2 underline-offset-1">lofi art style, illustration</span>.</figcaption>
   </div>
-  <div>
-    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/detail-prompt.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">"A vibrant yellow banana-shaped couch sits in a cozy living room, its curve cradling a pile of colorful cushions. on the wooden floor, a patterned rug adds a touch of eclectic charm, and a potted plant sits in the corner, reaching towards the sunlight filtering through the windows"</figcaption>
+  <div class="flex-1 text-center">
+    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/better-prompt.png" class="w-full h-auto object-cover rounded-lg"/>
+    <figcaption class="mt-2 text-sm text-gray-500">A cute cat lounges on a floating leaf in a sparkling pool during a peaceful summer afternoon. Clear reflections ripple across the water, with sunlight casting soft, smooth highlights. The illustration is detailed and polished, with elegant lines and harmonious colors, evoking a relaxing, serene, and whimsical lofi mood, anime-inspired and visually comforting.</figcaption>
   </div>
 </div>
 
-## Prompt enhancing with GPT2
-
-Prompt enhancing is a technique for quickly improving prompt quality without spending too much effort constructing one. It uses a model like GPT2 pretrained on Stable Diffusion text prompts to automatically enrich a prompt with additional important keywords to generate high-quality images.
-
-The technique works by curating a list of specific keywords and forcing the model to generate those words to enhance the original prompt. This way, your prompt can be "a cat" and GPT2 can enhance the prompt to "cinematic film still of a cat basking in the sun on a roof in Turkey, highly detailed, high budget hollywood movie, cinemascope, moody, epic, gorgeous, film grain quality sharp focus beautiful detailed intricate stunning amazing epic".
+Be specific and add context. Use photography terms like lens type, focal length, camera angles, and depth of field.
 
 > [!TIP]
-> You should also use a [*offset noise*](https://www.crosslabs.org//blog/diffusion-with-offset-noise) LoRA to improve the contrast in bright and dark images and create better lighting overall. This [LoRA](https://hf.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/sd_xl_offset_example-lora_1.0.safetensors) is available from [stabilityai/stable-diffusion-xl-base-1.0](https://hf.co/stabilityai/stable-diffusion-xl-base-1.0).
-
-Start by defining certain styles and a list of words (you can check out a more comprehensive list of [words](https://hf.co/LykosAI/GPT-Prompt-Expansion-Fooocus-v2/blob/main/positive.txt) and [styles](https://github.com/lllyasviel/Fooocus/tree/main/sdxl_styles) used by Fooocus) to enhance a prompt with.
-
-```py
-import torch
-from transformers import GenerationConfig, GPT2LMHeadModel, GPT2Tokenizer, LogitsProcessor, LogitsProcessorList
-from diffusers import StableDiffusionXLPipeline
-
-styles = {
-    "cinematic": "cinematic film still of {prompt}, highly detailed, high budget hollywood movie, cinemascope, moody, epic, gorgeous, film grain",
-    "anime": "anime artwork of {prompt}, anime style, key visual, vibrant, studio anime, highly detailed",
-    "photographic": "cinematic photo of {prompt}, 35mm photograph, film, professional, 4k, highly detailed",
-    "comic": "comic of {prompt}, graphic illustration, comic art, graphic novel art, vibrant, highly detailed",
-    "lineart": "line art drawing {prompt}, professional, sleek, modern, minimalist, graphic, line art, vector graphics",
-    "pixelart": " pixel-art {prompt}, low-res, blocky, pixel art style, 8-bit graphics",
-}
-
-words = [
-    "aesthetic", "astonishing", "beautiful", "breathtaking", "composition", "contrasted", "epic", "moody", "enhanced",
-    "exceptional", "fascinating", "flawless", "glamorous", "glorious", "illumination", "impressive", "improved",
-    "inspirational", "magnificent", "majestic", "hyperrealistic", "smooth", "sharp", "focus", "stunning", "detailed",
-    "intricate", "dramatic", "high", "quality", "perfect", "light", "ultra", "highly", "radiant", "satisfying",
-    "soothing", "sophisticated", "stylish", "sublime", "terrific", "touching", "timeless", "wonderful", "unbelievable",
-    "elegant", "awesome", "amazing", "dynamic", "trendy",
-]
-```
-
-You may have noticed in the `words` list, there are certain words that can be paired together to create something more meaningful. For example, the words "high" and "quality" can be combined to create "high quality". Let's pair these words together and remove the words that can't be paired.
-
-```py
-word_pairs = ["highly detailed", "high quality", "enhanced quality", "perfect composition", "dynamic light"]
-
-def find_and_order_pairs(s, pairs):
-    words = s.split()
-    found_pairs = []
-    for pair in pairs:
-        pair_words = pair.split()
-        if pair_words[0] in words and pair_words[1] in words:
-            found_pairs.append(pair)
-            words.remove(pair_words[0])
-            words.remove(pair_words[1])
-
-    for word in words[:]:
-        for pair in pairs:
-            if word in pair.split():
-                words.remove(word)
-                break
-    ordered_pairs = ", ".join(found_pairs)
-    remaining_s = ", ".join(words)
-    return ordered_pairs, remaining_s
-```
-
-Next, implement a custom [`~transformers.LogitsProcessor`] class that assigns tokens in the `words` list a value of 0 and assigns tokens not in the `words` list a negative value so they aren't picked during generation. This way, generation is biased towards words in the `words` list. After a word from the list is used, it is also assigned a negative value so it isn't picked again.
-
-```py
-class CustomLogitsProcessor(LogitsProcessor):
-    def __init__(self, bias):
-        super().__init__()
-        self.bias = bias
-
-    def __call__(self, input_ids, scores):
-        if len(input_ids.shape) == 2:
-            last_token_id = input_ids[0, -1]
-            self.bias[last_token_id] = -1e10
-        return scores + self.bias
-
-word_ids = [tokenizer.encode(word, add_prefix_space=True)[0] for word in words]
-bias = torch.full((tokenizer.vocab_size,), -float("Inf")).to("cuda")
-bias[word_ids] = 0
-processor = CustomLogitsProcessor(bias)
-processor_list = LogitsProcessorList([processor])
-```
-
-Combine the prompt and the `cinematic` style prompt defined in the `styles` dictionary earlier.
-
-```py
-prompt = "a cat basking in the sun on a roof in Turkey"
-style = "cinematic"
-
-prompt = styles[style].format(prompt=prompt)
-prompt
-"cinematic film still of a cat basking in the sun on a roof in Turkey, highly detailed, high budget hollywood movie, cinemascope, moody, epic, gorgeous, film grain"
-```
-
-Load a GPT2 tokenizer and model from the [Gustavosta/MagicPrompt-Stable-Diffusion](https://huggingface.co/Gustavosta/MagicPrompt-Stable-Diffusion) checkpoint (this specific checkpoint is trained to generate prompts) to enhance the prompt.
-
-```py
-tokenizer = GPT2Tokenizer.from_pretrained("Gustavosta/MagicPrompt-Stable-Diffusion")
-model = GPT2LMHeadModel.from_pretrained("Gustavosta/MagicPrompt-Stable-Diffusion", torch_dtype=torch.float16).to(
-    "cuda"
-)
-model.eval()
-
-inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
-token_count = inputs["input_ids"].shape[1]
-max_new_tokens = 50 - token_count
-
-generation_config = GenerationConfig(
-    penalty_alpha=0.7,
-    top_k=50,
-    eos_token_id=model.config.eos_token_id,
-    pad_token_id=model.config.eos_token_id,
-    pad_token=model.config.pad_token_id,
-    do_sample=True,
-)
-
-with torch.no_grad():
-    generated_ids = model.generate(
-        input_ids=inputs["input_ids"],
-        attention_mask=inputs["attention_mask"],
-        max_new_tokens=max_new_tokens,
-        generation_config=generation_config,
-        logits_processor=proccesor_list,
-    )
-```
-
-Then you can combine the input prompt and the generated prompt. Feel free to take a look at what the generated prompt (`generated_part`) is, the word pairs that were found (`pairs`), and the remaining words (`words`). This is all packed together in the `enhanced_prompt`.
-
-```py
-output_tokens = [tokenizer.decode(generated_id, skip_special_tokens=True) for generated_id in generated_ids]
-input_part, generated_part = output_tokens[0][: len(prompt)], output_tokens[0][len(prompt) :]
-pairs, words = find_and_order_pairs(generated_part, word_pairs)
-formatted_generated_part = pairs + ", " + words
-enhanced_prompt = input_part + ", " + formatted_generated_part
-enhanced_prompt
-["cinematic film still of a cat basking in the sun on a roof in Turkey, highly detailed, high budget hollywood movie, cinemascope, moody, epic, gorgeous, film grain quality sharp focus beautiful detailed intricate stunning amazing epic"]
-```
-
-Finally, load a pipeline and the offset noise LoRA with a *low weight* to generate an image with the enhanced prompt.
-
-```py
-pipeline = StableDiffusionXLPipeline.from_pretrained(
-    "RunDiffusion/Juggernaut-XL-v9", torch_dtype=torch.float16, variant="fp16"
-).to("cuda")
-
-pipeline.load_lora_weights(
-    "stabilityai/stable-diffusion-xl-base-1.0",
-    weight_name="sd_xl_offset_example-lora_1.0.safetensors",
-    adapter_name="offset",
-)
-pipeline.set_adapters(["offset"], adapter_weights=[0.2])
-
-image = pipeline(
-    enhanced_prompt,
-    width=1152,
-    height=896,
-    guidance_scale=7.5,
-    num_inference_steps=25,
-).images[0]
-image
-```
-
-<div class="flex gap-4">
-  <div>
-    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/non-enhanced-prompt.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">"a cat basking in the sun on a roof in Turkey"</figcaption>
-  </div>
-  <div>
-    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/enhanced-prompt.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">"cinematic film still of a cat basking in the sun on a roof in Turkey, highly detailed, high budget hollywood movie, cinemascope, moody, epic, gorgeous, film grain"</figcaption>
-  </div>
-</div>
+> Try a [prompt enhancer](https://huggingface.co/models?sort=downloads&search=prompt+enhancer) to help improve your prompt structure.
 
 ## Prompt weighting
 
-Prompt weighting provides a way to emphasize or de-emphasize certain parts of a prompt, allowing for more control over the generated image. A prompt can include several concepts, which gets turned into contextualized text embeddings. The embeddings are used by the model to condition its cross-attention layers to generate an image (read the Stable Diffusion [blog post](https://huggingface.co/blog/stable_diffusion) to learn more about how it works).
+Prompt weighting makes some words stronger and others weaker. It scales attention scores so you control how much influence each concept has.
 
-Prompt weighting works by increasing or decreasing the scale of the text embedding vector that corresponds to its concept in the prompt because you may not necessarily want the model to focus on all concepts equally. The easiest way to prepare the prompt embeddings is to use [Stable Diffusion Long Prompt Weighted Embedding](https://github.com/xhinker/sd_embed) (sd_embed). Once you have the prompt-weighted embeddings, you can pass them to any pipeline that has a [prompt_embeds](https://huggingface.co/docs/diffusers/en/api/pipelines/stable_diffusion/text2img#diffusers.StableDiffusionPipeline.__call__.prompt_embeds) (and optionally [negative_prompt_embeds](https://huggingface.co/docs/diffusers/en/api/pipelines/stable_diffusion/text2img#diffusers.StableDiffusionPipeline.__call__.negative_prompt_embeds)) parameter, such as [`StableDiffusionPipeline`], [`StableDiffusionControlNetPipeline`], and [`StableDiffusionXLPipeline`].
+Diffusers handles this through `prompt_embeds` and `pooled_prompt_embeds` arguments which take scaled text embedding vectors. Use the [sd_embed](https://github.com/xhinker/sd_embed) library to generate these embeddings. It also supports longer prompts.
 
-> [!TIP]
-> If your favorite pipeline doesn't have a `prompt_embeds` parameter, please open an [issue](https://github.com/huggingface/diffusers/issues/new/choose) so we can add it!
-
-This guide will show you how to weight your prompts with sd_embed.
-
-Before you begin, make sure you have the latest version of sd_embed installed:
-
-```bash
-pip install git+https://github.com/xhinker/sd_embed.git@main
-```
-
-For this example, let's use [`StableDiffusionXLPipeline`].
+> [!NOTE]
+> The sd_embed library only supports Stable Diffusion, Stable Diffusion XL, Stable Diffusion 3, Stable Cascade, and Flux. Prompt weighting doesn't necessarily help for newer models like Flux which already has very good prompt adherence.
 
 ```py
-from diffusers import StableDiffusionXLPipeline, UniPCMultistepScheduler
-import torch
-
-pipe = StableDiffusionXLPipeline.from_pretrained("Lykon/dreamshaper-xl-1-0", torch_dtype=torch.float16)
-pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
-pipe.to("cuda")
+!uv pip install git+https://github.com/xhinker/sd_embed.git@main
 ```
 
-To upweight or downweight a concept, surround the text with parentheses. More parentheses applies a heavier weight on the text. You can also append a numerical multiplier to the text to indicate how much you want to increase or decrease its weights by.
+Format weighted text with numerical multipliers or parentheses. More parentheses mean stronger weighting.
 
 | format | multiplier |
 |---|---|
-| `(hippo)` | increase by 1.1x |
-| `((hippo))` | increase by 1.21x |
-| `(hippo:1.5)` | increase by 1.5x |
-| `(hippo:0.5)` | decrease by 4x |
+| `(cat)` | increase by 1.1x |
+| `((cat))` | increase by 1.21x |
+| `(cat:1.5)` | increase by 1.5x |
+| `(cat:0.5)` | decrease by 4x |
 
-Create a prompt and use a combination of parentheses and numerical multipliers to upweight various text.
+Create a weighted prompt and pass it to [get_weighted_text_embeddings_sdxl](https://github.com/xhinker/sd_embed/blob/4a47f71150a22942fa606fb741a1c971d95ba56f/src/sd_embed/embedding_funcs.py#L405) to generate embeddings.
+
+> [!TIP]
+> You could also pass negative prompts to `negative_prompt_embeds` and `negative_pooled_prompt_embeds`.
 
 ```py
+import torch
+from diffusers import DiffusionPipeline
 from sd_embed.embedding_funcs import get_weighted_text_embeddings_sdxl
 
-prompt = """A whimsical and creative image depicting a hybrid creature that is a mix of a waffle and a hippopotamus. 
-This imaginative creature features the distinctive, bulky body of a hippo, 
-but with a texture and appearance resembling a golden-brown, crispy waffle. 
-The creature might have elements like waffle squares across its skin and a syrup-like sheen. 
-It's set in a surreal environment that playfully combines a natural water habitat of a hippo with elements of a breakfast table setting, 
-possibly including oversized utensils or plates in the background. 
-The image should evoke a sense of playful absurdity and culinary fantasy.
-"""
-
-neg_prompt = """\
-skin spots,acnes,skin blemishes,age spot,(ugly:1.2),(duplicate:1.2),(morbid:1.21),(mutilated:1.2),\
-(tranny:1.2),mutated hands,(poorly drawn hands:1.5),blurry,(bad anatomy:1.2),(bad proportions:1.3),\
-extra limbs,(disfigured:1.2),(missing arms:1.2),(extra legs:1.2),(fused fingers:1.5),\
-(too many fingers:1.5),(unclear eyes:1.2),lowers,bad hands,missing fingers,extra digit,\
-bad hands,missing fingers,(extra arms and legs),(worst quality:2),(low quality:2),\
-(normal quality:2),lowres,((monochrome)),((grayscale))
-"""
-```
-
-Use the `get_weighted_text_embeddings_sdxl` function to generate the prompt embeddings and the negative prompt embeddings. It'll also generated the pooled and negative pooled prompt embeddings since you're using the SDXL model.
-
-> [!TIP]
-> You can safely ignore the error message below about the token index length exceeding the models maximum sequence length. All your tokens will be used in the embedding process.
->
-> ```
-> Token indices sequence length is longer than the specified maximum sequence length for this model
-> ```
-
-```py
-( 
-  prompt_embeds,
-  prompt_neg_embeds,
-  pooled_prompt_embeds,
-  negative_pooled_prompt_embeds
-) = get_weighted_text_embeddings_sdxl(
-    pipe,
-    prompt=prompt,
-    neg_prompt=neg_prompt
+pipeline = DiffusionPipeline.from_pretrained(
+    "Lykon/dreamshaper-xl-1-0", torch_dtype=torch.bfloat16, device_map="cuda"
 )
 
-image = pipe(
-    prompt_embeds=prompt_embeds,
-    negative_prompt_embeds=prompt_neg_embeds,
-    pooled_prompt_embeds=pooled_prompt_embeds,
-    negative_pooled_prompt_embeds=negative_pooled_prompt_embeds,
-    num_inference_steps=30,
-    height=1024,
-    width=1024 + 512,
-    guidance_scale=4.0,
-    generator=torch.Generator("cuda").manual_seed(2)
-).images[0]
-image
+prompt = """
+A (cute cat:1.4) lounges on a (floating leaf:1.2) in a (sparkling pool:1.1) during a peaceful summer afternoon.
+Gentle ripples reflect pastel skies, while (sunlight:1.1) casts soft highlights. The illustration is smooth and polished
+with elegant, sketchy lines and subtle gradients, evoking a ((whimsical, nostalgic, dreamy lofi atmosphere:2.0)), 
+(anime-inspired:1.6), calming, comforting, and visually serene.
+"""
+
+prompt_embeds, _, pooled_prompt_embeds, *_ = get_weighted_text_embeddings_sdxl(pipeline, prompt=prompt)
+```
+
+Pass the embeddings to `prompt_embeds` and `pooled_prompt_embeds` to generate your image.
+
+```py
+image = pipeline(prompt_embeds=prompt_embeds, pooled_prompt_embeds=pooled_prompt_embeds).images[0]
 ```
 
 <div class="flex justify-center">
-  <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/sd_embed_sdxl.png"/>
+  <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/prompt-embed-sdxl.png"/>
 </div>
 
-> [!TIP]
-> Refer to the [sd_embed](https://github.com/xhinker/sd_embed) repository for additional details about long prompt weighting for FLUX.1, Stable Cascade, and Stable Diffusion 1.5.
-
-### Textual inversion
-
-[Textual inversion](../training/text_inversion) is a technique for learning a specific concept from some images which you can use to generate new images conditioned on that concept.
-
-Create a pipeline and use the [`~loaders.TextualInversionLoaderMixin.load_textual_inversion`] function to load the textual inversion embeddings (feel free to browse the [Stable Diffusion Conceptualizer](https://huggingface.co/spaces/sd-concepts-library/stable-diffusion-conceptualizer) for 100+ trained concepts):
-
-```py
-import torch
-from diffusers import StableDiffusionPipeline
-
-pipe = StableDiffusionPipeline.from_pretrained(
-  "stable-diffusion-v1-5/stable-diffusion-v1-5",
-  torch_dtype=torch.float16,
-).to("cuda")
-pipe.load_textual_inversion("sd-concepts-library/midjourney-style")
-```
-
-Add the `<midjourney-style>` text to the prompt to trigger the textual inversion.
-
-```py
-from sd_embed.embedding_funcs import get_weighted_text_embeddings_sd15
-
-prompt = """<midjourney-style> A whimsical and creative image depicting a hybrid creature that is a mix of a waffle and a hippopotamus. 
-This imaginative creature features the distinctive, bulky body of a hippo, 
-but with a texture and appearance resembling a golden-brown, crispy waffle. 
-The creature might have elements like waffle squares across its skin and a syrup-like sheen. 
-It's set in a surreal environment that playfully combines a natural water habitat of a hippo with elements of a breakfast table setting, 
-possibly including oversized utensils or plates in the background. 
-The image should evoke a sense of playful absurdity and culinary fantasy.
-"""
-
-neg_prompt = """\
-skin spots,acnes,skin blemishes,age spot,(ugly:1.2),(duplicate:1.2),(morbid:1.21),(mutilated:1.2),\
-(tranny:1.2),mutated hands,(poorly drawn hands:1.5),blurry,(bad anatomy:1.2),(bad proportions:1.3),\
-extra limbs,(disfigured:1.2),(missing arms:1.2),(extra legs:1.2),(fused fingers:1.5),\
-(too many fingers:1.5),(unclear eyes:1.2),lowers,bad hands,missing fingers,extra digit,\
-bad hands,missing fingers,(extra arms and legs),(worst quality:2),(low quality:2),\
-(normal quality:2),lowres,((monochrome)),((grayscale))
-"""
-```
-
-Use the `get_weighted_text_embeddings_sd15` function to generate the prompt embeddings and the negative prompt embeddings.
-
-```py
-( 
-  prompt_embeds,
-  prompt_neg_embeds,
-) = get_weighted_text_embeddings_sd15(
-    pipe,
-    prompt=prompt,
-    neg_prompt=neg_prompt
-)
-
-image = pipe(
-    prompt_embeds=prompt_embeds,
-    negative_prompt_embeds=prompt_neg_embeds,
-    height=768,
-    width=896,
-    guidance_scale=4.0,
-    generator=torch.Generator("cuda").manual_seed(2)
-).images[0]
-image
-```
-
-<div class="flex justify-center">
-  <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/sd_embed_textual_inversion.png"/>
-</div>
-
-### DreamBooth
-
-[DreamBooth](../training/dreambooth) is a technique for generating contextualized images of a subject given just a few images of the subject to train on. It is similar to textual inversion, but DreamBooth trains the full model whereas textual inversion only fine-tunes the text embeddings. This means you should use [`~DiffusionPipeline.from_pretrained`] to load the DreamBooth model (feel free to browse the [Stable Diffusion Dreambooth Concepts Library](https://huggingface.co/sd-dreambooth-library) for 100+ trained models):
-
-```py
-import torch
-from diffusers import DiffusionPipeline, UniPCMultistepScheduler
-
-pipe = DiffusionPipeline.from_pretrained("sd-dreambooth-library/dndcoverart-v1", torch_dtype=torch.float16).to("cuda")
-pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
-```
-
-Depending on the model you use, you'll need to incorporate the model's unique identifier into your prompt. For example, the `dndcoverart-v1` model uses the identifier `dndcoverart`:
-
-```py
-from sd_embed.embedding_funcs import get_weighted_text_embeddings_sd15
-
-prompt = """dndcoverart of A whimsical and creative image depicting a hybrid creature that is a mix of a waffle and a hippopotamus. 
-This imaginative creature features the distinctive, bulky body of a hippo, 
-but with a texture and appearance resembling a golden-brown, crispy waffle. 
-The creature might have elements like waffle squares across its skin and a syrup-like sheen. 
-It's set in a surreal environment that playfully combines a natural water habitat of a hippo with elements of a breakfast table setting, 
-possibly including oversized utensils or plates in the background. 
-The image should evoke a sense of playful absurdity and culinary fantasy.
-"""
-
-neg_prompt = """\
-skin spots,acnes,skin blemishes,age spot,(ugly:1.2),(duplicate:1.2),(morbid:1.21),(mutilated:1.2),\
-(tranny:1.2),mutated hands,(poorly drawn hands:1.5),blurry,(bad anatomy:1.2),(bad proportions:1.3),\
-extra limbs,(disfigured:1.2),(missing arms:1.2),(extra legs:1.2),(fused fingers:1.5),\
-(too many fingers:1.5),(unclear eyes:1.2),lowers,bad hands,missing fingers,extra digit,\
-bad hands,missing fingers,(extra arms and legs),(worst quality:2),(low quality:2),\
-(normal quality:2),lowres,((monochrome)),((grayscale))
-"""
-
-(
-    prompt_embeds
-    , prompt_neg_embeds
-) = get_weighted_text_embeddings_sd15(
-    pipe
-    , prompt = prompt
-    , neg_prompt = neg_prompt
-)
-```
-
-<div class="flex justify-center">
-  <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/sd_embed_dreambooth.png"/>
-</div>
+Prompt weighting works with [Textual inversion](./textual_inversion_inference) and [DreamBooth](./dreambooth) adapters too.

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

@@ -280,5 +280,5 @@ This is really what 🧨 Diffusers is designed for: to make it intuitive and eas
 
 For your next steps, feel free to:
 
-* Learn how to [build and contribute a pipeline](../using-diffusers/contribute_pipeline) to 🧨 Diffusers. We can't wait and see what you'll come up with!
+* Learn how to [build and contribute a pipeline](../conceptual/contribution) to 🧨 Diffusers. We can't wait and see what you'll come up with!
 * Explore [existing pipelines](../api/pipelines/overview) in the library, and see if you can deconstruct and build a pipeline from scratch using the models and schedulers separately.

docs/source/ko/optimization/torch2.0.md

@@ -173,7 +173,7 @@ mask_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data
 init_image = download_image(img_url).resize((512, 512))
 mask_image = download_image(mask_url).resize((512, 512))
 
-path = "runwayml/stable-diffusion-inpainting"
+path = "stable-diffusion-v1-5/stable-diffusion-inpainting"
 
 run_compile = True  # Set True / False
 

docs/source/ko/training/adapt_a_model.md

@@ -28,12 +28,12 @@ pipeline.unet.config["in_channels"]
 4
 ```
 
-인페인팅은 입력 샘플에 9개의 채널이 필요합니다. [`runwayml/stable-diffusion-inpainting`](https://huggingface.co/runwayml/stable-diffusion-inpainting)와 같은 사전학습된 인페인팅 모델에서 이 값을 확인할 수 있습니다:
+인페인팅은 입력 샘플에 9개의 채널이 필요합니다. [`stable-diffusion-v1-5/stable-diffusion-inpainting`](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-inpainting)와 같은 사전학습된 인페인팅 모델에서 이 값을 확인할 수 있습니다:
 
 ```py
 from diffusers import StableDiffusionPipeline
 
-pipeline = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-inpainting")
+pipeline = StableDiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-inpainting")
 pipeline.unet.config["in_channels"]
 9
 ```

docs/source/ko/using-diffusers/inpaint.md

@@ -14,7 +14,7 @@ specific language governing permissions and limitations under the License.
 
 [[open-in-colab]]
 
-[`StableDiffusionInpaintPipeline`]은 마스크와 텍스트 프롬프트를 제공하여 이미지의 특정 부분을 편집할 수 있도록 합니다. 이 기능은 인페인팅 작업을 위해 특별히 훈련된 [`runwayml/stable-diffusion-inpainting`](https://huggingface.co/runwayml/stable-diffusion-inpainting)과 같은 Stable Diffusion 버전을 사용합니다.
+[`StableDiffusionInpaintPipeline`]은 마스크와 텍스트 프롬프트를 제공하여 이미지의 특정 부분을 편집할 수 있도록 합니다. 이 기능은 인페인팅 작업을 위해 특별히 훈련된 [`stable-diffusion-v1-5/stable-diffusion-inpainting`](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-inpainting)과 같은 Stable Diffusion 버전을 사용합니다.
 
 먼저 [`StableDiffusionInpaintPipeline`] 인스턴스를 불러옵니다:
 
@@ -27,7 +27,7 @@ from io import BytesIO
 from diffusers import StableDiffusionInpaintPipeline
 
 pipeline = StableDiffusionInpaintPipeline.from_pretrained(
-    "runwayml/stable-diffusion-inpainting",
+    "stable-diffusion-v1-5/stable-diffusion-inpainting",
     torch_dtype=torch.float16,
 )
 pipeline = pipeline.to("cuda")
@@ -61,12 +61,3 @@ image = pipe(prompt=prompt, image=init_image, mask_image=mask_image).images[0]
 
 > [!WARNING]
 > 이전의 실험적인 인페인팅 구현에서는 품질이 낮은 다른 프로세스를 사용했습니다. 이전 버전과의 호환성을 보장하기 위해 새 모델이 포함되지 않은 사전학습된 파이프라인을 불러오면 이전 인페인팅 방법이 계속 적용됩니다.
-
-아래 Space에서 이미지 인페인팅을 직접 해보세요!
-
-<iframe
-  src="https://runwayml-stable-diffusion-inpainting.hf.space"
-  frameborder="0"
-  width="850"
-  height="500"
-></iframe>

docs/source/pt/_toctree.yml

@@ -1,8 +1,10 @@
 - sections:
-    - local: index
-      title: 🧨 Diffusers
-    - local: quicktour
-      title: Tour rápido
-    - local: installation
-      title: Instalação
+  - local: index
+    title: Diffusers
+  - local: installation
+    title: Instalação
+  - local: quicktour
+    title: Tour rápido
+  - local: stable_diffusion
+    title: Desempenho básico
   title: Primeiros passos

docs/source/pt/index.md

@@ -18,11 +18,11 @@ specific language governing permissions and limitations under the License.
 
 # Diffusers
 
-🤗 Diffusers é uma biblioteca de modelos de difusão de última geração para geração de imagens, áudio e até mesmo estruturas 3D de moléculas. Se você está procurando uma solução de geração simples ou queira treinar seu próprio modelo de difusão, 🤗 Diffusers é uma modular caixa de ferramentas que suporta ambos. Nossa biblioteca é desenhada com foco em [usabilidade em vez de desempenho](conceptual/philosophy#usability-over-performance), [simples em vez de fácil](conceptual/philosophy#simple-over-easy) e [customizável em vez de abstrações](conceptual/philosophy#tweakable-contributorfriendly-over-abstraction).
+🤗 Diffusers é uma biblioteca de modelos de difusão de última geração para geração de imagens, áudio e até mesmo estruturas 3D de moléculas. Se você está procurando uma solução de geração simples ou quer treinar seu próprio modelo de difusão, 🤗 Diffusers é uma caixa de ferramentas modular que suporta ambos. Nossa biblioteca é desenhada com foco em [usabilidade em vez de desempenho](conceptual/philosophy#usability-over-performance), [simples em vez de fácil](conceptual/philosophy#simple-over-easy) e [customizável em vez de abstrações](conceptual/philosophy#tweakable-contributorfriendly-over-abstraction).
 
 A Biblioteca tem três componentes principais:
 
-- Pipelines de última geração para a geração em poucas linhas de código. Têm muitos pipelines no 🤗 Diffusers, veja a tabela no pipeline [Visão geral](api/pipelines/overview) para uma lista completa de pipelines disponíveis e as tarefas que eles resolvem.
+- Pipelines de última geração para a geração em poucas linhas de código. Há muitos pipelines no 🤗 Diffusers, veja a tabela no pipeline [Visão geral](api/pipelines/overview) para uma lista completa de pipelines disponíveis e as tarefas que eles resolvem.
 - Intercambiáveis [agendadores de ruído](api/schedulers/overview) para balancear as compensações entre velocidade e qualidade de geração.
 - [Modelos](api/models) pré-treinados que podem ser usados como se fossem blocos de construção, e combinados com agendadores, para criar seu próprio sistema de difusão de ponta a ponta.
 

docs/source/pt/installation.md

@@ -21,7 +21,7 @@ specific language governing permissions and limitations under the License.
 
 Recomenda-se instalar 🤗 Diffusers em um [ambiente virtual](https://docs.python.org/3/library/venv.html).
 Se você não está familiarizado com ambiente virtuals, veja o [guia](https://packaging.python.org/guides/installing-using-pip-and-virtual-environments/).
-Um ambiente virtual deixa mais fácil gerenciar diferentes projetos e evitar problemas de compatibilidade entre dependências.
+Um ambiente virtual facilita gerenciar diferentes projetos e evitar problemas de compatibilidade entre dependências.
 
 Comece criando um ambiente virtual no diretório do projeto:
 
@@ -100,12 +100,12 @@ pip install -e ".[flax]"
 </jax>
 </frameworkcontent>
 
-Esses comandos irá linkar a pasta que você clonou o repositório e os caminhos das suas bibliotecas Python.
+Esses comandos irão vincular a pasta que você clonou o repositório e os caminhos das suas bibliotecas Python.
 Python então irá procurar dentro da pasta que você clonou além dos caminhos normais das bibliotecas.
 Por exemplo, se o pacote python for tipicamente instalado no `~/anaconda3/envs/main/lib/python3.10/site-packages/`, o Python também irá procurar na pasta `~/diffusers/` que você clonou.
 
 > [!WARNING]
-> Você deve deixar a pasta `diffusers` se você quiser continuar usando a biblioteca.
+> Você deve manter a pasta `diffusers` se quiser continuar usando a biblioteca.
 
 Agora você pode facilmente atualizar seu clone para a última versão do 🤗 Diffusers com o seguinte comando:
 

docs/source/pt/stable_diffusion.md

@@ -0,0 +1,132 @@
+<!--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.
+-->
+
+[[open-in-colab]]
+
+# Desempenho básico
+
+Difusão é um processo aleatório que demanda muito processamento. Você pode precisar executar o [`DiffusionPipeline`] várias vezes antes de obter o resultado desejado. Por isso é importante equilibrar cuidadosamente a velocidade de geração e o uso de memória para iterar mais rápido.
+
+Este guia recomenda algumas dicas básicas de desempenho para usar o [`DiffusionPipeline`]. Consulte a seção de documentação sobre Otimização de Inferência, como [Acelerar inferência](./optimization/fp16) ou [Reduzir uso de memória](./optimization/memory) para guias de desempenho mais detalhados.
+
+## Uso de memória
+
+Reduzir a quantidade de memória usada indiretamente acelera a geração e pode ajudar um modelo a caber no dispositivo.
+
+O método [`~DiffusionPipeline.enable_model_cpu_offload`] move um modelo para a CPU quando não está em uso para economizar memória da GPU.
+
+```py
+import torch
+from diffusers import DiffusionPipeline
+
+pipeline = DiffusionPipeline.from_pretrained(
+  "stabilityai/stable-diffusion-xl-base-1.0",
+  torch_dtype=torch.bfloat16,
+  device_map="cuda"
+)
+pipeline.enable_model_cpu_offload()
+
+prompt = """
+cinematic film still of a cat sipping a margarita in a pool in Palm Springs, California
+highly detailed, high budget hollywood movie, cinemascope, moody, epic, gorgeous, film grain
+"""
+pipeline(prompt).images[0]
+print(f"Memória máxima reservada: {torch.cuda.max_memory_allocated() / 1024**3:.2f} GB")
+```
+
+## Velocidade de inferência
+
+O processo de remoção de ruído é o mais exigente computacionalmente durante a difusão. Métodos que otimizam este processo aceleram a velocidade de inferência. Experimente os seguintes métodos para acelerar.
+
+- Adicione `device_map="cuda"` para colocar o pipeline em uma GPU. Colocar um modelo em um acelerador, como uma GPU, aumenta a velocidade porque realiza computações em paralelo.
+- Defina `torch_dtype=torch.bfloat16` para executar o pipeline em meia-precisão. Reduzir a precisão do tipo de dado aumenta a velocidade porque leva menos tempo para realizar computações em precisão mais baixa.
+
+```py
+import torch
+import time
+from diffusers import DiffusionPipeline, DPMSolverMultistepScheduler
+
+pipeline = DiffusionPipeline.from_pretrained(
+  "stabilityai/stable-diffusion-xl-base-1.0",
+  torch_dtype=torch.bfloat16,
+  device_map="cuda"
+)
+```
+
+- Use um agendador mais rápido, como [`DPMSolverMultistepScheduler`], que requer apenas ~20-25 passos.
+- Defina `num_inference_steps` para um valor menor. Reduzir o número de passos de inferência reduz o número total de computações. No entanto, isso pode resultar em menor qualidade de geração.
+
+```py
+pipeline.scheduler = DPMSolverMultistepScheduler.from_config(pipeline.scheduler.config)
+
+prompt = """
+cinematic film still of a cat sipping a margarita in a pool in Palm Springs, California
+highly detailed, high budget hollywood movie, cinemascope, moody, epic, gorgeous, film grain
+"""
+
+start_time = time.perf_counter()
+image = pipeline(prompt).images[0]
+end_time = time.perf_counter()
+
+print(f"Geração de imagem levou {end_time - start_time:.3f} segundos")
+```
+
+## Qualidade de geração
+
+Muitos modelos de difusão modernos entregam imagens de alta qualidade imediatamente. No entanto, você ainda pode melhorar a qualidade de geração experimentando o seguinte.
+
+- Experimente um prompt mais detalhado e descritivo. Inclua detalhes como o meio da imagem, assunto, estilo e estética. Um prompt negativo também pode ajudar, guiando um modelo para longe de características indesejáveis usando palavras como baixa qualidade ou desfocado.
+
+    ```py
+    import torch
+    from diffusers import DiffusionPipeline
+
+    pipeline = DiffusionPipeline.from_pretrained(
+        "stabilityai/stable-diffusion-xl-base-1.0",
+        torch_dtype=torch.bfloat16,
+        device_map="cuda"
+    )
+
+    prompt = """
+    cinematic film still of a cat sipping a margarita in a pool in Palm Springs, California
+    highly detailed, high budget hollywood movie, cinemascope, moody, epic, gorgeous, film grain
+    """
+    negative_prompt = "low quality, blurry, ugly, poor details"
+    pipeline(prompt, negative_prompt=negative_prompt).images[0]
+    ```
+
+    Para mais detalhes sobre como criar prompts melhores, consulte a documentação sobre [Técnicas de prompt](./using-diffusers/weighted_prompts).
+
+- Experimente um agendador diferente, como [`HeunDiscreteScheduler`] ou [`LMSDiscreteScheduler`], que sacrifica velocidade de geração por qualidade.
+
+    ```py
+    import torch
+    from diffusers import DiffusionPipeline, HeunDiscreteScheduler
+
+    pipeline = DiffusionPipeline.from_pretrained(
+        "stabilityai/stable-diffusion-xl-base-1.0",
+        torch_dtype=torch.bfloat16,
+        device_map="cuda"
+    )
+    pipeline.scheduler = HeunDiscreteScheduler.from_config(pipeline.scheduler.config)
+
+    prompt = """
+    cinematic film still of a cat sipping a margarita in a pool in Palm Springs, California
+    highly detailed, high budget hollywood movie, cinemascope, moody, epic, gorgeous, film grain
+    """
+    negative_prompt = "low quality, blurry, ugly, poor details"
+    pipeline(prompt, negative_prompt=negative_prompt).images[0]
+    ```
+
+## Próximos passos
+
+Diffusers oferece otimizações mais avançadas e poderosas, como [group-offloading](./optimization/memory#group-offloading) e [compilação regional](./optimization/fp16#regional-compilation). Para saber mais sobre como maximizar o desempenho, consulte a seção sobre Otimização de Inferência.

docs/source/zh/training/adapt_a_model.md

@@ -16,12 +16,12 @@ pipeline.unet.config["in_channels"]
 4
 ```
 
-而图像修复任务需要输入样本具有9个通道。您可以在 [`runwayml/stable-diffusion-inpainting`](https://huggingface.co/runwayml/stable-diffusion-inpainting) 这样的预训练修复模型中验证此参数：
+而图像修复任务需要输入样本具有9个通道。您可以在 [`stable-diffusion-v1-5/stable-diffusion-inpainting`](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-inpainting) 这样的预训练修复模型中验证此参数：
 
 ```python
 from diffusers import StableDiffusionPipeline
 
-pipeline = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-inpainting", use_safetensors=True)
+pipeline = StableDiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-inpainting", use_safetensors=True)
 pipeline.unet.config["in_channels"]
 9
 ```

examples/community/README.md

@@ -88,7 +88,7 @@ PIXART-α Controlnet pipeline | Implementation of the controlnet model for pixar
 | FaithDiff Stable Diffusion XL Pipeline | Implementation of [(CVPR 2025) FaithDiff: Unleashing Diffusion Priors for Faithful Image Super-resolutionUnleashing Diffusion Priors for Faithful Image Super-resolution](https://huggingface.co/papers/2411.18824) - FaithDiff is a faithful image super-resolution method that leverages latent diffusion models by actively adapting the diffusion prior and jointly fine-tuning its components (encoder and diffusion model) with an alignment module to ensure high fidelity and structural consistency. | [FaithDiff Stable Diffusion XL Pipeline](#faithdiff-stable-diffusion-xl-pipeline) | [![Hugging Face Models](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Models-blue)](https://huggingface.co/jychen9811/FaithDiff) | [Junyang Chen, Jinshan Pan, Jiangxin Dong, IMAG Lab, (Adapted by Eliseu Silva)](https://github.com/JyChen9811/FaithDiff) |
 | Stable Diffusion 3 InstructPix2Pix Pipeline | Implementation of Stable Diffusion 3 InstructPix2Pix Pipeline | [Stable Diffusion 3 InstructPix2Pix Pipeline](#stable-diffusion-3-instructpix2pix-pipeline) | [![Hugging Face Models](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Models-blue)](https://huggingface.co/BleachNick/SD3_UltraEdit_freeform) [![Hugging Face Models](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Models-blue)](https://huggingface.co/CaptainZZZ/sd3-instructpix2pix) | [Jiayu Zhang](https://github.com/xduzhangjiayu) and [Haozhe Zhao](https://github.com/HaozheZhao)|
 | Flux Kontext multiple images | A modified version of the `FluxKontextPipeline` that supports calling Flux Kontext with multiple reference images.| [Flux Kontext multiple input Pipeline](#flux-kontext-multiple-images) | - |  [Net-Mist](https://github.com/Net-Mist) |
-
+| Flux Fill ControlNet Pipeline | A modified version of the `FluxFillPipeline` and `FluxControlNetInpaintPipeline` that supports Controlnet with Flux Fill model.| [Flux Fill ControlNet Pipeline](#Flux-Fill-ControlNet-Pipeline) | - |  [pratim4dasude](https://github.com/pratim4dasude) |
 
 To load a custom pipeline you just need to pass the `custom_pipeline` argument to `DiffusionPipeline`, as one of the files in `diffusers/examples/community`. Feel free to send a PR with your own pipelines, we will merge them quickly.
 
@@ -1328,7 +1328,7 @@ model = CLIPSegForImageSegmentation.from_pretrained("CIDAS/clipseg-rd64-refined"
 
 # Load Stable Diffusion Inpainting Pipeline with custom pipeline
 pipe = DiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-inpainting",
+    "stable-diffusion-v1-5/stable-diffusion-inpainting",
     custom_pipeline="text_inpainting",
     segmentation_model=model,
     segmentation_processor=processor
@@ -5488,7 +5488,7 @@ Editing at Scale", many thanks to their contribution!
 
 This implementation of Flux Kontext allows users to pass multiple reference images. Each image is encoded separately, and the resulting latent vectors are concatenated.
 
-As explained in Section 3 of [the paper](https://arxiv.org/pdf/2506.15742), the model's sequence concatenation mechanism can extend its capabilities to handle multiple reference images. However, note that the current version of Flux Kontext was not trained for this use case. In practice, stacking along the first axis does not yield correct results, while stacking along the other two axes appears to work.
+As explained in Section 3 of [the paper](https://huggingface.co/papers/2506.15742), the model's sequence concatenation mechanism can extend its capabilities to handle multiple reference images. However, note that the current version of Flux Kontext was not trained for this use case. In practice, stacking along the first axis does not yield correct results, while stacking along the other two axes appears to work.
 
 ## Example Usage
 
@@ -5527,3 +5527,106 @@ images = pipe(
 ).images
 images[0].save("pizzeria.png")
 ```
+
+# Flux Fill ControlNet Pipeline
+
+This implementation of Flux Fill + ControlNet Inpaint combines the fill-style masked editing of FLUX.1-Fill-dev with full ControlNet conditioning. The base image is processed through the Fill model while the ControlNet receives the corresponding conditioning input (depth, canny, pose, etc.), and both outputs are fused during denoising to guide structure and composition.
+
+While FLUX.1-Fill-dev is designed for mask-based edits, it was not originally trained to operate jointly with ControlNet. In practice, this combined setup works well for structured inpainting tasks, though results may vary depending on the conditioning strength and the alignment between the mask and the control input.
+
+## Example Usage
+
+
+```python
+import torch
+from diffusers import (
+    FluxControlNetModel,
+    FluxPriorReduxPipeline,
+)
+from diffusers.utils import load_image
+
+# NEW PIPELINE (updated name)
+from pipline_flux_fill_controlnet_Inpaint import  FluxControlNetFillInpaintPipeline
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+dtype = torch.bfloat16
+
+# Models
+base_model = "black-forest-labs/FLUX.1-Fill-dev"
+controlnet_model = "Shakker-Labs/FLUX.1-dev-ControlNet-Union-Pro-2.0"
+prior_model = "black-forest-labs/FLUX.1-Redux-dev"
+
+# Load ControlNet
+controlnet = FluxControlNetModel.from_pretrained(
+    controlnet_model,
+    torch_dtype=dtype,
+)
+
+# Load Fill + ControlNet Pipeline
+fill_pipe = FluxControlNetFillInpaintPipeline.from_pretrained(
+    base_model,
+    controlnet=controlnet,
+    torch_dtype=dtype,
+).to(device)
+
+# OPTIONAL FP8
+# fill_pipe.transformer.enable_layerwise_casting(
+#     storage_dtype=torch.float8_e4m3fn,
+#     compute_dtype=torch.bfloat16
+# )
+
+#  OPTIONAL Prior Redux
+#pipe_prior_redux = FluxPriorReduxPipeline.from_pretrained(
+#    prior_model,
+#    torch_dtype=dtype,
+#).to(device)
+
+# Inputs
+
+# combined_image = load_image("person_input.png")
+
+
+# 1. Prior conditioning
+#prior_out = pipe_prior_redux(
+#    image=cloth_image,
+#    prompt=cloth_prompt,
+#)
+
+# 2. Fill Inpaint with ControlNet
+
+# canny (0), tile (1), depth (2), blur (3), pose (4), gray (5), low quality (6).
+
+img = load_image(r"imgs/background.jpg")
+mask = load_image(r"imgs/mask.png")
+
+control_image_depth = load_image(r"imgs/dog_depth _2.png")
+
+result = fill_pipe(
+    prompt="a dog on a bench",
+    image=img,
+    mask_image=mask,
+
+    control_image=control_image_depth,
+    control_mode=[2],  # union mode
+    control_guidance_start=0.0,
+    control_guidance_end=0.8,
+    controlnet_conditioning_scale=0.9,
+
+    height=1024,
+    width=1024,
+
+    strength=1.0,
+    guidance_scale=50.0,
+    num_inference_steps=60,
+    max_sequence_length=512,
+
+#    **prior_out,
+)
+
+# result.images[0].save("flux_fill_controlnet_inpaint.png")
+
+from datetime import datetime
+timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
+result.images[0].save(f"flux_fill_controlnet_inpaint_depth{timestamp}.jpg")
+```
+