Merge branch 'main' into sdxl-vae-fix

* new flux fill controlnet inpaint pipline

* Delete src/diffusers/pipelines/flux/pipline_flux_fill_controlnet_Inpaint.py

deleting from main flux pipeline

* Fluc_fill_controlnet community pipline

* Update README.md

* Apply style fixes

.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

.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 != ''
 

.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/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
@@ -73,6 +73,8 @@ jobs:
         run: |
           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: |
@@ -84,7 +86,7 @@ jobs:
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
           pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            -s -v -k "not Flax and not Onnx" \
+             -k "not Flax and not Onnx" \
             --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
             --report-log=tests_pipeline_${{ matrix.module }}_cuda.log \
             tests/pipelines/${{ matrix.module }}
@@ -126,6 +128,8 @@ jobs:
         uv pip install -e ".[quality]"
         uv pip install peft@git+https://github.com/huggingface/peft.git
         uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+        #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+        uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1 
         uv pip install pytest-reportlog
     - name: Environment
       run: python utils/print_env.py
@@ -138,7 +142,7 @@ jobs:
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
         pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "not Flax and not Onnx" \
+          -k "not Flax and not Onnx" \
           --make-reports=tests_torch_${{ matrix.module }}_cuda \
           --report-log=tests_torch_${{ matrix.module }}_cuda.log \
           tests/${{ matrix.module }}
@@ -151,7 +155,7 @@ jobs:
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
         pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -s -v --make-reports=examples_torch_cuda \
+          --make-reports=examples_torch_cuda \
           --report-log=examples_torch_cuda.log \
           examples/
 
@@ -190,6 +194,8 @@ jobs:
     - name: Install dependencies
       run: |
         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
@@ -198,7 +204,7 @@ jobs:
         HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
         RUN_COMPILE: yes
       run: |
-        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
@@ -232,6 +238,8 @@ jobs:
           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: |
@@ -281,6 +289,8 @@ jobs:
           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: |
@@ -293,7 +303,7 @@ jobs:
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
           pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            -s -v -k "not Flax and not Onnx" \
+            -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 \
@@ -358,6 +368,8 @@ jobs:
               uv pip install ${{ join(matrix.config.additional_deps, ' ') }}
           fi
           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
@@ -405,6 +417,8 @@ jobs:
         run: |
           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: |
@@ -531,7 +545,7 @@ jobs:
 #          HF_HOME: /System/Volumes/Data/mnt/cache
 #          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
 #        run: |
-#          ${CONDA_RUN} 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
@@ -587,7 +601,7 @@ jobs:
 #          HF_HOME: /System/Volumes/Data/mnt/cache
 #          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
 #        run: |
-#          ${CONDA_RUN} 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_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
@@ -109,7 +109,8 @@ jobs:
     - name: Install dependencies
       run: |
         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 --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
@@ -120,7 +121,7 @@ jobs:
       if: ${{ matrix.config.framework == 'pytorch_pipelines' }}
       run: |
         pytest -n 8 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "not Flax and not Onnx" \
+          -k "not Flax and not Onnx" \
           --make-reports=tests_${{ matrix.config.report }} \
           tests/modular_pipelines
 

.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
@@ -115,7 +115,8 @@ jobs:
     - name: Install dependencies
       run: |
         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 --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
@@ -126,7 +127,7 @@ jobs:
       if: ${{ matrix.config.framework == 'pytorch_pipelines' }}
       run: |
         pytest -n 8 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "not Flax and not Onnx" \
+          -k "not Flax and not Onnx" \
           --make-reports=tests_${{ matrix.config.report }} \
           tests/pipelines
 
@@ -134,7 +135,7 @@ jobs:
       if: ${{ matrix.config.framework == 'pytorch_models' }}
       run: |
         pytest -n 4 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "not Flax and not Onnx and not Dependency" \
+          -k "not Flax and not Onnx and not Dependency" \
           --make-reports=tests_${{ matrix.config.report }} \
           tests/models tests/schedulers tests/others
 
@@ -246,7 +247,8 @@ jobs:
         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 --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: |
@@ -255,11 +257,11 @@ jobs:
     - name: Run fast PyTorch LoRA tests with PEFT
       run: |
         pytest -n 4 --max-worker-restart=0 --dist=loadfile \
-          -s -v \
+          \
           --make-reports=tests_peft_main \
           tests/lora/
         pytest -n 4 --max-worker-restart=0 --dist=loadfile \
-          -s -v \
+          \
           --make-reports=tests_models_lora_peft_main \
           tests/models/ -k "lora"
 

.github/workflows/pr_tests_gpu.yml

@@ -1,4 +1,4 @@
-name: Fast GPU Tests on PR 
+name: Fast GPU Tests on PR
 
 on:
   pull_request:
@@ -24,7 +24,7 @@ env:
   DIFFUSERS_IS_CI: yes
   OMP_NUM_THREADS: 8
   MKL_NUM_THREADS: 8
-  HF_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
 
@@ -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
@@ -131,7 +131,8 @@ jobs:
         run: |
           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 --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: |
@@ -149,18 +150,18 @@ jobs:
           # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
-          if [ "${{ matrix.module }}" = "ip_adapters" ]; then 
+          if [ "${{ matrix.module }}" = "ip_adapters" ]; then
               pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-              -s -v -k "not Flax and not Onnx" \
+              -k "not Flax and not Onnx" \
               --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
               tests/pipelines/${{ matrix.module }}
-          else 
+          else
               pattern=$(cat ${{ steps.extract_tests.outputs.pattern_file }})
               pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-              -s -v -k "not Flax and not Onnx and $pattern" \
+              -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() }}
@@ -201,7 +202,8 @@ jobs:
         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 --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: |
@@ -222,11 +224,11 @@ jobs:
       run: |
         pattern=$(cat ${{ steps.extract_tests.outputs.pattern_file }})
         if [ -z "$pattern" ]; then
-          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
-          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
@@ -262,7 +264,8 @@ jobs:
         nvidia-smi
     - name: Install dependencies
       run: |
-        uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+        #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
@@ -274,7 +277,7 @@ jobs:
         HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
       run: |
         uv pip install ".[training]"
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v --make-reports=examples_torch_cuda examples/
+        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.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
 
@@ -76,6 +76,8 @@ jobs:
         run: |
           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
@@ -86,7 +88,7 @@ jobs:
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
           pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            -s -v -k "not Flax and not Onnx" \
+            -k "not Flax and not Onnx" \
             --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
             tests/pipelines/${{ matrix.module }}
       - name: Failure short reports
@@ -127,6 +129,8 @@ jobs:
         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: |
@@ -139,7 +143,7 @@ jobs:
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
         pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "not Flax and not Onnx" \
+          -k "not Flax and not Onnx" \
           --make-reports=tests_torch_cuda_${{ matrix.module }} \
           tests/${{ matrix.module }}
 
@@ -178,6 +182,8 @@ jobs:
     - name: Install dependencies
       run: |
         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
@@ -186,7 +192,7 @@ jobs:
         HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
         RUN_COMPILE: yes
       run: |
-        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
@@ -227,7 +233,7 @@ jobs:
       env:
         HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
       run: |
-        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
@@ -270,7 +276,7 @@ jobs:
         HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
       run: |
         uv pip install ".[training]"
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v --make-reports=examples_torch_cuda examples/
+        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
 
@@ -70,7 +70,7 @@ jobs:
       if: ${{ matrix.config.framework == 'pytorch' }}
       run: |
         pytest -n 4 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "not Flax and not Onnx" \
+          -k "not Flax and not Onnx" \
           --make-reports=tests_${{ matrix.config.report }} \
           tests/
 

.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

@@ -84,7 +84,7 @@ jobs:
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
           pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            -s -v -k "not Flax and not Onnx" \
+            -k "not Flax and not Onnx" \
             --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
             tests/pipelines/${{ matrix.module }}
       - name: Failure short reports
@@ -137,7 +137,7 @@ jobs:
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
         pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "not Flax and not Onnx" \
+          -k "not Flax and not Onnx" \
           --make-reports=tests_torch_${{ matrix.module }}_cuda \
           tests/${{ matrix.module }}
 
@@ -187,7 +187,7 @@ jobs:
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
           pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            -s -v -k "not Flax and not Onnx" \
+            -k "not Flax and not Onnx" \
             --make-reports=tests_torch_minimum_cuda \
             tests/models/test_modeling_common.py \
             tests/pipelines/test_pipelines_common.py \
@@ -240,7 +240,7 @@ jobs:
         HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
         RUN_COMPILE: yes
       run: |
-        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
@@ -281,7 +281,7 @@ jobs:
       env:
         HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
       run: |
-        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
@@ -326,7 +326,7 @@ jobs:
         HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
       run: |
         uv pip install ".[training]"
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v --make-reports=examples_torch_cuda examples/
+        pytest -n 1 --max-worker-restart=0 --dist=loadfile --make-reports=examples_torch_cuda examples/
 
     - name: Failure short reports
       if: ${{ failure() }}

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

@@ -33,7 +33,7 @@ RUN uv pip install --no-cache-dir "git+https://github.com/huggingface/diffusers.
 RUN uv pip install --no-cache-dir \
     accelerate \
     numpy==1.26.4 \
-    hf_transfer \
+    hf_xet \
     setuptools==69.5.1 \
     bitsandbytes \
     torchao \

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

@@ -31,7 +31,7 @@ RUN uv pip install --no-cache-dir "git+https://github.com/huggingface/diffusers.
 RUN uv pip install --no-cache-dir \
     accelerate \
     numpy==1.26.4 \
-    hf_transfer
+    hf_xet
 
 RUN apt-get clean && rm -rf /var/lib/apt/lists/* && apt-get autoremove && apt-get autoclean
 

docker/diffusers-pytorch-cuda/Dockerfile

@@ -44,6 +44,6 @@ RUN uv pip install --no-cache-dir \
     accelerate \
     numpy==1.26.4 \
     pytorch-lightning \
-    hf_transfer
+    hf_xet
 
 CMD ["/bin/bash"]

docker/diffusers-pytorch-minimum-cuda/Dockerfile

@@ -47,6 +47,6 @@ RUN uv pip install --no-cache-dir \
     accelerate \
     numpy==1.26.4 \
     pytorch-lightning \
-    hf_transfer
+    hf_xet
 
 CMD ["/bin/bash"]

docker/diffusers-pytorch-xformers-cuda/Dockerfile

@@ -44,7 +44,7 @@ RUN uv pip install --no-cache-dir \
     accelerate \
     numpy==1.26.4 \
     pytorch-lightning \
-    hf_transfer \
+    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
@@ -44,9 +43,8 @@
     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: Prompting
@@ -56,9 +54,8 @@
     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
@@ -362,6 +355,8 @@
         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 +379,8 @@
         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 +391,12 @@
         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 +411,8 @@
         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 +425,10 @@
         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 +449,230 @@
         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/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 +741,8 @@
       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 +759,5 @@
       title: VAE Image Processor
     - local: api/video_processor
       title: Video Processor
+    title: Internal classes
+  title: API

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

@@ -107,6 +107,9 @@ 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/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/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/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/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/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 +1,188 @@
+<!-- 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 descriptio and a starting frame.
+
+```python
+model_id = 
+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 descriptio and a starting frame.
+
+```python
+model_id = "Efficient-Large-Model/SANA-Video_2B_480p_diffusers"
+pipe = SanaImageToVideoPipeline.from_pretrained(
+    model_id,
+    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/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/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/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.
@@ -100,6 +140,7 @@ Refer to the table below for a complete list of available attention backends and
 | `_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_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 |

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/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/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")

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/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/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")
+```
+

examples/community/adaptive_mask_inpainting.py

@@ -126,7 +126,7 @@ EXAMPLE_DOC_STRING = """
         ...     "lllyasviel/control_v11p_sd15_inpaint", torch_dtype=torch.float16
         ... )
         >>> pipe = StableDiffusionControlNetInpaintPipeline.from_pretrained(
-        ...     "runwayml/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16
+        ...     "stable-diffusion-v1-5/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16
         ... )
 
         >>> pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config)
@@ -347,7 +347,7 @@ class AdaptiveMaskInpaintPipeline(
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for more details
             about a model's potential harms.
         feature_extractor ([`~transformers.CLIPImageProcessor`]):
             A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
@@ -429,8 +429,8 @@ class AdaptiveMaskInpaintPipeline(
                 "The configuration file of the unet has set the default `sample_size` to smaller than"
                 " 64 which seems highly unlikely .If you're checkpoint is a fine-tuned version of any of the"
                 " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
-                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
+                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                 " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                 " in the config might lead to incorrect results in future versions. If you have downloaded this"
                 " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"
@@ -970,7 +970,7 @@ class AdaptiveMaskInpaintPipeline(
         >>> default_mask_image = download_image(mask_url).resize((512, 512))
 
         >>> pipe = AdaptiveMaskInpaintPipeline.from_pretrained(
-        ...     "runwayml/stable-diffusion-inpainting", torch_dtype=torch.float16
+        ...     "stable-diffusion-v1-5/stable-diffusion-inpainting", torch_dtype=torch.float16
         ... )
         >>> pipe = pipe.to("cuda")
 
@@ -1095,7 +1095,7 @@ class AdaptiveMaskInpaintPipeline(
 
         # 8. Check that sizes of mask, masked image and latents match
         if num_channels_unet == 9:
-            # default case for runwayml/stable-diffusion-inpainting
+            # default case for stable-diffusion-v1-5/stable-diffusion-inpainting
             num_channels_mask = mask.shape[1]
             num_channels_masked_image = masked_image_latents.shape[1]
             if num_channels_latents + num_channels_mask + num_channels_masked_image != self.unet.config.in_channels:

examples/community/composable_stable_diffusion.py

@@ -62,7 +62,7 @@ class ComposableStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin)
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
+            Please, refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for details.
         feature_extractor ([`CLIPImageProcessor`]):
             Model that extracts features from generated images to be used as inputs for the `safety_checker`.
     """
@@ -145,8 +145,8 @@ class ComposableStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin)
                 "The configuration file of the unet has set the default `sample_size` to smaller than"
                 " 64 which seems highly unlikely. If your checkpoint is a fine-tuned version of any of the"
                 " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
-                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
+                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                 " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                 " in the config might lead to incorrect results in future versions. If you have downloaded this"
                 " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"

examples/community/fresco_v2v.py

@@ -1276,7 +1276,7 @@ class FrescoV2VPipeline(StableDiffusionControlNetImg2ImgPipeline):
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for more details
             about a model's potential harms.
         feature_extractor ([`~transformers.CLIPImageProcessor`]):
             A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.

examples/community/hd_painter.py

@@ -678,7 +678,7 @@ class StableDiffusionHDPainterPipeline(StableDiffusionInpaintPipeline):
 
         # 8. Check that sizes of mask, masked image and latents match
         if num_channels_unet == 9:
-            # default case for runwayml/stable-diffusion-inpainting
+            # default case for stable-diffusion-v1-5/stable-diffusion-inpainting
             num_channels_mask = mask.shape[1]
             num_channels_masked_image = masked_image_latents.shape[1]
             if num_channels_latents + num_channels_mask + num_channels_masked_image != self.unet.config.in_channels:

examples/community/img2img_inpainting.py

@@ -45,7 +45,7 @@ def check_size(image, height, width):
         raise ValueError(f"Image size should be {height}x{width}, but got {h}x{w}")
 
 
-def overlay_inner_image(image, inner_image, paste_offset: Tuple[int] = (0, 0)):
+def overlay_inner_image(image, inner_image, paste_offset: Tuple[int, ...] = (0, 0)):
     inner_image = inner_image.convert("RGBA")
     image = image.convert("RGB")
 
@@ -78,7 +78,7 @@ class ImageToImageInpaintingPipeline(DiffusionPipeline):
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
+            Please, refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for details.
         feature_extractor ([`CLIPImageProcessor`]):
             Model that extracts features from generated images to be used as inputs for the `safety_checker`.
     """

examples/community/instaflow_one_step.py

@@ -86,7 +86,7 @@ class InstaFlowPipeline(
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for more details
             about a model's potential harms.
         feature_extractor ([`~transformers.CLIPImageProcessor`]):
             A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
@@ -165,8 +165,8 @@ class InstaFlowPipeline(
                 "The configuration file of the unet has set the default `sample_size` to smaller than"
                 " 64 which seems highly unlikely. If your checkpoint is a fine-tuned version of any of the"
                 " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
-                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
+                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                 " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                 " in the config might lead to incorrect results in future versions. If you have downloaded this"
                 " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"

examples/community/ip_adapter_face_id.py

@@ -166,7 +166,7 @@ class IPAdapterFaceIDStableDiffusionPipeline(
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for more details
             about a model's potential harms.
         feature_extractor ([`~transformers.CLIPImageProcessor`]):
             A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
@@ -247,8 +247,8 @@ class IPAdapterFaceIDStableDiffusionPipeline(
                 "The configuration file of the unet has set the default `sample_size` to smaller than"
                 " 64 which seems highly unlikely. If your checkpoint is a fine-tuned version of any of the"
                 " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
-                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
+                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                 " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                 " in the config might lead to incorrect results in future versions. If you have downloaded this"
                 " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"

examples/community/kohya_hires_fix.py

@@ -414,7 +414,7 @@ class StableDiffusionHighResFixPipeline(StableDiffusionPipeline):
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for more details
             about a model's potential harms.
         feature_extractor ([`~transformers.CLIPImageProcessor`]):
             A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.

examples/community/latent_consistency_interpolate.py

@@ -222,7 +222,7 @@ class LatentConsistencyModelWalkPipeline(
             supports [`LCMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for more details
             about a model's potential harms.
         feature_extractor ([`~transformers.CLIPImageProcessor`]):
             A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.

examples/community/llm_grounded_diffusion.py

@@ -302,7 +302,7 @@ class LLMGroundedDiffusionPipeline(
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for more details
             about a model's potential harms.
         feature_extractor ([`~transformers.CLIPImageProcessor`]):
             A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
@@ -392,8 +392,8 @@ class LLMGroundedDiffusionPipeline(
                 "The configuration file of the unet has set the default `sample_size` to smaller than"
                 " 64 which seems highly unlikely. If your checkpoint is a fine-tuned version of any of the"
                 " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
-                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
+                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                 " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                 " in the config might lead to incorrect results in future versions. If you have downloaded this"
                 " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"

examples/community/lpw_stable_diffusion.py

@@ -552,8 +552,8 @@ class StableDiffusionLongPromptWeightingPipeline(
                 "The configuration file of the unet has set the default `sample_size` to smaller than"
                 " 64 which seems highly unlikely. If your checkpoint is a fine-tuned version of any of the"
                 " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
-                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
+                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                 " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                 " in the config might lead to incorrect results in future versions. If you have downloaded this"
                 " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"

examples/community/lpw_stable_diffusion_xl.py

@@ -29,7 +29,6 @@ from diffusers.loaders import (
     TextualInversionLoaderMixin,
 )
 from diffusers.models import AutoencoderKL, ImageProjection, UNet2DConditionModel
-from diffusers.models.attention_processor import AttnProcessor2_0, XFormersAttnProcessor
 from diffusers.models.lora import adjust_lora_scale_text_encoder
 from diffusers.pipelines.pipeline_utils import StableDiffusionMixin
 from diffusers.pipelines.stable_diffusion_xl.pipeline_output import StableDiffusionXLPipelineOutput
@@ -1328,18 +1327,8 @@ class SDXLLongPromptWeightingPipeline(
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_upscale.StableDiffusionUpscalePipeline.upcast_vae
     def upcast_vae(self):
-        dtype = self.vae.dtype
+        deprecate("upcast_vae", "1.0.0", "`upcast_vae` is deprecated. Please use `pipe.vae.to(torch.float32)`")
         self.vae.to(dtype=torch.float32)
-        use_torch_2_0_or_xformers = isinstance(
-            self.vae.decoder.mid_block.attentions[0].processor,
-            (AttnProcessor2_0, XFormersAttnProcessor),
-        )
-        # if xformers or torch_2_0 is used attention block does not need
-        # to be in float32 which can save lots of memory
-        if use_torch_2_0_or_xformers:
-            self.vae.post_quant_conv.to(dtype)
-            self.vae.decoder.conv_in.to(dtype)
-            self.vae.decoder.mid_block.to(dtype)
 
     # Copied from diffusers.pipelines.latent_consistency_models.pipeline_latent_consistency_text2img.LatentConsistencyModelPipeline.get_guidance_scale_embedding
     def get_guidance_scale_embedding(self, w, embedding_dim=512, dtype=torch.float32):
@@ -1765,7 +1754,7 @@ class SDXLLongPromptWeightingPipeline(
 
             # Check that sizes of mask, masked image and latents match
             if num_channels_unet == 9:
-                # default case for runwayml/stable-diffusion-inpainting
+                # default case for stable-diffusion-v1-5/stable-diffusion-inpainting
                 num_channels_mask = mask.shape[1]
                 num_channels_masked_image = masked_image_latents.shape[1]
                 if num_channels_latents + num_channels_mask + num_channels_masked_image != num_channels_unet:

examples/community/matryoshka.py

@@ -1966,16 +1966,21 @@ class MatryoshkaUNet2DConditionModel(
         center_input_sample: bool = False,
         flip_sin_to_cos: bool = True,
         freq_shift: int = 0,
-        down_block_types: Tuple[str] = (
+        down_block_types: Tuple[str, ...] = (
             "CrossAttnDownBlock2D",
             "CrossAttnDownBlock2D",
             "CrossAttnDownBlock2D",
             "DownBlock2D",
         ),
         mid_block_type: Optional[str] = "UNetMidBlock2DCrossAttn",
-        up_block_types: Tuple[str] = ("UpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D"),
+        up_block_types: Tuple[str, ...] = (
+            "UpBlock2D",
+            "CrossAttnUpBlock2D",
+            "CrossAttnUpBlock2D",
+            "CrossAttnUpBlock2D",
+        ),
         only_cross_attention: Union[bool, Tuple[bool]] = False,
-        block_out_channels: Tuple[int] = (320, 640, 1280, 1280),
+        block_out_channels: Tuple[int, ...] = (320, 640, 1280, 1280),
         layers_per_block: Union[int, Tuple[int]] = 2,
         downsample_padding: int = 1,
         mid_block_scale_factor: float = 1,
@@ -2294,10 +2299,10 @@ class MatryoshkaUNet2DConditionModel(
 
     def _check_config(
         self,
-        down_block_types: Tuple[str],
-        up_block_types: Tuple[str],
+        down_block_types: Tuple[str, ...],
+        up_block_types: Tuple[str, ...],
         only_cross_attention: Union[bool, Tuple[bool]],
-        block_out_channels: Tuple[int],
+        block_out_channels: Tuple[int, ...],
         layers_per_block: Union[int, Tuple[int]],
         cross_attention_dim: Union[int, Tuple[int]],
         transformer_layers_per_block: Union[int, Tuple[int], Tuple[Tuple[int]]],
@@ -3729,8 +3734,8 @@ class MatryoshkaPipeline(
                 "The configuration file of the unet has set the default `sample_size` to smaller than"
                 " 64 which seems highly unlikely. If your checkpoint is a fine-tuned version of any of the"
                 " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
-                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
+                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                 " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                 " in the config might lead to incorrect results in future versions. If you have downloaded this"
                 " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"

examples/community/mixture_tiling_sdxl.py

@@ -30,17 +30,13 @@ from diffusers.loaders import (
     TextualInversionLoaderMixin,
 )
 from diffusers.models import AutoencoderKL, UNet2DConditionModel
-from diffusers.models.attention_processor import (
-    AttnProcessor2_0,
-    FusedAttnProcessor2_0,
-    XFormersAttnProcessor,
-)
 from diffusers.models.lora import adjust_lora_scale_text_encoder
 from diffusers.pipelines.pipeline_utils import DiffusionPipeline, StableDiffusionMixin
 from diffusers.pipelines.stable_diffusion_xl.pipeline_output import StableDiffusionXLPipelineOutput
 from diffusers.schedulers import KarrasDiffusionSchedulers, LMSDiscreteScheduler
 from diffusers.utils import (
     USE_PEFT_BACKEND,
+    deprecate,
     is_invisible_watermark_available,
     is_torch_xla_available,
     logging,
@@ -710,22 +706,8 @@ class StableDiffusionXLTilingPipeline(
         return torch.tile(weights_torch, (nbatches, self.unet.config.in_channels, 1, 1))
 
     def upcast_vae(self):
-        dtype = self.vae.dtype
+        deprecate("upcast_vae", "1.0.0", "`upcast_vae` is deprecated. Please use `pipe.vae.to(torch.float32)`")
         self.vae.to(dtype=torch.float32)
-        use_torch_2_0_or_xformers = isinstance(
-            self.vae.decoder.mid_block.attentions[0].processor,
-            (
-                AttnProcessor2_0,
-                XFormersAttnProcessor,
-                FusedAttnProcessor2_0,
-            ),
-        )
-        # if xformers or torch_2_0 is used attention block does not need
-        # to be in float32 which can save lots of memory
-        if use_torch_2_0_or_xformers:
-            self.vae.post_quant_conv.to(dtype)
-            self.vae.decoder.conv_in.to(dtype)
-            self.vae.decoder.mid_block.to(dtype)
 
     # Copied from diffusers.pipelines.latent_consistency_models.pipeline_latent_consistency_text2img.LatentConsistencyModelPipeline.get_guidance_scale_embedding
     def get_guidance_scale_embedding(

examples/community/mod_controlnet_tile_sr_sdxl.py

@@ -39,16 +39,13 @@ from diffusers.models import (
     MultiControlNetModel,
     UNet2DConditionModel,
 )
-from diffusers.models.attention_processor import (
-    AttnProcessor2_0,
-    XFormersAttnProcessor,
-)
 from diffusers.models.lora import adjust_lora_scale_text_encoder
 from diffusers.pipelines.pipeline_utils import DiffusionPipeline, StableDiffusionMixin
 from diffusers.pipelines.stable_diffusion_xl.pipeline_output import StableDiffusionXLPipelineOutput
 from diffusers.schedulers import KarrasDiffusionSchedulers, LMSDiscreteScheduler
 from diffusers.utils import (
     USE_PEFT_BACKEND,
+    deprecate,
     logging,
     replace_example_docstring,
     scale_lora_layers,
@@ -1220,23 +1217,9 @@ class StableDiffusionXLControlNetTileSRPipeline(
 
         return tile_weights, tile_row_overlaps, tile_col_overlaps
 
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_upscale.StableDiffusionUpscalePipeline.upcast_vae
     def upcast_vae(self):
-        dtype = self.vae.dtype
+        deprecate("upcast_vae", "1.0.0", "`upcast_vae` is deprecated. Please use `pipe.vae.to(torch.float32)`")
         self.vae.to(dtype=torch.float32)
-        use_torch_2_0_or_xformers = isinstance(
-            self.vae.decoder.mid_block.attentions[0].processor,
-            (
-                AttnProcessor2_0,
-                XFormersAttnProcessor,
-            ),
-        )
-        # if xformers or torch_2_0 is used attention block does not need
-        # to be in float32 which can save lots of memory
-        if use_torch_2_0_or_xformers:
-            self.vae.post_quant_conv.to(dtype)
-            self.vae.decoder.conv_in.to(dtype)
-            self.vae.decoder.mid_block.to(dtype)
 
     @property
     def guidance_scale(self):

examples/community/multilingual_stable_diffusion.py

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

examples/community/pipeline_controlnet_xl_kolors.py

@@ -40,10 +40,6 @@ from diffusers.models import (
     MultiControlNetModel,
     UNet2DConditionModel,
 )
-from diffusers.models.attention_processor import (
-    AttnProcessor2_0,
-    XFormersAttnProcessor,
-)
 from diffusers.pipelines.kolors import ChatGLMModel, ChatGLMTokenizer
 from diffusers.pipelines.pipeline_utils import DiffusionPipeline, StableDiffusionMixin
 from diffusers.pipelines.stable_diffusion_xl.pipeline_output import StableDiffusionXLPipelineOutput
@@ -760,21 +756,8 @@ class KolorsControlNetPipeline(
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_upscale.StableDiffusionUpscalePipeline.upcast_vae
     def upcast_vae(self):
-        dtype = self.vae.dtype
+        deprecate("upcast_vae", "1.0.0", "`upcast_vae` is deprecated. Please use `pipe.vae.to(torch.float32)`")
         self.vae.to(dtype=torch.float32)
-        use_torch_2_0_or_xformers = isinstance(
-            self.vae.decoder.mid_block.attentions[0].processor,
-            (
-                AttnProcessor2_0,
-                XFormersAttnProcessor,
-            ),
-        )
-        # if xformers or torch_2_0 is used attention block does not need
-        # to be in float32 which can save lots of memory
-        if use_torch_2_0_or_xformers:
-            self.vae.post_quant_conv.to(dtype)
-            self.vae.decoder.conv_in.to(dtype)
-            self.vae.decoder.mid_block.to(dtype)
 
     @property
     def guidance_scale(self):

examples/community/pipeline_controlnet_xl_kolors_img2img.py

@@ -40,10 +40,6 @@ from diffusers.models import (
     MultiControlNetModel,
     UNet2DConditionModel,
 )
-from diffusers.models.attention_processor import (
-    AttnProcessor2_0,
-    XFormersAttnProcessor,
-)
 from diffusers.pipelines.kolors import ChatGLMModel, ChatGLMTokenizer
 from diffusers.pipelines.pipeline_utils import DiffusionPipeline, StableDiffusionMixin
 from diffusers.pipelines.stable_diffusion_xl.pipeline_output import StableDiffusionXLPipelineOutput
@@ -930,21 +926,8 @@ class KolorsControlNetImg2ImgPipeline(
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_upscale.StableDiffusionUpscalePipeline.upcast_vae
     def upcast_vae(self):
-        dtype = self.vae.dtype
+        deprecate("upcast_vae", "1.0.0", "`upcast_vae` is deprecated. Please use `pipe.vae.to(torch.float32)`")
         self.vae.to(dtype=torch.float32)
-        use_torch_2_0_or_xformers = isinstance(
-            self.vae.decoder.mid_block.attentions[0].processor,
-            (
-                AttnProcessor2_0,
-                XFormersAttnProcessor,
-            ),
-        )
-        # if xformers or torch_2_0 is used attention block does not need
-        # to be in float32 which can save lots of memory
-        if use_torch_2_0_or_xformers:
-            self.vae.post_quant_conv.to(dtype)
-            self.vae.decoder.conv_in.to(dtype)
-            self.vae.decoder.mid_block.to(dtype)
 
     @property
     def guidance_scale(self):

examples/community/pipeline_controlnet_xl_kolors_inpaint.py

@@ -39,10 +39,6 @@ from diffusers.models import (
     MultiControlNetModel,
     UNet2DConditionModel,
 )
-from diffusers.models.attention_processor import (
-    AttnProcessor2_0,
-    XFormersAttnProcessor,
-)
 from diffusers.pipelines.kolors import ChatGLMModel, ChatGLMTokenizer
 from diffusers.pipelines.pipeline_utils import DiffusionPipeline, StableDiffusionMixin
 from diffusers.pipelines.stable_diffusion_xl.pipeline_output import StableDiffusionXLPipelineOutput
@@ -1006,21 +1002,8 @@ class KolorsControlNetInpaintPipeline(
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_upscale.StableDiffusionUpscalePipeline.upcast_vae
     def upcast_vae(self):
-        dtype = self.vae.dtype
+        deprecate("upcast_vae", "1.0.0", "`upcast_vae` is deprecated. Please use `pipe.vae.to(torch.float32)`")
         self.vae.to(dtype=torch.float32)
-        use_torch_2_0_or_xformers = isinstance(
-            self.vae.decoder.mid_block.attentions[0].processor,
-            (
-                AttnProcessor2_0,
-                XFormersAttnProcessor,
-            ),
-        )
-        # if xformers or torch_2_0 is used attention block does not need
-        # to be in float32 which can save lots of memory
-        if use_torch_2_0_or_xformers:
-            self.vae.post_quant_conv.to(dtype)
-            self.vae.decoder.conv_in.to(dtype)
-            self.vae.decoder.mid_block.to(dtype)
 
     @property
     def denoising_end(self):
@@ -1607,7 +1590,7 @@ class KolorsControlNetInpaintPipeline(
 
         # 9. Check that sizes of mask, masked image and latents match
         if num_channels_unet == 9:
-            # default case for runwayml/stable-diffusion-inpainting
+            # default case for stable-diffusion-v1-5/stable-diffusion-inpainting
             num_channels_mask = mask.shape[1]
             num_channels_masked_image = masked_image_latents.shape[1]
             if num_channels_latents + num_channels_mask + num_channels_masked_image != self.unet.config.in_channels:

examples/community/pipeline_demofusion_sdxl.py

@@ -16,11 +16,11 @@ from diffusers.loaders import (
     TextualInversionLoaderMixin,
 )
 from diffusers.models import AutoencoderKL, UNet2DConditionModel
-from diffusers.models.attention_processor import AttnProcessor2_0, XFormersAttnProcessor
 from diffusers.models.lora import adjust_lora_scale_text_encoder
 from diffusers.pipelines.pipeline_utils import DiffusionPipeline, StableDiffusionMixin
 from diffusers.schedulers import KarrasDiffusionSchedulers
 from diffusers.utils import (
+    deprecate,
     is_accelerate_available,
     is_accelerate_version,
     is_invisible_watermark_available,
@@ -612,20 +612,9 @@ class DemoFusionSDXLPipeline(
 
         return image
 
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_upscale.StableDiffusionUpscalePipeline.upcast_vae
     def upcast_vae(self):
-        dtype = self.vae.dtype
+        deprecate("upcast_vae", "1.0.0", "`upcast_vae` is deprecated. Please use `pipe.vae.to(torch.float32)`")
         self.vae.to(dtype=torch.float32)
-        use_torch_2_0_or_xformers = isinstance(
-            self.vae.decoder.mid_block.attentions[0].processor,
-            (AttnProcessor2_0, XFormersAttnProcessor),
-        )
-        # if xformers or torch_2_0 is used attention block does not need
-        # to be in float32 which can save lots of memory
-        if use_torch_2_0_or_xformers:
-            self.vae.post_quant_conv.to(dtype)
-            self.vae.decoder.conv_in.to(dtype)
-            self.vae.decoder.mid_block.to(dtype)
 
     @torch.no_grad()
     @replace_example_docstring(EXAMPLE_DOC_STRING)

examples/community/pipeline_fabric.py

@@ -135,7 +135,7 @@ class FabricPipeline(DiffusionPipeline):
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for more details
             about a model's potential harms.
     """
 
@@ -163,8 +163,8 @@ class FabricPipeline(DiffusionPipeline):
                 "The configuration file of the unet has set the default `sample_size` to smaller than"
                 " 64 which seems highly unlikely. If your checkpoint is a fine-tuned version of any of the"
                 " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
-                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
+                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                 " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                 " in the config might lead to incorrect results in future versions. If you have downloaded this"
                 " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"

examples/community/pipeline_faithdiff_stable_diffusion_xl.py

@@ -40,13 +40,6 @@ from diffusers.loaders import (
     UNet2DConditionLoadersMixin,
 )
 from diffusers.models import AutoencoderKL
-from diffusers.models.attention_processor import (
-    AttnProcessor2_0,
-    FusedAttnProcessor2_0,
-    LoRAAttnProcessor2_0,
-    LoRAXFormersAttnProcessor,
-    XFormersAttnProcessor,
-)
 from diffusers.models.lora import adjust_lora_scale_text_encoder
 from diffusers.models.unets.unet_2d_blocks import UNetMidBlock2D, get_down_block
 from diffusers.pipelines.pipeline_utils import DiffusionPipeline, StableDiffusionMixin
@@ -438,16 +431,21 @@ class UNet2DConditionModel(OriginalUNet2DConditionModel, ConfigMixin, UNet2DCond
         center_input_sample: bool = False,
         flip_sin_to_cos: bool = True,
         freq_shift: int = 0,
-        down_block_types: Tuple[str] = (
+        down_block_types: Tuple[str, ...] = (
             "CrossAttnDownBlock2D",
             "CrossAttnDownBlock2D",
             "CrossAttnDownBlock2D",
             "DownBlock2D",
         ),
         mid_block_type: Optional[str] = "UNetMidBlock2DCrossAttn",
-        up_block_types: Tuple[str] = ("UpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D"),
+        up_block_types: Tuple[str, ...] = (
+            "UpBlock2D",
+            "CrossAttnUpBlock2D",
+            "CrossAttnUpBlock2D",
+            "CrossAttnUpBlock2D",
+        ),
         only_cross_attention: Union[bool, Tuple[bool]] = False,
-        block_out_channels: Tuple[int] = (320, 640, 1280, 1280),
+        block_out_channels: Tuple[int, ...] = (320, 640, 1280, 1280),
         layers_per_block: Union[int, Tuple[int]] = 2,
         downsample_padding: int = 1,
         mid_block_scale_factor: float = 1,
@@ -1637,24 +1635,8 @@ class FaithDiffStableDiffusionXLPipeline(
         return latents
 
     def upcast_vae(self):
-        dtype = self.vae.dtype
+        deprecate("upcast_vae", "1.0.0", "`upcast_vae` is deprecated. Please use `pipe.vae.to(torch.float32)`")
         self.vae.to(dtype=torch.float32)
-        use_torch_2_0_or_xformers = isinstance(
-            self.vae.decoder.mid_block.attentions[0].processor,
-            (
-                AttnProcessor2_0,
-                XFormersAttnProcessor,
-                LoRAXFormersAttnProcessor,
-                LoRAAttnProcessor2_0,
-                FusedAttnProcessor2_0,
-            ),
-        )
-        # if xformers or torch_2_0 is used attention block does not need
-        # to be in float32 which can save lots of memory
-        if use_torch_2_0_or_xformers:
-            self.vae.post_quant_conv.to(dtype)
-            self.vae.decoder.conv_in.to(dtype)
-            self.vae.decoder.mid_block.to(dtype)
 
     # Copied from diffusers.pipelines.latent_consistency_models.pipeline_latent_consistency_text2img.LatentConsistencyModelPipeline.get_guidance_scale_embedding
     def get_guidance_scale_embedding(

examples/community/pipeline_kolors_differential_img2img.py

@@ -22,13 +22,12 @@ from diffusers.callbacks import MultiPipelineCallbacks, PipelineCallback
 from diffusers.image_processor import PipelineImageInput, VaeImageProcessor
 from diffusers.loaders import IPAdapterMixin, StableDiffusionXLLoraLoaderMixin
 from diffusers.models import AutoencoderKL, ImageProjection, UNet2DConditionModel
-from diffusers.models.attention_processor import AttnProcessor2_0, FusedAttnProcessor2_0, XFormersAttnProcessor
 from diffusers.pipelines.kolors.pipeline_output import KolorsPipelineOutput
 from diffusers.pipelines.kolors.text_encoder import ChatGLMModel
 from diffusers.pipelines.kolors.tokenizer import ChatGLMTokenizer
 from diffusers.pipelines.pipeline_utils import DiffusionPipeline, StableDiffusionMixin
 from diffusers.schedulers import KarrasDiffusionSchedulers
-from diffusers.utils import is_torch_xla_available, logging, replace_example_docstring
+from diffusers.utils import deprecate, is_torch_xla_available, logging, replace_example_docstring
 from diffusers.utils.torch_utils import randn_tensor
 
 
@@ -709,24 +708,9 @@ class KolorsDifferentialImg2ImgPipeline(
         add_time_ids = torch.tensor([add_time_ids], dtype=dtype)
         return add_time_ids
 
-    # Copied from diffusers.pipelines.stable_diffusion_xl.pipeline_stable_diffusion_xl.StableDiffusionXLPipeline.upcast_vae
     def upcast_vae(self):
-        dtype = self.vae.dtype
+        deprecate("upcast_vae", "1.0.0", "`upcast_vae` is deprecated. Please use `pipe.vae.to(torch.float32)`")
         self.vae.to(dtype=torch.float32)
-        use_torch_2_0_or_xformers = isinstance(
-            self.vae.decoder.mid_block.attentions[0].processor,
-            (
-                AttnProcessor2_0,
-                XFormersAttnProcessor,
-                FusedAttnProcessor2_0,
-            ),
-        )
-        # if xformers or torch_2_0 is used attention block does not need
-        # to be in float32 which can save lots of memory
-        if use_torch_2_0_or_xformers:
-            self.vae.post_quant_conv.to(dtype)
-            self.vae.decoder.conv_in.to(dtype)
-            self.vae.decoder.mid_block.to(dtype)
 
     # Copied from diffusers.pipelines.latent_consistency_models.pipeline_latent_consistency_text2img.LatentConsistencyModelPipeline.get_guidance_scale_embedding
     def get_guidance_scale_embedding(

examples/community/pipeline_kolors_inpainting.py

@@ -32,12 +32,6 @@ from diffusers.loaders import (
     TextualInversionLoaderMixin,
 )
 from diffusers.models import AutoencoderKL, ImageProjection, UNet2DConditionModel
-from diffusers.models.attention_processor import (
-    AttnProcessor2_0,
-    LoRAAttnProcessor2_0,
-    LoRAXFormersAttnProcessor,
-    XFormersAttnProcessor,
-)
 from diffusers.pipelines.kolors import ChatGLMModel, ChatGLMTokenizer
 from diffusers.pipelines.pipeline_utils import DiffusionPipeline, StableDiffusionMixin
 from diffusers.pipelines.stable_diffusion_xl.pipeline_output import StableDiffusionXLPipelineOutput
@@ -1008,23 +1002,8 @@ class KolorsInpaintPipeline(
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_upscale.StableDiffusionUpscalePipeline.upcast_vae
     def upcast_vae(self):
-        dtype = self.vae.dtype
+        deprecate("upcast_vae", "1.0.0", "`upcast_vae` is deprecated. Please use `pipe.vae.to(torch.float32)`")
         self.vae.to(dtype=torch.float32)
-        use_torch_2_0_or_xformers = isinstance(
-            self.vae.decoder.mid_block.attentions[0].processor,
-            (
-                AttnProcessor2_0,
-                XFormersAttnProcessor,
-                LoRAXFormersAttnProcessor,
-                LoRAAttnProcessor2_0,
-            ),
-        )
-        # if xformers or torch_2_0 is used attention block does not need
-        # to be in float32 which can save lots of memory
-        if use_torch_2_0_or_xformers:
-            self.vae.post_quant_conv.to(dtype)
-            self.vae.decoder.conv_in.to(dtype)
-            self.vae.decoder.mid_block.to(dtype)
 
     # Copied from diffusers.pipelines.latent_consistency_models.pipeline_latent_consistency_text2img.LatentConsistencyModelPipeline.get_guidance_scale_embedding
     def get_guidance_scale_embedding(
@@ -1487,7 +1466,7 @@ class KolorsInpaintPipeline(
 
         # 8. Check that sizes of mask, masked image and latents match
         if num_channels_unet == 9:
-            # default case for runwayml/stable-diffusion-inpainting
+            # default case for stable-diffusion-v1-5/stable-diffusion-inpainting
             num_channels_mask = mask.shape[1]
             num_channels_masked_image = masked_image_latents.shape[1]
             if num_channels_latents + num_channels_mask + num_channels_masked_image != self.unet.config.in_channels:

examples/community/pipeline_prompt2prompt.py

@@ -106,7 +106,7 @@ class Prompt2PromptPipeline(
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for more details
             about a model's potential harms.
         feature_extractor ([`~transformers.CLIPImageProcessor`]):
             A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
@@ -187,8 +187,8 @@ class Prompt2PromptPipeline(
                 "The configuration file of the unet has set the default `sample_size` to smaller than"
                 " 64 which seems highly unlikely. If your checkpoint is a fine-tuned version of any of the"
                 " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
-                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
+                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                 " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                 " in the config might lead to incorrect results in future versions. If you have downloaded this"
                 " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"

examples/community/pipeline_sdxl_style_aligned.py

@@ -45,8 +45,6 @@ from diffusers.models import AutoencoderKL, ImageProjection, UNet2DConditionMode
 from diffusers.models.attention_processor import (
     Attention,
     AttnProcessor2_0,
-    FusedAttnProcessor2_0,
-    XFormersAttnProcessor,
 )
 from diffusers.models.lora import adjust_lora_scale_text_encoder
 from diffusers.pipelines.pipeline_utils import DiffusionPipeline, StableDiffusionMixin
@@ -1151,22 +1149,8 @@ class StyleAlignedSDXLPipeline(
         return add_time_ids
 
     def upcast_vae(self):
-        dtype = self.vae.dtype
+        deprecate("upcast_vae", "1.0.0", "`upcast_vae` is deprecated. Please use `pipe.vae.to(torch.float32)`")
         self.vae.to(dtype=torch.float32)
-        use_torch_2_0_or_xformers = isinstance(
-            self.vae.decoder.mid_block.attentions[0].processor,
-            (
-                AttnProcessor2_0,
-                XFormersAttnProcessor,
-                FusedAttnProcessor2_0,
-            ),
-        )
-        # if xformers or torch_2_0 is used attention block does not need
-        # to be in float32 which can save lots of memory
-        if use_torch_2_0_or_xformers:
-            self.vae.post_quant_conv.to(dtype)
-            self.vae.decoder.conv_in.to(dtype)
-            self.vae.decoder.mid_block.to(dtype)
 
     def _enable_shared_attention_processors(
         self,
@@ -1730,7 +1714,7 @@ class StyleAlignedSDXLPipeline(
 
             # Check that sizes of mask, masked image and latents match
             if num_channels_unet == 9:
-                # default case for runwayml/stable-diffusion-inpainting
+                # default case for stable-diffusion-v1-5/stable-diffusion-inpainting
                 num_channels_mask = mask.shape[1]
                 num_channels_masked_image = masked_image_latents.shape[1]
                 if num_channels_latents + num_channels_mask + num_channels_masked_image != num_channels_unet:

examples/community/pipeline_stable_diffusion_boxdiff.py

@@ -59,7 +59,7 @@ EXAMPLE_DOC_STRING = """
         >>> import torch
         >>> from diffusers import StableDiffusionPipeline
 
-        >>> pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
+        >>> pipe = StableDiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16)
         >>> pipe = pipe.to("cuda")
 
         >>> prompt = "a photo of an astronaut riding a horse on mars"
@@ -392,7 +392,7 @@ class StableDiffusionBoxDiffPipeline(
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for more details
             about a model's potential harms.
         feature_extractor ([`~transformers.CLIPImageProcessor`]):
             A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
@@ -473,8 +473,8 @@ class StableDiffusionBoxDiffPipeline(
                 "The configuration file of the unet has set the default `sample_size` to smaller than"
                 " 64 which seems highly unlikely. If your checkpoint is a fine-tuned version of any of the"
                 " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
-                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
+                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                 " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                 " in the config might lead to incorrect results in future versions. If you have downloaded this"
                 " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"

examples/community/pipeline_stable_diffusion_pag.py

@@ -42,7 +42,7 @@ EXAMPLE_DOC_STRING = """
         ```py
         >>> import torch
         >>> from diffusers import StableDiffusionPipeline
-        >>> pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
+        >>> pipe = StableDiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16)
         >>> pipe = pipe.to("cuda")
         >>> prompt = "a photo of an astronaut riding a horse on mars"
         >>> image = pipe(prompt).images[0]
@@ -359,7 +359,7 @@ class StableDiffusionPAGPipeline(
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for more details
             about a model's potential harms.
         feature_extractor ([`~transformers.CLIPImageProcessor`]):
             A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
@@ -440,8 +440,8 @@ class StableDiffusionPAGPipeline(
                 "The configuration file of the unet has set the default `sample_size` to smaller than"
                 " 64 which seems highly unlikely. If your checkpoint is a fine-tuned version of any of the"
                 " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
-                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
+                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                 " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                 " in the config might lead to incorrect results in future versions. If you have downloaded this"
                 " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"

examples/community/pipeline_stable_diffusion_upscale_ldm3d.py

@@ -100,7 +100,7 @@ class StableDiffusionUpscaleLDM3DPipeline(
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for more details
             about a model's potential harms.
         feature_extractor ([`~transformers.CLIPImageProcessor`]):
             A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
@@ -503,24 +503,9 @@ class StableDiffusionUpscaleLDM3DPipeline(
         latents = latents * self.scheduler.init_noise_sigma
         return latents
 
-    # def upcast_vae(self):
-    #     dtype = self.vae.dtype
-    #     self.vae.to(dtype=torch.float32)
-    #     use_torch_2_0_or_xformers = isinstance(
-    #         self.vae.decoder.mid_block.attentions[0].processor,
-    #         (
-    #             AttnProcessor2_0,
-    #             XFormersAttnProcessor,
-    #             LoRAXFormersAttnProcessor,
-    #             LoRAAttnProcessor2_0,
-    #         ),
-    #     )
-    #     # if xformers or torch_2_0 is used attention block does not need
-    #     # to be in float32 which can save lots of memory
-    #     if use_torch_2_0_or_xformers:
-    #         self.vae.post_quant_conv.to(dtype)
-    #         self.vae.decoder.conv_in.to(dtype)
-    #         self.vae.decoder.mid_block.to(dtype)
+    def upcast_vae(self):
+        deprecate("upcast_vae", "1.0.0", "`upcast_vae` is deprecated. Please use `pipe.vae.to(torch.float32)`")
+        self.vae.to(dtype=torch.float32)
 
     @torch.no_grad()
     def __call__(

examples/community/pipeline_stable_diffusion_xl_attentive_eraser.py

@@ -35,12 +35,6 @@ from diffusers.loaders import (
     TextualInversionLoaderMixin,
 )
 from diffusers.models import AutoencoderKL, ImageProjection, UNet2DConditionModel
-from diffusers.models.attention_processor import (
-    AttnProcessor2_0,
-    LoRAAttnProcessor2_0,
-    LoRAXFormersAttnProcessor,
-    XFormersAttnProcessor,
-)
 from diffusers.models.lora import adjust_lora_scale_text_encoder
 from diffusers.pipelines.pipeline_utils import DiffusionPipeline, StableDiffusionMixin
 from diffusers.pipelines.stable_diffusion_xl.pipeline_output import StableDiffusionXLPipelineOutput
@@ -1282,23 +1276,8 @@ class StableDiffusionXL_AE_Pipeline(
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_upscale.StableDiffusionUpscalePipeline.upcast_vae
     def upcast_vae(self):
-        dtype = self.vae.dtype
+        deprecate("upcast_vae", "1.0.0", "`upcast_vae` is deprecated. Please use `pipe.vae.to(torch.float32)`")
         self.vae.to(dtype=torch.float32)
-        use_torch_2_0_or_xformers = isinstance(
-            self.vae.decoder.mid_block.attentions[0].processor,
-            (
-                AttnProcessor2_0,
-                XFormersAttnProcessor,
-                LoRAXFormersAttnProcessor,
-                LoRAAttnProcessor2_0,
-            ),
-        )
-        # if xformers or torch_2_0 is used attention block does not need
-        # to be in float32 which can save lots of memory
-        if use_torch_2_0_or_xformers:
-            self.vae.post_quant_conv.to(dtype)
-            self.vae.decoder.conv_in.to(dtype)
-            self.vae.decoder.mid_block.to(dtype)
 
     # Copied from diffusers.pipelines.latent_consistency_models.pipeline_latent_consistency_text2img.LatentConsistencyModelPipeline.get_guidance_scale_embedding
     def get_guidance_scale_embedding(self, w, embedding_dim=512, dtype=torch.float32):
@@ -2042,7 +2021,7 @@ class StableDiffusionXL_AE_Pipeline(
 
         # 8. Check that sizes of mask, masked image and latents match
         if num_channels_unet == 9:
-            # default case for runwayml/stable-diffusion-inpainting
+            # default case for stable-diffusion-v1-5/stable-diffusion-inpainting
             num_channels_mask = mask.shape[1]
             num_channels_masked_image = masked_image_latents.shape[1]
             if num_channels_latents + num_channels_mask + num_channels_masked_image != self.unet.config.in_channels:

examples/community/pipeline_stable_diffusion_xl_controlnet_adapter.py

@@ -25,7 +25,6 @@ from transformers import CLIPTextModel, CLIPTextModelWithProjection, CLIPTokeniz
 from diffusers.image_processor import PipelineImageInput, VaeImageProcessor
 from diffusers.loaders import FromSingleFileMixin, StableDiffusionXLLoraLoaderMixin, TextualInversionLoaderMixin
 from diffusers.models import AutoencoderKL, ControlNetModel, MultiAdapter, T2IAdapter, UNet2DConditionModel
-from diffusers.models.attention_processor import AttnProcessor2_0, XFormersAttnProcessor
 from diffusers.models.lora import adjust_lora_scale_text_encoder
 from diffusers.pipelines.controlnet.multicontrolnet import MultiControlNetModel
 from diffusers.pipelines.pipeline_utils import DiffusionPipeline, StableDiffusionMixin
@@ -34,6 +33,7 @@ from diffusers.schedulers import KarrasDiffusionSchedulers
 from diffusers.utils import (
     PIL_INTERPOLATION,
     USE_PEFT_BACKEND,
+    deprecate,
     logging,
     replace_example_docstring,
     scale_lora_layers,
@@ -188,7 +188,7 @@ class StableDiffusionXLControlNetAdapterPipeline(
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
+            Please, refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for details.
         feature_extractor ([`CLIPImageProcessor`]):
             Model that extracts features from generated images to be used as inputs for the `safety_checker`.
     """
@@ -793,20 +793,9 @@ class StableDiffusionXLControlNetAdapterPipeline(
         add_time_ids = torch.tensor([add_time_ids], dtype=dtype)
         return add_time_ids
 
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_upscale.StableDiffusionUpscalePipeline.upcast_vae
     def upcast_vae(self):
-        dtype = self.vae.dtype
+        deprecate("upcast_vae", "1.0.0", "`upcast_vae` is deprecated. Please use `pipe.vae.to(torch.float32)`")
         self.vae.to(dtype=torch.float32)
-        use_torch_2_0_or_xformers = isinstance(
-            self.vae.decoder.mid_block.attentions[0].processor,
-            (AttnProcessor2_0, XFormersAttnProcessor),
-        )
-        # if xformers or torch_2_0 is used attention block does not need
-        # to be in float32 which can save lots of memory
-        if use_torch_2_0_or_xformers:
-            self.vae.post_quant_conv.to(dtype)
-            self.vae.decoder.conv_in.to(dtype)
-            self.vae.decoder.mid_block.to(dtype)
 
     # Copied from diffusers.pipelines.t2i_adapter.pipeline_stable_diffusion_adapter.StableDiffusionAdapterPipeline._default_height_width
     def _default_height_width(self, height, width, image):

examples/community/pipeline_stable_diffusion_xl_controlnet_adapter_inpaint.py

@@ -43,7 +43,6 @@ from diffusers.models import (
     T2IAdapter,
     UNet2DConditionModel,
 )
-from diffusers.models.attention_processor import AttnProcessor2_0, XFormersAttnProcessor
 from diffusers.models.lora import adjust_lora_scale_text_encoder
 from diffusers.pipelines.controlnet.multicontrolnet import MultiControlNetModel
 from diffusers.pipelines.pipeline_utils import StableDiffusionMixin
@@ -52,6 +51,7 @@ from diffusers.schedulers import KarrasDiffusionSchedulers
 from diffusers.utils import (
     PIL_INTERPOLATION,
     USE_PEFT_BACKEND,
+    deprecate,
     logging,
     replace_example_docstring,
     scale_lora_layers,
@@ -330,7 +330,7 @@ class StableDiffusionXLControlNetAdapterInpaintPipeline(
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
+            Please, refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for details.
         feature_extractor ([`CLIPImageProcessor`]):
             Model that extracts features from generated images to be used as inputs for the `safety_checker`.
         requires_aesthetics_score (`bool`, *optional*, defaults to `"False"`):
@@ -1130,20 +1130,9 @@ class StableDiffusionXLControlNetAdapterInpaintPipeline(
 
         return add_time_ids, add_neg_time_ids
 
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_upscale.StableDiffusionUpscalePipeline.upcast_vae
     def upcast_vae(self):
-        dtype = self.vae.dtype
+        deprecate("upcast_vae", "1.0.0", "`upcast_vae` is deprecated. Please use `pipe.vae.to(torch.float32)`")
         self.vae.to(dtype=torch.float32)
-        use_torch_2_0_or_xformers = isinstance(
-            self.vae.decoder.mid_block.attentions[0].processor,
-            (AttnProcessor2_0, XFormersAttnProcessor),
-        )
-        # if xformers or torch_2_0 is used attention block does not need
-        # to be in float32 which can save lots of memory
-        if use_torch_2_0_or_xformers:
-            self.vae.post_quant_conv.to(dtype)
-            self.vae.decoder.conv_in.to(dtype)
-            self.vae.decoder.mid_block.to(dtype)
 
     # Copied from diffusers.pipelines.t2i_adapter.pipeline_stable_diffusion_adapter.StableDiffusionAdapterPipeline._default_height_width
     def _default_height_width(self, height, width, image):
@@ -1569,7 +1558,7 @@ class StableDiffusionXLControlNetAdapterInpaintPipeline(
 
         # 8. Check that sizes of mask, masked image and latents match
         if num_channels_unet == 9:
-            # default case for runwayml/stable-diffusion-inpainting
+            # default case for stable-diffusion-v1-5/stable-diffusion-inpainting
             num_channels_mask = mask.shape[1]
             num_channels_masked_image = masked_image_latents.shape[1]
             if num_channels_latents + num_channels_mask + num_channels_masked_image != self.unet.config.in_channels:

examples/community/pipeline_stable_diffusion_xl_differential_img2img.py

@@ -35,10 +35,6 @@ from diffusers.loaders import (
     TextualInversionLoaderMixin,
 )
 from diffusers.models import AutoencoderKL, ImageProjection, UNet2DConditionModel
-from diffusers.models.attention_processor import (
-    AttnProcessor2_0,
-    XFormersAttnProcessor,
-)
 from diffusers.models.lora import adjust_lora_scale_text_encoder
 from diffusers.pipelines.pipeline_utils import DiffusionPipeline, StableDiffusionMixin
 from diffusers.pipelines.stable_diffusion_xl.pipeline_output import StableDiffusionXLPipelineOutput
@@ -848,21 +844,8 @@ class StableDiffusionXLDifferentialImg2ImgPipeline(
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_upscale.StableDiffusionUpscalePipeline.upcast_vae
     def upcast_vae(self):
-        dtype = self.vae.dtype
+        deprecate("upcast_vae", "1.0.0", "`upcast_vae` is deprecated. Please use `pipe.vae.to(torch.float32)`")
         self.vae.to(dtype=torch.float32)
-        use_torch_2_0_or_xformers = isinstance(
-            self.vae.decoder.mid_block.attentions[0].processor,
-            (
-                AttnProcessor2_0,
-                XFormersAttnProcessor,
-            ),
-        )
-        # if xformers or torch_2_0 is used attention block does not need
-        # to be in float32 which can save lots of memory
-        if use_torch_2_0_or_xformers:
-            self.vae.post_quant_conv.to(dtype)
-            self.vae.decoder.conv_in.to(dtype)
-            self.vae.decoder.mid_block.to(dtype)
 
     # Copied from diffusers.pipelines.latent_consistency_models.pipeline_latent_consistency_text2img.LatentConsistencyModelPipeline.get_guidance_scale_embedding
     def get_guidance_scale_embedding(

examples/community/pipeline_stable_diffusion_xl_ipex.py

@@ -32,10 +32,6 @@ from diffusers.loaders import (
     TextualInversionLoaderMixin,
 )
 from diffusers.models import AutoencoderKL, UNet2DConditionModel
-from diffusers.models.attention_processor import (
-    AttnProcessor2_0,
-    XFormersAttnProcessor,
-)
 from diffusers.models.lora import adjust_lora_scale_text_encoder
 from diffusers.pipelines.stable_diffusion_xl import StableDiffusionXLPipelineOutput
 from diffusers.schedulers import KarrasDiffusionSchedulers
@@ -658,23 +654,9 @@ class StableDiffusionXLPipelineIpex(
         add_time_ids = torch.tensor([add_time_ids], dtype=dtype)
         return add_time_ids
 
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_upscale.StableDiffusionUpscalePipeline.upcast_vae
     def upcast_vae(self):
-        dtype = self.vae.dtype
+        deprecate("upcast_vae", "1.0.0", "`upcast_vae` is deprecated. Please use `pipe.vae.to(torch.float32)`")
         self.vae.to(dtype=torch.float32)
-        use_torch_2_0_or_xformers = isinstance(
-            self.vae.decoder.mid_block.attentions[0].processor,
-            (
-                AttnProcessor2_0,
-                XFormersAttnProcessor,
-            ),
-        )
-        # if xformers or torch_2_0 is used attention block does not need
-        # to be in float32 which can save lots of memory
-        if use_torch_2_0_or_xformers:
-            self.vae.post_quant_conv.to(dtype)
-            self.vae.decoder.conv_in.to(dtype)
-            self.vae.decoder.mid_block.to(dtype)
 
     # Copied from diffusers.pipelines.latent_consistency_models.pipeline_latent_consistency_text2img.LatentConsistencyModelPipeline.get_guidance_scale_embedding
     def get_guidance_scale_embedding(self, w, embedding_dim=512, dtype=torch.float32):

examples/community/pipeline_zero1to3.py

@@ -46,7 +46,7 @@ EXAMPLE_DOC_STRING = """
         >>> import torch
         >>> from diffusers import StableDiffusionPipeline
 
-        >>> pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
+        >>> pipe = StableDiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16)
         >>> pipe = pipe.to("cuda")
 
         >>> prompt = "a photo of an astronaut riding a horse on mars"
@@ -86,7 +86,7 @@ class Zero1to3StableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin):
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
+            Please, refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for details.
         feature_extractor ([`CLIPImageProcessor`]):
             Model that extracts features from generated images to be used as inputs for the `safety_checker`.
         cc_projection ([`CCProjection`]):
@@ -164,8 +164,8 @@ class Zero1to3StableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin):
                 "The configuration file of the unet has set the default `sample_size` to smaller than"
                 " 64 which seems highly unlikely. If your checkpoint is a fine-tuned version of any of the"
                 " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
-                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
+                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                 " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                 " in the config might lead to incorrect results in future versions. If you have downloaded this"
                 " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"

examples/community/regional_prompting_stable_diffusion.py

@@ -490,7 +490,7 @@ class RegionalPromptingStableDiffusionPipeline(
     def prepare_extra_step_kwargs(self, generator, eta):
         # prepare extra kwargs for the scheduler step, since not all schedulers have the same signature
         # eta (η) is only used with the DDIMScheduler, it will be ignored for other schedulers.
-        # eta corresponds to η in DDIM paper: https://arxiv.org/abs/2010.02502
+        # eta corresponds to η in DDIM paper: https://huggingface.co/papers/2010.02502
         # and should be between [0, 1]
 
         accepts_eta = "eta" in set(inspect.signature(self.scheduler.step).parameters.keys())
@@ -841,7 +841,7 @@ class RegionalPromptingStableDiffusionPipeline(
             num_images_per_prompt (`int`, *optional*, defaults to 1):
                 The number of images to generate per prompt.
             eta (`float`, *optional*, defaults to 0.0):
-                Corresponds to parameter eta (η) from the [DDIM](https://arxiv.org/abs/2010.02502) paper. Only applies
+                Corresponds to parameter eta (η) from the [DDIM](https://huggingface.co/papers/2010.02502) paper. Only applies
                 to the [`~schedulers.DDIMScheduler`], and is ignored in other schedulers.
             generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
                 A [`torch.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make
@@ -872,7 +872,7 @@ class RegionalPromptingStableDiffusionPipeline(
                 [`self.processor`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
             guidance_rescale (`float`, *optional*, defaults to 0.0):
                 Guidance rescale factor from [Common Diffusion Noise Schedules and Sample Steps are
-                Flawed](https://arxiv.org/pdf/2305.08891.pdf). Guidance rescale factor should fix overexposure when
+                Flawed](https://huggingface.co/papers/2305.08891). Guidance rescale factor should fix overexposure when
                 using zero terminal SNR.
             clip_skip (`int`, *optional*):
                 Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that
@@ -1062,7 +1062,7 @@ class RegionalPromptingStableDiffusionPipeline(
                     noise_pred = noise_pred_uncond + self.guidance_scale * (noise_pred_text - noise_pred_uncond)
 
                 if self.do_classifier_free_guidance and self.guidance_rescale > 0.0:
-                    # Based on 3.4. in https://arxiv.org/pdf/2305.08891.pdf
+                    # Based on 3.4. in https://huggingface.co/papers/2305.08891
                     noise_pred = rescale_noise_cfg(noise_pred, noise_pred_text, guidance_rescale=self.guidance_rescale)
 
                 # compute the previous noisy sample x_t -> x_t-1
@@ -1668,7 +1668,7 @@ def rescale_noise_cfg(noise_cfg, noise_pred_text, guidance_rescale=0.0):
     r"""
     Rescales `noise_cfg` tensor based on `guidance_rescale` to improve image quality and fix overexposure. Based on
     Section 3.4 from [Common Diffusion Noise Schedules and Sample Steps are
-    Flawed](https://arxiv.org/pdf/2305.08891.pdf).
+    Flawed](https://huggingface.co/papers/2305.08891).
 
     Args:
         noise_cfg (`torch.Tensor`):