up

docs: improve docstring scheduling_ddim_inverse.py

.github/workflows/benchmark.yml

@@ -28,7 +28,7 @@ jobs:
       options: --shm-size "16gb" --ipc host --gpus all
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           fetch-depth: 2
       - name: NVIDIA-SMI
@@ -58,7 +58,7 @@ jobs:
 
       - name: Test suite reports artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: benchmark_test_reports
           path: benchmarks/${{ env.BASE_PATH }}

.github/workflows/build_docker_images.yml

@@ -28,7 +28,7 @@ jobs:
         uses: docker/setup-buildx-action@v1
 
       - name: Check out code
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
 
       - name: Find Changed Dockerfiles
         id: file_changes
@@ -99,7 +99,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v1
       - name: Login to Docker Hub

.github/workflows/build_pr_documentation.yml

@@ -17,10 +17,10 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
 
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: '3.10'
 

.github/workflows/codeql.yml

@@ -0,0 +1,22 @@
+---
+name: CodeQL Security Analysis For Github Actions
+
+on:
+  push:
+    branches: ["main"]
+  workflow_dispatch:
+  # pull_request:
+
+jobs:
+  codeql:
+    name: CodeQL Analysis
+    uses: huggingface/security-workflows/.github/workflows/codeql-reusable.yml@v1
+    permissions:
+      security-events: write
+      packages: read
+      actions: read
+      contents: read
+    with:
+      languages: '["actions","python"]'
+      queries: 'security-extended,security-and-quality'
+      runner: 'ubuntu-latest' #optional if need custom runner

.github/workflows/mirror_community_pipeline.yml

@@ -24,7 +24,6 @@ jobs:
   mirror_community_pipeline:
     env:
       SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_COMMUNITY_MIRROR }}
-
     runs-on: ubuntu-22.04
     steps:
       # Checkout to correct ref
@@ -39,37 +38,41 @@ jobs:
       #     If ref is 'refs/heads/main' => set 'main'
       #     Else it must be a tag => set {tag}
       - name: Set checkout_ref and path_in_repo
+        env:
+          EVENT_NAME: ${{ github.event_name }}
+          EVENT_INPUT_REF: ${{ github.event.inputs.ref }}
+          GITHUB_REF: ${{ github.ref }}
         run: |
-          if [ "${{ github.event_name }}" == "workflow_dispatch" ]; then
-            if [ -z "${{ github.event.inputs.ref }}" ]; then
+          if [ "$EVENT_NAME" == "workflow_dispatch" ]; then
+            if [ -z "$EVENT_INPUT_REF" ]; then
               echo "Error: Missing ref input"
               exit 1
-            elif [ "${{ github.event.inputs.ref }}" == "main" ]; then
+            elif [ "$EVENT_INPUT_REF" == "main" ]; then
               echo "CHECKOUT_REF=refs/heads/main" >> $GITHUB_ENV
               echo "PATH_IN_REPO=main" >> $GITHUB_ENV
             else
-              echo "CHECKOUT_REF=refs/tags/${{ github.event.inputs.ref }}" >> $GITHUB_ENV
-              echo "PATH_IN_REPO=${{ github.event.inputs.ref }}" >> $GITHUB_ENV
+              echo "CHECKOUT_REF=refs/tags/$EVENT_INPUT_REF" >> $GITHUB_ENV
+              echo "PATH_IN_REPO=$EVENT_INPUT_REF" >> $GITHUB_ENV
             fi
-          elif [ "${{ github.ref }}" == "refs/heads/main" ]; then
-            echo "CHECKOUT_REF=${{ github.ref }}" >> $GITHUB_ENV
+          elif [ "$GITHUB_REF" == "refs/heads/main" ]; then
+            echo "CHECKOUT_REF=$GITHUB_REF" >> $GITHUB_ENV
             echo "PATH_IN_REPO=main" >> $GITHUB_ENV
           else
             # e.g. refs/tags/v0.28.1 -> v0.28.1
-            echo "CHECKOUT_REF=${{ github.ref }}" >> $GITHUB_ENV
-            echo "PATH_IN_REPO=$(echo ${{ github.ref }} | sed 's/^refs\/tags\///')" >> $GITHUB_ENV
+            echo "CHECKOUT_REF=$GITHUB_REF" >> $GITHUB_ENV
+            echo "PATH_IN_REPO=$(echo $GITHUB_REF | sed 's/^refs\/tags\///')" >> $GITHUB_ENV
           fi
       - name: Print env vars
         run: |
           echo "CHECKOUT_REF: ${{ env.CHECKOUT_REF }}"
           echo "PATH_IN_REPO: ${{ env.PATH_IN_REPO }}"
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v6
         with:
           ref: ${{ env.CHECKOUT_REF }}
 
       # Setup + install dependencies
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v6
         with:
           python-version: "3.10"
       - name: Install dependencies
@@ -99,4 +102,4 @@ jobs:
       - name: Report failure status
         if: ${{ failure() }}
         run: |
-          pip install requests && python utils/notify_community_pipelines_mirror.py --status=failure
+          pip install requests && python utils/notify_community_pipelines_mirror.py --status=failure

.github/workflows/nightly_tests.yml

@@ -28,7 +28,7 @@ jobs:
       pipeline_test_matrix: ${{ steps.fetch_pipeline_matrix.outputs.pipeline_test_matrix }}
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           fetch-depth: 2
       - name: Install dependencies
@@ -44,7 +44,7 @@ jobs:
 
       - name: Pipeline Tests Artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: test-pipelines.json
           path: reports
@@ -64,7 +64,7 @@ jobs:
       options: --shm-size "16gb" --ipc host --gpus all
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           fetch-depth: 2
       - name: NVIDIA-SMI
@@ -97,7 +97,7 @@ jobs:
           cat reports/tests_pipeline_${{ matrix.module }}_cuda_failures_short.txt
       - name: Test suite reports artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: pipeline_${{ matrix.module }}_test_reports
           path: reports
@@ -119,7 +119,7 @@ jobs:
         module: [models, schedulers, lora, others, single_file, examples]
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -167,7 +167,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: torch_${{ matrix.module }}_cuda_test_reports
         path: reports
@@ -184,7 +184,7 @@ jobs:
 
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -211,7 +211,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: torch_compile_test_reports
         path: reports
@@ -228,7 +228,7 @@ jobs:
       options: --shm-size "16gb" --ipc host --gpus all
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           fetch-depth: 2
       - name: NVIDIA-SMI
@@ -263,7 +263,7 @@ jobs:
           cat reports/tests_big_gpu_torch_cuda_failures_short.txt
       - name: Test suite reports artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: torch_cuda_big_gpu_test_reports
           path: reports
@@ -280,7 +280,7 @@ jobs:
         shell: bash
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           fetch-depth: 2
 
@@ -321,7 +321,7 @@ jobs:
 
       - name: Test suite reports artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: torch_minimum_version_cuda_test_reports
           path: reports
@@ -355,7 +355,7 @@ jobs:
       options: --shm-size "20gb" --ipc host --gpus all
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           fetch-depth: 2
       - name: NVIDIA-SMI
@@ -391,7 +391,7 @@ jobs:
           cat reports/tests_${{ matrix.config.backend }}_torch_cuda_failures_short.txt
       - name: Test suite reports artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: torch_cuda_${{ matrix.config.backend }}_reports
           path: reports
@@ -408,7 +408,7 @@ jobs:
       options: --shm-size "20gb" --ipc host --gpus all
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           fetch-depth: 2
       - name: NVIDIA-SMI
@@ -441,7 +441,7 @@ jobs:
           cat reports/tests_pipeline_level_quant_torch_cuda_failures_short.txt
       - name: Test suite reports artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: torch_cuda_pipeline_level_quant_reports
           path: reports
@@ -466,7 +466,7 @@ jobs:
       image: diffusers/diffusers-pytorch-cpu
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           fetch-depth: 2
 
@@ -474,7 +474,7 @@ jobs:
         run: mkdir -p combined_reports
 
       - name: Download all test reports
-        uses: actions/download-artifact@v4
+        uses: actions/download-artifact@v7
         with:
           path: artifacts
 
@@ -500,7 +500,7 @@ jobs:
           cat $CONSOLIDATED_REPORT_PATH >> $GITHUB_STEP_SUMMARY
 
       - name: Upload consolidated report
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: consolidated_test_report
           path: ${{ env.CONSOLIDATED_REPORT_PATH }}
@@ -514,7 +514,7 @@ jobs:
 #
 #    steps:
 #      - name: Checkout diffusers
-#        uses: actions/checkout@v3
+#        uses: actions/checkout@v6
 #        with:
 #          fetch-depth: 2
 #
@@ -554,7 +554,7 @@ jobs:
 #
 #      - name: Test suite reports artifacts
 #        if: ${{ always() }}
-#        uses: actions/upload-artifact@v4
+#        uses: actions/upload-artifact@v6
 #        with:
 #          name: torch_mps_test_reports
 #          path: reports
@@ -570,7 +570,7 @@ jobs:
 #
 #    steps:
 #      - name: Checkout diffusers
-#        uses: actions/checkout@v3
+#        uses: actions/checkout@v6
 #        with:
 #          fetch-depth: 2
 #
@@ -610,7 +610,7 @@ jobs:
 #
 #      - name: Test suite reports artifacts
 #        if: ${{ always() }}
-#        uses: actions/upload-artifact@v4
+#        uses: actions/upload-artifact@v6
 #        with:
 #          name: torch_mps_test_reports
 #          path: reports

.github/workflows/notify_slack_about_release.yml

@@ -10,10 +10,10 @@ jobs:
     runs-on: ubuntu-22.04
 
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v6
 
     - name: Setup Python
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v6
       with:
         python-version: '3.8'
 

.github/workflows/pr_dependency_test.yml

@@ -18,9 +18,9 @@ jobs:
   check_dependencies:
     runs-on: ubuntu-22.04
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v6
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v6
         with:
           python-version: "3.8"
       - name: Install dependencies

.github/workflows/pr_modular_tests.yml

@@ -1,3 +1,4 @@
+
 name: Fast PR tests for Modular
 
 on:
@@ -35,9 +36,9 @@ jobs:
   check_code_quality:
     runs-on: ubuntu-22.04
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v6
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v6
         with:
           python-version: "3.10"
       - name: Install dependencies
@@ -55,9 +56,9 @@ jobs:
     needs: check_code_quality
     runs-on: ubuntu-22.04
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v6
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v6
         with:
           python-version: "3.10"
       - name: Install dependencies
@@ -77,23 +78,13 @@ jobs:
 
   run_fast_tests:
     needs: [check_code_quality, check_repository_consistency]
-    strategy:
-      fail-fast: false
-      matrix:
-        config:
-          - name: Fast PyTorch Modular Pipeline CPU tests
-            framework: pytorch_pipelines
-            runner: aws-highmemory-32-plus
-            image: diffusers/diffusers-pytorch-cpu
-            report: torch_cpu_modular_pipelines
-
-    name: ${{ matrix.config.name }}
+    name: Fast PyTorch Modular Pipeline CPU tests
 
     runs-on:
-      group: ${{ matrix.config.runner }}
+      group: aws-highmemory-32-plus
 
     container:
-      image: ${{ matrix.config.image }}
+      image: diffusers/diffusers-pytorch-cpu
       options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
 
     defaults:
@@ -102,7 +93,7 @@ jobs:
 
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -118,22 +109,19 @@ jobs:
         python utils/print_env.py
 
     - name: Run fast PyTorch Pipeline CPU tests
-      if: ${{ matrix.config.framework == 'pytorch_pipelines' }}
       run: |
         pytest -n 8 --max-worker-restart=0 --dist=loadfile \
           -k "not Flax and not Onnx" \
-          --make-reports=tests_${{ matrix.config.report }} \
+          --make-reports=tests_torch_cpu_modular_pipelines \
           tests/modular_pipelines
 
     - name: Failure short reports
       if: ${{ failure() }}
-      run: cat reports/tests_${{ matrix.config.report }}_failures_short.txt
+      run: cat reports/tests_torch_cpu_modular_pipelines_failures_short.txt
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
-        name: pr_${{ matrix.config.framework }}_${{ matrix.config.report }}_test_reports
+        name: pr_pytorch_pipelines_torch_cpu_modular_pipelines_test_reports
         path: reports
-
-

.github/workflows/pr_test_fetcher.yml

@@ -28,7 +28,7 @@ jobs:
       test_map: ${{ steps.set_matrix.outputs.test_map }}
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 0
     - name: Install dependencies
@@ -42,7 +42,7 @@ jobs:
       run: |
         python utils/tests_fetcher.py | tee test_preparation.txt
     - name: Report fetched tests
-      uses: actions/upload-artifact@v3
+      uses: actions/upload-artifact@v6
       with:
         name: test_fetched
         path: test_preparation.txt
@@ -83,7 +83,7 @@ jobs:
         shell: bash
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -109,7 +109,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v3
+      uses: actions/upload-artifact@v6
       with:
           name: ${{ matrix.modules }}_test_reports
           path: reports
@@ -138,7 +138,7 @@ jobs:
 
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -164,7 +164,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: pr_${{ matrix.config.report }}_test_reports
         path: reports

.github/workflows/pr_tests.yml

@@ -31,9 +31,9 @@ jobs:
   check_code_quality:
     runs-on: ubuntu-22.04
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v6
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v6
         with:
           python-version: "3.8"
       - name: Install dependencies
@@ -51,9 +51,9 @@ jobs:
     needs: check_code_quality
     runs-on: ubuntu-22.04
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v6
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v6
         with:
           python-version: "3.8"
       - name: Install dependencies
@@ -108,7 +108,7 @@ jobs:
 
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -153,7 +153,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: pr_${{ matrix.config.framework }}_${{ matrix.config.report }}_test_reports
         path: reports
@@ -185,7 +185,7 @@ jobs:
 
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -211,7 +211,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: pr_${{ matrix.config.report }}_test_reports
         path: reports
@@ -236,7 +236,7 @@ jobs:
 
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -273,7 +273,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: pr_main_test_reports
         path: reports

.github/workflows/pr_tests_gpu.yml

@@ -32,9 +32,9 @@ jobs:
   check_code_quality:
     runs-on: ubuntu-22.04
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v6
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v6
         with:
           python-version: "3.8"
       - name: Install dependencies
@@ -52,9 +52,9 @@ jobs:
     needs: check_code_quality
     runs-on: ubuntu-22.04
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v6
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v6
         with:
           python-version: "3.8"
       - name: Install dependencies
@@ -83,7 +83,7 @@ jobs:
       pipeline_test_matrix: ${{ steps.fetch_pipeline_matrix.outputs.pipeline_test_matrix }}
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           fetch-depth: 2
       - name: Install dependencies
@@ -100,7 +100,7 @@ jobs:
           echo "pipeline_test_matrix=$matrix" >> $GITHUB_OUTPUT
       - name: Pipeline Tests Artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: test-pipelines.json
           path: reports
@@ -120,7 +120,7 @@ jobs:
       options: --shm-size "16gb" --ipc host --gpus all
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           fetch-depth: 2
 
@@ -170,7 +170,7 @@ jobs:
           cat reports/tests_pipeline_${{ matrix.module }}_cuda_failures_short.txt
       - name: Test suite reports artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: pipeline_${{ matrix.module }}_test_reports
           path: reports
@@ -193,7 +193,7 @@ jobs:
         module: [models, schedulers, lora, others]
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -239,7 +239,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: torch_cuda_test_reports_${{ matrix.module }}
         path: reports
@@ -255,7 +255,7 @@ jobs:
       options: --gpus all --shm-size "16gb" --ipc host
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -287,7 +287,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: examples_test_reports
         path: reports

.github/workflows/pr_torch_dependency_test.yml

@@ -18,9 +18,9 @@ jobs:
   check_torch_dependencies:
     runs-on: ubuntu-22.04
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v6
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v6
         with:
           python-version: "3.8"
       - name: Install dependencies

.github/workflows/push_tests.yml

@@ -29,7 +29,7 @@ jobs:
       pipeline_test_matrix: ${{ steps.fetch_pipeline_matrix.outputs.pipeline_test_matrix }}
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           fetch-depth: 2
       - name: Install dependencies
@@ -46,7 +46,7 @@ jobs:
           echo "pipeline_test_matrix=$matrix" >> $GITHUB_OUTPUT
       - name: Pipeline Tests Artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: test-pipelines.json
           path: reports
@@ -66,7 +66,7 @@ jobs:
       options: --shm-size "16gb" --ipc host --gpus all
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           fetch-depth: 2
       - name: NVIDIA-SMI
@@ -98,7 +98,7 @@ jobs:
           cat reports/tests_pipeline_${{ matrix.module }}_cuda_failures_short.txt
       - name: Test suite reports artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: pipeline_${{ matrix.module }}_test_reports
           path: reports
@@ -120,7 +120,7 @@ jobs:
         module: [models, schedulers, lora, others, single_file]
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -155,7 +155,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: torch_cuda_test_reports_${{ matrix.module }}
         path: reports
@@ -172,7 +172,7 @@ jobs:
 
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -199,7 +199,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: torch_compile_test_reports
         path: reports
@@ -216,7 +216,7 @@ jobs:
 
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -240,7 +240,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: torch_xformers_test_reports
         path: reports
@@ -256,7 +256,7 @@ jobs:
       options: --gpus all --shm-size "16gb" --ipc host
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -286,7 +286,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: examples_test_reports
         path: reports

.github/workflows/push_tests_fast.yml

@@ -54,7 +54,7 @@ jobs:
 
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -88,7 +88,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: pr_${{ matrix.config.report }}_test_reports
         path: reports

.github/workflows/push_tests_mps.yml

@@ -23,7 +23,7 @@ jobs:
 
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -65,7 +65,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: pr_torch_mps_test_reports
         path: reports

.github/workflows/pypi_publish.yaml

@@ -15,10 +15,10 @@ jobs:
       latest_branch: ${{ steps.set_latest_branch.outputs.latest_branch }}
     steps:
       - name: Checkout Repo
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
 
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v6
         with:
           python-version: '3.8'
 
@@ -40,12 +40,12 @@ jobs:
 
     steps:
       - name: Checkout Repo
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           ref: ${{ needs.find-and-checkout-latest-branch.outputs.latest_branch }}
 
       - name: Setup Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v6
         with:
           python-version: "3.8"
 

.github/workflows/release_tests_fast.yml

@@ -27,7 +27,7 @@ jobs:
       pipeline_test_matrix: ${{ steps.fetch_pipeline_matrix.outputs.pipeline_test_matrix }}
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           fetch-depth: 2
       - name: Install dependencies
@@ -44,7 +44,7 @@ jobs:
           echo "pipeline_test_matrix=$matrix" >> $GITHUB_OUTPUT
       - name: Pipeline Tests Artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: test-pipelines.json
           path: reports
@@ -64,7 +64,7 @@ jobs:
       options: --shm-size "16gb" --ipc host --gpus all
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           fetch-depth: 2
       - name: NVIDIA-SMI
@@ -94,7 +94,7 @@ jobs:
           cat reports/tests_pipeline_${{ matrix.module }}_cuda_failures_short.txt
       - name: Test suite reports artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: pipeline_${{ matrix.module }}_test_reports
           path: reports
@@ -116,7 +116,7 @@ jobs:
         module: [models, schedulers, lora, others, single_file]
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -149,7 +149,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: torch_cuda_${{ matrix.module }}_test_reports
         path: reports
@@ -166,7 +166,7 @@ jobs:
         shell: bash
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           fetch-depth: 2
 
@@ -205,7 +205,7 @@ jobs:
 
       - name: Test suite reports artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: torch_minimum_version_cuda_test_reports
           path: reports
@@ -222,7 +222,7 @@ jobs:
 
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -247,7 +247,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: torch_compile_test_reports
         path: reports
@@ -264,7 +264,7 @@ jobs:
 
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -288,7 +288,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: torch_xformers_test_reports
         path: reports
@@ -305,7 +305,7 @@ jobs:
 
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -336,7 +336,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: examples_test_reports
         path: reports

.github/workflows/run_tests_from_a_pr.yml

@@ -57,7 +57,7 @@ jobs:
         shell: bash -e {0}
 
       - name: Checkout PR branch
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           ref: refs/pull/${{ inputs.pr_number }}/head
 

.github/workflows/ssh-pr-runner.yml

@@ -27,7 +27,7 @@ jobs:
 
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           fetch-depth: 2
 

.github/workflows/ssh-runner.yml

@@ -35,7 +35,7 @@ jobs:
 
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           fetch-depth: 2
 

.github/workflows/stale.yml

@@ -15,10 +15,10 @@ jobs:
     env:
       GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v6
 
     - name: Setup Python
-      uses: actions/setup-python@v1
+      uses: actions/setup-python@v6
       with:
         python-version: 3.8
 

.github/workflows/trufflehog.yml

@@ -8,7 +8,7 @@ jobs:
     runs-on: ubuntu-22.04
     steps:
     - name: Checkout code
-      uses: actions/checkout@v4
+      uses: actions/checkout@v6
       with:
         fetch-depth: 0
     - name: Secret Scanning

.github/workflows/typos.yml

@@ -8,7 +8,7 @@ jobs:
     runs-on: ubuntu-22.04
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v6
 
       - name: typos-action
         uses: crate-ci/typos@v1.12.4

.github/workflows/update_metadata.yml

@@ -15,7 +15,7 @@ jobs:
         shell: bash -l {0}
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v6
 
       - name: Setup environment
         run: |

CONTRIBUTING.md

@@ -1,506 +0,0 @@
-<!--Copyright 2025 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
--->
-
-# How to contribute to Diffusers 🧨
-
-We ❤️ contributions from the open-source community! Everyone is welcome, and all types of participation –not just code– are valued and appreciated. Answering questions, helping others, reaching out, and improving the documentation are all immensely valuable to the community, so don't be afraid and get involved if you're up for it!
-
-Everyone is encouraged to start by saying 👋 in our public Discord channel. We discuss the latest trends in diffusion models, ask questions, show off personal projects, help each other with contributions, or just hang out ☕. <a href="https://discord.gg/G7tWnz98XR"><img alt="Join us on Discord" src="https://img.shields.io/discord/823813159592001537?color=5865F2&logo=Discord&logoColor=white"></a>
-
-Whichever way you choose to contribute, we strive to be part of an open, welcoming, and kind community. Please, read our [code of conduct](https://github.com/huggingface/diffusers/blob/main/CODE_OF_CONDUCT.md) and be mindful to respect it during your interactions. We also recommend you become familiar with the [ethical guidelines](https://huggingface.co/docs/diffusers/conceptual/ethical_guidelines) that guide our project and ask you to adhere to the same principles of transparency and responsibility.
-
-We enormously value feedback from the community, so please do not be afraid to speak up if you believe you have valuable feedback that can help improve the library - every message, comment, issue, and pull request (PR) is read and considered.
-
-## Overview
-
-You can contribute in many ways ranging from answering questions on issues to adding new diffusion models to
-the core library.
-
-In the following, we give an overview of different ways to contribute, ranked by difficulty in ascending order. All of them are valuable to the community.
-
-* 1. Asking and answering questions on [the Diffusers discussion forum](https://discuss.huggingface.co/c/discussion-related-to-httpsgithubcomhuggingfacediffusers) or on [Discord](https://discord.gg/G7tWnz98XR).
-* 2. Opening new issues on [the GitHub Issues tab](https://github.com/huggingface/diffusers/issues/new/choose).
-* 3. Answering issues on [the GitHub Issues tab](https://github.com/huggingface/diffusers/issues).
-* 4. Fix a simple issue, marked by the "Good first issue" label, see [here](https://github.com/huggingface/diffusers/issues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22).
-* 5. Contribute to the [documentation](https://github.com/huggingface/diffusers/tree/main/docs/source).
-* 6. Contribute a [Community Pipeline](https://github.com/huggingface/diffusers/issues?q=is%3Aopen+is%3Aissue+label%3Acommunity-examples).
-* 7. Contribute to the [examples](https://github.com/huggingface/diffusers/tree/main/examples).
-* 8. Fix a more difficult issue, marked by the "Good second issue" label, see [here](https://github.com/huggingface/diffusers/issues?q=is%3Aopen+is%3Aissue+label%3A%22Good+second+issue%22).
-* 9. Add a new pipeline, model, or scheduler, see ["New Pipeline/Model"](https://github.com/huggingface/diffusers/issues?q=is%3Aopen+is%3Aissue+label%3A%22New+pipeline%2Fmodel%22) and ["New scheduler"](https://github.com/huggingface/diffusers/issues?q=is%3Aopen+is%3Aissue+label%3A%22New+scheduler%22) issues. For this contribution, please have a look at [Design Philosophy](https://github.com/huggingface/diffusers/blob/main/PHILOSOPHY.md).
-
-As said before, **all contributions are valuable to the community**.
-In the following, we will explain each contribution a bit more in detail.
-
-For all contributions 4-9, you will need to open a PR. It is explained in detail how to do so in [Opening a pull request](#how-to-open-a-pr).
-
-### 1. Asking and answering questions on the Diffusers discussion forum or on the Diffusers Discord
-
-Any question or comment related to the Diffusers library can be asked on the [discussion forum](https://discuss.huggingface.co/c/discussion-related-to-httpsgithubcomhuggingfacediffusers/) or on [Discord](https://discord.gg/G7tWnz98XR). Such questions and comments include (but are not limited to):
-- Reports of training or inference experiments in an attempt to share knowledge
-- Presentation of personal projects
-- Questions to non-official training examples
-- Project proposals
-- General feedback
-- Paper summaries
-- Asking for help on personal projects that build on top of the Diffusers library
-- General questions
-- Ethical questions regarding diffusion models
-- ...
-
-Every question that is asked on the forum or on Discord actively encourages the community to publicly
-share knowledge and might very well help a beginner in the future who has the same question you're
-having. Please do pose any questions you might have.
-In the same spirit, you are of immense help to the community by answering such questions because this way you are publicly documenting knowledge for everybody to learn from.
-
-**Please** keep in mind that the more effort you put into asking or answering a question, the higher
-the quality of the publicly documented knowledge. In the same way, well-posed and well-answered questions create a high-quality knowledge database accessible to everybody, while badly posed questions or answers reduce the overall quality of the public knowledge database.
-In short, a high quality question or answer is *precise*, *concise*, *relevant*, *easy-to-understand*, *accessible*, and *well-formatted/well-posed*. For more information, please have a look through the [How to write a good issue](#how-to-write-a-good-issue) section.
-
-**NOTE about channels**:
-[*The forum*](https://discuss.huggingface.co/c/discussion-related-to-httpsgithubcomhuggingfacediffusers/63) is much better indexed by search engines, such as Google. Posts are ranked by popularity rather than chronologically. Hence, it's easier to look up questions and answers that we posted some time ago.
-In addition, questions and answers posted in the forum can easily be linked to.
-In contrast, *Discord* has a chat-like format that invites fast back-and-forth communication.
-While it will most likely take less time for you to get an answer to your question on Discord, your
-question won't be visible anymore over time. Also, it's much harder to find information that was posted a while back on Discord. We therefore strongly recommend using the forum for high-quality questions and answers in an attempt to create long-lasting knowledge for the community. If discussions on Discord lead to very interesting answers and conclusions, we recommend posting the results on the forum to make the information more available for future readers.
-
-### 2. Opening new issues on the GitHub issues tab
-
-The 🧨 Diffusers library is robust and reliable thanks to the users who notify us of
-the problems they encounter. So thank you for reporting an issue.
-
-Remember, GitHub issues are reserved for technical questions directly related to the Diffusers library, bug reports, feature requests, or feedback on the library design.
-
-In a nutshell, this means that everything that is **not** related to the **code of the Diffusers library** (including the documentation) should **not** be asked on GitHub, but rather on either the [forum](https://discuss.huggingface.co/c/discussion-related-to-httpsgithubcomhuggingfacediffusers/63) or [Discord](https://discord.gg/G7tWnz98XR).
-
-**Please consider the following guidelines when opening a new issue**:
-- Make sure you have searched whether your issue has already been asked before (use the search bar on GitHub under Issues).
-- Please never report a new issue on another (related) issue. If another issue is highly related, please
-open a new issue nevertheless and link to the related issue.
-- Make sure your issue is written in English. Please use one of the great, free online translation services, such as [DeepL](https://www.deepl.com/translator) to translate from your native language to English if you are not comfortable in English.
-- Check whether your issue might be solved by updating to the newest Diffusers version. Before posting your issue, please make sure that `python -c "import diffusers; print(diffusers.__version__)"` is higher or matches the latest Diffusers version.
-- Remember that the more effort you put into opening a new issue, the higher the quality of your answer will be and the better the overall quality of the Diffusers issues.
-
-New issues usually include the following.
-
-#### 2.1. Reproducible, minimal bug reports
-
-A bug report should always have a reproducible code snippet and be as minimal and concise as possible.
-This means in more detail:
-- Narrow the bug down as much as you can, **do not just dump your whole code file**.
-- Format your code.
-- Do not include any external libraries except for Diffusers depending on them.
-- **Always** provide all necessary information about your environment; for this, you can run: `diffusers-cli env` in your shell and copy-paste the displayed information to the issue.
-- Explain the issue. If the reader doesn't know what the issue is and why it is an issue, she cannot solve it.
-- **Always** make sure the reader can reproduce your issue with as little effort as possible. If your code snippet cannot be run because of missing libraries or undefined variables, the reader cannot help you. Make sure your reproducible code snippet is as minimal as possible and can be copy-pasted into a simple Python shell.
-- If in order to reproduce your issue a model and/or dataset is required, make sure the reader has access to that model or dataset. You can always upload your model or dataset to the [Hub](https://huggingface.co) to make it easily downloadable. Try to keep your model and dataset as small as possible, to make the reproduction of your issue as effortless as possible.
-
-For more information, please have a look through the [How to write a good issue](#how-to-write-a-good-issue) section.
-
-You can open a bug report [here](https://github.com/huggingface/diffusers/issues/new?assignees=&labels=bug&projects=&template=bug-report.yml).
-
-#### 2.2. Feature requests
-
-A world-class feature request addresses the following points:
-
-1. Motivation first:
-* Is it related to a problem/frustration with the library? If so, please explain
-why. Providing a code snippet that demonstrates the problem is best.
-* Is it related to something you would need for a project? We'd love to hear
-about it!
-* Is it something you worked on and think could benefit the community?
-Awesome! Tell us what problem it solved for you.
-2. Write a *full paragraph* describing the feature;
-3. Provide a **code snippet** that demonstrates its future use;
-4. In case this is related to a paper, please attach a link;
-5. Attach any additional information (drawings, screenshots, etc.) you think may help.
-
-You can open a feature request [here](https://github.com/huggingface/diffusers/issues/new?assignees=&labels=&template=feature_request.md&title=).
-
-#### 2.3 Feedback
-
-Feedback about the library design and why it is good or not good helps the core maintainers immensely to build a user-friendly library. To understand the philosophy behind the current design philosophy, please have a look [here](https://huggingface.co/docs/diffusers/conceptual/philosophy). If you feel like a certain design choice does not fit with the current design philosophy, please explain why and how it should be changed. If a certain design choice follows the design philosophy too much, hence restricting use cases, explain why and how it should be changed.
-If a certain design choice is very useful for you, please also leave a note as this is great feedback for future design decisions.
-
-You can open an issue about feedback [here](https://github.com/huggingface/diffusers/issues/new?assignees=&labels=&template=feedback.md&title=).
-
-#### 2.4 Technical questions
-
-Technical questions are mainly about why certain code of the library was written in a certain way, or what a certain part of the code does. Please make sure to link to the code in question and please provide detail on
-why this part of the code is difficult to understand.
-
-You can open an issue about a technical question [here](https://github.com/huggingface/diffusers/issues/new?assignees=&labels=bug&template=bug-report.yml).
-
-#### 2.5 Proposal to add a new model, scheduler, or pipeline
-
-If the diffusion model community released a new model, pipeline, or scheduler that you would like to see in the Diffusers library, please provide the following information:
-
-* Short description of the diffusion pipeline, model, or scheduler and link to the paper or public release.
-* Link to any of its open-source implementation.
-* Link to the model weights if they are available.
-
-If you are willing to contribute to the model yourself, let us know so we can best guide you. Also, don't forget
-to tag the original author of the component (model, scheduler, pipeline, etc.) by GitHub handle if you can find it.
-
-You can open a request for a model/pipeline/scheduler [here](https://github.com/huggingface/diffusers/issues/new?assignees=&labels=New+model%2Fpipeline%2Fscheduler&template=new-model-addition.yml).
-
-### 3. Answering issues on the GitHub issues tab
-
-Answering issues on GitHub might require some technical knowledge of Diffusers, but we encourage everybody to give it a try even if you are not 100% certain that your answer is correct.
-Some tips to give a high-quality answer to an issue:
-- Be as concise and minimal as possible.
-- Stay on topic. An answer to the issue should concern the issue and only the issue.
-- Provide links to code, papers, or other sources that prove or encourage your point.
-- Answer in code. If a simple code snippet is the answer to the issue or shows how the issue can be solved, please provide a fully reproducible code snippet.
-
-Also, many issues tend to be simply off-topic, duplicates of other issues, or irrelevant. It is of great
-help to the maintainers if you can answer such issues, encouraging the author of the issue to be
-more precise, provide the link to a duplicated issue or redirect them to [the forum](https://discuss.huggingface.co/c/discussion-related-to-httpsgithubcomhuggingfacediffusers/63) or [Discord](https://discord.gg/G7tWnz98XR).
-
-If you have verified that the issued bug report is correct and requires a correction in the source code,
-please have a look at the next sections.
-
-For all of the following contributions, you will need to open a PR. It is explained in detail how to do so in the [Opening a pull request](#how-to-open-a-pr) section.
-
-### 4. Fixing a "Good first issue"
-
-*Good first issues* are marked by the [Good first issue](https://github.com/huggingface/diffusers/issues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22) label. Usually, the issue already
-explains how a potential solution should look so that it is easier to fix.
-If the issue hasn't been closed and you would like to try to fix this issue, you can just leave a message "I would like to try this issue.". There are usually three scenarios:
-- a.) The issue description already proposes a fix. In this case and if the solution makes sense to you, you can open a PR or draft PR to fix it.
-- b.) The issue description does not propose a fix. In this case, you can ask what a proposed fix could look like and someone from the Diffusers team should answer shortly. If you have a good idea of how to fix it, feel free to directly open a PR.
-- c.) There is already an open PR to fix the issue, but the issue hasn't been closed yet. If the PR has gone stale, you can simply open a new PR and link to the stale PR. PRs often go stale if the original contributor who wanted to fix the issue suddenly cannot find the time anymore to proceed. This often happens in open-source and is very normal. In this case, the community will be very happy if you give it a new try and leverage the knowledge of the existing PR. If there is already a PR and it is active, you can help the author by giving suggestions, reviewing the PR or even asking whether you can contribute to the PR.
-
-
-### 5. Contribute to the documentation
-
-A good library **always** has good documentation! The official documentation is often one of the first points of contact for new users of the library, and therefore contributing to the documentation is a **highly
-valuable contribution**.
-
-Contributing to the library can have many forms:
-
-- Correcting spelling or grammatical errors.
-- Correct incorrect formatting of the docstring. If you see that the official documentation is weirdly displayed or a link is broken, we are very happy if you take some time to correct it.
-- Correct the shape or dimensions of a docstring input or output tensor.
-- Clarify documentation that is hard to understand or incorrect.
-- Update outdated code examples.
-- Translating the documentation to another language.
-
-Anything displayed on [the official Diffusers doc page](https://huggingface.co/docs/diffusers/index) is part of the official documentation and can be corrected, adjusted in the respective [documentation source](https://github.com/huggingface/diffusers/tree/main/docs/source).
-
-Please have a look at [this page](https://github.com/huggingface/diffusers/tree/main/docs) on how to verify changes made to the documentation locally.
-
-
-### 6. Contribute a community pipeline
-
-[Pipelines](https://huggingface.co/docs/diffusers/api/pipelines/overview) are usually the first point of contact between the Diffusers library and the user.
-Pipelines are examples of how to use Diffusers [models](https://huggingface.co/docs/diffusers/api/models/overview) and [schedulers](https://huggingface.co/docs/diffusers/api/schedulers/overview).
-We support two types of pipelines:
-
-- Official Pipelines
-- Community Pipelines
-
-Both official and community pipelines follow the same design and consist of the same type of components.
-
-Official pipelines are tested and maintained by the core maintainers of Diffusers. Their code
-resides in [src/diffusers/pipelines](https://github.com/huggingface/diffusers/tree/main/src/diffusers/pipelines).
-In contrast, community pipelines are contributed and maintained purely by the **community** and are **not** tested.
-They reside in [examples/community](https://github.com/huggingface/diffusers/tree/main/examples/community) and while they can be accessed via the [PyPI diffusers package](https://pypi.org/project/diffusers/), their code is not part of the PyPI distribution.
-
-The reason for the distinction is that the core maintainers of the Diffusers library cannot maintain and test all
-possible ways diffusion models can be used for inference, but some of them may be of interest to the community.
-Officially released diffusion pipelines,
-such as Stable Diffusion are added to the core src/diffusers/pipelines package which ensures
-high quality of maintenance, no backward-breaking code changes, and testing.
-More bleeding edge pipelines should be added as community pipelines. If usage for a community pipeline is high, the pipeline can be moved to the official pipelines upon request from the community. This is one of the ways we strive to be a community-driven library.
-
-To add a community pipeline, one should add a <name-of-the-community>.py file to [examples/community](https://github.com/huggingface/diffusers/tree/main/examples/community) and adapt the [examples/community/README.md](https://github.com/huggingface/diffusers/tree/main/examples/community/README.md) to include an example of the new pipeline.
-
-An example can be seen [here](https://github.com/huggingface/diffusers/pull/2400).
-
-Community pipeline PRs are only checked at a superficial level and ideally they should be maintained by their original authors.
-
-Contributing a community pipeline is a great way to understand how Diffusers models and schedulers work. Having contributed a community pipeline is usually the first stepping stone to contributing an official pipeline to the
-core package.
-
-### 7. Contribute to training examples
-
-Diffusers examples are a collection of training scripts that reside in [examples](https://github.com/huggingface/diffusers/tree/main/examples).
-
-We support two types of training examples:
-
-- Official training examples
-- Research training examples
-
-Research training examples are located in [examples/research_projects](https://github.com/huggingface/diffusers/tree/main/examples/research_projects) whereas official training examples include all folders under [examples](https://github.com/huggingface/diffusers/tree/main/examples) except the `research_projects` and `community` folders.
-The official training examples are maintained by the Diffusers' core maintainers whereas the research training examples are maintained by the community.
-This is because of the same reasons put forward in [6. Contribute a community pipeline](#6-contribute-a-community-pipeline) for official pipelines vs. community pipelines: It is not feasible for the core maintainers to maintain all possible training methods for diffusion models.
-If the Diffusers core maintainers and the community consider a certain training paradigm to be too experimental or not popular enough, the corresponding training code should be put in the `research_projects` folder and maintained by the author.
-
-Both official training and research examples consist of a directory that contains one or more training scripts, a `requirements.txt` file, and a `README.md` file. In order for the user to make use of the
-training examples, it is required to clone the repository:
-
-```bash
-git clone https://github.com/huggingface/diffusers
-```
-
-as well as to install all additional dependencies required for training:
-
-```bash
-cd diffusers
-pip install -r examples/<your-example-folder>/requirements.txt
-```
-
-Therefore when adding an example, the `requirements.txt` file shall define all pip dependencies required for your training example so that once all those are installed, the user can run the example's training script. See, for example, the [DreamBooth `requirements.txt` file](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/requirements.txt).
-
-Training examples of the Diffusers library should adhere to the following philosophy:
-- All the code necessary to run the examples should be found in a single Python file.
-- One should be able to run the example from the command line with `python <your-example>.py --args`.
-- Examples should be kept simple and serve as **an example** on how to use Diffusers for training. The purpose of example scripts is **not** to create state-of-the-art diffusion models, but rather to reproduce known training schemes without adding too much custom logic. As a byproduct of this point, our examples also strive to serve as good educational materials.
-
-To contribute an example, it is highly recommended to look at already existing examples such as [dreambooth](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/train_dreambooth.py) to get an idea of how they should look like.
-We strongly advise contributors to make use of the [Accelerate library](https://github.com/huggingface/accelerate) as it's tightly integrated
-with Diffusers.
-Once an example script works, please make sure to add a comprehensive `README.md` that states how to use the example exactly. This README should include:
-- An example command on how to run the example script as shown [here e.g.](https://github.com/huggingface/diffusers/tree/main/examples/dreambooth#running-locally-with-pytorch).
-- A link to some training results (logs, models, ...) that show what the user can expect as shown [here e.g.](https://api.wandb.ai/report/patrickvonplaten/xm6cd5q5).
-- If you are adding a non-official/research training example, **please don't forget** to add a sentence that you are maintaining this training example which includes your git handle as shown [here](https://github.com/huggingface/diffusers/tree/main/examples/research_projects/intel_opts#diffusers-examples-with-intel-optimizations).
-
-If you are contributing to the official training examples, please also make sure to add a test to [examples/test_examples.py](https://github.com/huggingface/diffusers/blob/main/examples/test_examples.py). This is not necessary for non-official training examples.
-
-### 8. Fixing a "Good second issue"
-
-*Good second issues* are marked by the [Good second issue](https://github.com/huggingface/diffusers/issues?q=is%3Aopen+is%3Aissue+label%3A%22Good+second+issue%22) label. Good second issues are
-usually more complicated to solve than [Good first issues](https://github.com/huggingface/diffusers/issues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22).
-The issue description usually gives less guidance on how to fix the issue and requires
-a decent understanding of the library by the interested contributor.
-If you are interested in tackling a good second issue, feel free to open a PR to fix it and link the PR to the issue. If you see that a PR has already been opened for this issue but did not get merged, have a look to understand why it wasn't merged and try to open an improved PR.
-Good second issues are usually more difficult to get merged compared to good first issues, so don't hesitate to ask for help from the core maintainers. If your PR is almost finished the core maintainers can also jump into your PR and commit to it in order to get it merged.
-
-### 9. Adding pipelines, models, schedulers
-
-Pipelines, models, and schedulers are the most important pieces of the Diffusers library.
-They provide easy access to state-of-the-art diffusion technologies and thus allow the community to
-build powerful generative AI applications.
-
-By adding a new model, pipeline, or scheduler you might enable a new powerful use case for any of the user interfaces relying on Diffusers which can be of immense value for the whole generative AI ecosystem.
-
-Diffusers has a couple of open feature requests for all three components - feel free to gloss over them
-if you don't know yet what specific component you would like to add:
-- [Model or pipeline](https://github.com/huggingface/diffusers/issues?q=is%3Aopen+is%3Aissue+label%3A%22New+pipeline%2Fmodel%22)
-- [Scheduler](https://github.com/huggingface/diffusers/issues?q=is%3Aopen+is%3Aissue+label%3A%22New+scheduler%22)
-
-Before adding any of the three components, it is strongly recommended that you give the [Philosophy guide](https://github.com/huggingface/diffusers/blob/main/PHILOSOPHY.md) a read to better understand the design of any of the three components. Please be aware that
-we cannot merge model, scheduler, or pipeline additions that strongly diverge from our design philosophy
-as it will lead to API inconsistencies. If you fundamentally disagree with a design choice, please
-open a [Feedback issue](https://github.com/huggingface/diffusers/issues/new?assignees=&labels=&template=feedback.md&title=) instead so that it can be discussed whether a certain design
-pattern/design choice shall be changed everywhere in the library and whether we shall update our design philosophy. Consistency across the library is very important for us.
-
-Please make sure to add links to the original codebase/paper to the PR and ideally also ping the
-original author directly on the PR so that they can follow the progress and potentially help with questions.
-
-If you are unsure or stuck in the PR, don't hesitate to leave a message to ask for a first review or help.
-
-## How to write a good issue
-
-**The better your issue is written, the higher the chances that it will be quickly resolved.**
-
-1. Make sure that you've used the correct template for your issue. You can pick between *Bug Report*, *Feature Request*, *Feedback about API Design*, *New model/pipeline/scheduler addition*, *Forum*, or a blank issue. Make sure to pick the correct one when opening [a new issue](https://github.com/huggingface/diffusers/issues/new/choose).
-2. **Be precise**: Give your issue a fitting title. Try to formulate your issue description as simple as possible. The more precise you are when submitting an issue, the less time it takes to understand the issue and potentially solve it. Make sure to open an issue for one issue only and not for multiple issues. If you found multiple issues, simply open multiple issues. If your issue is a bug, try to be as precise as possible about what bug it is - you should not just write "Error in diffusers".
-3. **Reproducibility**: No reproducible code snippet == no solution. If you encounter a bug, maintainers **have to be able to reproduce** it. Make sure that you include a code snippet that can be copy-pasted into a Python interpreter to reproduce the issue. Make sure that your code snippet works, *i.e.* that there are no missing imports or missing links to images, ... Your issue should contain an error message **and** a code snippet that can be copy-pasted without any changes to reproduce the exact same error message. If your issue is using local model weights or local data that cannot be accessed by the reader, the issue cannot be solved. If you cannot share your data or model, try to make a dummy model or dummy data.
-4. **Minimalistic**: Try to help the reader as much as you can to understand the issue as quickly as possible by staying as concise as possible. Remove all code / all information that is irrelevant to the issue. If you have found a bug, try to create the easiest code example you can to demonstrate your issue, do not just dump your whole workflow into the issue as soon as you have found a bug. E.g., if you train a model and get an error at some point during the training, you should first try to understand what part of the training code is responsible for the error and try to reproduce it with a couple of lines. Try to use dummy data instead of full datasets.
-5. Add links. If you are referring to a certain naming, method, or model make sure to provide a link so that the reader can better understand what you mean. If you are referring to a specific PR or issue, make sure to link it to your issue. Do not assume that the reader knows what you are talking about. The more links you add to your issue the better.
-6. Formatting. Make sure to nicely format your issue by formatting code into Python code syntax, and error messages into normal code syntax. See the [official GitHub formatting docs](https://docs.github.com/en/get-started/writing-on-github/getting-started-with-writing-and-formatting-on-github/basic-writing-and-formatting-syntax) for more information.
-7. Think of your issue not as a ticket to be solved, but rather as a beautiful entry to a well-written encyclopedia. Every added issue is a contribution to publicly available knowledge. By adding a nicely written issue you not only make it easier for maintainers to solve your issue, but you are helping the whole community to better understand a certain aspect of the library.
-
-## How to write a good PR
-
-1. Be a chameleon. Understand existing design patterns and syntax and make sure your code additions flow seamlessly into the existing code base. Pull requests that significantly diverge from existing design patterns or user interfaces will not be merged.
-2. Be laser focused. A pull request should solve one problem and one problem only. Make sure to not fall into the trap of "also fixing another problem while we're adding it". It is much more difficult to review pull requests that solve multiple, unrelated problems at once.
-3. If helpful, try to add a code snippet that displays an example of how your addition can be used.
-4. The title of your pull request should be a summary of its contribution.
-5. If your pull request addresses an issue, please mention the issue number in
-the pull request description to make sure they are linked (and people
-consulting the issue know you are working on it);
-6. To indicate a work in progress please prefix the title with `[WIP]`. These
-are useful to avoid duplicated work, and to differentiate it from PRs ready
-to be merged;
-7. Try to formulate and format your text as explained in [How to write a good issue](#how-to-write-a-good-issue).
-8. Make sure existing tests pass;
-9. Add high-coverage tests. No quality testing = no merge.
-- If you are adding new `@slow` tests, make sure they pass using
-`RUN_SLOW=1 python -m pytest tests/test_my_new_model.py`.
-CircleCI does not run the slow tests, but GitHub Actions does every night!
-10. All public methods must have informative docstrings that work nicely with markdown. See [`pipeline_latent_diffusion.py`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/latent_diffusion/pipeline_latent_diffusion.py) for an example.
-11. Due to the rapidly growing repository, it is important to make sure that no files that would significantly weigh down the repository are added. This includes images, videos, and other non-text files. We prefer to leverage a hf.co hosted `dataset` like
-[`hf-internal-testing`](https://huggingface.co/hf-internal-testing) or [huggingface/documentation-images](https://huggingface.co/datasets/huggingface/documentation-images) to place these files.
-If an external contribution, feel free to add the images to your PR and ask a Hugging Face member to migrate your images
-to this dataset.
-
-## How to open a PR
-
-Before writing code, we strongly advise you to search through the existing PRs or
-issues to make sure that nobody is already working on the same thing. If you are
-unsure, it is always a good idea to open an issue to get some feedback.
-
-You will need basic `git` proficiency to be able to contribute to
-🧨 Diffusers. `git` is not the easiest tool to use but it has the greatest
-manual. Type `git --help` in a shell and enjoy. If you prefer books, [Pro
-Git](https://git-scm.com/book/en/v2) is a very good reference.
-
-Follow these steps to start contributing ([supported Python versions](https://github.com/huggingface/diffusers/blob/42f25d601a910dceadaee6c44345896b4cfa9928/setup.py#L270)):
-
-1. Fork the [repository](https://github.com/huggingface/diffusers) by
-clicking on the 'Fork' button on the repository's page. This creates a copy of the code
-under your GitHub user account.
-
-2. Clone your fork to your local disk, and add the base repository as a remote:
-
- ```bash
- $ git clone git@github.com:<your GitHub handle>/diffusers.git
- $ cd diffusers
- $ git remote add upstream https://github.com/huggingface/diffusers.git
- ```
-
-3. Create a new branch to hold your development changes:
-
- ```bash
- $ git checkout -b a-descriptive-name-for-my-changes
- ```
-
-**Do not** work on the `main` branch.
-
-4. Set up a development environment by running the following command in a virtual environment:
-
- ```bash
- $ pip install -e ".[dev]"
- ```
-
-If you have already cloned the repo, you might need to `git pull` to get the most recent changes in the
-library.
-
-5. Develop the features on your branch.
-
-As you work on the features, you should make sure that the test suite
-passes. You should run the tests impacted by your changes like this:
-
- ```bash
- $ pytest tests/<TEST_TO_RUN>.py
- ```
-
-Before you run the tests, please make sure you install the dependencies required for testing. You can do so
-with this command:
-
- ```bash
- $ pip install -e ".[test]"
- ```
-
-You can also run the full test suite with the following command, but it takes
-a beefy machine to produce a result in a decent amount of time now that
-Diffusers has grown a lot. Here is the command for it:
-
- ```bash
- $ make test
- ```
-
-🧨 Diffusers relies on `ruff` and `isort` to format its source code
-consistently. After you make changes, apply automatic style corrections and code verifications
-that can't be automated in one go with:
-
- ```bash
- $ make style
- ```
-
-🧨 Diffusers also uses `ruff` and a few custom scripts to check for coding mistakes. Quality
-control runs in CI, however, you can also run the same checks with:
-
- ```bash
- $ make quality
- ```
-
-Once you're happy with your changes, add changed files using `git add` and
-make a commit with `git commit` to record your changes locally:
-
- ```bash
- $ git add modified_file.py
- $ git commit -m "A descriptive message about your changes."
- ```
-
-It is a good idea to sync your copy of the code with the original
-repository regularly. This way you can quickly account for changes:
-
- ```bash
- $ git pull upstream main
- ```
-
-Push the changes to your account using:
-
- ```bash
- $ git push -u origin a-descriptive-name-for-my-changes
- ```
-
-6. Once you are satisfied, go to the
-webpage of your fork on GitHub. Click on 'Pull request' to send your changes
-to the project maintainers for review.
-
-7. It's ok if maintainers ask you for changes. It happens to core contributors
-too! So everyone can see the changes in the Pull request, work in your local
-branch and push the changes to your fork. They will automatically appear in
-the pull request.
-
-### Tests
-
-An extensive test suite is included to test the library behavior and several examples. Library tests can be found in
-the [tests folder](https://github.com/huggingface/diffusers/tree/main/tests).
-
-We like `pytest` and `pytest-xdist` because it's faster. From the root of the
-repository, here's how to run tests with `pytest` for the library:
-
-```bash
-$ python -m pytest -n auto --dist=loadfile -s -v ./tests/
-```
-
-In fact, that's how `make test` is implemented!
-
-You can specify a smaller set of tests in order to test only the feature
-you're working on.
-
-By default, slow tests are skipped. Set the `RUN_SLOW` environment variable to
-`yes` to run them. This will download many gigabytes of models — make sure you
-have enough disk space and a good Internet connection, or a lot of patience!
-
-```bash
-$ RUN_SLOW=yes python -m pytest -n auto --dist=loadfile -s -v ./tests/
-```
-
-`unittest` is fully supported, here's how to run tests with it:
-
-```bash
-$ python -m unittest discover -s tests -t . -v
-$ python -m unittest discover -s examples -t examples -v
-```
-
-### Syncing forked main with upstream (HuggingFace) main
-
-To avoid pinging the upstream repository which adds reference notes to each upstream PR and sends unnecessary notifications to the developers involved in these PRs,
-when syncing the main branch of a forked repository, please, follow these steps:
-1. When possible, avoid syncing with the upstream using a branch and PR on the forked repository. Instead, merge directly into the forked main.
-2. If a PR is absolutely necessary, use the following steps after checking out your branch:
-```bash
-$ git checkout -b your-branch-for-syncing
-$ git pull --squash --no-commit upstream main
-$ git commit -m '<your message without GitHub references>'
-$ git push --set-upstream origin your-branch-for-syncing
-```
-
-### Style guide
-
-For documentation strings, 🧨 Diffusers follows the [Google style](https://google.github.io/styleguide/pyguide.html).

CONTRIBUTING.md

@@ -0,0 +1 @@
+docs/source/en/conceptual/contribution.md

docker/diffusers-pytorch-cuda/Dockerfile

@@ -1,8 +1,8 @@
-FROM nvidia/cuda:12.1.0-runtime-ubuntu20.04
+FROM nvidia/cuda:12.8.0-runtime-ubuntu22.04
 LABEL maintainer="Hugging Face"
 LABEL repository="diffusers"
 
-ARG PYTHON_VERSION=3.12
+ARG PYTHON_VERSION=3.11
 ENV DEBIAN_FRONTEND=noninteractive
 
 RUN apt-get -y update \
@@ -32,10 +32,12 @@ RUN uv venv --python ${PYTHON_VERSION} --seed ${VIRTUAL_ENV}
 ENV PATH="$VIRTUAL_ENV/bin:$PATH"
 
 # pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
+# Install torch, torchvision, and torchaudio together to ensure compatibility
 RUN uv pip install --no-cache-dir \
     torch \
     torchvision \
-    torchaudio
+    torchaudio \
+    --index-url https://download.pytorch.org/whl/cu128
 
 RUN uv pip install --no-cache-dir "git+https://github.com/huggingface/diffusers.git@main#egg=diffusers[test]"
 

docker/diffusers-pytorch-xformers-cuda/Dockerfile

@@ -1,8 +1,8 @@
-FROM nvidia/cuda:12.1.0-runtime-ubuntu20.04
+FROM nvidia/cuda:12.8.0-runtime-ubuntu22.04
 LABEL maintainer="Hugging Face"
 LABEL repository="diffusers"
 
-ARG PYTHON_VERSION=3.12
+ARG PYTHON_VERSION=3.11
 ENV DEBIAN_FRONTEND=noninteractive
 
 RUN apt-get -y update \
@@ -32,10 +32,12 @@ RUN uv venv --python ${PYTHON_VERSION} --seed ${VIRTUAL_ENV}
 ENV PATH="$VIRTUAL_ENV/bin:$PATH"
 
 # pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
+# Install torch, torchvision, and torchaudio together to ensure compatibility
 RUN uv pip install --no-cache-dir \
     torch \
     torchvision \
-    torchaudio
+    torchaudio \
+    --index-url https://download.pytorch.org/whl/cu128
 
 RUN uv pip install --no-cache-dir "git+https://github.com/huggingface/diffusers.git@main#egg=diffusers[test]"
 

docs/source/en/_toctree.yml

@@ -54,6 +54,8 @@
     title: Batch inference
   - local: training/distributed_inference
     title: Distributed inference
+  - local: hybrid_inference/overview
+    title: Remote inference
   title: Inference
 - isExpanded: false
   sections:
@@ -88,17 +90,6 @@
       title: FreeU
     title: Community optimizations
   title: Inference optimization
-- isExpanded: false
-  sections:
-  - local: hybrid_inference/overview
-    title: Overview
-  - local: hybrid_inference/vae_decode
-    title: VAE Decode
-  - local: hybrid_inference/vae_encode
-    title: VAE Encode
-  - local: hybrid_inference/api_reference
-    title: API Reference
-  title: Hybrid Inference
 - isExpanded: false
   sections:
   - local: modular_diffusers/overview
@@ -270,6 +261,8 @@
       title: Outputs
     - local: api/quantization
       title: Quantization
+    - local: hybrid_inference/api_reference
+      title: Remote inference
     - local: api/parallel
       title: Parallel inference
     title: Main Classes
@@ -353,16 +346,24 @@
         title: Flux2Transformer2DModel
       - local: api/models/flux_transformer
         title: FluxTransformer2DModel
+      - local: api/models/glm_image_transformer2d
+        title: GlmImageTransformer2DModel
       - local: api/models/hidream_image_transformer
         title: HiDreamImageTransformer2DModel
       - local: api/models/hunyuan_transformer2d
         title: HunyuanDiT2DModel
       - local: api/models/hunyuanimage_transformer_2d
         title: HunyuanImageTransformer2DModel
+      - local: api/models/hunyuan_video15_transformer_3d
+        title: HunyuanVideo15Transformer3DModel
       - local: api/models/hunyuan_video_transformer_3d
         title: HunyuanVideoTransformer3DModel
       - local: api/models/latte_transformer3d
         title: LatteTransformer3DModel
+      - local: api/models/longcat_image_transformer2d
+        title: LongCatImageTransformer2DModel
+      - local: api/models/ltx2_video_transformer3d
+        title: LTX2VideoTransformer3DModel
       - local: api/models/ltx_video_transformer3d
         title: LTXVideoTransformer3DModel
       - local: api/models/lumina2_transformer2d
@@ -373,6 +374,8 @@
         title: MochiTransformer3DModel
       - local: api/models/omnigen_transformer
         title: OmniGenTransformer2DModel
+      - local: api/models/ovisimage_transformer2d
+        title: OvisImageTransformer2DModel
       - local: api/models/pixart_transformer2d
         title: PixArtTransformer2DModel
       - local: api/models/prior_transformer
@@ -397,6 +400,8 @@
         title: WanAnimateTransformer3DModel
       - local: api/models/wan_transformer_3d
         title: WanTransformer3DModel
+      - local: api/models/z_image_transformer2d
+        title: ZImageTransformer2DModel
       title: Transformers
     - sections:
       - local: api/models/stable_cascade_unet
@@ -433,6 +438,12 @@
         title: AutoencoderKLHunyuanImageRefiner
       - local: api/models/autoencoder_kl_hunyuan_video
         title: AutoencoderKLHunyuanVideo
+      - local: api/models/autoencoder_kl_hunyuan_video15
+        title: AutoencoderKLHunyuanVideo15
+      - local: api/models/autoencoderkl_audio_ltx_2
+        title: AutoencoderKLLTX2Audio
+      - local: api/models/autoencoderkl_ltx_2
+        title: AutoencoderKLLTX2Video
       - local: api/models/autoencoderkl_ltx_video
         title: AutoencoderKLLTXVideo
       - local: api/models/autoencoderkl_magvit
@@ -485,6 +496,8 @@
         title: Bria 3.2
       - local: api/pipelines/bria_fibo
         title: Bria Fibo
+      - local: api/pipelines/bria_fibo_edit
+        title: Bria Fibo Edit
       - local: api/pipelines/chroma
         title: Chroma
       - local: api/pipelines/cogview3
@@ -531,6 +544,8 @@
         title: Flux2
       - local: api/pipelines/control_flux_inpaint
         title: FluxControlInpaint
+      - local: api/pipelines/glm_image
+        title: GLM-Image
       - local: api/pipelines/hidream
         title: HiDream-I1
       - local: api/pipelines/hunyuandit
@@ -545,6 +560,8 @@
         title: Kandinsky 2.2
       - local: api/pipelines/kandinsky3
         title: Kandinsky 3
+      - local: api/pipelines/kandinsky5_image
+        title: Kandinsky 5.0 Image
       - local: api/pipelines/kolors
         title: Kolors
       - local: api/pipelines/latent_consistency_models
@@ -553,6 +570,8 @@
         title: Latent Diffusion
       - local: api/pipelines/ledits_pp
         title: LEDITS++
+      - local: api/pipelines/longcat_image
+        title: LongCat-Image
       - local: api/pipelines/lumina2
         title: Lumina 2.0
       - local: api/pipelines/lumina
@@ -563,6 +582,8 @@
         title: MultiDiffusion
       - local: api/pipelines/omnigen
         title: OmniGen
+      - local: api/pipelines/ovis_image
+        title: Ovis-Image
       - local: api/pipelines/pag
         title: PAG
       - local: api/pipelines/paint_by_example
@@ -638,6 +659,8 @@
         title: VisualCloze
       - local: api/pipelines/wuerstchen
         title: Wuerstchen
+      - local: api/pipelines/z_image
+        title: Z-Image
       title: Image
     - sections:
       - local: api/pipelines/allegro
@@ -652,12 +675,16 @@
         title: Framepack
       - local: api/pipelines/hunyuan_video
         title: HunyuanVideo
+      - local: api/pipelines/hunyuan_video15
+        title: HunyuanVideo1.5
       - local: api/pipelines/i2vgenxl
         title: I2VGen-XL
       - local: api/pipelines/kandinsky5_video
         title: Kandinsky 5.0 Video
       - local: api/pipelines/latte
         title: Latte
+      - local: api/pipelines/ltx2
+        title: LTX-2
       - local: api/pipelines/ltx_video
         title: LTXVideo
       - local: api/pipelines/mochi

docs/source/en/api/cache.md

@@ -29,8 +29,14 @@ Cache methods speedup diffusion transformers by storing and reusing intermediate
 
 [[autodoc]] apply_faster_cache
 
-### FirstBlockCacheConfig
+## FirstBlockCacheConfig
 
 [[autodoc]] FirstBlockCacheConfig
 
 [[autodoc]] apply_first_block_cache
+
+### TaylorSeerCacheConfig
+
+[[autodoc]] TaylorSeerCacheConfig
+
+[[autodoc]] apply_taylorseer_cache

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

@@ -31,7 +31,9 @@ LoRA is a fast and lightweight training method that inserts and trains a signifi
 - [`AmusedLoraLoaderMixin`] is for the [`AmusedPipeline`].
 - [`HiDreamImageLoraLoaderMixin`] provides similar functions for [HiDream Image](https://huggingface.co/docs/diffusers/main/en/api/pipelines/hidream)
 - [`QwenImageLoraLoaderMixin`] provides similar functions for [Qwen Image](https://huggingface.co/docs/diffusers/main/en/api/pipelines/qwen).
+- [`ZImageLoraLoaderMixin`] provides similar functions for [Z-Image](https://huggingface.co/docs/diffusers/main/en/api/pipelines/zimage).
 - [`Flux2LoraLoaderMixin`] provides similar functions for [Flux2](https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux2).
+- [`LTX2LoraLoaderMixin`] provides similar functions for [Flux2](https://huggingface.co/docs/diffusers/main/en/api/pipelines/ltx2).
 - [`LoraBaseMixin`] provides a base class with several utility methods to fuse, unfuse, unload, LoRAs and more.
 
 > [!TIP]
@@ -61,6 +63,10 @@ LoRA is a fast and lightweight training method that inserts and trains a signifi
 
 [[autodoc]] loaders.lora_pipeline.Flux2LoraLoaderMixin
 
+## LTX2LoraLoaderMixin
+
+[[autodoc]] loaders.lora_pipeline.LTX2LoraLoaderMixin
+
 ## CogVideoXLoraLoaderMixin
 
 [[autodoc]] loaders.lora_pipeline.CogVideoXLoraLoaderMixin
@@ -112,6 +118,10 @@ LoRA is a fast and lightweight training method that inserts and trains a signifi
 
 [[autodoc]] loaders.lora_pipeline.QwenImageLoraLoaderMixin
 
+## ZImageLoraLoaderMixin
+
+[[autodoc]] loaders.lora_pipeline.ZImageLoraLoaderMixin
+
 ## KandinskyLoraLoaderMixin
 [[autodoc]] loaders.lora_pipeline.KandinskyLoraLoaderMixin
 

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

@@ -0,0 +1,36 @@
+<!-- Copyright 2025 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License. -->
+
+# AutoencoderKLHunyuanVideo15
+
+The 3D variational autoencoder (VAE) model with KL loss used in [HunyuanVideo1.5](https://github.com/Tencent/HunyuanVideo1-1.5) by Tencent.
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import AutoencoderKLHunyuanVideo15
+
+vae = AutoencoderKLHunyuanVideo15.from_pretrained("hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v", subfolder="vae", torch_dtype=torch.float32)
+
+# make sure to enable tiling to avoid OOM
+vae.enable_tiling()
+```
+
+## AutoencoderKLHunyuanVideo15
+
+[[autodoc]] AutoencoderKLHunyuanVideo15
+  - decode
+  - encode
+  - all
+
+## DecoderOutput
+
+[[autodoc]] models.autoencoders.vae.DecoderOutput

docs/source/en/api/models/autoencoderkl_audio_ltx_2.md

@@ -0,0 +1,29 @@
+<!-- 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. -->
+
+# AutoencoderKLLTX2Audio
+
+The 3D variational autoencoder (VAE) model with KL loss used in [LTX-2](https://huggingface.co/Lightricks/LTX-2) was introduced by Lightricks. This is for encoding and decoding audio latent representations.
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import AutoencoderKLLTX2Audio
+
+vae = AutoencoderKLLTX2Audio.from_pretrained("Lightricks/LTX-2", subfolder="vae", torch_dtype=torch.float32).to("cuda")
+```
+
+## AutoencoderKLLTX2Audio
+
+[[autodoc]] AutoencoderKLLTX2Audio
+    - encode
+    - decode
+    - all

docs/source/en/api/models/autoencoderkl_ltx_2.md

@@ -0,0 +1,29 @@
+<!-- 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. -->
+
+# AutoencoderKLLTX2Video
+
+The 3D variational autoencoder (VAE) model with KL loss used in [LTX-2](https://huggingface.co/Lightricks/LTX-2) was introduced by Lightricks.
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import AutoencoderKLLTX2Video
+
+vae = AutoencoderKLLTX2Video.from_pretrained("Lightricks/LTX-2", subfolder="vae", torch_dtype=torch.float32).to("cuda")
+```
+
+## AutoencoderKLLTX2Video
+
+[[autodoc]] AutoencoderKLLTX2Video
+    - decode
+    - encode
+    - all

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

@@ -33,6 +33,21 @@ url = "https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5/blob/m
 pipe = StableDiffusionControlNetPipeline.from_single_file(url, controlnet=controlnet)
 ```
 
+## Loading from Control LoRA
+
+Control-LoRA is introduced by Stability AI in [stabilityai/control-lora](https://huggingface.co/stabilityai/control-lora) by adding low-rank parameter efficient fine tuning to ControlNet. This approach offers a more efficient and compact method to bring model control to a wider variety of consumer GPUs.
+
+```py
+from diffusers import ControlNetModel, UNet2DConditionModel
+
+lora_id = "stabilityai/control-lora"
+lora_filename = "control-LoRAs-rank128/control-lora-canny-rank128.safetensors"
+
+unet = UNet2DConditionModel.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", subfolder="unet", torch_dtype=torch.bfloat16).to("cuda")
+controlnet = ControlNetModel.from_unet(unet).to(device="cuda", dtype=torch.bfloat16)
+controlnet.load_lora_adapter(lora_id, weight_name=lora_filename, prefix=None, controlnet_config=controlnet.config)
+```
+
 ## ControlNetModel
 
 [[autodoc]] ControlNetModel

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

@@ -42,4 +42,4 @@ pipe = FluxControlNetPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", co
 
 ## FluxControlNetOutput
 
-[[autodoc]] models.controlnet_flux.FluxControlNetOutput
+[[autodoc]] models.controlnets.controlnet_flux.FluxControlNetOutput

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

@@ -43,4 +43,4 @@ controlnet = SparseControlNetModel.from_pretrained("guoyww/animatediff-sparsectr
 
 ## SparseControlNetOutput
 
-[[autodoc]] models.controlnet_sparsectrl.SparseControlNetOutput
+[[autodoc]] models.controlnets.controlnet_sparsectrl.SparseControlNetOutput

docs/source/en/api/models/glm_image_transformer2d.md

@@ -0,0 +1,18 @@
+<!--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. -->
+
+# GlmImageTransformer2DModel
+
+A Diffusion Transformer model for 2D data from [GlmImageTransformer2DModel] (TODO).
+
+## GlmImageTransformer2DModel
+
+[[autodoc]] GlmImageTransformer2DModel

docs/source/en/api/models/hunyuan_video15_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. -->
+
+# HunyuanVideo15Transformer3DModel
+
+A Diffusion Transformer model for 3D video-like data used in [HunyuanVideo1.5](https://github.com/Tencent/HunyuanVideo1-1.5).
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import HunyuanVideo15Transformer3DModel
+
+transformer = HunyuanVideo15Transformer3DModel.from_pretrained("hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v" subfolder="transformer", torch_dtype=torch.bfloat16)
+```
+
+## HunyuanVideo15Transformer3DModel
+
+[[autodoc]] HunyuanVideo15Transformer3DModel
+
+## Transformer2DModelOutput
+
+[[autodoc]] models.modeling_outputs.Transformer2DModelOutput

docs/source/en/api/models/longcat_image_transformer2d.md

@@ -0,0 +1,25 @@
+<!--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.
+-->
+
+# LongCatImageTransformer2DModel
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import LongCatImageTransformer2DModel
+
+transformer = LongCatImageTransformer2DModel.from_pretrained("meituan-longcat/LongCat-Image ", subfolder="transformer", torch_dtype=torch.bfloat16)
+```
+
+## LongCatImageTransformer2DModel
+
+[[autodoc]] LongCatImageTransformer2DModel

docs/source/en/api/models/ltx2_video_transformer3d.md

@@ -0,0 +1,26 @@
+<!-- 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. -->
+
+# LTX2VideoTransformer3DModel
+
+A Diffusion Transformer model for 3D data from [LTX](https://huggingface.co/Lightricks/LTX-2) was introduced by Lightricks.
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import LTX2VideoTransformer3DModel
+
+transformer = LTX2VideoTransformer3DModel.from_pretrained("Lightricks/LTX-2", subfolder="transformer", torch_dtype=torch.bfloat16).to("cuda")
+```
+
+## LTX2VideoTransformer3DModel
+
+[[autodoc]] LTX2VideoTransformer3DModel

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

@@ -0,0 +1,24 @@
+<!-- Copyright 2025 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License. -->
+
+# OvisImageTransformer2DModel
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import OvisImageTransformer2DModel
+
+transformer = OvisImageTransformer2DModel.from_pretrained("AIDC-AI/Ovis-Image-7B", subfolder="transformer", torch_dtype=torch.bfloat16)
+```
+
+## OvisImageTransformer2DModel
+
+[[autodoc]] OvisImageTransformer2DModel

docs/source/en/api/models/z_image_transformer2d.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.
+-->
+
+# ZImageTransformer2DModel
+
+A Transformer model for image-like data from [Z-Image](https://huggingface.co/Tongyi-MAI/Z-Image-Turbo).
+
+## ZImageTransformer2DModel
+
+[[autodoc]] ZImageTransformer2DModel

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

@@ -21,9 +21,10 @@ With only 8 billion parameters, FIBO provides a new level of image quality, prom
 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.
+> [!NOTE]
+> Avoid using freeform text prompts directly with FIBO because it does not produce the best results.
 
-you can learn more about FIBO in  [Bria Fibo Hugging Face page](https://huggingface.co/briaai/FIBO).
+Refer to the Bria Fibo Hugging Face [page](https://huggingface.co/briaai/FIBO) to learn more.
 
 
 ## Usage
@@ -37,9 +38,8 @@ hf auth login
 ```
 
 
-## BriaPipeline
+## BriaFiboPipeline
 
-[[autodoc]] BriaPipeline
+[[autodoc]] BriaFiboPipeline
 	- all
-	- __call__
-
+	- __call__

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

@@ -0,0 +1,33 @@
+<!--Copyright 2025 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# Bria Fibo Edit
+
+Fibo Edit is an 8B parameter image-to-image model that introduces a new paradigm of structured control, operating on JSON inputs paired with source images to enable deterministic and repeatable editing workflows.
+Featuring native masking for granular precision, it moves beyond simple prompt-based diffusion to offer explicit, interpretable control optimized for production environments.
+Its lightweight architecture is designed for deep customization, empowering researchers to build specialized "Edit" models for domain-specific tasks while delivering top-tier aesthetic quality
+
+## 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-Edit), 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
+```
+
+
+## BriaFiboEditPipeline
+
+[[autodoc]] BriaFiboEditPipeline
+	- all
+	- __call__

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

@@ -99,3 +99,9 @@ image.save("chroma-single-file.png")
 [[autodoc]] ChromaImg2ImgPipeline
 	- all
 	- __call__
+
+## ChromaInpaintPipeline
+
+[[autodoc]] ChromaInpaintPipeline
+  - all
+  - __call__

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

@@ -30,6 +30,10 @@
 
 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.
 
+Available Models/LoRAs:
+- [nvidia/ChronoEdit-14B-Diffusers](https://huggingface.co/nvidia/ChronoEdit-14B-Diffusers)
+- [nvidia/ChronoEdit-14B-Diffusers-Upscaler-Lora](https://huggingface.co/nvidia/ChronoEdit-14B-Diffusers-Upscaler-Lora)
+- [nvidia/ChronoEdit-14B-Diffusers-Paint-Brush-Lora](https://huggingface.co/nvidia/ChronoEdit-14B-Diffusers-Paint-Brush-Lora)
 
 ### Image Editing
 
@@ -100,6 +104,7 @@ Image.fromarray((output[-1] * 255).clip(0, 255).astype("uint8")).save("output.pn
 import torch
 import numpy as np
 from diffusers import AutoencoderKLWan, ChronoEditTransformer3DModel, ChronoEditPipeline
+from diffusers.schedulers import UniPCMultistepScheduler
 from diffusers.utils import export_to_video, load_image
 from transformers import CLIPVisionModel
 from PIL import Image
@@ -109,9 +114,8 @@ image_encoder = CLIPVisionModel.from_pretrained(model_id, subfolder="image_encod
 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.load_lora_weights("nvidia/ChronoEdit-14B-Diffusers", weight_name="lora/chronoedit_distill_lora.safetensors", adapter_name="distill")
+pipe.fuse_lora(adapter_names=["distill"], lora_scale=1.0)
 pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config, flow_shift=2.0)
 pipe.to("cuda")
 
@@ -145,6 +149,57 @@ export_to_video(output, "output.mp4", fps=16)
 Image.fromarray((output[-1] * 255).clip(0, 255).astype("uint8")).save("output.png")
 ```
 
+### Inference with Multiple LoRAs
+
+```py
+import torch
+import numpy as np
+from diffusers import AutoencoderKLWan, ChronoEditTransformer3DModel, ChronoEditPipeline
+from diffusers.schedulers import UniPCMultistepScheduler
+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.load_lora_weights("nvidia/ChronoEdit-14B-Diffusers-Paint-Brush-Lora", weight_name="paintbrush_lora_diffusers.safetensors", adapter_name="paintbrush")
+pipe.load_lora_weights("nvidia/ChronoEdit-14B-Diffusers", weight_name="lora/chronoedit_distill_lora.safetensors", adapter_name="distill")
+pipe.fuse_lora(adapter_names=["paintbrush", "distill"], lora_scale=1.0)
+pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config, flow_shift=2.0)
+pipe.to("cuda")
+
+image = load_image(
+    "https://raw.githubusercontent.com/nv-tlabs/ChronoEdit/refs/heads/main/assets/images/input_paintbrush.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 = (
+    "Turn the pencil sketch in the image into an actual object that is consistent with the image’s content. The user wants to change the sketch to a crown and a hat."
+)
+
+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_1.png")
+```
+
 ## ChronoEditPipeline
 
 [[autodoc]] ChronoEditPipeline

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

@@ -70,6 +70,12 @@ output.save("output.png")
   - all
   - __call__
 
+## Cosmos2_5_PredictBasePipeline
+
+[[autodoc]] Cosmos2_5_PredictBasePipeline
+  - all
+  - __call__
+
 ## CosmosPipelineOutput
 
 [[autodoc]] pipelines.cosmos.pipeline_output.CosmosPipelineOutput

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

@@ -21,7 +21,7 @@ The abstract from the paper is:
 
 *Image generation has recently seen tremendous advances, with diffusion models allowing to synthesize convincing images for a large variety of text prompts. In this article, we propose DiffEdit, a method to take advantage of text-conditioned diffusion models for the task of semantic image editing, where the goal is to edit an image based on a text query. Semantic image editing is an extension of image generation, with the additional constraint that the generated image should be as similar as possible to a given input image. Current editing methods based on diffusion models usually require to provide a mask, making the task much easier by treating it as a conditional inpainting task. In contrast, our main contribution is able to automatically generate a mask highlighting regions of the input image that need to be edited, by contrasting predictions of a diffusion model conditioned on different text prompts. Moreover, we rely on latent inference to preserve content in those regions of interest and show excellent synergies with mask-based diffusion. DiffEdit achieves state-of-the-art editing performance on ImageNet. In addition, we evaluate semantic image editing in more challenging settings, using images from the COCO dataset as well as text-based generated images.*
 
-The original codebase can be found at [Xiang-cd/DiffEdit-stable-diffusion](https://github.com/Xiang-cd/DiffEdit-stable-diffusion), and you can try it out in this [demo](https://blog.problemsolversguild.com/technical/research/2022/11/02/DiffEdit-Implementation.html).
+The original codebase can be found at [Xiang-cd/DiffEdit-stable-diffusion](https://github.com/Xiang-cd/DiffEdit-stable-diffusion), and you can try it out in this [demo](https://blog.problemsolversguild.com/posts/2022-11-02-diffedit-implementation.html).
 
 This pipeline was contributed by [clarencechen](https://github.com/clarencechen). ❤️
 

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

@@ -26,8 +26,20 @@ Original model checkpoints for Flux can be found [here](https://huggingface.co/b
 >
 > [Caching](../../optimization/cache) may also speed up inference by storing and reusing intermediate outputs.
 
+## Caption upsampling
+
+Flux.2 can potentially generate better better outputs with better prompts. We can "upsample"
+an input prompt by setting the `caption_upsample_temperature` argument in the pipeline call arguments.
+The [official implementation](https://github.com/black-forest-labs/flux2/blob/5a5d316b1b42f6b59a8c9194b77c8256be848432/src/flux2/text_encoder.py#L140) recommends this value to be 0.15.
+
 ## Flux2Pipeline
 
 [[autodoc]] Flux2Pipeline
+	- all
+	- __call__
+
+## Flux2KleinPipeline
+
+[[autodoc]] Flux2KleinPipeline
 	- all
 	- __call__

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

@@ -0,0 +1,95 @@
+<!--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.
+-->
+
+# GLM-Image
+
+## Overview
+
+GLM-Image is an image generation model adopts a hybrid autoregressive + diffusion decoder architecture, effectively pushing the upper bound of visual fidelity and fine-grained details. In general image generation quality, it aligns with industry-standard LDM-based approaches, while demonstrating significant advantages in knowledge-intensive image generation scenarios.
+
+Model architecture: a hybrid autoregressive + diffusion decoder design、
+
++ Autoregressive generator: a 9B-parameter model initialized from [GLM-4-9B-0414](https://huggingface.co/zai-org/GLM-4-9B-0414), with an expanded vocabulary to incorporate visual tokens. The model first generates a compact encoding of approximately 256 tokens, then expands to 1K–4K tokens, corresponding to 1K–2K high-resolution image outputs. You can check AR model in class `GlmImageForConditionalGeneration` of `transformers` library.
++ Diffusion Decoder: a 7B-parameter decoder based on a single-stream DiT architecture for latent-space image decoding. It is equipped with a Glyph Encoder text module, significantly improving accurate text rendering within images.
+
+Post-training with decoupled reinforcement learning: the model introduces a fine-grained, modular feedback strategy using the GRPO algorithm, substantially enhancing both semantic understanding and visual detail quality.
+
++ Autoregressive module: provides low-frequency feedback signals focused on aesthetics and semantic alignment, improving instruction following and artistic expressiveness.
++ Decoder module: delivers high-frequency feedback targeting detail fidelity and text accuracy, resulting in highly realistic textures, lighting, and color reproduction, as well as more precise text rendering.
+
+GLM-Image supports both text-to-image and image-to-image generation within a single model
+
++ Text-to-image: generates high-detail images from textual descriptions, with particularly strong performance in information-dense scenarios.
++ Image-to-image: supports a wide range of tasks, including image editing, style transfer, multi-subject consistency, and identity-preserving generation for people and objects.
+
+This pipeline was contributed by [zRzRzRzRzRzRzR](https://github.com/zRzRzRzRzRzRzR). The codebase can be found [here](https://huggingface.co/zai-org/GLM-Image).
+
+## Usage examples
+
+### Text to Image Generation
+
+```python
+import torch
+from diffusers.pipelines.glm_image import GlmImagePipeline
+
+pipe = GlmImagePipeline.from_pretrained("zai-org/GLM-Image",torch_dtype=torch.bfloat16,device_map="cuda")
+prompt = "A beautifully designed modern food magazine style dessert recipe illustration, themed around a raspberry mousse cake. The overall layout is clean and bright, divided into four main areas: the top left features a bold black title 'Raspberry Mousse Cake Recipe Guide', with a soft-lit close-up photo of the finished cake on the right, showcasing a light pink cake adorned with fresh raspberries and mint leaves; the bottom left contains an ingredient list section, titled 'Ingredients' in a simple font, listing 'Flour 150g', 'Eggs 3', 'Sugar 120g', 'Raspberry puree 200g', 'Gelatin sheets 10g', 'Whipping cream 300ml', and 'Fresh raspberries', each accompanied by minimalist line icons (like a flour bag, eggs, sugar jar, etc.); the bottom right displays four equally sized step boxes, each containing high-definition macro photos and corresponding instructions, arranged from top to bottom as follows: Step 1 shows a whisk whipping white foam (with the instruction 'Whip egg whites to stiff peaks'), Step 2 shows a red-and-white mixture being folded with a spatula (with the instruction 'Gently fold in the puree and batter'), Step 3 shows pink liquid being poured into a round mold (with the instruction 'Pour into mold and chill for 4 hours'), Step 4 shows the finished cake decorated with raspberries and mint leaves (with the instruction 'Decorate with raspberries and mint'); a light brown information bar runs along the bottom edge, with icons on the left representing 'Preparation time: 30 minutes', 'Cooking time: 20 minutes', and 'Servings: 8'. The overall color scheme is dominated by creamy white and light pink, with a subtle paper texture in the background, featuring compact and orderly text and image layout with clear information hierarchy."
+image = pipe(
+    prompt=prompt,
+    height=32 * 32,
+    width=36 * 32,
+    num_inference_steps=30,
+    guidance_scale=1.5,
+    generator=torch.Generator(device="cuda").manual_seed(42),
+).images[0]
+
+image.save("output_t2i.png")
+```
+
+### Image to Image Generation
+
+```python
+import torch
+from diffusers.pipelines.glm_image import GlmImagePipeline
+from PIL import Image
+
+pipe = GlmImagePipeline.from_pretrained("zai-org/GLM-Image",torch_dtype=torch.bfloat16,device_map="cuda")
+image_path = "cond.jpg" 
+prompt = "Replace the background of the snow forest with an underground station featuring an automatic escalator."
+image = Image.open(image_path).convert("RGB")
+image = pipe(
+    prompt=prompt,
+    image=[image], # can input multiple images for multi-image-to-image generation such as [image, image1]
+    height=33 * 32,
+    width=32 * 32,
+    num_inference_steps=30,
+    guidance_scale=1.5,
+    generator=torch.Generator(device="cuda").manual_seed(42),
+).images[0]
+
+image.save("output_i2i.png")
+```
+
++ Since the AR model used in GLM-Image is configured with `do_sample=True` and a temperature of `0.95` by default, the generated images can vary significantly across runs. We do not recommend setting do_sample=False, as this may lead to incorrect or degenerate outputs from the AR model.
+
+## GlmImagePipeline
+
+[[autodoc]] pipelines.glm_image.pipeline_glm_image.GlmImagePipeline
+  - all
+  - __call__
+
+## GlmImagePipelineOutput
+
+[[autodoc]] pipelines.glm_image.pipeline_output.GlmImagePipelineOutput

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

@@ -0,0 +1,120 @@
+<!-- Copyright 2025 The HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License. -->
+
+
+# HunyuanVideo-1.5
+
+HunyuanVideo-1.5 is a lightweight yet powerful video generation model that achieves state-of-the-art visual quality and motion coherence with only 8.3 billion parameters, enabling efficient inference on consumer-grade GPUs. This achievement is built upon several key components, including meticulous data curation, an advanced DiT architecture with selective and sliding tile attention (SSTA), enhanced bilingual understanding through glyph-aware text encoding, progressive pre-training and post-training, and an efficient video super-resolution network. Leveraging these designs, we developed a unified framework capable of high-quality text-to-video and image-to-video generation across multiple durations and resolutions. Extensive experiments demonstrate that this compact and proficient model establishes a new state-of-the-art among open-source models.
+
+You can find all the original HunyuanVideo checkpoints under the [Tencent](https://huggingface.co/tencent) organization.
+
+> [!TIP]
+> Click on the HunyuanVideo models in the right sidebar for more examples of video generation tasks.
+>
+> The examples below use a checkpoint from [hunyuanvideo-community](https://huggingface.co/hunyuanvideo-community) because the weights are stored in a layout compatible with Diffusers.
+
+The example below demonstrates how to generate a video optimized for memory or inference speed.
+
+<hfoptions id="usage">
+<hfoption id="memory">
+
+Refer to the [Reduce memory usage](../../optimization/memory) guide for more details about the various memory saving techniques.
+
+
+```py
+import torch
+from diffusers import AutoModel, HunyuanVideo15Pipeline
+from diffusers.utils import export_to_video
+
+
+pipeline = HunyuanVideo15Pipeline.from_pretrained(
+    "HunyuanVideo-1.5-Diffusers-480p_t2v",
+    torch_dtype=torch.bfloat16,
+)
+
+# model-offloading and tiling
+pipeline.enable_model_cpu_offload()
+pipeline.vae.enable_tiling()
+
+prompt = "A fluffy teddy bear sits on a bed of soft pillows surrounded by children's toys."
+video = pipeline(prompt=prompt, num_frames=61, num_inference_steps=30).frames[0]
+export_to_video(video, "output.mp4", fps=15)
+```
+
+## Notes
+
+- HunyuanVideo1.5 use attention masks with variable-length sequences. For best performance, we recommend using an attention backend that handles padding efficiently.
+
+    - **H100/H800:** `_flash_3_hub` or `_flash_3_varlen_hub`
+    - **A100/A800/RTX 4090:** `flash_hub` or `flash_varlen_hub`
+    - **Other GPUs:** `sage_hub`
+
+Refer to the [Attention backends](../../optimization/attention_backends) guide for more details about using a different backend.
+
+
+```py
+pipe.transformer.set_attention_backend("flash_hub")  # or your preferred backend
+```
+
+- [`HunyuanVideo15Pipeline`] use guider and does not take `guidance_scale` parameter at runtime. 
+
+You can check the default guider configuration using `pipe.guider`:
+
+```py
+>>> pipe.guider 
+ClassifierFreeGuidance {
+  "_class_name": "ClassifierFreeGuidance",
+  "_diffusers_version": "0.36.0.dev0",
+  "enabled": true,
+  "guidance_rescale": 0.0,
+  "guidance_scale": 6.0,
+  "start": 0.0,
+  "stop": 1.0,
+  "use_original_formulation": false
+}
+
+State:
+  step: None
+  num_inference_steps: None
+  timestep: None
+  count_prepared: 0
+  enabled: True
+  num_conditions: 2
+```
+
+To update guider configuration, you can run `pipe.guider = pipe.guider.new(...)`
+
+```py
+pipe.guider = pipe.guider.new(guidance_scale=5.0)
+```
+
+Read more on Guider [here](../../modular_diffusers/guiders).
+
+
+
+## HunyuanVideo15Pipeline
+
+[[autodoc]] HunyuanVideo15Pipeline
+  - all
+  - __call__
+
+## HunyuanVideo15ImageToVideoPipeline
+
+[[autodoc]] HunyuanVideo15ImageToVideoPipeline
+  - all
+  - __call__
+
+## HunyuanVideo15PipelineOutput
+
+[[autodoc]] pipelines.hunyuan_video1_5.pipeline_output.HunyuanVideo15PipelineOutput

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

@@ -0,0 +1,116 @@
+<!--Copyright 2025 The HuggingFace Team and Kandinsky Lab Team. All rights reserved.
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+http://www.apache.org/licenses/LICENSE-2.0
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# Kandinsky 5.0 Image
+
+[Kandinsky 5.0](https://arxiv.org/abs/2511.14993) is a family of diffusion models for Video & Image generation. 
+
+Kandinsky 5.0 Image Lite is a lightweight image generation model (6B parameters).
+
+The model introduces several key innovations:
+- **Latent diffusion pipeline** with **Flow Matching** for improved training stability
+- **Diffusion Transformer (DiT)** as the main generative backbone with cross-attention to text embeddings
+- Dual text encoding using **Qwen2.5-VL** and **CLIP** for comprehensive text understanding
+- **Flux VAE** for efficient image encoding and decoding
+
+The original codebase can be found at [kandinskylab/Kandinsky-5](https://github.com/kandinskylab/Kandinsky-5).
+
+> [!TIP]
+> Check out the [Kandinsky Lab](https://huggingface.co/kandinskylab) organization on the Hub for the official model checkpoints for text-to-video generation, including pretrained, SFT, no-CFG, and distilled variants.
+
+
+## Available Models
+
+Kandinsky 5.0 Image Lite:
+
+| model_id | Description | Use Cases |
+|------------|-------------|-----------|
+| [**kandinskylab/Kandinsky-5.0-T2I-Lite-sft-Diffusers**](https://huggingface.co/kandinskylab/Kandinsky-5.0-T2I-Lite-sft-Diffusers) | 6B image Supervised Fine-Tuned model | Highest generation quality |
+| [**kandinskylab/Kandinsky-5.0-I2I-Lite-sft-Diffusers**](https://huggingface.co/kandinskylab/Kandinsky-5.0-I2I-Lite-sft-Diffusers) | 6B image editing Supervised Fine-Tuned model | Highest generation quality |
+| [**kandinskylab/Kandinsky-5.0-T2I-Lite-pretrain-Diffusers**](https://huggingface.co/kandinskylab/Kandinsky-5.0-T2I-Lite-pretrain-Diffusers) | 6B image Base pretrained model | Research and fine-tuning |
+| [**kandinskylab/Kandinsky-5.0-I2I-Lite-pretrain-Diffusers**](https://huggingface.co/kandinskylab/Kandinsky-5.0-I2I-Lite-pretrain-Diffusers) | 6B image editing Base pretrained model | Research and fine-tuning |
+
+## Usage Examples
+
+### Basic Text-to-Image Generation
+
+```python
+import torch
+from diffusers import Kandinsky5T2IPipeline
+
+# Load the pipeline
+model_id = "kandinskylab/Kandinsky-5.0-T2I-Lite-sft-Diffusers"
+pipe = Kandinsky5T2IPipeline.from_pretrained(model_id)
+_ = pipe.to(device='cuda',dtype=torch.bfloat16)
+
+# Generate image
+prompt = "A fluffy, expressive cat wearing a bright red hat with a soft, slightly textured fabric. The hat should look cozy and well-fitted on the cat’s head. On the front of the hat, add clean, bold white text that reads “SWEET”, clearly visible and neatly centered. Ensure the overall lighting highlights the hat’s color and the cat’s fur details."
+
+output = pipe(
+    prompt=prompt,
+    negative_prompt="",
+    height=1024,
+    width=1024,
+    num_inference_steps=50,
+    guidance_scale=3.5,
+).image[0]
+```
+
+### Basic Image-to-Image Generation
+
+```python
+import torch
+from diffusers import Kandinsky5I2IPipeline
+from diffusers.utils import load_image 
+# Load the pipeline
+model_id = "kandinskylab/Kandinsky-5.0-I2I-Lite-sft-Diffusers"
+pipe = Kandinsky5I2IPipeline.from_pretrained(model_id)
+
+_ = pipe.to(device='cuda',dtype=torch.bfloat16)
+pipe.enable_model_cpu_offload()                                               # <--- Enable CPU offloading for single GPU inference
+
+# Edit the input image
+image = load_image(
+    "https://huggingface.co/kandinsky-community/kandinsky-3/resolve/main/assets/title.jpg?download=true"
+)
+
+prompt = "Change the background from a winter night scene to a bright summer day. Place the character on a sandy beach with clear blue sky, soft sunlight, and gentle waves in the distance. Replace the winter clothing with a light short-sleeved T-shirt (in soft pastel colors) and casual shorts. Ensure the character’s fur reflects warm daylight instead of cold winter tones. Add small beach details such as seashells, footprints in the sand, and a few scattered beach toys nearby. Keep the oranges in the scene, but place them naturally on the sand."
+negative_prompt = ""
+
+output = pipe(
+    image=image,
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    guidance_scale=3.5,
+).image[0]
+```
+
+
+## Kandinsky5T2IPipeline
+
+[[autodoc]] Kandinsky5T2IPipeline
+    - all
+    - __call__
+
+## Kandinsky5I2IPipeline
+
+[[autodoc]] Kandinsky5I2IPipeline
+    - all
+    - __call__
+
+
+## Citation
+```bibtex
+@misc{kandinsky2025,
+    author = {Alexander Belykh and Alexander Varlamov and Alexey Letunovskiy and Anastasia Aliaskina and Anastasia Maltseva and Anastasiia Kargapoltseva and Andrey Shutkin and Anna Averchenkova and Anna Dmitrienko and Bulat Akhmatov and Denis Dimitrov and Denis Koposov and Denis Parkhomenko and Dmitrii and Ilya Vasiliev and Ivan Kirillov and Julia Agafonova and Kirill Chernyshev and Kormilitsyn Semen and Lev Novitskiy and Maria Kovaleva and Mikhail Mamaev and Mikhailov and Nikita Kiselev and Nikita Osterov and Nikolai Gerasimenko and Nikolai Vaulin and Olga Kim and Olga Vdovchenko and Polina Gavrilova and Polina Mikhailova and Tatiana Nikulina and Viacheslav Vasilev and Vladimir Arkhipkin and Vladimir Korviakov and Vladimir Polovnikov and Yury Kolabushin},
+    title = {Kandinsky 5.0: A family of diffusion models for Video & Image generation},
+    howpublished = {\url{https://github.com/kandinskylab/Kandinsky-5}},
+    year = 2025
+}
+```

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

@@ -1,4 +1,4 @@
-<!--Copyright 2025 The HuggingFace Team. All rights reserved.
+<!--Copyright 2025 The HuggingFace Team Kandinsky Lab Team. All rights reserved.
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at
 http://www.apache.org/licenses/LICENSE-2.0
@@ -9,10 +9,11 @@ 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](https://arxiv.org/abs/2511.14993) is a family of diffusion models for Video & Image generation.
 
+Kandinsky 5.0 Lite line-up of lightweight video generation models (2B parameters) that ranks #1 among open-source models in its class. It outperforms larger models and offers the best understanding of Russian concepts in the open-source ecosystem.
 
-Kandinsky 5.0 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.
+Kandinsky 5.0 Pro line-up of large high quality video generation models (19B parameters). It offers high qualty generation in HD and more generation formats like I2V.
 
 The model introduces several key innovations:
 - **Latent diffusion pipeline** with **Flow Matching** for improved training stability
@@ -21,45 +22,78 @@ The model introduces several key innovations:
 - **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).
+The original codebase can be found at [kandinskylab/Kandinsky-5](https://github.com/kandinskylab/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.
+> Check out the [Kandinsky Lab](https://huggingface.co/kandinskylab) organization on the Hub for the official model checkpoints for text-to-video generation, including pretrained, SFT, no-CFG, and distilled variants.
 
 ## Available Models
 
-Kandinsky 5.0 T2V Lite comes in several variants optimized for different use cases:
+Kandinsky 5.0 T2V Pro:
 
 | 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 |
+| **kandinskylab/Kandinsky-5.0-T2V-Pro-sft-5s-Diffusers** | 5 second Text-to-Video Pro model | High-quality text-to-video generation |
+| **kandinskylab/Kandinsky-5.0-I2V-Pro-sft-5s-Diffusers** | 5 second Image-to-Video Pro model | High-quality image-to-video generation |
 
-All models are available in 5-second and 10-second video generation versions.
+Kandinsky 5.0 T2V Lite:
+| model_id | Description | Use Cases |
+|------------|-------------|-----------|
+| **kandinskylab/Kandinsky-5.0-T2V-Lite-sft-5s-Diffusers** | 5 second Supervised Fine-Tuned model | Highest generation quality |
+| **kandinskylab/Kandinsky-5.0-T2V-Lite-sft-10s-Diffusers** | 10 second Supervised Fine-Tuned model | Highest generation quality |
+| **kandinskylab/Kandinsky-5.0-T2V-Lite-nocfg-5s-Diffusers** | 5 second Classifier-Free Guidance distilled | 2× faster inference |
+| **kandinskylab/Kandinsky-5.0-T2V-Lite-nocfg-10s-Diffusers** | 10 second Classifier-Free Guidance distilled | 2× faster inference |
+| **kandinskylab/Kandinsky-5.0-T2V-Lite-distilled16steps-5s-Diffusers** | 5 second Diffusion distilled to 16 steps | 6× faster inference, minimal quality loss |
+| **kandinskylab/Kandinsky-5.0-T2V-Lite-distilled16steps-10s-Diffusers** | 10 second Diffusion distilled to 16 steps | 6× faster inference, minimal quality loss |
+| **kandinskylab/Kandinsky-5.0-T2V-Lite-pretrain-5s-Diffusers** | 5 second Base pretrained model | Research and fine-tuning |
+| **kandinskylab/Kandinsky-5.0-T2V-Lite-pretrain-10s-Diffusers** | 10 second Base pretrained model | Research and fine-tuning |
 
-## Kandinsky5T2VPipeline
-
-[[autodoc]] Kandinsky5T2VPipeline
-    - all
-    - __call__
 
 ## Usage Examples
 
 ### Basic Text-to-Video Generation
 
+#### Pro
+**⚠️ Warning!** all Pro models should be infered with pipeline.enable_model_cpu_offload()  
 ```python
 import torch
 from diffusers import Kandinsky5T2VPipeline
 from diffusers.utils import export_to_video
 
 # Load the pipeline
-model_id = "ai-forever/Kandinsky-5.0-T2V-Lite-sft-5s-Diffusers"
+model_id = "kandinskylab/Kandinsky-5.0-T2V-Pro-sft-5s-Diffusers"
+pipe = Kandinsky5T2VPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
+
+pipe = pipe.to("cuda")
+pipeline.transformer.set_attention_backend("flex")                            # <--- Set attention bakend to Flex
+pipeline.enable_model_cpu_offload()                                           # <--- Enable cpu offloading for single GPU inference
+pipeline.transformer.compile(mode="max-autotune-no-cudagraphs", dynamic=True) # <--- Compile with max-autotune-no-cudagraphs
+
+# Generate video
+prompt = "A cat and a dog baking a cake together in a kitchen."
+negative_prompt = "Static, 2D cartoon, cartoon, 2d animation, paintings, images, worst quality, low quality, ugly, deformed, walking backwards"
+
+output = pipe(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    height=768,
+    width=1024,
+    num_frames=121,  # ~5 seconds at 24fps
+    num_inference_steps=50,
+    guidance_scale=5.0,
+).frames[0]
+
+export_to_video(output, "output.mp4", fps=24, quality=9)
+```
+
+#### Lite
+```python
+import torch
+from diffusers import Kandinsky5T2VPipeline
+from diffusers.utils import export_to_video
+
+# Load the pipeline
+model_id = "kandinskylab/Kandinsky-5.0-T2V-Lite-sft-5s-Diffusers"
 pipe = Kandinsky5T2VPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
 pipe = pipe.to("cuda")
 
@@ -85,14 +119,14 @@ export_to_video(output, "output.mp4", fps=24, quality=9)
 
 ```python
 pipe = Kandinsky5T2VPipeline.from_pretrained(
-    "ai-forever/Kandinsky-5.0-T2V-Lite-sft-10s-Diffusers", 
+    "kandinskylab/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
+)                                       # <--- Set attention bakend to Flex
 pipe.transformer.compile(
     mode="max-autotune-no-cudagraphs", 
     dynamic=True
@@ -118,7 +152,7 @@ export_to_video(output, "output.mp4", fps=24, quality=9)
 **⚠️ 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"
+model_id = "kandinskylab/Kandinsky-5.0-T2V-Lite-distilled16steps-5s-Diffusers"
 pipe = Kandinsky5T2VPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
 pipe = pipe.to("cuda")
 
@@ -132,18 +166,145 @@ export_to_video(output, "output.mp4", fps=24, quality=9)
 ```
 
 
+### Basic Image-to-Video Generation
+**⚠️ Warning!** all Pro models should be infered with pipeline.enable_model_cpu_offload()  
+```python
+import torch
+from diffusers import Kandinsky5T2VPipeline
+from diffusers.utils import export_to_video
+
+# Load the pipeline
+model_id = "kandinskylab/Kandinsky-5.0-I2V-Pro-sft-5s-Diffusers"
+pipe = Kandinsky5T2VPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
+
+pipe = pipe.to("cuda")
+pipeline.transformer.set_attention_backend("flex")                            # <--- Set attention bakend to Flex
+pipeline.enable_model_cpu_offload()                                           # <--- Enable cpu offloading for single GPU inference
+pipeline.transformer.compile(mode="max-autotune-no-cudagraphs", dynamic=True) # <--- Compile with max-autotune-no-cudagraphs
+
+# Generate video
+image = load_image(
+    "https://huggingface.co/kandinsky-community/kandinsky-3/resolve/main/assets/title.jpg?download=true"
+)
+height = 896
+width = 896
+image = image.resize((width, height))
+
+prompt = "An funny furry creture smiles happily and holds a sign that says 'Kandinsky'"
+negative_prompt = ""
+
+output = pipe(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    height=height,
+    width=width,
+    num_frames=121,  # ~5 seconds at 24fps
+    num_inference_steps=50,
+    guidance_scale=5.0,
+).frames[0]
+
+export_to_video(output, "output.mp4", fps=24, quality=9)
+```
+
+
+
+## Kandinsky 5.0 Pro Side-by-Side evaluation
+
+<table border="0" style="width: 200; text-align: left; margin-top: 20px;">
+  <tr>
+      <td>
+          <img width="200" alt="image" src="https://github.com/user-attachments/assets/73e5ff00-2735-40fd-8f01-767de9181918" />
+      </td>
+      <td>
+         <img width="200" alt="image" src="https://github.com/user-attachments/assets/f449a9e7-74b7-481d-82da-02723e396acd" />
+      </td>
+
+  <tr>
+      <td>
+          Comparison with Veo 3 
+      </td>
+      <td>
+          Comparison with Veo 3 fast
+      </td>
+  <tr>
+      <td>
+          <img width="200" alt="image" src="https://github.com/user-attachments/assets/a6902fb6-b5e8-4093-adad-aa4caab79c6d" />
+      </td>
+      <td>
+          <img width="200" alt="image" src="https://github.com/user-attachments/assets/09986015-3d07-4de8-b942-c145039b9b2d" />
+      </td>
+  <tr>
+      <td>
+          Comparison with Wan 2.2 A14B Text-to-Video mode
+      </td>
+      <td>
+          Comparison with Wan 2.2 A14B Image-to-Video mode
+      </td>
+
+</table>
+
+
+## Kandinsky 5.0 Lite Side-by-Side evaluation
+
+The evaluation is based on the expanded prompts from the [Movie Gen benchmark](https://github.com/facebookresearch/MovieGenBench), which are available in the expanded_prompt column of the benchmark/moviegen_bench.csv file.
+
+<table border="0" style="width: 400; text-align: left; margin-top: 20px;">
+  <tr>
+      <td>
+          <img src="https://github.com/kandinskylab/kandinsky-5/raw/main/assets/sbs/kandinsky_5_video_lite_vs_sora.jpg" width=400 >
+      </td>
+      <td>
+          <img src="https://github.com/kandinskylab/kandinsky-5/raw/main/assets/sbs/kandinsky_5_video_lite_vs_wan_2.1_14B.jpg" width=400 >
+      </td>
+  <tr>
+      <td>
+          <img src="https://github.com/kandinskylab/kandinsky-5/raw/main/assets/sbs/kandinsky_5_video_lite_vs_wan_2.2_5B.jpg" width=400 >
+      </td>
+      <td>
+          <img src="https://github.com/kandinskylab/kandinsky-5/raw/main/assets/sbs/kandinsky_5_video_lite_vs_wan_2.2_A14B.jpg" width=400 >
+      </td>
+  <tr>
+      <td>
+          <img src="https://github.com/kandinskylab/kandinsky-5/raw/main/assets/sbs/kandinsky_5_video_lite_vs_wan_2.1_1.3B.jpg" width=400 >
+      </td>
+
+</table>
+
+
+
+
+## Kandinsky 5.0 Lite Distill Side-by-Side evaluation
+
+<table border="0" style="width: 400; text-align: left; margin-top: 20px;">
+  <tr>
+      <td>
+          <img src="https://github.com/kandinskylab/kandinsky-5/raw/main/assets/sbs/kandinsky_5_video_lite_5s_vs_kandinsky_5_video_lite_distill_5s.jpg" width=400 >
+      </td>
+      <td>
+          <img src="https://github.com/kandinskylab/kandinsky-5/raw/main/assets/sbs/kandinsky_5_video_lite_10s_vs_kandinsky_5_video_lite_distill_10s.jpg" width=400 >
+      </td>
+
+</table>
+
+## Kandinsky5T2VPipeline
+
+[[autodoc]] Kandinsky5T2VPipeline
+    - all
+    - __call__
+
+## Kandinsky5I2VPipeline
+
+[[autodoc]] Kandinsky5I2VPipeline
+    - all
+    - __call__
+
+
 ## Citation
 ```bibtex
 @misc{kandinsky2025,
-    author = {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},
+    author = {Alexander Belykh and Alexander Varlamov and Alexey Letunovskiy and Anastasia Aliaskina and Anastasia Maltseva and Anastasiia Kargapoltseva and Andrey Shutkin and Anna Averchenkova and Anna Dmitrienko and Bulat Akhmatov and Denis Dimitrov and Denis Koposov and Denis Parkhomenko and Dmitrii and Ilya Vasiliev and Ivan Kirillov and Julia Agafonova and Kirill Chernyshev and Kormilitsyn Semen and Lev Novitskiy and Maria Kovaleva and Mikhail Mamaev and Mikhailov and Nikita Kiselev and Nikita Osterov and Nikolai Gerasimenko and Nikolai Vaulin and Olga Kim and Olga Vdovchenko and Polina Gavrilova and Polina Mikhailova and Tatiana Nikulina and Viacheslav Vasilev and Vladimir Arkhipkin and Vladimir Korviakov and Vladimir Polovnikov and Yury Kolabushin},
     title = {Kandinsky 5.0: A family of diffusion models for Video & Image generation},
-    howpublished = {\url{https://github.com/ai-forever/Kandinsky-5}},
+    howpublished = {\url{https://github.com/kandinskylab/Kandinsky-5}},
     year = 2025
 }
 ```

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

@@ -0,0 +1,114 @@
+<!--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.
+-->
+
+# LongCat-Image
+
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
+
+We introduce LongCat-Image, a pioneering open-source and bilingual (Chinese-English) foundation model for image generation, designed to address core challenges in multilingual text rendering, photorealism, deployment efficiency, and developer accessibility prevalent in current leading models.
+
+
+### Key Features
+- 🌟 **Exceptional Efficiency and Performance**: With only **6B parameters**, LongCat-Image surpasses numerous open-source models that are several times larger across multiple benchmarks, demonstrating the immense potential of efficient model design.
+- 🌟 **Superior Editing Performance**: LongCat-Image-Edit model achieves state-of-the-art performance among open-source models, delivering leading instruction-following and image quality with superior visual consistency.
+- 🌟 **Powerful Chinese Text Rendering**: LongCat-Image demonstrates superior accuracy and stability in rendering common Chinese characters compared to existing SOTA open-source models and achieves industry-leading coverage of the Chinese dictionary.
+- 🌟 **Remarkable Photorealism**: Through an innovative data strategy and training framework, LongCat-Image achieves remarkable photorealism in generated images.
+- 🌟 **Comprehensive Open-Source Ecosystem**: We provide a complete toolchain, from intermediate checkpoints to full training code, significantly lowering the barrier for further research and development.
+
+For more details, please refer to the comprehensive [***LongCat-Image Technical Report***](https://arxiv.org/abs/2412.11963)
+
+
+## Usage Example
+
+```py
+import torch
+import diffusers
+from diffusers import LongCatImagePipeline
+
+weight_dtype = torch.bfloat16
+pipe = LongCatImagePipeline.from_pretrained("meituan-longcat/LongCat-Image", torch_dtype=torch.bfloat16 )
+pipe.to('cuda')
+# pipe.enable_model_cpu_offload()
+
+prompt = '一个年轻的亚裔女性，身穿黄色针织衫，搭配白色项链。她的双手放在膝盖上，表情恬静。背景是一堵粗糙的砖墙，午后的阳光温暖地洒在她身上，营造出一种宁静而温馨的氛围。镜头采用中距离视角，突出她的神态和服饰的细节。光线柔和地打在她的脸上，强调她的五官和饰品的质感，增加画面的层次感与亲和力。整个画面构图简洁，砖墙的纹理与阳光的光影效果相得益彰，突显出人物的优雅与从容。'
+image = pipe(
+    prompt,
+    height=768,
+    width=1344,
+    guidance_scale=4.0,
+    num_inference_steps=50,
+    num_images_per_prompt=1,
+    generator=torch.Generator("cpu").manual_seed(43),
+    enable_cfg_renorm=True,
+    enable_prompt_rewrite=True,
+).images[0]
+image.save(f'./longcat_image_t2i_example.png')
+```
+
+
+This pipeline was contributed by LongCat-Image Team. The original codebase can be found [here](https://github.com/meituan-longcat/LongCat-Image).
+
+Available models:
+<div style="overflow-x: auto; margin-bottom: 16px;">
+  <table style="border-collapse: collapse; width: 100%;">
+    <thead>
+      <tr>
+        <th style="white-space: nowrap; padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa;">Models</th>
+        <th style="white-space: nowrap; padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa;">Type</th>
+        <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa;">Description</th>
+        <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa;">Download Link</th>
+      </tr>
+    </thead>
+    <tbody>
+      <tr>
+        <td style="white-space: nowrap; padding: 8px; border: 1px solid #d0d7de;">LongCat&#8209;Image</td>
+        <td style="white-space: nowrap; padding: 8px; border: 1px solid #d0d7de;">Text&#8209;to&#8209;Image</td>
+        <td style="padding: 8px; border: 1px solid #d0d7de;">Final Release. The standard model for out&#8209;of&#8209;the&#8209;box inference.</td>
+        <td style="padding: 8px; border: 1px solid #d0d7de;">
+          <span style="white-space: nowrap;">🤗&nbsp;<a href="https://huggingface.co/meituan-longcat/LongCat-Image">Huggingface</a></span>
+        </td>
+      </tr>
+      <tr>
+        <td style="white-space: nowrap; padding: 8px; border: 1px solid #d0d7de;">LongCat&#8209;Image&#8209;Dev</td>
+        <td style="white-space: nowrap; padding: 8px; border: 1px solid #d0d7de;">Text&#8209;to&#8209;Image</td>
+        <td style="padding: 8px; border: 1px solid #d0d7de;">Development. Mid-training checkpoint, suitable for fine-tuning.</td>
+        <td style="padding: 8px; border: 1px solid #d0d7de;">
+          <span style="white-space: nowrap;">🤗&nbsp;<a href="https://huggingface.co/meituan-longcat/LongCat-Image-Dev">Huggingface</a></span>
+        </td>
+      </tr>
+      <tr>
+        <td style="white-space: nowrap; padding: 8px; border: 1px solid #d0d7de;">LongCat&#8209;Image&#8209;Edit</td>
+        <td style="white-space: nowrap; padding: 8px; border: 1px solid #d0d7de;">Image Editing</td>
+        <td style="padding: 8px; border: 1px solid #d0d7de;">Specialized model for image editing.</td>
+        <td style="padding: 8px; border: 1px solid #d0d7de;">
+          <span style="white-space: nowrap;">🤗&nbsp;<a href="https://huggingface.co/meituan-longcat/LongCat-Image-Edit">Huggingface</a></span>
+        </td>
+      </tr>
+    </tbody>
+  </table>
+</div>
+
+## LongCatImagePipeline
+
+[[autodoc]] LongCatImagePipeline
+- all
+- __call__
+
+## LongCatImagePipelineOutput
+
+[[autodoc]] pipelines.longcat_image.pipeline_output.LongCatImagePipelineOutput
+
+
+

docs/source/en/api/pipelines/ltx2.md

@@ -0,0 +1,47 @@
+<!-- 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. -->
+
+# LTX-2
+
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
+LTX-2 is a DiT-based audio-video foundation model designed to generate synchronized video and audio within a single model. It brings together the core building blocks of modern video generation, with open weights and a focus on practical, local execution.
+
+You can find all the original LTX-Video checkpoints under the [Lightricks](https://huggingface.co/Lightricks) organization.
+
+The original codebase for LTX-2 can be found [here](https://github.com/Lightricks/LTX-2).
+
+## LTX2Pipeline
+
+[[autodoc]] LTX2Pipeline
+  - all
+  - __call__
+
+## LTX2ImageToVideoPipeline
+
+[[autodoc]] LTX2ImageToVideoPipeline
+  - all
+  - __call__
+
+## LTX2LatentUpsamplePipeline
+
+[[autodoc]] LTX2LatentUpsamplePipeline
+  - all
+  - __call__
+
+## LTX2PipelineOutput
+
+[[autodoc]] pipelines.ltx2.pipeline_output.LTX2PipelineOutput

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

@@ -136,7 +136,7 @@ export_to_video(video, "output.mp4", fps=24)
   - The recommended dtype for the transformer, VAE, and text encoder is `torch.bfloat16`. The VAE and text encoder can also be `torch.float32` or `torch.float16`.
   - For guidance-distilled variants of LTX-Video, set `guidance_scale` to `1.0`. The `guidance_scale` for any other model should be set higher, like `5.0`, for good generation quality.
   - For timestep-aware VAE variants (LTX-Video 0.9.1 and above), set `decode_timestep` to `0.05` and `image_cond_noise_scale` to `0.025`.
-  - For variants that support interpolation between multiple conditioning images and videos (LTX-Video 0.9.5 and above), use similar images and videos for the best results. Divergence from the conditioning inputs may lead to abrupt transitionts in the generated video.
+  - For variants that support interpolation between multiple conditioning images and videos (LTX-Video 0.9.5 and above), use similar images and videos for the best results. Divergence from the conditioning inputs may lead to abrupt transitions in the generated video.
 
 - LTX-Video 0.9.7 includes a spatial latent upscaler and a 13B parameter transformer. During inference, a low resolution video is quickly generated first and then upscaled and refined.
 
@@ -329,7 +329,7 @@ export_to_video(video, "output.mp4", fps=24)
 
   <details>
   <summary>Show example code</summary>
-  
+
   ```python
   import torch
   from diffusers import LTXConditionPipeline, LTXLatentUpsamplePipeline
@@ -474,6 +474,12 @@ export_to_video(video, "output.mp4", fps=24)
 
   </details>
 
+## LTXI2VLongMultiPromptPipeline
+
+[[autodoc]] LTXI2VLongMultiPromptPipeline
+  - all
+  - __call__
+
 ## LTXPipeline
 
 [[autodoc]] LTXPipeline

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

@@ -0,0 +1,50 @@
+<!--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.
+-->
+
+# Ovis-Image
+
+![concepts](https://github.com/AIDC-AI/Ovis-Image/blob/main/docs/imgs/ovis_image_case.png)
+
+Ovis-Image is a 7B text-to-image model specifically optimized for high-quality text rendering, designed to operate efficiently under stringent computational constraints.
+
+[Ovis-Image Technical Report](https://arxiv.org/abs/2511.22982) from Alibaba Group, by Guo-Hua Wang, Liangfu Cao, Tianyu Cui, Minghao Fu, Xiaohao Chen, Pengxin Zhan, Jianshan Zhao, Lan Li, Bowen Fu, Jiaqi Liu, Qing-Guo Chen.
+
+The abstract from the paper is:
+
+*We introduce Ovis-Image, a 7B text-to-image model specifically optimized for high-quality text rendering, designed to operate efficiently under stringent computational constraints. Built upon our previous Ovis-U1 framework, Ovis-Image integrates a diffusion-based visual decoder with the stronger Ovis 2.5 multimodal backbone, leveraging a text-centric training pipeline that combines large-scale pre-training with carefully tailored post-training refinements. Despite its compact architecture, Ovis-Image achieves text rendering performance on par with significantly larger open models such as Qwen-Image and approaches closed-source systems like Seedream and GPT4o. Crucially, the model remains deployable on a single high-end GPU with moderate memory, narrowing the gap between frontier-level text rendering and practical deployment. Our results indicate that combining a strong multimodal backbone with a carefully designed, text-focused training recipe is sufficient to achieve reliable bilingual text rendering without resorting to oversized or proprietary models.*
+
+**Highlights**: 
+
+*   **Strong text rendering at a compact 7B scale**: Ovis-Image is a 7B text-to-image model that delivers text rendering quality comparable to much larger 20B-class systems such as Qwen-Image and competitive with leading closed-source models like GPT4o in text-centric scenarios, while remaining small enough to run on widely accessible hardware.
+*   **High fidelity on text-heavy, layout-sensitive prompts**: The model excels on prompts that demand tight alignment between linguistic content and rendered typography (e.g., posters, banners, logos, UI mockups, infographics), producing legible, correctly spelled, and semantically consistent text across diverse fonts, sizes, and aspect ratios without compromising overall visual quality.
+*   **Efficiency and deployability**: With its 7B parameter budget and streamlined architecture, Ovis-Image fits on a single high-end GPU with moderate memory, supports low-latency interactive use, and scales to batch production serving, bringing near–frontier text rendering to applications where tens-of-billions–parameter models are impractical.
+
+
+This pipeline was contributed by Ovis-Image Team. The original codebase can be found [here](https://github.com/AIDC-AI/Ovis-Image).
+
+Available models:
+
+| Model | Recommended dtype |
+|:-----:|:-----------------:|
+| [`AIDC-AI/Ovis-Image-7B`](https://huggingface.co/AIDC-AI/Ovis-Image-7B) | `torch.bfloat16` |
+
+Refer to [this](https://huggingface.co/collections/AIDC-AI/ovis-image) collection for more information.
+
+## OvisImagePipeline
+
+[[autodoc]] OvisImagePipeline
+	- all
+	- __call__
+
+## OvisImagePipelineOutput
+
+[[autodoc]] pipelines.ovis_image.pipeline_output.OvisImagePipelineOutput

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

@@ -95,7 +95,7 @@ image.save("qwen_fewsteps.png")
 
 With [`QwenImageEditPlusPipeline`], one can provide multiple images as input reference.
 
-```
+```py
 import torch
 from PIL import Image
 from diffusers import QwenImageEditPlusPipeline
@@ -108,12 +108,46 @@ pipe = QwenImageEditPlusPipeline.from_pretrained(
 image_1 = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/grumpy.jpg")
 image_2 = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/peng.png")
 image = pipe(
-    image=[image_1, image_2], 
-    prompt='''put the penguin and the cat at a game show called "Qwen Edit Plus Games"''', 
+    image=[image_1, image_2],
+    prompt='''put the penguin and the cat at a game show called "Qwen Edit Plus Games"''',
     num_inference_steps=50
 ).images[0]
 ```
 
+## Performance
+
+### torch.compile
+
+Using `torch.compile` on the transformer provides ~2.4x speedup (A100 80GB: 4.70s → 1.93s):
+
+```python
+import torch
+from diffusers import QwenImagePipeline
+
+pipe = QwenImagePipeline.from_pretrained("Qwen/Qwen-Image", torch_dtype=torch.bfloat16).to("cuda")
+pipe.transformer = torch.compile(pipe.transformer)
+
+# First call triggers compilation (~7s overhead)
+# Subsequent calls run at ~2.4x faster
+image = pipe("a cat", num_inference_steps=50).images[0]
+```
+
+### Batched Inference with Variable-Length Prompts
+
+When using classifier-free guidance (CFG) with prompts of different lengths, the pipeline properly handles padding through attention masking. This ensures padding tokens do not influence the generated output.
+
+```python
+# CFG with different prompt lengths works correctly
+image = pipe(
+    prompt="A cat",
+    negative_prompt="blurry, low quality, distorted",
+    true_cfg_scale=3.5,
+    num_inference_steps=50,
+).images[0]
+```
+
+For detailed benchmark scripts and results, see [this gist](https://gist.github.com/cdutr/bea337e4680268168550292d7819dc2f).
+
 ## QwenImagePipeline
 
 [[autodoc]] QwenImagePipeline

docs/source/en/api/pipelines/skyreels_v2.md

@@ -37,7 +37,8 @@ The following SkyReels-V2 models are supported in Diffusers:
 - [SkyReels-V2 I2V 1.3B - 540P](https://huggingface.co/Skywork/SkyReels-V2-I2V-1.3B-540P-Diffusers)
 - [SkyReels-V2 I2V 14B - 540P](https://huggingface.co/Skywork/SkyReels-V2-I2V-14B-540P-Diffusers)
 - [SkyReels-V2 I2V 14B - 720P](https://huggingface.co/Skywork/SkyReels-V2-I2V-14B-720P-Diffusers)
-- [SkyReels-V2 FLF2V 1.3B - 540P](https://huggingface.co/Skywork/SkyReels-V2-FLF2V-1.3B-540P-Diffusers)
+
+This model was contributed by [M. Tolga Cangöz](https://github.com/tolgacangoz).
 
 > [!TIP]
 > Click on the SkyReels-V2 models in the right sidebar for more examples of video generation.

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

@@ -250,9 +250,6 @@ 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.

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

@@ -0,0 +1,66 @@
+<!--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.
+-->
+
+# Z-Image
+
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
+[Z-Image](https://huggingface.co/papers/2511.22699) is a powerful and highly efficient image generation model with 6B parameters. Currently there's only one model with two more to be released:
+
+|Model|Hugging Face|
+|---|---|
+|Z-Image-Turbo|https://huggingface.co/Tongyi-MAI/Z-Image-Turbo|
+
+## Z-Image-Turbo
+
+Z-Image-Turbo is a distilled version of Z-Image that matches or exceeds leading competitors with only 8 NFEs (Number of Function Evaluations). It offers sub-second inference latency on enterprise-grade H800 GPUs and fits comfortably within 16G VRAM consumer devices. It excels in photorealistic image generation, bilingual text rendering (English & Chinese), and robust instruction adherence.
+
+## Image-to-image
+
+Use [`ZImageImg2ImgPipeline`] to transform an existing image based on a text prompt.
+
+```python
+import torch
+from diffusers import ZImageImg2ImgPipeline
+from diffusers.utils import load_image
+
+pipe = ZImageImg2ImgPipeline.from_pretrained("Tongyi-MAI/Z-Image-Turbo", torch_dtype=torch.bfloat16)
+pipe.to("cuda")
+
+url = "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg"
+init_image = load_image(url).resize((1024, 1024))
+
+prompt = "A fantasy landscape with mountains and a river, detailed, vibrant colors"
+image = pipe(
+    prompt,
+    image=init_image,
+    strength=0.6,
+    num_inference_steps=9,
+    guidance_scale=0.0,
+    generator=torch.Generator("cuda").manual_seed(42),
+).images[0]
+image.save("zimage_img2img.png")
+```
+
+## ZImagePipeline
+
+[[autodoc]] ZImagePipeline
+	- all
+	- __call__
+
+## ZImageImg2ImgPipeline
+
+[[autodoc]] ZImageImg2ImgPipeline
+	- all
+	- __call__

docs/source/en/hybrid_inference/api_reference.md

@@ -1,9 +1,11 @@
-# Hybrid Inference API Reference
+# Remote inference
 
-## Remote Decode
+Remote inference provides access to an [Inference Endpoint](https://huggingface.co/docs/inference-endpoints/index) to offload local generation requirements for decoding and encoding.
+
+## remote_decode
 
 [[autodoc]] utils.remote_utils.remote_decode
 
-## Remote Encode
+## remote_encode
 
 [[autodoc]] utils.remote_utils.remote_encode

docs/source/en/hybrid_inference/overview.md

@@ -10,51 +10,296 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
 specific language governing permissions and limitations under the License.
 -->
 
-# Hybrid Inference
-
-**Empowering local AI builders with Hybrid Inference**
-
+# Remote inference
 
 > [!TIP]
-> Hybrid Inference is an [experimental feature](https://huggingface.co/blog/remote_vae).
-> Feedback can be provided [here](https://github.com/huggingface/diffusers/issues/new?template=remote-vae-pilot-feedback.yml).
+> This is currently an experimental feature, and if you have any feedback, please feel free to leave it [here](https://github.com/huggingface/diffusers/issues/new?template=remote-vae-pilot-feedback.yml).
+
+Remote inference offloads the decoding and encoding process to a remote endpoint to relax the memory requirements for local inference with large models. This feature is powered by [Inference Endpoints](https://huggingface.co/docs/inference-endpoints/index). Refer to the table below for the supported models and endpoint.
+
+| Model | Endpoint | Checkpoint | Support |
+|---|---|---|---|
+| Stable Diffusion v1 | https://q1bj3bpq6kzilnsu.us-east-1.aws.endpoints.huggingface.cloud | [stabilityai/sd-vae-ft-mse](https://huggingface.co/stabilityai/sd-vae-ft-mse) | encode/decode |
+| Stable Diffusion XL | https://x2dmsqunjd6k9prw.us-east-1.aws.endpoints.huggingface.cloud | [madebyollin/sdxl-vae-fp16-fix](https://huggingface.co/madebyollin/sdxl-vae-fp16-fix) | encode/decode |
+| Flux | https://whhx50ex1aryqvw6.us-east-1.aws.endpoints.huggingface.cloud | [black-forest-labs/FLUX.1-schnell](https://huggingface.co/black-forest-labs/FLUX.1-schnell) | encode/decode |
+| HunyuanVideo | https://o7ywnmrahorts457.us-east-1.aws.endpoints.huggingface.cloud | [hunyuanvideo-community/HunyuanVideo](https://huggingface.co/hunyuanvideo-community/HunyuanVideo) | decode |
+
+This guide will show you how to encode and decode latents with remote inference.
+
+## Encoding
+
+Encoding converts images and videos into latent representations. Refer to the table below for the supported VAEs.
+
+Pass an image to [`~utils.remote_encode`] to encode it. The specific `scaling_factor` and `shift_factor` values for each model can be found in the [Remote inference](../hybrid_inference/api_reference) API reference.
+
+```py
+import torch
+from diffusers import FluxPipeline
+from diffusers.utils import load_image
+from diffusers.utils.remote_utils import remote_encode
+
+pipeline = FluxPipeline.from_pretrained(
+    "black-forest-labs/FLUX.1-schnell",
+    torch_dtype=torch.float16,
+    vae=None,
+    device_map="cuda"
+)
+
+init_image = load_image(
+    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg"
+)
+init_image = init_image.resize((768, 512))
+
+init_latent = remote_encode(
+    endpoint="https://whhx50ex1aryqvw6.us-east-1.aws.endpoints.huggingface.cloud",
+    image=init_image,
+    scaling_factor=0.3611,
+    shift_factor=0.1159
+)
+```
+
+## Decoding
+
+Decoding converts latent representations back into images or videos. Refer to the table below for the available and supported VAEs.
+
+Set the output type to `"latent"` in the pipeline and set the `vae` to `None`. Pass the latents to the [`~utils.remote_decode`] function. For Flux, the latents are packed so the `height` and `width` also need to be passed. The specific `scaling_factor` and `shift_factor` values for each model can be found in the [Remote inference](../hybrid_inference/api_reference) API reference.
+
+<hfoptions id="decode">
+<hfoption id="Flux">
+
+```py
+from diffusers import FluxPipeline
+
+pipeline = FluxPipeline.from_pretrained(
+    "black-forest-labs/FLUX.1-schnell",
+    torch_dtype=torch.bfloat16,
+    vae=None,
+    device_map="cuda"
+)
+
+prompt = """
+A photorealistic Apollo-era photograph of a cat in a small astronaut suit with a bubble helmet, standing on the Moon and holding a flagpole planted in the dusty lunar soil. The flag shows a colorful paw-print emblem. Earth glows in the black sky above the stark gray surface, with sharp shadows and high-contrast lighting like vintage NASA photos.
+"""
+
+latent = pipeline(
+    prompt=prompt,
+    guidance_scale=0.0,
+    num_inference_steps=4,
+    output_type="latent",
+).images
+image = remote_decode(
+    endpoint="https://whhx50ex1aryqvw6.us-east-1.aws.endpoints.huggingface.cloud/",
+    tensor=latent,
+    height=1024,
+    width=1024,
+    scaling_factor=0.3611,
+    shift_factor=0.1159,
+)
+image.save("image.jpg")
+```
+
+</hfoption>
+<hfoption id="HunyuanVideo">
+
+```py
+import torch
+from diffusers import HunyuanVideoPipeline, HunyuanVideoTransformer3DModel
+
+transformer = HunyuanVideoTransformer3DModel.from_pretrained(
+    "hunyuanvideo-community/HunyuanVideo", subfolder="transformer", torch_dtype=torch.bfloat16
+)
+pipeline = HunyuanVideoPipeline.from_pretrained(
+    model_id, transformer=transformer, vae=None, torch_dtype=torch.float16, device_map="cuda"
+)
+
+latent = pipeline(
+    prompt="A cat walks on the grass, realistic",
+    height=320,
+    width=512,
+    num_frames=61,
+    num_inference_steps=30,
+    output_type="latent",
+).frames
+
+video = remote_decode(
+    endpoint="https://o7ywnmrahorts457.us-east-1.aws.endpoints.huggingface.cloud/",
+    tensor=latent,
+    output_type="mp4",
+)
+
+if isinstance(video, bytes):
+    with open("video.mp4", "wb") as f:
+        f.write(video)
+```
+
+</hfoption>
+</hfoptions>
+
+## Queuing
+
+Remote inference supports queuing to process multiple generation requests. While the current latent is being decoded, you can queue the next prompt.
+
+```py
+import queue
+import threading
+from IPython.display import display
+from diffusers import StableDiffusionXLPipeline
+
+def decode_worker(q: queue.Queue):
+    while True:
+        item = q.get()
+        if item is None:
+            break
+        image = remote_decode(
+            endpoint="https://q1bj3bpq6kzilnsu.us-east-1.aws.endpoints.huggingface.cloud/",
+            tensor=item,
+            scaling_factor=0.13025,
+        )
+        display(image)
+        q.task_done()
+
+q = queue.Queue()
+thread = threading.Thread(target=decode_worker, args=(q,), daemon=True)
+thread.start()
+
+def decode(latent: torch.Tensor):
+    q.put(latent)
+
+prompts = [
+    "A grainy Apollo-era style photograph of a cat in a snug astronaut suit with a bubble helmet, standing on the lunar surface and gripping a flag with a paw-print emblem. The gray Moon landscape stretches behind it, Earth glowing vividly in the black sky, shadows crisp and high-contrast.",
+    "A vintage 1960s sci-fi pulp magazine cover illustration of a heroic cat astronaut planting a flag on the Moon. Bold, saturated colors, exaggerated space gear, playful typography floating in the background, Earth painted in bright blues and greens.",
+    "A hyper-detailed cinematic shot of a cat astronaut on the Moon holding a fluttering flag, fur visible through the helmet glass, lunar dust scattering under its feet. The vastness of space and Earth in the distance create an epic, awe-inspiring tone.",
+    "A colorful cartoon drawing of a happy cat wearing a chunky, oversized spacesuit, proudly holding a flag with a big paw print on it. The Moon’s surface is simplified with craters drawn like doodles, and Earth in the sky has a smiling face.",
+    "A monochrome 1969-style press photo of a “first cat on the Moon” moment. The cat, in a tiny astronaut suit, stands by a planted flag, with grainy textures, scratches, and a blurred Earth in the background, mimicking old archival space photos."
+]
 
 
+pipeline = StableDiffusionXLPipeline.from_pretrained(
+    "https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0",
+    torch_dtype=torch.float16,
+    vae=None,
+    device_map="cuda"
+)
 
-## Why use Hybrid Inference?
+pipeline.unet = pipeline.unet.to(memory_format=torch.channels_last)
+pipeline.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
 
-Hybrid Inference offers a fast and simple way to offload local generation requirements.
+_ = pipeline(
+    prompt=prompts[0],
+    output_type="latent",
+)
 
-- 🚀 **Reduced Requirements:** Access powerful models without expensive hardware.
-- 💎 **Without Compromise:** Achieve the highest quality without sacrificing performance.
-- 💰 **Cost Effective:** It's free! 🤑
-- 🎯 **Diverse Use Cases:** Fully compatible with Diffusers 🧨 and the wider community.
-- 🔧 **Developer-Friendly:** Simple requests, fast responses.
+for prompt in prompts:
+    latent = pipeline(
+        prompt=prompt,
+        output_type="latent",
+    ).images
+    decode(latent)
 
----
+q.put(None)
+thread.join()
+```
 
-## Available Models
+## Benchmarks
 
-* **VAE Decode 🖼️:** Quickly decode latent representations into high-quality images without compromising performance or workflow speed.
-* **VAE Encode 🔢:** Efficiently encode images into latent representations for generation and training.
-* **Text Encoders 📃 (coming soon):** Compute text embeddings for your prompts quickly and accurately, ensuring a smooth and high-quality workflow.
+The tables demonstrate the memory requirements for encoding and decoding with Stable Diffusion v1.5 and SDXL on different GPUs.
 
----
+For the majority of these GPUs, the memory usage dictates whether other models (text encoders, UNet/transformer) need to be offloaded or required tiled encoding. The latter two techniques increases inference time and impacts quality.
 
-## Integrations
+<details><summary>Encoding - Stable Diffusion v1.5</summary>
 
-* **[SD.Next](https://github.com/vladmandic/sdnext):** All-in-one UI with direct supports Hybrid Inference.
-* **[ComfyUI-HFRemoteVae](https://github.com/kijai/ComfyUI-HFRemoteVae):** ComfyUI node for Hybrid Inference.
+| GPU                           | Resolution   |   Time (seconds) |   Memory (%) |   Tiled Time (secs) |   Tiled Memory (%) |
+|:------------------------------|:-------------|-----------------:|-------------:|--------------------:|-------------------:|
+| NVIDIA GeForce RTX 4090       | 512x512      |            0.015 |      3.51901 |               0.015 |            3.51901 |
+| NVIDIA GeForce RTX 4090       | 256x256      |            0.004 |      1.3154  |               0.005 |            1.3154  |
+| NVIDIA GeForce RTX 4090       | 2048x2048    |            0.402 |     47.1852  |               0.496 |            3.51901 |
+| NVIDIA GeForce RTX 4090       | 1024x1024    |            0.078 |     12.2658  |               0.094 |            3.51901 |
+| NVIDIA GeForce RTX 4080 SUPER | 512x512      |            0.023 |      5.30105 |               0.023 |            5.30105 |
+| NVIDIA GeForce RTX 4080 SUPER | 256x256      |            0.006 |      1.98152 |               0.006 |            1.98152 |
+| NVIDIA GeForce RTX 4080 SUPER | 2048x2048    |            0.574 |     71.08    |               0.656 |            5.30105 |
+| NVIDIA GeForce RTX 4080 SUPER | 1024x1024    |            0.111 |     18.4772  |               0.14  |            5.30105 |
+| NVIDIA GeForce RTX 3090       | 512x512      |            0.032 |      3.52782 |               0.032 |            3.52782 |
+| NVIDIA GeForce RTX 3090       | 256x256      |            0.01  |      1.31869 |               0.009 |            1.31869 |
+| NVIDIA GeForce RTX 3090       | 2048x2048    |            0.742 |     47.3033  |               0.954 |            3.52782 |
+| NVIDIA GeForce RTX 3090       | 1024x1024    |            0.136 |     12.2965  |               0.207 |            3.52782 |
+| NVIDIA GeForce RTX 3080       | 512x512      |            0.036 |      8.51761 |               0.036 |            8.51761 |
+| NVIDIA GeForce RTX 3080       | 256x256      |            0.01  |      3.18387 |               0.01  |            3.18387 |
+| NVIDIA GeForce RTX 3080       | 2048x2048    |            0.863 |     86.7424  |               1.191 |            8.51761 |
+| NVIDIA GeForce RTX 3080       | 1024x1024    |            0.157 |     29.6888  |               0.227 |            8.51761 |
+| NVIDIA GeForce RTX 3070       | 512x512      |            0.051 |     10.6941  |               0.051 |           10.6941  |
+| NVIDIA GeForce RTX 3070       | 256x256      |            0.015 |      3.99743 |               0.015 |            3.99743 |
+| NVIDIA GeForce RTX 3070       | 2048x2048    |            1.217 |     96.054   |               1.482 |           10.6941  |
+| NVIDIA GeForce RTX 3070       | 1024x1024    |            0.223 |     37.2751  |               0.327 |           10.6941  |
 
-## Changelog
+</details>
 
-- March 10 2025: Added VAE encode
-- March 2 2025: Initial release with VAE decoding
+<details><summary>Encoding SDXL</summary>
 
-## Contents
+| GPU                           | Resolution   |   Time (seconds) |   Memory Consumed (%) |   Tiled Time (seconds) |   Tiled Memory (%) |
+|:------------------------------|:-------------|-----------------:|----------------------:|-----------------------:|-------------------:|
+| NVIDIA GeForce RTX 4090       | 512x512      |            0.029 |               4.95707 |                  0.029 |            4.95707 |
+| NVIDIA GeForce RTX 4090       | 256x256      |            0.007 |               2.29666 |                  0.007 |            2.29666 |
+| NVIDIA GeForce RTX 4090       | 2048x2048    |            0.873 |              66.3452  |                  0.863 |           15.5649  |
+| NVIDIA GeForce RTX 4090       | 1024x1024    |            0.142 |              15.5479  |                  0.143 |           15.5479  |
+| NVIDIA GeForce RTX 4080 SUPER | 512x512      |            0.044 |               7.46735 |                  0.044 |            7.46735 |
+| NVIDIA GeForce RTX 4080 SUPER | 256x256      |            0.01  |               3.4597  |                  0.01  |            3.4597  |
+| NVIDIA GeForce RTX 4080 SUPER | 2048x2048    |            1.317 |              87.1615  |                  1.291 |           23.447   |
+| NVIDIA GeForce RTX 4080 SUPER | 1024x1024    |            0.213 |              23.4215  |                  0.214 |           23.4215  |
+| NVIDIA GeForce RTX 3090       | 512x512      |            0.058 |               5.65638 |                  0.058 |            5.65638 |
+| NVIDIA GeForce RTX 3090       | 256x256      |            0.016 |               2.45081 |                  0.016 |            2.45081 |
+| NVIDIA GeForce RTX 3090       | 2048x2048    |            1.755 |              77.8239  |                  1.614 |           18.4193  |
+| NVIDIA GeForce RTX 3090       | 1024x1024    |            0.265 |              18.4023  |                  0.265 |           18.4023  |
+| NVIDIA GeForce RTX 3080       | 512x512      |            0.064 |              13.6568  |                  0.064 |           13.6568  |
+| NVIDIA GeForce RTX 3080       | 256x256      |            0.018 |               5.91728 |                  0.018 |            5.91728 |
+| NVIDIA GeForce RTX 3080       | 2048x2048    |          OOM     |             OOM       |                  1.866 |           44.4717  |
+| NVIDIA GeForce RTX 3080       | 1024x1024    |            0.302 |              44.4308  |                  0.302 |           44.4308  |
+| NVIDIA GeForce RTX 3070       | 512x512      |            0.093 |              17.1465  |                  0.093 |           17.1465  |
+| NVIDIA GeForce RTX 3070       | 256x256      |            0.025 |               7.42931 |                  0.026 |            7.42931 |
+| NVIDIA GeForce RTX 3070       | 2048x2048    |          OOM     |             OOM       |                  2.674 |           55.8355  |
+| NVIDIA GeForce RTX 3070       | 1024x1024    |            0.443 |              55.7841  |                  0.443 |           55.7841  |
 
-The documentation is organized into three sections:
+</details>
 
-* **VAE Decode** Learn the basics of how to use VAE Decode with Hybrid Inference.
-* **VAE Encode** Learn the basics of how to use VAE Encode with Hybrid Inference.
-* **API Reference** Dive into task-specific settings and parameters.
+<details><summary>Decoding - Stable Diffusion v1.5</summary>
+
+| GPU | Resolution | Time (seconds) | Memory (%) | Tiled Time (secs) | Tiled Memory (%) |
+| --- | --- | --- | --- | --- | --- |
+| NVIDIA GeForce RTX 4090 | 512x512 | 0.031 | 5.60% | 0.031 (0%) | 5.60% |
+| NVIDIA GeForce RTX 4090 | 1024x1024 | 0.148 | 20.00% | 0.301 (+103%) | 5.60% |
+| NVIDIA GeForce RTX 4080 | 512x512 | 0.05 | 8.40% | 0.050 (0%) | 8.40% |
+| NVIDIA GeForce RTX 4080 | 1024x1024 | 0.224 | 30.00% | 0.356 (+59%) | 8.40% |
+| NVIDIA GeForce RTX 4070 Ti | 512x512 | 0.066 | 11.30% | 0.066 (0%) | 11.30% |
+| NVIDIA GeForce RTX 4070 Ti | 1024x1024 | 0.284 | 40.50% | 0.454 (+60%) | 11.40% |
+| NVIDIA GeForce RTX 3090 | 512x512 | 0.062 | 5.20% | 0.062 (0%) | 5.20% |
+| NVIDIA GeForce RTX 3090 | 1024x1024 | 0.253 | 18.50% | 0.464 (+83%) | 5.20% |
+| NVIDIA GeForce RTX 3080 | 512x512 | 0.07 | 12.80% | 0.070 (0%) | 12.80% |
+| NVIDIA GeForce RTX 3080 | 1024x1024 | 0.286 | 45.30% | 0.466 (+63%) | 12.90% |
+| NVIDIA GeForce RTX 3070 | 512x512 | 0.102 | 15.90% | 0.102 (0%) | 15.90% |
+| NVIDIA GeForce RTX 3070 | 1024x1024 | 0.421 | 56.30% | 0.746 (+77%) | 16.00% |
+
+</details>
+
+<details><summary>Decoding SDXL</summary>
+
+| GPU | Resolution | Time (seconds) | Memory Consumed (%) | Tiled Time (seconds) | Tiled Memory (%) |
+| --- | --- | --- | --- | --- | --- |
+| NVIDIA GeForce RTX 4090 | 512x512 | 0.057 | 10.00% | 0.057 (0%) | 10.00% |
+| NVIDIA GeForce RTX 4090 | 1024x1024 | 0.256 | 35.50% | 0.257 (+0.4%) | 35.50% |
+| NVIDIA GeForce RTX 4080 | 512x512 | 0.092 | 15.00% | 0.092 (0%) | 15.00% |
+| NVIDIA GeForce RTX 4080 | 1024x1024 | 0.406 | 53.30% | 0.406 (0%) | 53.30% |
+| NVIDIA GeForce RTX 4070 Ti | 512x512 | 0.121 | 20.20% | 0.120 (-0.8%) | 20.20% |
+| NVIDIA GeForce RTX 4070 Ti | 1024x1024 | 0.519 | 72.00% | 0.519 (0%) | 72.00% |
+| NVIDIA GeForce RTX 3090 | 512x512 | 0.107 | 10.50% | 0.107 (0%) | 10.50% |
+| NVIDIA GeForce RTX 3090 | 1024x1024 | 0.459 | 38.00% | 0.460 (+0.2%) | 38.00% |
+| NVIDIA GeForce RTX 3080 | 512x512 | 0.121 | 25.60% | 0.121 (0%) | 25.60% |
+| NVIDIA GeForce RTX 3080 | 1024x1024 | 0.524 | 93.00% | 0.524 (0%) | 93.00% |
+| NVIDIA GeForce RTX 3070 | 512x512 | 0.183 | 31.80% | 0.183 (0%) | 31.80% |
+| NVIDIA GeForce RTX 3070 | 1024x1024 | 0.794 | 96.40% | 0.794 (0%) | 96.40% |
+
+</details>
+
+
+## Resources
+
+- Remote inference is also supported in [SD.Next](https://github.com/vladmandic/sdnext) and [ComfyUI-HFRemoteVae](https://github.com/kijai/ComfyUI-HFRemoteVae).
+- Refer to the [Remote VAEs for decoding with Inference Endpoints](https://huggingface.co/blog/remote_vae) blog post to learn more.

docs/source/en/hybrid_inference/vae_decode.md

@@ -1,345 +0,0 @@
-# Getting Started: VAE Decode with Hybrid Inference
-
-VAE decode is an essential component of diffusion models - turning latent representations into images or videos.
-
-## Memory
-
-These tables demonstrate the VRAM requirements for VAE decode with SD v1 and SD XL on different GPUs.
-
-For the majority of these GPUs the memory usage % dictates other models (text encoders, UNet/Transformer) must be offloaded, or tiled decoding has to be used which increases time taken and impacts quality.
-
-<details><summary>SD v1.5</summary>
-
-| GPU | Resolution | Time (seconds) | Memory (%) | Tiled Time (secs) | Tiled Memory (%) |
-| --- | --- | --- | --- | --- | --- |
-| NVIDIA GeForce RTX 4090 | 512x512 | 0.031 | 5.60% | 0.031 (0%) | 5.60% |
-| NVIDIA GeForce RTX 4090 | 1024x1024 | 0.148 | 20.00% | 0.301 (+103%) | 5.60% |
-| NVIDIA GeForce RTX 4080 | 512x512 | 0.05 | 8.40% | 0.050 (0%) | 8.40% |
-| NVIDIA GeForce RTX 4080 | 1024x1024 | 0.224 | 30.00% | 0.356 (+59%) | 8.40% |
-| NVIDIA GeForce RTX 4070 Ti | 512x512 | 0.066 | 11.30% | 0.066 (0%) | 11.30% |
-| NVIDIA GeForce RTX 4070 Ti | 1024x1024 | 0.284 | 40.50% | 0.454 (+60%) | 11.40% |
-| NVIDIA GeForce RTX 3090 | 512x512 | 0.062 | 5.20% | 0.062 (0%) | 5.20% |
-| NVIDIA GeForce RTX 3090 | 1024x1024 | 0.253 | 18.50% | 0.464 (+83%) | 5.20% |
-| NVIDIA GeForce RTX 3080 | 512x512 | 0.07 | 12.80% | 0.070 (0%) | 12.80% |
-| NVIDIA GeForce RTX 3080 | 1024x1024 | 0.286 | 45.30% | 0.466 (+63%) | 12.90% |
-| NVIDIA GeForce RTX 3070 | 512x512 | 0.102 | 15.90% | 0.102 (0%) | 15.90% |
-| NVIDIA GeForce RTX 3070 | 1024x1024 | 0.421 | 56.30% | 0.746 (+77%) | 16.00% |
-
-</details>
-
-<details><summary>SDXL</summary>
-
-| GPU | Resolution | Time (seconds) | Memory Consumed (%) | Tiled Time (seconds) | Tiled Memory (%) |
-| --- | --- | --- | --- | --- | --- |
-| NVIDIA GeForce RTX 4090 | 512x512 | 0.057 | 10.00% | 0.057 (0%) | 10.00% |
-| NVIDIA GeForce RTX 4090 | 1024x1024 | 0.256 | 35.50% | 0.257 (+0.4%) | 35.50% |
-| NVIDIA GeForce RTX 4080 | 512x512 | 0.092 | 15.00% | 0.092 (0%) | 15.00% |
-| NVIDIA GeForce RTX 4080 | 1024x1024 | 0.406 | 53.30% | 0.406 (0%) | 53.30% |
-| NVIDIA GeForce RTX 4070 Ti | 512x512 | 0.121 | 20.20% | 0.120 (-0.8%) | 20.20% |
-| NVIDIA GeForce RTX 4070 Ti | 1024x1024 | 0.519 | 72.00% | 0.519 (0%) | 72.00% |
-| NVIDIA GeForce RTX 3090 | 512x512 | 0.107 | 10.50% | 0.107 (0%) | 10.50% |
-| NVIDIA GeForce RTX 3090 | 1024x1024 | 0.459 | 38.00% | 0.460 (+0.2%) | 38.00% |
-| NVIDIA GeForce RTX 3080 | 512x512 | 0.121 | 25.60% | 0.121 (0%) | 25.60% |
-| NVIDIA GeForce RTX 3080 | 1024x1024 | 0.524 | 93.00% | 0.524 (0%) | 93.00% |
-| NVIDIA GeForce RTX 3070 | 512x512 | 0.183 | 31.80% | 0.183 (0%) | 31.80% |
-| NVIDIA GeForce RTX 3070 | 1024x1024 | 0.794 | 96.40% | 0.794 (0%) | 96.40% |
-
-</details>
-
-## Available VAEs
-
-|   | **Endpoint** | **Model** |
-|:-:|:-----------:|:--------:|
-| **Stable Diffusion v1** | [https://q1bj3bpq6kzilnsu.us-east-1.aws.endpoints.huggingface.cloud](https://q1bj3bpq6kzilnsu.us-east-1.aws.endpoints.huggingface.cloud) | [`stabilityai/sd-vae-ft-mse`](https://hf.co/stabilityai/sd-vae-ft-mse) |
-| **Stable Diffusion XL** | [https://x2dmsqunjd6k9prw.us-east-1.aws.endpoints.huggingface.cloud](https://x2dmsqunjd6k9prw.us-east-1.aws.endpoints.huggingface.cloud) | [`madebyollin/sdxl-vae-fp16-fix`](https://hf.co/madebyollin/sdxl-vae-fp16-fix) |
-| **Flux** | [https://whhx50ex1aryqvw6.us-east-1.aws.endpoints.huggingface.cloud](https://whhx50ex1aryqvw6.us-east-1.aws.endpoints.huggingface.cloud) | [`black-forest-labs/FLUX.1-schnell`](https://hf.co/black-forest-labs/FLUX.1-schnell) |
-| **HunyuanVideo** | [https://o7ywnmrahorts457.us-east-1.aws.endpoints.huggingface.cloud](https://o7ywnmrahorts457.us-east-1.aws.endpoints.huggingface.cloud) | [`hunyuanvideo-community/HunyuanVideo`](https://hf.co/hunyuanvideo-community/HunyuanVideo) |
-
-
-> [!TIP]
-> Model support can be requested [here](https://github.com/huggingface/diffusers/issues/new?template=remote-vae-pilot-feedback.yml).
-
-
-## Code
-
-> [!TIP]
-> Install `diffusers` from `main` to run the code: `pip install git+https://github.com/huggingface/diffusers@main`
-
-
-A helper method simplifies interacting with Hybrid Inference.
-
-```python
-from diffusers.utils.remote_utils import remote_decode
-```
-
-### Basic example
-
-Here, we show how to use the remote VAE on random tensors.
-
-<details><summary>Code</summary>
-
-```python
-image = remote_decode(
-    endpoint="https://q1bj3bpq6kzilnsu.us-east-1.aws.endpoints.huggingface.cloud/",
-    tensor=torch.randn([1, 4, 64, 64], dtype=torch.float16),
-    scaling_factor=0.18215,
-)
-```
-
-</details>
-
-<figure class="image flex flex-col items-center justify-center text-center m-0 w-full">
-<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/remote_vae/output.png"/>
-</figure>
-
-Usage for Flux is slightly different. Flux latents are packed so we need to send the `height` and `width`.
-
-<details><summary>Code</summary>
-
-```python
-image = remote_decode(
-    endpoint="https://whhx50ex1aryqvw6.us-east-1.aws.endpoints.huggingface.cloud/",
-    tensor=torch.randn([1, 4096, 64], dtype=torch.float16),
-    height=1024,
-    width=1024,
-    scaling_factor=0.3611,
-    shift_factor=0.1159,
-)
-```
-
-</details>
-
-<figure class="image flex flex-col items-center justify-center text-center m-0 w-full">
-<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/remote_vae/flux_random_latent.png"/>
-</figure>
-
-Finally, an example for HunyuanVideo.
-
-<details><summary>Code</summary>
-
-```python
-video = remote_decode(
-    endpoint="https://o7ywnmrahorts457.us-east-1.aws.endpoints.huggingface.cloud/",
-    tensor=torch.randn([1, 16, 3, 40, 64], dtype=torch.float16),
-    output_type="mp4",
-)
-with open("video.mp4", "wb") as f:
-    f.write(video)
-```
-
-</details>
-
-<figure class="image flex flex-col items-center justify-center text-center m-0 w-full">
-   <video
-      alt="queue.mp4"
-      autoplay loop autobuffer muted playsinline
-    >
-    <source src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/remote_vae/video_1.mp4" type="video/mp4">
-  </video>
-</figure>
-
-
-### Generation
-
-But we want to use the VAE on an actual pipeline to get an actual image, not random noise. The example below shows how to do it with SD v1.5. 
-
-<details><summary>Code</summary>
-
-```python
-from diffusers import StableDiffusionPipeline
-
-pipe = StableDiffusionPipeline.from_pretrained(
-    "stable-diffusion-v1-5/stable-diffusion-v1-5",
-    torch_dtype=torch.float16,
-    variant="fp16",
-    vae=None,
-).to("cuda")
-
-prompt = "Strawberry ice cream, in a stylish modern glass, coconut, splashing milk cream and honey, in a gradient purple background, fluid motion, dynamic movement, cinematic lighting, Mysterious"
-
-latent = pipe(
-    prompt=prompt,
-    output_type="latent",
-).images
-image = remote_decode(
-    endpoint="https://q1bj3bpq6kzilnsu.us-east-1.aws.endpoints.huggingface.cloud/",
-    tensor=latent,
-    scaling_factor=0.18215,
-)
-image.save("test.jpg")
-```
-
-</details>
-
-<figure class="image flex flex-col items-center justify-center text-center m-0 w-full">
-<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/remote_vae/test.jpg"/>
-</figure>
-
-Here’s another example with Flux.
-
-<details><summary>Code</summary>
-
-```python
-from diffusers import FluxPipeline
-
-pipe = FluxPipeline.from_pretrained(
-    "black-forest-labs/FLUX.1-schnell",
-    torch_dtype=torch.bfloat16,
-    vae=None,
-).to("cuda")
-
-prompt = "Strawberry ice cream, in a stylish modern glass, coconut, splashing milk cream and honey, in a gradient purple background, fluid motion, dynamic movement, cinematic lighting, Mysterious"
-
-latent = pipe(
-    prompt=prompt,
-    guidance_scale=0.0,
-    num_inference_steps=4,
-    output_type="latent",
-).images
-image = remote_decode(
-    endpoint="https://whhx50ex1aryqvw6.us-east-1.aws.endpoints.huggingface.cloud/",
-    tensor=latent,
-    height=1024,
-    width=1024,
-    scaling_factor=0.3611,
-    shift_factor=0.1159,
-)
-image.save("test.jpg")
-```
-
-</details>
-
-<figure class="image flex flex-col items-center justify-center text-center m-0 w-full">
-<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/remote_vae/test_1.jpg"/>
-</figure>
-
-Here’s an example with HunyuanVideo.
-
-<details><summary>Code</summary>
-
-```python
-from diffusers import HunyuanVideoPipeline, HunyuanVideoTransformer3DModel
-
-model_id = "hunyuanvideo-community/HunyuanVideo"
-transformer = HunyuanVideoTransformer3DModel.from_pretrained(
-    model_id, subfolder="transformer", torch_dtype=torch.bfloat16
-)
-pipe = HunyuanVideoPipeline.from_pretrained(
-    model_id, transformer=transformer, vae=None, torch_dtype=torch.float16
-).to("cuda")
-
-latent = pipe(
-    prompt="A cat walks on the grass, realistic",
-    height=320,
-    width=512,
-    num_frames=61,
-    num_inference_steps=30,
-    output_type="latent",
-).frames
-
-video = remote_decode(
-    endpoint="https://o7ywnmrahorts457.us-east-1.aws.endpoints.huggingface.cloud/",
-    tensor=latent,
-    output_type="mp4",
-)
-
-if isinstance(video, bytes):
-    with open("video.mp4", "wb") as f:
-        f.write(video)
-```
-
-</details>
-
-<figure class="image flex flex-col items-center justify-center text-center m-0 w-full">
-   <video
-      alt="queue.mp4"
-      autoplay loop autobuffer muted playsinline
-    >
-    <source src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/remote_vae/video.mp4" type="video/mp4">
-  </video>
-</figure>
-
-
-### Queueing
-
-One of the great benefits of using a remote VAE is that we can queue multiple generation requests. While the current latent is being processed for decoding, we can already queue another one. This helps improve concurrency. 
-
-
-<details><summary>Code</summary>
-
-```python
-import queue
-import threading
-from IPython.display import display
-from diffusers import StableDiffusionPipeline
-
-def decode_worker(q: queue.Queue):
-    while True:
-        item = q.get()
-        if item is None:
-            break
-        image = remote_decode(
-            endpoint="https://q1bj3bpq6kzilnsu.us-east-1.aws.endpoints.huggingface.cloud/",
-            tensor=item,
-            scaling_factor=0.18215,
-        )
-        display(image)
-        q.task_done()
-
-q = queue.Queue()
-thread = threading.Thread(target=decode_worker, args=(q,), daemon=True)
-thread.start()
-
-def decode(latent: torch.Tensor):
-    q.put(latent)
-
-prompts = [
-    "Blueberry ice cream, in a stylish modern glass , ice cubes, nuts, mint leaves, splashing milk cream, in a gradient purple background, fluid motion, dynamic movement, cinematic lighting, Mysterious",
-    "Lemonade in a glass, mint leaves, in an aqua and white background, flowers, ice cubes, halo, fluid motion, dynamic movement, soft lighting, digital painting, rule of thirds composition, Art by Greg rutkowski, Coby whitmore",
-    "Comic book art, beautiful, vintage, pastel neon colors, extremely detailed pupils, delicate features, light on face, slight smile, Artgerm, Mary Blair, Edmund Dulac, long dark locks, bangs, glowing, fashionable style, fairytale ambience, hot pink.",
-    "Masterpiece, vanilla cone ice cream garnished with chocolate syrup, crushed nuts, choco flakes, in a brown background, gold, cinematic lighting, Art by WLOP",
-    "A bowl of milk, falling cornflakes, berries, blueberries, in a white background, soft lighting, intricate details, rule of thirds, octane render, volumetric lighting",
-    "Cold Coffee with cream, crushed almonds, in a glass, choco flakes, ice cubes, wet, in a wooden background, cinematic lighting, hyper realistic painting, art by Carne Griffiths, octane render, volumetric lighting, fluid motion, dynamic movement, muted colors,",
-]
-
-pipe = StableDiffusionPipeline.from_pretrained(
-    "Lykon/dreamshaper-8",
-    torch_dtype=torch.float16,
-    vae=None,
-).to("cuda")
-
-pipe.unet = pipe.unet.to(memory_format=torch.channels_last)
-pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
-
-_ = pipe(
-    prompt=prompts[0],
-    output_type="latent",
-)
-
-for prompt in prompts:
-    latent = pipe(
-        prompt=prompt,
-        output_type="latent",
-    ).images
-    decode(latent)
-
-q.put(None)
-thread.join()
-```
-
-</details>
-
-
-<figure class="image flex flex-col items-center justify-center text-center m-0 w-full">
-   <video
-      alt="queue.mp4"
-      autoplay loop autobuffer muted playsinline
-    >
-    <source src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/remote_vae/queue.mp4" type="video/mp4">
-  </video>
-</figure>
-
-## Integrations
-
-* **[SD.Next](https://github.com/vladmandic/sdnext):** All-in-one UI with direct supports Hybrid Inference.
-* **[ComfyUI-HFRemoteVae](https://github.com/kijai/ComfyUI-HFRemoteVae):** ComfyUI node for Hybrid Inference.

docs/source/en/hybrid_inference/vae_encode.md

@@ -1,183 +0,0 @@
-# Getting Started: VAE Encode with Hybrid Inference
-
-VAE encode is used for training, image-to-image and image-to-video - turning into images or videos into latent representations.
-
-## Memory
-
-These tables demonstrate the VRAM requirements for VAE encode with SD v1 and SD XL on different GPUs.
-
-For the majority of these GPUs the memory usage % dictates other models (text encoders, UNet/Transformer) must be offloaded, or tiled encoding has to be used which increases time taken and impacts quality.
-
-<details><summary>SD v1.5</summary>
-
-| GPU                           | Resolution   |   Time (seconds) |   Memory (%) |   Tiled Time (secs) |   Tiled Memory (%) |
-|:------------------------------|:-------------|-----------------:|-------------:|--------------------:|-------------------:|
-| NVIDIA GeForce RTX 4090       | 512x512      |            0.015 |      3.51901 |               0.015 |            3.51901 |
-| NVIDIA GeForce RTX 4090       | 256x256      |            0.004 |      1.3154  |               0.005 |            1.3154  |
-| NVIDIA GeForce RTX 4090       | 2048x2048    |            0.402 |     47.1852  |               0.496 |            3.51901 |
-| NVIDIA GeForce RTX 4090       | 1024x1024    |            0.078 |     12.2658  |               0.094 |            3.51901 |
-| NVIDIA GeForce RTX 4080 SUPER | 512x512      |            0.023 |      5.30105 |               0.023 |            5.30105 |
-| NVIDIA GeForce RTX 4080 SUPER | 256x256      |            0.006 |      1.98152 |               0.006 |            1.98152 |
-| NVIDIA GeForce RTX 4080 SUPER | 2048x2048    |            0.574 |     71.08    |               0.656 |            5.30105 |
-| NVIDIA GeForce RTX 4080 SUPER | 1024x1024    |            0.111 |     18.4772  |               0.14  |            5.30105 |
-| NVIDIA GeForce RTX 3090       | 512x512      |            0.032 |      3.52782 |               0.032 |            3.52782 |
-| NVIDIA GeForce RTX 3090       | 256x256      |            0.01  |      1.31869 |               0.009 |            1.31869 |
-| NVIDIA GeForce RTX 3090       | 2048x2048    |            0.742 |     47.3033  |               0.954 |            3.52782 |
-| NVIDIA GeForce RTX 3090       | 1024x1024    |            0.136 |     12.2965  |               0.207 |            3.52782 |
-| NVIDIA GeForce RTX 3080       | 512x512      |            0.036 |      8.51761 |               0.036 |            8.51761 |
-| NVIDIA GeForce RTX 3080       | 256x256      |            0.01  |      3.18387 |               0.01  |            3.18387 |
-| NVIDIA GeForce RTX 3080       | 2048x2048    |            0.863 |     86.7424  |               1.191 |            8.51761 |
-| NVIDIA GeForce RTX 3080       | 1024x1024    |            0.157 |     29.6888  |               0.227 |            8.51761 |
-| NVIDIA GeForce RTX 3070       | 512x512      |            0.051 |     10.6941  |               0.051 |           10.6941  |
-| NVIDIA GeForce RTX 3070       | 256x256      |            0.015 |      3.99743 |               0.015 |            3.99743 |
-| NVIDIA GeForce RTX 3070       | 2048x2048    |            1.217 |     96.054   |               1.482 |           10.6941  |
-| NVIDIA GeForce RTX 3070       | 1024x1024    |            0.223 |     37.2751  |               0.327 |           10.6941  |
-
-
-</details>
-
-<details><summary>SDXL</summary>
-
-| GPU                           | Resolution   |   Time (seconds) |   Memory Consumed (%) |   Tiled Time (seconds) |   Tiled Memory (%) |
-|:------------------------------|:-------------|-----------------:|----------------------:|-----------------------:|-------------------:|
-| NVIDIA GeForce RTX 4090       | 512x512      |            0.029 |               4.95707 |                  0.029 |            4.95707 |
-| NVIDIA GeForce RTX 4090       | 256x256      |            0.007 |               2.29666 |                  0.007 |            2.29666 |
-| NVIDIA GeForce RTX 4090       | 2048x2048    |            0.873 |              66.3452  |                  0.863 |           15.5649  |
-| NVIDIA GeForce RTX 4090       | 1024x1024    |            0.142 |              15.5479  |                  0.143 |           15.5479  |
-| NVIDIA GeForce RTX 4080 SUPER | 512x512      |            0.044 |               7.46735 |                  0.044 |            7.46735 |
-| NVIDIA GeForce RTX 4080 SUPER | 256x256      |            0.01  |               3.4597  |                  0.01  |            3.4597  |
-| NVIDIA GeForce RTX 4080 SUPER | 2048x2048    |            1.317 |              87.1615  |                  1.291 |           23.447   |
-| NVIDIA GeForce RTX 4080 SUPER | 1024x1024    |            0.213 |              23.4215  |                  0.214 |           23.4215  |
-| NVIDIA GeForce RTX 3090       | 512x512      |            0.058 |               5.65638 |                  0.058 |            5.65638 |
-| NVIDIA GeForce RTX 3090       | 256x256      |            0.016 |               2.45081 |                  0.016 |            2.45081 |
-| NVIDIA GeForce RTX 3090       | 2048x2048    |            1.755 |              77.8239  |                  1.614 |           18.4193  |
-| NVIDIA GeForce RTX 3090       | 1024x1024    |            0.265 |              18.4023  |                  0.265 |           18.4023  |
-| NVIDIA GeForce RTX 3080       | 512x512      |            0.064 |              13.6568  |                  0.064 |           13.6568  |
-| NVIDIA GeForce RTX 3080       | 256x256      |            0.018 |               5.91728 |                  0.018 |            5.91728 |
-| NVIDIA GeForce RTX 3080       | 2048x2048    |          OOM     |             OOM       |                  1.866 |           44.4717  |
-| NVIDIA GeForce RTX 3080       | 1024x1024    |            0.302 |              44.4308  |                  0.302 |           44.4308  |
-| NVIDIA GeForce RTX 3070       | 512x512      |            0.093 |              17.1465  |                  0.093 |           17.1465  |
-| NVIDIA GeForce RTX 3070       | 256x256      |            0.025 |               7.42931 |                  0.026 |            7.42931 |
-| NVIDIA GeForce RTX 3070       | 2048x2048    |          OOM     |             OOM       |                  2.674 |           55.8355  |
-| NVIDIA GeForce RTX 3070       | 1024x1024    |            0.443 |              55.7841  |                  0.443 |           55.7841  |
-
-</details>
-
-## Available VAEs
-
-|   | **Endpoint** | **Model** |
-|:-:|:-----------:|:--------:|
-| **Stable Diffusion v1** | [https://qc6479g0aac6qwy9.us-east-1.aws.endpoints.huggingface.cloud](https://qc6479g0aac6qwy9.us-east-1.aws.endpoints.huggingface.cloud) | [`stabilityai/sd-vae-ft-mse`](https://hf.co/stabilityai/sd-vae-ft-mse) |
-| **Stable Diffusion XL** | [https://xjqqhmyn62rog84g.us-east-1.aws.endpoints.huggingface.cloud](https://xjqqhmyn62rog84g.us-east-1.aws.endpoints.huggingface.cloud) | [`madebyollin/sdxl-vae-fp16-fix`](https://hf.co/madebyollin/sdxl-vae-fp16-fix) |
-| **Flux** | [https://ptccx55jz97f9zgo.us-east-1.aws.endpoints.huggingface.cloud](https://ptccx55jz97f9zgo.us-east-1.aws.endpoints.huggingface.cloud) | [`black-forest-labs/FLUX.1-schnell`](https://hf.co/black-forest-labs/FLUX.1-schnell) |
-
-
-> [!TIP]
-> Model support can be requested [here](https://github.com/huggingface/diffusers/issues/new?template=remote-vae-pilot-feedback.yml).
-
-
-## Code
-
-> [!TIP]
-> Install `diffusers` from `main` to run the code: `pip install git+https://github.com/huggingface/diffusers@main`
-
-
-A helper method simplifies interacting with Hybrid Inference.
-
-```python
-from diffusers.utils.remote_utils import remote_encode
-```
-
-### Basic example
-
-Let's encode an image, then decode it to demonstrate.
-
-<figure class="image flex flex-col items-center justify-center text-center m-0 w-full">
-<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg"/>
-</figure>
-
-<details><summary>Code</summary>
-
-```python
-from diffusers.utils import load_image
-from diffusers.utils.remote_utils import remote_decode
-
-image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg?download=true")
-
-latent = remote_encode(
-    endpoint="https://ptccx55jz97f9zgo.us-east-1.aws.endpoints.huggingface.cloud/",
-    scaling_factor=0.3611,
-    shift_factor=0.1159,
-)
-
-decoded = remote_decode(
-    endpoint="https://whhx50ex1aryqvw6.us-east-1.aws.endpoints.huggingface.cloud/",
-    tensor=latent,
-    scaling_factor=0.3611,
-    shift_factor=0.1159,
-)
-```
-
-</details>
-
-<figure class="image flex flex-col items-center justify-center text-center m-0 w-full">
-<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/remote_vae/decoded.png"/>
-</figure>
-
-
-### Generation
-
-Now let's look at a generation example, we'll encode the image, generate then remotely decode too!
-
-<details><summary>Code</summary>
-
-```python
-import torch
-from diffusers import StableDiffusionImg2ImgPipeline
-from diffusers.utils import load_image
-from diffusers.utils.remote_utils import remote_decode, remote_encode
-
-pipe = StableDiffusionImg2ImgPipeline.from_pretrained(
-    "stable-diffusion-v1-5/stable-diffusion-v1-5",
-    torch_dtype=torch.float16,
-    variant="fp16",
-    vae=None,
-).to("cuda")
-
-init_image = load_image(
-    "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg"
-)
-init_image = init_image.resize((768, 512))
-
-init_latent = remote_encode(
-    endpoint="https://qc6479g0aac6qwy9.us-east-1.aws.endpoints.huggingface.cloud/",
-    image=init_image,
-    scaling_factor=0.18215,
-)
-
-prompt = "A fantasy landscape, trending on artstation"
-latent = pipe(
-    prompt=prompt,
-    image=init_latent,
-    strength=0.75,
-    output_type="latent",
-).images
-
-image = remote_decode(
-    endpoint="https://q1bj3bpq6kzilnsu.us-east-1.aws.endpoints.huggingface.cloud/",
-    tensor=latent,
-    scaling_factor=0.18215,
-)
-image.save("fantasy_landscape.jpg")
-```
-
-</details>
-
-<figure class="image flex flex-col items-center justify-center text-center m-0 w-full">
-<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/remote_vae/fantasy_landscape.png"/>
-</figure>
-
-## Integrations
-
-* **[SD.Next](https://github.com/vladmandic/sdnext):** All-in-one UI with direct supports Hybrid Inference.
-* **[ComfyUI-HFRemoteVae](https://github.com/kijai/ComfyUI-HFRemoteVae):** ComfyUI node for Hybrid Inference.

docs/source/en/modular_diffusers/custom_blocks.md

@@ -140,7 +140,7 @@ class Florence2ImageAnnotatorBlock(ModularPipelineBlocks):
                 type_hint=str,
                 required=True,
                 default="mask_image",
-                description="""Output type from annotation predictions. Availabe options are
+                description="""Output type from annotation predictions. Available options are
                 mask_image:
                     -black and white mask image for the given image based on the task type
                 mask_overlay:
@@ -256,7 +256,7 @@ class Florence2ImageAnnotatorBlock(ModularPipelineBlocks):
                 type_hint=str,
                 required=True,
                 default="mask_image",
-                description="""Output type from annotation predictions. Availabe options are
+                description="""Output type from annotation predictions. Available options are
                 mask_image:
                     -black and white mask image for the given image based on the task type
                 mask_overlay:

docs/source/en/modular_diffusers/guiders.md

@@ -159,7 +159,7 @@ Change the [`~ComponentSpec.default_creation_method`] to `from_pretrained` and u
 ```py
 guider_spec = t2i_pipeline.get_component_spec("guider")
 guider_spec.default_creation_method="from_pretrained"
-guider_spec.repo="YiYiXu/modular-loader-t2i-guider"
+guider_spec.pretrained_model_name_or_path="YiYiXu/modular-loader-t2i-guider"
 guider_spec.subfolder="pag_guider"
 pag_guider = guider_spec.load()
 t2i_pipeline.update_components(guider=pag_guider)

docs/source/en/modular_diffusers/loop_sequential_pipeline_blocks.md

@@ -53,7 +53,7 @@ The loop wrapper can pass additional arguments, like current iteration index, to
 
 A loop block is a [`~modular_pipelines.ModularPipelineBlocks`], but the `__call__` method behaves differently.
 
-- It recieves the iteration variable from the loop wrapper.
+- It receives the iteration variable from the loop wrapper.
 - It works directly with the [`~modular_pipelines.BlockState`] instead of the [`~modular_pipelines.PipelineState`].
 - It doesn't require retrieving or updating the [`~modular_pipelines.BlockState`].
 

docs/source/en/modular_diffusers/modular_pipeline.md

@@ -313,14 +313,14 @@ unet_spec
 ComponentSpec(
     name='unet',
     type_hint=<class 'diffusers.models.unets.unet_2d_condition.UNet2DConditionModel'>,
-    repo='RunDiffusion/Juggernaut-XL-v9',
+    pretrained_model_name_or_path='RunDiffusion/Juggernaut-XL-v9',
     subfolder='unet',
     variant='fp16',
     default_creation_method='from_pretrained'
 )
 
 # modify to load from a different repository
-unet_spec.repo = "stabilityai/stable-diffusion-xl-base-1.0"
+unet_spec.pretrained_model_name_or_path = "stabilityai/stable-diffusion-xl-base-1.0"
 
 # load component with modified spec
 unet = unet_spec.load(torch_dtype=torch.float16)

docs/source/en/optimization/attention_backends.md

@@ -32,7 +32,7 @@ This guide will show you how to set and use the different attention backends.
 
 The [`~ModelMixin.set_attention_backend`] method iterates through all the modules in the model and sets the appropriate attention backend to use. The attention backend setting persists until [`~ModelMixin.reset_attention_backend`] is called.
 
-The example below demonstrates how to enable the `_flash_3_hub` implementation for FlashAttention-3 from the [kernel](https://github.com/huggingface/kernels) library, which allows you to instantly use optimized compute kernels from the Hub without requiring any setup.
+The example below demonstrates how to enable the `_flash_3_hub` implementation for FlashAttention-3 from the [`kernels`](https://github.com/huggingface/kernels) library, which allows you to instantly use optimized compute kernels from the Hub without requiring any setup.
 
 > [!NOTE]
 > FlashAttention-3 is not supported for non-Hopper architectures, in which case, use FlashAttention with `set_attention_backend("flash")`.
@@ -141,10 +141,12 @@ Refer to the table below for a complete list of available attention backends and
 | `flash` | [FlashAttention](https://github.com/Dao-AILab/flash-attention) | FlashAttention-2 |
 | `flash_hub` | [FlashAttention](https://github.com/Dao-AILab/flash-attention) | FlashAttention-2 from kernels |
 | `flash_varlen` | [FlashAttention](https://github.com/Dao-AILab/flash-attention) | Variable length FlashAttention |
+| `flash_varlen_hub` | [FlashAttention](https://github.com/Dao-AILab/flash-attention) | Variable length FlashAttention from kernels |
 | `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 |
+| `_flash_3_varlen_hub` | [FlashAttention](https://github.com/Dao-AILab/flash-attention) | Variable length FlashAttention-3 from kernels |
 | `sage` | [SageAttention](https://github.com/thu-ml/SageAttention) | Quantized attention (INT8 QK) |
 | `sage_hub` | [SageAttention](https://github.com/thu-ml/SageAttention) | Quantized attention (INT8 QK) from kernels |
 | `sage_varlen` | [SageAttention](https://github.com/thu-ml/SageAttention) | Variable length SageAttention |
@@ -154,4 +156,4 @@ Refer to the table below for a complete list of available attention backends and
 | `_sage_qk_int8_pv_fp16_triton` | [SageAttention](https://github.com/thu-ml/SageAttention) | INT8 QK + FP16 PV (Triton) |
 | `xformers` | [xFormers](https://github.com/facebookresearch/xformers) | Memory-efficient attention |
 
-</details>
+</details>

docs/source/en/optimization/cache.md

@@ -66,4 +66,48 @@ config = FasterCacheConfig(
     tensor_format="BFCHW",
 )
 pipeline.transformer.enable_cache(config)
-```
+```
+
+## FirstBlockCache
+
+[FirstBlock Cache](https://huggingface.co/docs/diffusers/main/en/api/cache#diffusers.FirstBlockCacheConfig) checks how much the early layers of the denoiser changes from one timestep to the next. If the change is small, the model skips the expensive later layers and reuses the previous output.
+
+```py
+import torch
+from diffusers import DiffusionPipeline
+from diffusers.hooks import apply_first_block_cache, FirstBlockCacheConfig
+
+pipeline = DiffusionPipeline.from_pretrained(
+    "Qwen/Qwen-Image", torch_dtype=torch.bfloat16
+)
+apply_first_block_cache(pipeline.transformer, FirstBlockCacheConfig(threshold=0.2))
+```
+## TaylorSeer Cache
+
+[TaylorSeer Cache](https://huggingface.co/papers/2403.06923) accelerates diffusion inference by using Taylor series expansions to approximate and cache intermediate activations across denoising steps. The method predicts future outputs based on past computations, reusing them at specified intervals to reduce redundant calculations.
+
+This caching mechanism delivers strong results with minimal additional memory overhead. For detailed performance analysis, see [our findings here](https://github.com/huggingface/diffusers/pull/12648#issuecomment-3610615080).
+
+To enable TaylorSeer Cache, create a [`TaylorSeerCacheConfig`] and pass it to your pipeline's transformer:
+
+- `cache_interval`: Number of steps to reuse cached outputs before performing a full forward pass
+- `disable_cache_before_step`: Initial steps that use full computations to gather data for approximations
+- `max_order`: Approximation accuracy (in theory, higher values improve quality but increase memory usage but we recommend it should be set to `1`)
+
+```python
+import torch
+from diffusers import FluxPipeline, TaylorSeerCacheConfig
+
+pipe = FluxPipeline.from_pretrained(
+    "black-forest-labs/FLUX.1-dev",
+    torch_dtype=torch.bfloat16,
+).to("cuda")
+
+config = TaylorSeerCacheConfig(
+    cache_interval=5,
+    max_order=1,
+    disable_cache_before_step=10,
+    taylor_factors_dtype=torch.bfloat16,
+)
+pipe.transformer.enable_cache(config)
+```

docs/source/en/quantization/modelopt.md

@@ -11,7 +11,7 @@ specific language governing permissions and limitations under the License. -->
 
 # NVIDIA ModelOpt
 
-[NVIDIA-ModelOpt](https://github.com/NVIDIA/TensorRT-Model-Optimizer) is a unified library of state-of-the-art model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM or TensorRT to optimize inference speed.
+[NVIDIA-ModelOpt](https://github.com/NVIDIA/Model-Optimizer) is a unified library of state-of-the-art model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM or TensorRT to optimize inference speed.
 
 Before you begin, make sure you have nvidia_modelopt installed.
 
@@ -57,7 +57,7 @@ image.save("output.png")
 >
 > The quantization methods in NVIDIA-ModelOpt are designed to reduce the memory footprint of model weights using various QAT (Quantization-Aware Training) and PTQ (Post-Training Quantization) techniques while maintaining model performance. However, the actual performance gain during inference depends on the deployment framework (e.g., TRT-LLM, TensorRT) and the specific hardware configuration.  
 > 
-> More details can be found [here](https://github.com/NVIDIA/TensorRT-Model-Optimizer/tree/main/examples).
+> More details can be found [here](https://github.com/NVIDIA/Model-Optimizer/tree/main/examples).
 
 ## NVIDIAModelOptConfig
 
@@ -86,7 +86,7 @@ The quantization methods supported are as follows:
 | **NVFP4** | `nvfp4 weight only`, `nvfp4 block quantization` | `quant_type`, `quant_type + channel_quantize + block_quantize` | `channel_quantize = -1 is only supported for now`|
 
 
-Refer to the [official modelopt documentation](https://nvidia.github.io/TensorRT-Model-Optimizer/) for a better understanding of the available quantization methods and the exhaustive list of configuration options available.
+Refer to the [official modelopt documentation](https://nvidia.github.io/Model-Optimizer/) for a better understanding of the available quantization methods and the exhaustive list of configuration options available.
 
 ## Serializing and Deserializing quantized models
 

docs/source/en/quantization/torchao.md

@@ -33,7 +33,7 @@ pipeline_quant_config = PipelineQuantizationConfig(
 )
 pipeline = DiffusionPipeline.from_pretrained(
     "black-forest-labs/FLUX.1-dev",
-    quantzation_config=pipeline_quant_config,
+    quantization_config=pipeline_quant_config,
     torch_dtype=torch.bfloat16,
     device_map="cuda"
 )
@@ -50,7 +50,7 @@ pipeline_quant_config = PipelineQuantizationConfig(
 )
 pipeline = DiffusionPipeline.from_pretrained(
     "black-forest-labs/FLUX.1-dev",
-    quantzation_config=pipeline_quant_config,
+    quantization_config=pipeline_quant_config,
     torch_dtype=torch.bfloat16,
     device_map="cuda"
 )
@@ -70,7 +70,7 @@ pipeline_quant_config = PipelineQuantizationConfig(
 )
 pipeline = DiffusionPipeline.from_pretrained(
     "black-forest-labs/FLUX.1-dev",
-    quantzation_config=pipeline_quant_config,
+    quantization_config=pipeline_quant_config,
     torch_dtype=torch.bfloat16,
     device_map="cuda"
 )

docs/source/en/training/distributed_inference.md

@@ -237,6 +237,8 @@ By selectively loading and unloading the models you need at a given stage and sh
 
 Use [`~ModelMixin.set_attention_backend`] to switch to a more optimized attention backend. Refer to this [table](../optimization/attention_backends#available-backends) for a complete list of available backends.
 
+Most attention backends are compatible with context parallelism. Open an [issue](https://github.com/huggingface/diffusers/issues/new) if a backend is not compatible.
+
 ### Ring Attention
 
 Key (K) and value (V) representations communicate between devices using [Ring Attention](https://huggingface.co/papers/2310.01889). This ensures each split sees every other token's K/V. Each GPU computes attention for its local K/V and passes it to the next GPU in the ring. No single GPU holds the full sequence, which reduces communication latency.
@@ -245,38 +247,58 @@ Pass a [`ContextParallelConfig`] to the `parallel_config` argument of the transf
 
 ```py
 import torch
-from diffusers import AutoModel, QwenImagePipeline, ContextParallelConfig
+from torch import distributed as dist
+from diffusers import DiffusionPipeline, ContextParallelConfig
 
-try:
-    torch.distributed.init_process_group("nccl")
-    rank = torch.distributed.get_rank()
-    device = torch.device("cuda", rank % torch.cuda.device_count())
+def setup_distributed():
+    if not dist.is_initialized():
+        dist.init_process_group(backend="nccl")
+    rank = dist.get_rank()
+    device = torch.device(f"cuda:{rank}")
     torch.cuda.set_device(device)
-    
-    transformer = AutoModel.from_pretrained("Qwen/Qwen-Image", subfolder="transformer", torch_dtype=torch.bfloat16, parallel_config=ContextParallelConfig(ring_degree=2))
-    pipeline = QwenImagePipeline.from_pretrained("Qwen/Qwen-Image", transformer=transformer, torch_dtype=torch.bfloat16, device_map="cuda")
-    pipeline.transformer.set_attention_backend("flash")
+    return device
+
+def main():
+    device = setup_distributed()
+    world_size = dist.get_world_size()
+
+    pipeline = DiffusionPipeline.from_pretrained(
+        "black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16
+    ).to(device)
+    pipeline.transformer.set_attention_backend("_native_cudnn")
+
+    cp_config = ContextParallelConfig(ring_degree=world_size)
+    pipeline.transformer.enable_parallelism(config=cp_config)
 
     prompt = """
     cinematic film still of a cat sipping a margarita in a pool in Palm Springs, California
     highly detailed, high budget hollywood movie, cinemascope, moody, epic, gorgeous, film grain
     """
-    
+
     # Must specify generator so all ranks start with same latents (or pass your own)
     generator = torch.Generator().manual_seed(42)
-    image = pipeline(prompt, num_inference_steps=50, generator=generator).images[0]
-    
-    if rank == 0:
-        image.save("output.png")
+    image = pipeline(
+        prompt,
+        guidance_scale=3.5,
+        num_inference_steps=50,
+        generator=generator,
+    ).images[0]
 
-except Exception as e:
-    print(f"An error occurred: {e}")
-    torch.distributed.breakpoint()
-    raise
+    if dist.get_rank() == 0:
+        image.save(f"output.png")
 
-finally:
-    if torch.distributed.is_initialized():
-        torch.distributed.destroy_process_group()
+    if dist.is_initialized():
+        dist.destroy_process_group()
+
+
+if __name__ == "__main__":
+    main()
+```
+
+The script above needs to be run with a distributed launcher, such as [torchrun](https://docs.pytorch.org/docs/stable/elastic/run.html), that is compatible with PyTorch. `--nproc-per-node` is set to the number of GPUs available.
+
+```shell
+torchrun --nproc-per-node 2 above_script.py
 ```
 
 ### Ulysses Attention
@@ -288,5 +310,55 @@ finally:
 Pass the [`ContextParallelConfig`] to [`~ModelMixin.enable_parallelism`].
 
 ```py
+# Depending on the number of GPUs available.
 pipeline.transformer.enable_parallelism(config=ContextParallelConfig(ulysses_degree=2))
-```
+```
+
+### Unified Attention
+
+[Unified Sequence Parallelism](https://huggingface.co/papers/2405.07719) combines Ring Attention and Ulysses Attention into a single approach for efficient long-sequence processing. It applies Ulysses's *all-to-all* communication first to redistribute heads and sequence tokens, then uses Ring Attention to process the redistributed data, and finally reverses the *all-to-all* to restore the original layout.
+
+This hybrid approach leverages the strengths of both methods:
+- **Ulysses Attention** efficiently parallelizes across attention heads
+- **Ring Attention** handles very long sequences with minimal memory overhead
+- Together, they enable 2D parallelization across both heads and sequence dimensions
+
+[`ContextParallelConfig`] supports Unified Attention by specifying both `ulysses_degree` and `ring_degree`. The total number of devices used is `ulysses_degree * ring_degree`, arranged in a 2D grid where Ulysses and Ring groups are orthogonal (non-overlapping).
+Pass the [`ContextParallelConfig`] with both `ulysses_degree` and `ring_degree` set to bigger than 1 to [`~ModelMixin.enable_parallelism`].
+
+```py
+pipeline.transformer.enable_parallelism(config=ContextParallelConfig(ulysses_degree=2, ring_degree=2))
+```
+
+> [!TIP]
+> Unified Attention is to be used when there are enough devices to arrange in a 2D grid (at least 4 devices).
+
+We ran a benchmark with Ulysess, Ring, and Unified Attention with [this script](https://github.com/huggingface/diffusers/pull/12693#issuecomment-3694727532) on a node of 4 H100 GPUs. The results are summarized as follows:
+
+| CP Backend         | Time / Iter (ms) | Steps / Sec | Peak Memory (GB) |
+|--------------------|------------------|-------------|------------------|
+| ulysses            | 6670.789         | 7.50        | 33.85            |
+| ring               | 13076.492        | 3.82        | 56.02            |
+| unified_balanced   | 11068.705        | 4.52        | 33.85            |
+
+From the above table, it's clear that Ulysses provides better throughput, but the number of devices it can use remains limited to the number of attention heads, a limitation that is solved by unified attention.
+
+### parallel_config
+
+Pass `parallel_config` during model initialization to enable context parallelism.
+
+```py
+CKPT_ID = "black-forest-labs/FLUX.1-dev"
+
+cp_config = ContextParallelConfig(ring_degree=2)
+transformer = AutoModel.from_pretrained(
+    CKPT_ID, 
+    subfolder="transformer", 
+    torch_dtype=torch.bfloat16, 
+    parallel_config=cp_config
+)
+
+pipeline = DiffusionPipeline.from_pretrained(
+    CKPT_ID, transformer=transformer, torch_dtype=torch.bfloat16,
+).to(device)
+```

docs/source/zh/modular_diffusers/guiders.md

@@ -157,7 +157,7 @@ guider.push_to_hub("YiYiXu/modular-loader-t2i-guider", subfolder="pag_guider")
 ```py
 guider_spec = t2i_pipeline.get_component_spec("guider")
 guider_spec.default_creation_method="from_pretrained"
-guider_spec.repo="YiYiXu/modular-loader-t2i-guider"
+guider_spec.pretrained_model_name_or_path="YiYiXu/modular-loader-t2i-guider"
 guider_spec.subfolder="pag_guider"
 pag_guider = guider_spec.load()
 t2i_pipeline.update_components(guider=pag_guider)

docs/source/zh/modular_diffusers/modular_pipeline.md

@@ -313,14 +313,14 @@ unet_spec
 ComponentSpec(
     name='unet',
     type_hint=<class 'diffusers.models.unets.unet_2d_condition.UNet2DConditionModel'>,
-    repo='RunDiffusion/Juggernaut-XL-v9',
+    pretrained_model_name_or_path='RunDiffusion/Juggernaut-XL-v9',
     subfolder='unet',
     variant='fp16',
     default_creation_method='from_pretrained'
 )
 
 # 修改以从不同的仓库加载
-unet_spec.repo = "stabilityai/stable-diffusion-xl-base-1.0"
+unet_spec.pretrained_model_name_or_path = "stabilityai/stable-diffusion-xl-base-1.0"
 
 # 使用修改后的规范加载组件
 unet = unet_spec.load(torch_dtype=torch.float16)

examples/advanced_diffusion_training/train_dreambooth_lora_flux_advanced.py

@@ -94,7 +94,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.36.0.dev0")
+check_min_version("0.37.0.dev0")
 
 logger = get_logger(__name__)
 

examples/advanced_diffusion_training/train_dreambooth_lora_sd15_advanced.py

@@ -88,7 +88,7 @@ from diffusers.utils.import_utils import is_xformers_available
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.36.0.dev0")
+check_min_version("0.37.0.dev0")
 
 logger = get_logger(__name__)
 

examples/advanced_diffusion_training/train_dreambooth_lora_sdxl_advanced.py

@@ -95,7 +95,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.36.0.dev0")
+check_min_version("0.37.0.dev0")
 
 logger = get_logger(__name__)
 
@@ -1929,6 +1929,8 @@ def main(args):
 
     if args.cache_latents:
         latents_cache = []
+        # Store vae config before potential deletion
+        vae_scaling_factor = vae.config.scaling_factor
         for batch in tqdm(train_dataloader, desc="Caching latents"):
             with torch.no_grad():
                 batch["pixel_values"] = batch["pixel_values"].to(
@@ -1940,6 +1942,8 @@ def main(args):
             del vae
             if torch.cuda.is_available():
                 torch.cuda.empty_cache()
+    else:
+        vae_scaling_factor = vae.config.scaling_factor
 
     # Scheduler and math around the number of training steps.
     # Check the PR https://github.com/huggingface/diffusers/pull/8312 for detailed explanation.
@@ -2109,13 +2113,13 @@ def main(args):
                     model_input = vae.encode(pixel_values).latent_dist.sample()
 
                 if latents_mean is None and latents_std is None:
-                    model_input = model_input * vae.config.scaling_factor
+                    model_input = model_input * vae_scaling_factor
                     if args.pretrained_vae_model_name_or_path is None:
                         model_input = model_input.to(weight_dtype)
                 else:
                     latents_mean = latents_mean.to(device=model_input.device, dtype=model_input.dtype)
                     latents_std = latents_std.to(device=model_input.device, dtype=model_input.dtype)
-                    model_input = (model_input - latents_mean) * vae.config.scaling_factor / latents_std
+                    model_input = (model_input - latents_mean) * vae_scaling_factor / latents_std
                     model_input = model_input.to(dtype=weight_dtype)
 
                 # Sample noise that we'll add to the latents

examples/cogvideo/train_cogvideox_image_to_video_lora.py

@@ -61,7 +61,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.36.0.dev0")
+check_min_version("0.37.0.dev0")
 
 logger = get_logger(__name__)
 
@@ -149,13 +149,13 @@ def get_args():
         "--validation_prompt",
         type=str,
         default=None,
-        help="One or more prompt(s) that is used during validation to verify that the model is learning. Multiple validation prompts should be separated by the '--validation_prompt_seperator' string.",
+        help="One or more prompt(s) that is used during validation to verify that the model is learning. Multiple validation prompts should be separated by the '--validation_prompt_separator' string.",
     )
     parser.add_argument(
         "--validation_images",
         type=str,
         default=None,
-        help="One or more image path(s) that is used during validation to verify that the model is learning. Multiple validation paths should be separated by the '--validation_prompt_seperator' string. These should correspond to the order of the validation prompts.",
+        help="One or more image path(s) that is used during validation to verify that the model is learning. Multiple validation paths should be separated by the '--validation_prompt_separator' string. These should correspond to the order of the validation prompts.",
     )
     parser.add_argument(
         "--validation_prompt_separator",

examples/cogvideo/train_cogvideox_lora.py

@@ -52,7 +52,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.36.0.dev0")
+check_min_version("0.37.0.dev0")
 
 logger = get_logger(__name__)
 
@@ -140,7 +140,7 @@ def get_args():
         "--validation_prompt",
         type=str,
         default=None,
-        help="One or more prompt(s) that is used during validation to verify that the model is learning. Multiple validation prompts should be separated by the '--validation_prompt_seperator' string.",
+        help="One or more prompt(s) that is used during validation to verify that the model is learning. Multiple validation prompts should be separated by the '--validation_prompt_separator' string.",
     )
     parser.add_argument(
         "--validation_prompt_separator",

examples/cogview4-control/train_control_cogview4.py

@@ -60,7 +60,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.36.0.dev0")
+check_min_version("0.37.0.dev0")
 
 logger = get_logger(__name__)
 

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):

examples/community/marigold_depth_estimation.py

@@ -43,7 +43,7 @@ from diffusers.utils import BaseOutput, check_min_version
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.36.0.dev0")
+check_min_version("0.37.0.dev0")
 
 
 class MarigoldDepthOutput(BaseOutput):

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/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):

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_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
@@ -1642,24 +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_hunyuandit_differential_img2img.py

@@ -21,8 +21,8 @@ from transformers import (
     BertModel,
     BertTokenizer,
     CLIPImageProcessor,
-    MT5Tokenizer,
     T5EncoderModel,
+    T5Tokenizer,
 )
 
 from diffusers.callbacks import MultiPipelineCallbacks, PipelineCallback
@@ -260,7 +260,7 @@ class HunyuanDiTDifferentialImg2ImgPipeline(DiffusionPipeline):
             The HunyuanDiT model designed by Tencent Hunyuan.
         text_encoder_2 (`T5EncoderModel`):
             The mT5 embedder. Specifically, it is 't5-v1_1-xxl'.
-        tokenizer_2 (`MT5Tokenizer`):
+        tokenizer_2 (`T5Tokenizer`):
             The tokenizer for the mT5 embedder.
         scheduler ([`DDPMScheduler`]):
             A scheduler to be used in combination with HunyuanDiT to denoise the encoded image latents.
@@ -295,7 +295,7 @@ class HunyuanDiTDifferentialImg2ImgPipeline(DiffusionPipeline):
         feature_extractor: CLIPImageProcessor,
         requires_safety_checker: bool = True,
         text_encoder_2=T5EncoderModel,
-        tokenizer_2=MT5Tokenizer,
+        tokenizer_2=T5Tokenizer,
     ):
         super().__init__()
 

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(

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,

examples/community/pipeline_stable_diffusion_upscale_ldm3d.py

@@ -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):

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,
@@ -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):