update

This reverts commit 21a03f93ef.

.github/workflows/benchmark.yml

@@ -28,7 +28,7 @@ jobs:
       options: --shm-size "16gb" --ipc host --gpus all
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v6
+        uses: actions/checkout@v3
         with:
           fetch-depth: 2
       - name: NVIDIA-SMI
@@ -58,7 +58,7 @@ jobs:
 
       - name: Test suite reports artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v6
+        uses: actions/upload-artifact@v4
         with:
           name: benchmark_test_reports
           path: benchmarks/${{ 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@v6
+        uses: actions/checkout@v3
 
       - name: Find Changed Dockerfiles
         id: file_changes
@@ -99,7 +99,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@v3
       - 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@v6
+        uses: actions/checkout@v4
 
       - name: Set up Python
-        uses: actions/setup-python@v6
+        uses: actions/setup-python@v5
         with:
           python-version: '3.10'
 

.github/workflows/codeql.yml

@@ -1,22 +0,0 @@
----
-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

@@ -24,6 +24,7 @@ jobs:
   mirror_community_pipeline:
     env:
       SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_COMMUNITY_MIRROR }}
+
     runs-on: ubuntu-22.04
     steps:
       # Checkout to correct ref
@@ -38,41 +39,37 @@ 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: ${{ github.ref }}
         run: |
-          if [ "$EVENT_NAME" == "workflow_dispatch" ]; then
-            if [ -z "$EVENT_INPUT_REF" ]; then
+          if [ "${{ github.event_name }}" == "workflow_dispatch" ]; then
+            if [ -z "${{ github.event.inputs.ref }}" ]; then
               echo "Error: Missing ref input"
               exit 1
-            elif [ "$EVENT_INPUT_REF" == "main" ]; then
+            elif [ "${{ github.event.inputs.ref }}" == "main" ]; then
               echo "CHECKOUT_REF=refs/heads/main" >> $GITHUB_ENV
               echo "PATH_IN_REPO=main" >> $GITHUB_ENV
             else
-              echo "CHECKOUT_REF=refs/tags/$EVENT_INPUT_REF" >> $GITHUB_ENV
-              echo "PATH_IN_REPO=$EVENT_INPUT_REF" >> $GITHUB_ENV
+              echo "CHECKOUT_REF=refs/tags/${{ github.event.inputs.ref }}" >> $GITHUB_ENV
+              echo "PATH_IN_REPO=${{ github.event.inputs.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@v6
+      - uses: actions/checkout@v3
         with:
           ref: ${{ env.CHECKOUT_REF }}
 
       # Setup + install dependencies
       - name: Set up Python
-        uses: actions/setup-python@v6
+        uses: actions/setup-python@v4
         with:
           python-version: "3.10"
       - name: Install dependencies
@@ -102,4 +99,4 @@ 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@v6
+        uses: actions/checkout@v3
         with:
           fetch-depth: 2
       - name: Install dependencies
@@ -44,7 +44,7 @@ jobs:
 
       - name: Pipeline Tests Artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v6
+        uses: actions/upload-artifact@v4
         with:
           name: test-pipelines.json
           path: reports
@@ -64,7 +64,7 @@ jobs:
       options: --shm-size "16gb" --ipc host --gpus all
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v6
+        uses: actions/checkout@v3
         with:
           fetch-depth: 2
       - name: NVIDIA-SMI
@@ -97,7 +97,7 @@ jobs:
           cat reports/tests_pipeline_${{ matrix.module }}_cuda_failures_short.txt
       - name: Test suite reports artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v6
+        uses: actions/upload-artifact@v4
         with:
           name: pipeline_${{ 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@v6
+      uses: actions/checkout@v3
       with:
         fetch-depth: 2
 
@@ -167,7 +167,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v6
+      uses: actions/upload-artifact@v4
       with:
         name: torch_${{ matrix.module }}_cuda_test_reports
         path: reports
@@ -184,7 +184,7 @@ jobs:
 
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v6
+      uses: actions/checkout@v3
       with:
         fetch-depth: 2
 
@@ -211,7 +211,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v6
+      uses: actions/upload-artifact@v4
       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@v6
+        uses: actions/checkout@v3
         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@v6
+        uses: actions/upload-artifact@v4
         with:
           name: torch_cuda_big_gpu_test_reports
           path: reports
@@ -280,7 +280,7 @@ jobs:
         shell: bash
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v6
+        uses: actions/checkout@v3
         with:
           fetch-depth: 2
 
@@ -321,7 +321,7 @@ jobs:
 
       - name: Test suite reports artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v6
+        uses: actions/upload-artifact@v4
         with:
           name: torch_minimum_version_cuda_test_reports
           path: reports
@@ -355,7 +355,7 @@ jobs:
       options: --shm-size "20gb" --ipc host --gpus all
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v6
+        uses: actions/checkout@v3
         with:
           fetch-depth: 2
       - name: NVIDIA-SMI
@@ -391,7 +391,7 @@ jobs:
           cat reports/tests_${{ matrix.config.backend }}_torch_cuda_failures_short.txt
       - name: Test suite reports artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v6
+        uses: actions/upload-artifact@v4
         with:
           name: torch_cuda_${{ 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@v6
+        uses: actions/checkout@v3
         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@v6
+        uses: actions/upload-artifact@v4
         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@v6
+        uses: actions/checkout@v3
         with:
           fetch-depth: 2
 
@@ -474,7 +474,7 @@ jobs:
         run: mkdir -p combined_reports
 
       - name: Download all test reports
-        uses: actions/download-artifact@v7
+        uses: actions/download-artifact@v4
         with:
           path: artifacts
 
@@ -500,7 +500,7 @@ jobs:
           cat $CONSOLIDATED_REPORT_PATH >> $GITHUB_STEP_SUMMARY
 
       - name: Upload consolidated report
-        uses: actions/upload-artifact@v6
+        uses: actions/upload-artifact@v4
         with:
           name: consolidated_test_report
           path: ${{ env.CONSOLIDATED_REPORT_PATH }}
@@ -514,7 +514,7 @@ jobs:
 #
 #    steps:
 #      - name: Checkout diffusers
-#        uses: actions/checkout@v6
+#        uses: actions/checkout@v3
 #        with:
 #          fetch-depth: 2
 #
@@ -554,7 +554,7 @@ jobs:
 #
 #      - name: Test suite reports artifacts
 #        if: ${{ always() }}
-#        uses: actions/upload-artifact@v6
+#        uses: actions/upload-artifact@v4
 #        with:
 #          name: torch_mps_test_reports
 #          path: reports
@@ -570,7 +570,7 @@ jobs:
 #
 #    steps:
 #      - name: Checkout diffusers
-#        uses: actions/checkout@v6
+#        uses: actions/checkout@v3
 #        with:
 #          fetch-depth: 2
 #
@@ -610,7 +610,7 @@ jobs:
 #
 #      - name: Test suite reports artifacts
 #        if: ${{ always() }}
-#        uses: actions/upload-artifact@v6
+#        uses: actions/upload-artifact@v4
 #        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@v6
+    - uses: actions/checkout@v3
 
     - name: Setup Python
-      uses: actions/setup-python@v6
+      uses: actions/setup-python@v4
       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@v6
+      - uses: actions/checkout@v3
       - name: Set up Python
-        uses: actions/setup-python@v6
+        uses: actions/setup-python@v4
         with:
           python-version: "3.8"
       - name: Install dependencies

.github/workflows/pr_modular_tests.yml

@@ -1,4 +1,3 @@
-
 name: Fast PR tests for Modular
 
 on:
@@ -36,9 +35,9 @@ jobs:
   check_code_quality:
     runs-on: ubuntu-22.04
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v3
       - name: Set up Python
-        uses: actions/setup-python@v6
+        uses: actions/setup-python@v4
         with:
           python-version: "3.10"
       - name: Install dependencies
@@ -56,9 +55,9 @@ jobs:
     needs: check_code_quality
     runs-on: ubuntu-22.04
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v3
       - name: Set up Python
-        uses: actions/setup-python@v6
+        uses: actions/setup-python@v4
         with:
           python-version: "3.10"
       - name: Install dependencies
@@ -78,13 +77,23 @@ jobs:
 
   run_fast_tests:
     needs: [check_code_quality, check_repository_consistency]
-    name: Fast PyTorch Modular Pipeline CPU tests
+    strategy:
+      fail-fast: false
+      matrix:
+        config:
+          - name: Fast PyTorch Modular Pipeline CPU tests
+            framework: pytorch_pipelines
+            runner: aws-highmemory-32-plus
+            image: diffusers/diffusers-pytorch-cpu
+            report: torch_cpu_modular_pipelines
+
+    name: ${{ matrix.config.name }}
 
     runs-on:
-      group: aws-highmemory-32-plus
+      group: ${{ matrix.config.runner }}
 
     container:
-      image: diffusers/diffusers-pytorch-cpu
+      image: ${{ matrix.config.image }}
       options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
 
     defaults:
@@ -93,7 +102,7 @@ jobs:
 
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v6
+      uses: actions/checkout@v3
       with:
         fetch-depth: 2
 
@@ -109,19 +118,22 @@ jobs:
         python utils/print_env.py
 
     - name: Run fast PyTorch Pipeline CPU tests
+      if: ${{ matrix.config.framework == 'pytorch_pipelines' }}
       run: |
         pytest -n 8 --max-worker-restart=0 --dist=loadfile \
           -k "not Flax and not Onnx" \
-          --make-reports=tests_torch_cpu_modular_pipelines \
+          --make-reports=tests_${{ matrix.config.report }} \
           tests/modular_pipelines
 
     - name: Failure short reports
       if: ${{ failure() }}
-      run: cat reports/tests_torch_cpu_modular_pipelines_failures_short.txt
+      run: cat reports/tests_${{ matrix.config.report }}_failures_short.txt
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v6
+      uses: actions/upload-artifact@v4
       with:
-        name: pr_pytorch_pipelines_torch_cpu_modular_pipelines_test_reports
+        name: pr_${{ matrix.config.framework }}_${{ matrix.config.report }}_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@v6
+      uses: actions/checkout@v3
       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@v6
+      uses: actions/upload-artifact@v3
       with:
         name: test_fetched
         path: test_preparation.txt
@@ -83,7 +83,7 @@ jobs:
         shell: bash
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v6
+      uses: actions/checkout@v3
       with:
         fetch-depth: 2
 
@@ -109,7 +109,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v6
+      uses: actions/upload-artifact@v3
       with:
           name: ${{ matrix.modules }}_test_reports
           path: reports
@@ -138,7 +138,7 @@ jobs:
 
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v6
+      uses: actions/checkout@v3
       with:
         fetch-depth: 2
 
@@ -164,7 +164,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v6
+      uses: actions/upload-artifact@v4
       with:
         name: pr_${{ 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@v6
+      - uses: actions/checkout@v3
       - name: Set up Python
-        uses: actions/setup-python@v6
+        uses: actions/setup-python@v4
         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@v6
+      - uses: actions/checkout@v3
       - name: Set up Python
-        uses: actions/setup-python@v6
+        uses: actions/setup-python@v4
         with:
           python-version: "3.8"
       - name: Install dependencies
@@ -108,7 +108,7 @@ jobs:
 
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v6
+      uses: actions/checkout@v3
       with:
         fetch-depth: 2
 
@@ -153,7 +153,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v6
+      uses: actions/upload-artifact@v4
       with:
         name: pr_${{ matrix.config.framework }}_${{ matrix.config.report }}_test_reports
         path: reports
@@ -185,7 +185,7 @@ jobs:
 
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v6
+      uses: actions/checkout@v3
       with:
         fetch-depth: 2
 
@@ -211,7 +211,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v6
+      uses: actions/upload-artifact@v4
       with:
         name: pr_${{ matrix.config.report }}_test_reports
         path: reports
@@ -236,7 +236,7 @@ jobs:
 
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v6
+      uses: actions/checkout@v3
       with:
         fetch-depth: 2
 
@@ -273,7 +273,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v6
+      uses: actions/upload-artifact@v4
       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@v6
+      - uses: actions/checkout@v3
       - name: Set up Python
-        uses: actions/setup-python@v6
+        uses: actions/setup-python@v4
         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@v6
+      - uses: actions/checkout@v3
       - name: Set up Python
-        uses: actions/setup-python@v6
+        uses: actions/setup-python@v4
         with:
           python-version: "3.8"
       - name: Install dependencies
@@ -83,7 +83,7 @@ jobs:
       pipeline_test_matrix: ${{ steps.fetch_pipeline_matrix.outputs.pipeline_test_matrix }}
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v6
+        uses: actions/checkout@v3
         with:
           fetch-depth: 2
       - name: Install dependencies
@@ -100,7 +100,7 @@ jobs:
           echo "pipeline_test_matrix=$matrix" >> $GITHUB_OUTPUT
       - name: Pipeline Tests Artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v6
+        uses: actions/upload-artifact@v4
         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@v6
+        uses: actions/checkout@v3
         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: ${{ always() }}
-        uses: actions/upload-artifact@v6
+        uses: actions/upload-artifact@v4
         with:
           name: pipeline_${{ matrix.module }}_test_reports
           path: reports
@@ -193,7 +193,7 @@ jobs:
         module: [models, schedulers, lora, others]
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v6
+      uses: actions/checkout@v3
       with:
         fetch-depth: 2
 
@@ -239,7 +239,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v6
+      uses: actions/upload-artifact@v4
       with:
         name: torch_cuda_test_reports_${{ matrix.module }}
         path: reports
@@ -255,7 +255,7 @@ jobs:
       options: --gpus all --shm-size "16gb" --ipc host
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v6
+      uses: actions/checkout@v3
       with:
         fetch-depth: 2
 
@@ -287,7 +287,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v6
+      uses: actions/upload-artifact@v4
       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@v6
+      - uses: actions/checkout@v3
       - name: Set up Python
-        uses: actions/setup-python@v6
+        uses: actions/setup-python@v4
         with:
           python-version: "3.8"
       - name: Install dependencies

.github/workflows/push_tests.yml

@@ -29,7 +29,7 @@ jobs:
       pipeline_test_matrix: ${{ steps.fetch_pipeline_matrix.outputs.pipeline_test_matrix }}
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v6
+        uses: actions/checkout@v3
         with:
           fetch-depth: 2
       - name: Install dependencies
@@ -46,7 +46,7 @@ jobs:
           echo "pipeline_test_matrix=$matrix" >> $GITHUB_OUTPUT
       - name: Pipeline Tests Artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v6
+        uses: actions/upload-artifact@v4
         with:
           name: test-pipelines.json
           path: reports
@@ -66,7 +66,7 @@ jobs:
       options: --shm-size "16gb" --ipc host --gpus all
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v6
+        uses: actions/checkout@v3
         with:
           fetch-depth: 2
       - name: NVIDIA-SMI
@@ -98,7 +98,7 @@ jobs:
           cat reports/tests_pipeline_${{ matrix.module }}_cuda_failures_short.txt
       - name: Test suite reports artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v6
+        uses: actions/upload-artifact@v4
         with:
           name: pipeline_${{ 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@v6
+      uses: actions/checkout@v3
       with:
         fetch-depth: 2
 
@@ -155,7 +155,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v6
+      uses: actions/upload-artifact@v4
       with:
         name: torch_cuda_test_reports_${{ matrix.module }}
         path: reports
@@ -172,7 +172,7 @@ jobs:
 
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v6
+      uses: actions/checkout@v3
       with:
         fetch-depth: 2
 
@@ -199,7 +199,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v6
+      uses: actions/upload-artifact@v4
       with:
         name: torch_compile_test_reports
         path: reports
@@ -216,7 +216,7 @@ jobs:
 
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v6
+      uses: actions/checkout@v3
       with:
         fetch-depth: 2
 
@@ -240,7 +240,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v6
+      uses: actions/upload-artifact@v4
       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@v6
+      uses: actions/checkout@v3
       with:
         fetch-depth: 2
 
@@ -286,7 +286,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v6
+      uses: actions/upload-artifact@v4
       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@v6
+      uses: actions/checkout@v3
       with:
         fetch-depth: 2
 
@@ -88,7 +88,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v6
+      uses: actions/upload-artifact@v4
       with:
         name: pr_${{ 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@v6
+      uses: actions/checkout@v3
       with:
         fetch-depth: 2
 
@@ -65,7 +65,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v6
+      uses: actions/upload-artifact@v4
       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@v6
+        uses: actions/checkout@v3
 
       - name: Set up Python
-        uses: actions/setup-python@v6
+        uses: actions/setup-python@v4
         with:
           python-version: '3.8'
 
@@ -40,12 +40,12 @@ jobs:
 
     steps:
       - name: Checkout Repo
-        uses: actions/checkout@v6
+        uses: actions/checkout@v3
         with:
           ref: ${{ needs.find-and-checkout-latest-branch.outputs.latest_branch }}
 
       - name: Setup Python
-        uses: actions/setup-python@v6
+        uses: actions/setup-python@v4
         with:
           python-version: "3.8"
 

.github/workflows/release_tests_fast.yml

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

.github/workflows/ssh-runner.yml

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

.github/workflows/stale.yml

@@ -15,10 +15,10 @@ jobs:
     env:
       GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
     steps:
-    - uses: actions/checkout@v6
+    - uses: actions/checkout@v2
 
     - name: Setup Python
-      uses: actions/setup-python@v6
+      uses: actions/setup-python@v1
       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@v6
+      uses: actions/checkout@v4
       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@v6
+      - uses: actions/checkout@v3
 
       - 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@v6
+      - uses: actions/checkout@v3
 
       - name: Setup environment
         run: |

docs/source/en/_toctree.yml

@@ -54,8 +54,6 @@
     title: Batch inference
   - local: training/distributed_inference
     title: Distributed inference
-  - local: hybrid_inference/overview
-    title: Remote inference
   title: Inference
 - isExpanded: false
   sections:
@@ -90,6 +88,17 @@
       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
@@ -261,8 +270,6 @@
       title: Outputs
     - local: api/quantization
       title: Quantization
-    - local: hybrid_inference/api_reference
-      title: Remote inference
     - local: api/parallel
       title: Parallel inference
     title: Main Classes
@@ -342,28 +349,18 @@
         title: DiTTransformer2DModel
       - local: api/models/easyanimate_transformer3d
         title: EasyAnimateTransformer3DModel
-      - local: api/models/flux2_transformer
-        title: Flux2Transformer2DModel
       - local: api/models/flux_transformer
         title: FluxTransformer2DModel
-      - local: api/models/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
@@ -374,8 +371,6 @@
         title: MochiTransformer3DModel
       - local: api/models/omnigen_transformer
         title: OmniGenTransformer2DModel
-      - local: api/models/ovisimage_transformer2d
-        title: OvisImageTransformer2DModel
       - local: api/models/pixart_transformer2d
         title: PixArtTransformer2DModel
       - local: api/models/prior_transformer
@@ -400,8 +395,6 @@
         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
@@ -438,12 +431,6 @@
         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
@@ -538,12 +525,8 @@
         title: EasyAnimate
       - local: api/pipelines/flux
         title: Flux
-      - local: api/pipelines/flux2
-        title: Flux2
       - local: api/pipelines/control_flux_inpaint
         title: FluxControlInpaint
-      - local: api/pipelines/glm_image
-        title: GLM-Image
       - local: api/pipelines/hidream
         title: HiDream-I1
       - local: api/pipelines/hunyuandit
@@ -558,8 +541,6 @@
         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
@@ -568,8 +549,6 @@
         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
@@ -580,8 +559,6 @@
         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
@@ -657,8 +634,6 @@
         title: VisualCloze
       - local: api/pipelines/wuerstchen
         title: Wuerstchen
-      - local: api/pipelines/z_image
-        title: Z-Image
       title: Image
     - sections:
       - local: api/pipelines/allegro
@@ -673,16 +648,12 @@
         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

@@ -29,14 +29,8 @@ 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

@@ -30,10 +30,7 @@ LoRA is a fast and lightweight training method that inserts and trains a signifi
 - [`CogView4LoraLoaderMixin`] provides similar functions for [CogView4](https://huggingface.co/docs/diffusers/main/en/api/pipelines/cogview4).
 - [`AmusedLoraLoaderMixin`] is for the [`AmusedPipeline`].
 - [`HiDreamImageLoraLoaderMixin`] provides similar functions for [HiDream Image](https://huggingface.co/docs/diffusers/main/en/api/pipelines/hidream)
-- [`QwenImageLoraLoaderMixin`] provides similar functions for [Qwen Image](https://huggingface.co/docs/diffusers/main/en/api/pipelines/qwen).
-- [`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).
+- [`QwenImageLoraLoaderMixin`] provides similar functions for [Qwen Image](https://huggingface.co/docs/diffusers/main/en/api/pipelines/qwen)
 - [`LoraBaseMixin`] provides a base class with several utility methods to fuse, unfuse, unload, LoRAs and more.
 
 > [!TIP]
@@ -59,14 +56,6 @@ LoRA is a fast and lightweight training method that inserts and trains a signifi
 
 [[autodoc]] loaders.lora_pipeline.FluxLoraLoaderMixin
 
-## Flux2LoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.Flux2LoraLoaderMixin
-
-## LTX2LoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.LTX2LoraLoaderMixin
-
 ## CogVideoXLoraLoaderMixin
 
 [[autodoc]] loaders.lora_pipeline.CogVideoXLoraLoaderMixin
@@ -118,10 +107,6 @@ LoRA is a fast and lightweight training method that inserts and trains a signifi
 
 [[autodoc]] loaders.lora_pipeline.QwenImageLoraLoaderMixin
 
-## ZImageLoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.ZImageLoraLoaderMixin
-
 ## KandinskyLoraLoaderMixin
 [[autodoc]] loaders.lora_pipeline.KandinskyLoraLoaderMixin
 

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

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

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

@@ -1,29 +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. -->
-
-# 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

@@ -1,29 +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. -->
-
-# 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

@@ -33,21 +33,6 @@ 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.controlnets.controlnet_flux.FluxControlNetOutput
+[[autodoc]] models.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.controlnets.controlnet_sparsectrl.SparseControlNetOutput
+[[autodoc]] models.controlnet_sparsectrl.SparseControlNetOutput

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

@@ -1,19 +0,0 @@
-<!--Copyright 2025 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
--->
-
-# Flux2Transformer2DModel
-
-A Transformer model for image-like data from [Flux2](https://hf.co/black-forest-labs/FLUX.2-dev).
-
-## Flux2Transformer2DModel
-
-[[autodoc]] Flux2Transformer2DModel

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

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

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

@@ -1,30 +0,0 @@
-<!-- Copyright 2025 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License. -->
-
-# HunyuanVideo15Transformer3DModel
-
-A Diffusion Transformer model for 3D video-like data used in [HunyuanVideo1.5](https://github.com/Tencent/HunyuanVideo1-1.5).
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import HunyuanVideo15Transformer3DModel
-
-transformer = HunyuanVideo15Transformer3DModel.from_pretrained("hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v" subfolder="transformer", torch_dtype=torch.bfloat16)
-```
-
-## HunyuanVideo15Transformer3DModel
-
-[[autodoc]] HunyuanVideo15Transformer3DModel
-
-## Transformer2DModelOutput
-
-[[autodoc]] models.modeling_outputs.Transformer2DModelOutput

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

@@ -1,25 +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.
--->
-
-# 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

@@ -1,26 +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. -->
-
-# 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

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

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

@@ -1,19 +0,0 @@
-<!--Copyright 2025 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
--->
-
-# ZImageTransformer2DModel
-
-A Transformer model for image-like data from [Z-Image](https://huggingface.co/Tongyi-MAI/Z-Image-Turbo).
-
-## ZImageTransformer2DModel
-
-[[autodoc]] ZImageTransformer2DModel

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

@@ -21,10 +21,9 @@ 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.
 
-> [!NOTE]
-> Avoid using freeform text prompts directly with FIBO because it does not produce the best results.
+its not recommended to use freeform text prompts directly with FIBO, as it will not produce the best results.
 
-Refer to the Bria Fibo Hugging Face [page](https://huggingface.co/briaai/FIBO) to learn more.
+you can learn more about FIBO in  [Bria Fibo Hugging Face page](https://huggingface.co/briaai/FIBO).
 
 
 ## Usage
@@ -38,8 +37,9 @@ hf auth login
 ```
 
 
-## BriaFiboPipeline
+## BriaPipeline
 
-[[autodoc]] BriaFiboPipeline
+[[autodoc]] BriaPipeline
 	- all
-	- __call__
+	- __call__
+

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

@@ -30,10 +30,6 @@
 
 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
 
@@ -104,7 +100,6 @@ 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
@@ -114,8 +109,9 @@ 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)
-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)
+lora_path = hf_hub_download(repo_id=model_id, filename="lora/chronoedit_distill_lora.safetensors")
+pipe.load_lora_weights(lora_path)
+pipe.fuse_lora(lora_scale=1.0)
 pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config, flow_shift=2.0)
 pipe.to("cuda")
 
@@ -149,57 +145,6 @@ 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

@@ -70,12 +70,6 @@ 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/posts/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/technical/research/2022/11/02/DiffEdit-Implementation.html).
 
 This pipeline was contributed by [clarencechen](https://github.com/clarencechen). ❤️
 

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

@@ -1,39 +0,0 @@
-<!--Copyright 2025 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
--->
-
-# Flux2
-
-<div class="flex flex-wrap space-x-1">
-  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
-  <img alt="MPS" src="https://img.shields.io/badge/MPS-000000?style=flat&logo=apple&logoColor=white%22">
-</div>
-
-Flux.2 is the recent series of image generation models from Black Forest Labs, preceded by the [Flux.1](./flux.md) series. It is an entirely new model with a new architecture and pre-training done from scratch!
-
-Original model checkpoints for Flux can be found [here](https://huggingface.co/black-forest-labs). Original inference code can be found [here](https://github.com/black-forest-labs/flux2).
-
-> [!TIP]
-> Flux2 can be quite expensive to run on consumer hardware devices. However, you can perform a suite of optimizations to run it faster and in a more memory-friendly manner. Check out [this section](https://huggingface.co/blog/sd3#memory-optimizations-for-sd3) for more details. Additionally, Flux can benefit from quantization for memory efficiency with a trade-off in inference latency. Refer to [this blog post](https://huggingface.co/blog/quanto-diffusers) to learn more.
->
-> [Caching](../../optimization/cache) may also speed up inference by storing and reusing intermediate outputs.
-
-## Caption upsampling
-
-Flux.2 can potentially generate better better outputs with better prompts. We can "upsample"
-an input prompt by setting the `caption_upsample_temperature` argument in the pipeline call arguments.
-The [official implementation](https://github.com/black-forest-labs/flux2/blob/5a5d316b1b42f6b59a8c9194b77c8256be848432/src/flux2/text_encoder.py#L140) recommends this value to be 0.15.
-
-## Flux2Pipeline
-
-[[autodoc]] Flux2Pipeline
-	- all
-	- __call__

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

@@ -1,95 +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.
--->
-
-# 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

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

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

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

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

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

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

@@ -1,114 +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.
--->
-
-# 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

@@ -1,47 +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. -->
-
-# 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 transitions 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 transitionts 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
@@ -474,12 +474,6 @@ 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

@@ -1,50 +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.
--->
-
-# 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
@@ -108,46 +108,12 @@ 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/sana_video.md

@@ -43,13 +43,11 @@ Note: The recommended dtype mentioned is for the transformer weights. The text e
 <hfoptions id="generation pipelines">`
 <hfoption id="Text-to-Video">
 
-The example below demonstrates how to use the text-to-video pipeline to generate a video using a text description.
+The example below demonstrates how to use the text-to-video pipeline to generate a video using a text descriptio and a starting frame.
 
 ```python
-pipe = SanaVideoPipeline.from_pretrained(
-    "Efficient-Large-Model/SANA-Video_2B_480p_diffusers", 
-    torch_dtype=torch.bfloat16,
-)
+model_id = 
+pipe = SanaVideoPipeline.from_pretrained("Efficient-Large-Model/SANA-Video_2B_480p_diffusers", torch_dtype=torch.bfloat16)
 pipe.text_encoder.to(torch.bfloat16)
 pipe.vae.to(torch.float32)
 pipe.to("cuda")
@@ -77,11 +75,12 @@ export_to_video(video, "sana_video.mp4", fps=16)
 </hfoption>
 <hfoption id="Image-to-Video">
 
-The example below demonstrates how to use the image-to-video pipeline to generate a video using a text description and a starting frame.
+The example below demonstrates how to use the image-to-video pipeline to generate a video using a text descriptio and a starting frame.
 
 ```python
+model_id = "Efficient-Large-Model/SANA-Video_2B_480p_diffusers"
 pipe = SanaImageToVideoPipeline.from_pretrained(
-    "Efficient-Large-Model/SANA-Video_2B_480p_diffusers",
+    model_id,
     torch_dtype=torch.bfloat16,
 )
 pipe.scheduler = FlowMatchEulerDiscreteScheduler.from_config(pipe.scheduler.config, flow_shift=8.0)

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

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

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

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

@@ -1,66 +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.
--->
-
-# 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

@@ -1,11 +1,9 @@
-# Remote inference
+# Hybrid Inference API Reference
 
-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
+## 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

@@ -10,296 +10,51 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
 specific language governing permissions and limitations under the License.
 -->
 
-# Remote inference
+# Hybrid Inference
+
+**Empowering local AI builders with Hybrid Inference**
+
 
 > [!TIP]
-> 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."
-]
+> 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).
 
 
-pipeline = StableDiffusionXLPipeline.from_pretrained(
-    "https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0",
-    torch_dtype=torch.float16,
-    vae=None,
-    device_map="cuda"
-)
 
-pipeline.unet = pipeline.unet.to(memory_format=torch.channels_last)
-pipeline.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+## Why use Hybrid Inference?
 
-_ = pipeline(
-    prompt=prompts[0],
-    output_type="latent",
-)
+Hybrid Inference offers a fast and simple way to offload local generation requirements.
 
-for prompt in prompts:
-    latent = pipeline(
-        prompt=prompt,
-        output_type="latent",
-    ).images
-    decode(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.
 
-q.put(None)
-thread.join()
-```
+---
 
-## Benchmarks
+## Available Models
 
-The tables demonstrate the memory requirements for encoding and decoding with Stable Diffusion v1.5 and SDXL on different GPUs.
+* **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.
 
-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.
+---
 
-<details><summary>Encoding - Stable Diffusion v1.5</summary>
+## Integrations
 
-| 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  |
+* **[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.
 
-</details>
+## Changelog
 
-<details><summary>Encoding SDXL</summary>
+- March 10 2025: Added VAE encode
+- March 2 2025: Initial release with VAE decoding
 
-| 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  |
+## Contents
 
-</details>
+The documentation is organized into three sections:
 
-<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.
+* **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.

docs/source/en/hybrid_inference/vae_decode.md

@@ -0,0 +1,345 @@
+# 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

@@ -0,0 +1,183 @@
+# 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. Available options are
+                description="""Output type from annotation predictions. Availabe options are
                 mask_image:
                     -black and white mask image for the given image based on the task type
                 mask_overlay:
@@ -256,7 +256,7 @@ class Florence2ImageAnnotatorBlock(ModularPipelineBlocks):
                 type_hint=str,
                 required=True,
                 default="mask_image",
-                description="""Output type from annotation predictions. Available options are
+                description="""Output type from annotation predictions. Availabe options are
                 mask_image:
                     -black and white mask image for the given image based on the task type
                 mask_overlay:

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.pretrained_model_name_or_path="YiYiXu/modular-loader-t2i-guider"
+guider_spec.repo="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 receives the iteration variable from the loop wrapper.
+- It recieves 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'>,
-    pretrained_model_name_or_path='RunDiffusion/Juggernaut-XL-v9',
+    repo='RunDiffusion/Juggernaut-XL-v9',
     subfolder='unet',
     variant='fp16',
     default_creation_method='from_pretrained'
 )
 
 # modify to load from a different repository
-unet_spec.pretrained_model_name_or_path = "stabilityai/stable-diffusion-xl-base-1.0"
+unet_spec.repo = "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 [`kernels`](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 [kernel](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")`.
@@ -139,16 +139,12 @@ Refer to the table below for a complete list of available attention backends and
 | `_native_npu` | [PyTorch native](https://docs.pytorch.org/docs/stable/generated/torch.nn.attention.SDPBackend.html#torch.nn.attention.SDPBackend) | NPU-optimized attention |
 | `_native_xla` | [PyTorch native](https://docs.pytorch.org/docs/stable/generated/torch.nn.attention.SDPBackend.html#torch.nn.attention.SDPBackend) | XLA-optimized attention |
 | `flash` | [FlashAttention](https://github.com/Dao-AILab/flash-attention) | FlashAttention-2 |
-| `flash_hub` | [FlashAttention](https://github.com/Dao-AILab/flash-attention) | FlashAttention-2 from kernels |
 | `flash_varlen` | [FlashAttention](https://github.com/Dao-AILab/flash-attention) | Variable length FlashAttention |
-| `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 |
 | `_sage_qk_int8_pv_fp8_cuda` | [SageAttention](https://github.com/thu-ml/SageAttention) | INT8 QK + FP8 PV (CUDA) |
 | `_sage_qk_int8_pv_fp8_cuda_sm90` | [SageAttention](https://github.com/thu-ml/SageAttention) | INT8 QK + FP8 PV (SM90) |
@@ -156,4 +152,4 @@ 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

@@ -66,48 +66,4 @@ 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/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/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.
 
 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/Model-Optimizer/tree/main/examples).
+> More details can be found [here](https://github.com/NVIDIA/TensorRT-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/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/TensorRT-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",
-    quantization_config=pipeline_quant_config,
+    quantzation_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",
-    quantization_config=pipeline_quant_config,
+    quantzation_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",
-    quantization_config=pipeline_quant_config,
+    quantzation_config=pipeline_quant_config,
     torch_dtype=torch.bfloat16,
     device_map="cuda"
 )

docs/source/en/training/distributed_inference.md

@@ -237,8 +237,6 @@ 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.
@@ -247,58 +245,38 @@ Pass a [`ContextParallelConfig`] to the `parallel_config` argument of the transf
 
 ```py
 import torch
-from torch import distributed as dist
-from diffusers import DiffusionPipeline, ContextParallelConfig
+from diffusers import AutoModel, QwenImagePipeline, ContextParallelConfig
 
-def setup_distributed():
-    if not dist.is_initialized():
-        dist.init_process_group(backend="nccl")
-    rank = dist.get_rank()
-    device = torch.device(f"cuda:{rank}")
+try:
+    torch.distributed.init_process_group("nccl")
+    rank = torch.distributed.get_rank()
+    device = torch.device("cuda", rank % torch.cuda.device_count())
     torch.cuda.set_device(device)
-    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)
+    
+    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")
 
     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,
-        guidance_scale=3.5,
-        num_inference_steps=50,
-        generator=generator,
-    ).images[0]
+    image = pipeline(prompt, num_inference_steps=50, generator=generator).images[0]
+    
+    if rank == 0:
+        image.save("output.png")
 
-    if dist.get_rank() == 0:
-        image.save(f"output.png")
+except Exception as e:
+    print(f"An error occurred: {e}")
+    torch.distributed.breakpoint()
+    raise
 
-    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
+finally:
+    if torch.distributed.is_initialized():
+        torch.distributed.destroy_process_group()
 ```
 
 ### Ulysses Attention
@@ -310,55 +288,5 @@ torchrun --nproc-per-node 2 above_script.py
 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/pt/_toctree.yml

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

docs/source/pt/index.md

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

docs/source/pt/installation.md

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

docs/source/pt/stable_diffusion.md

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

docs/source/zh/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.pretrained_model_name_or_path="YiYiXu/modular-loader-t2i-guider"
+guider_spec.repo="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'>,
-    pretrained_model_name_or_path='RunDiffusion/Juggernaut-XL-v9',
+    repo='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.pretrained_model_name_or_path = "stabilityai/stable-diffusion-xl-base-1.0"
+unet_spec.repo = "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("0.37.0.dev0")
+check_min_version("0.36.0.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("0.37.0.dev0")
+check_min_version("0.36.0.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("0.37.0.dev0")
+check_min_version("0.36.0.dev0")
 
 logger = get_logger(__name__)
 
@@ -1929,8 +1929,6 @@ 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(
@@ -1942,8 +1940,6 @@ 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.
@@ -2113,13 +2109,13 @@ 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_scaling_factor
+                    model_input = model_input * vae.config.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_scaling_factor / latents_std
+                    model_input = (model_input - latents_mean) * vae.config.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("0.37.0.dev0")
+check_min_version("0.36.0.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_separator' 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_seperator' 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_separator' 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_seperator' 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("0.37.0.dev0")
+check_min_version("0.36.0.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_separator' 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_seperator' 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("0.37.0.dev0")
+check_min_version("0.36.0.dev0")
 
 logger = get_logger(__name__)
 

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("0.37.0.dev0")
+check_min_version("0.36.0.dev0")
 
 
 class MarigoldDepthOutput(BaseOutput):

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 (`T5Tokenizer`):
+        tokenizer_2 (`MT5Tokenizer`):
             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=T5Tokenizer,
+        tokenizer_2=MT5Tokenizer,
     ):
         super().__init__()
 

examples/community/pipeline_z_image_differential_img2img.py

@@ -1,844 +0,0 @@
-# Copyright 2025 Alibaba Z-Image Team and The HuggingFace Team. All rights reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-import inspect
-from typing import Any, Callable, Dict, List, Optional, Union
-
-import torch
-from transformers import AutoTokenizer, PreTrainedModel
-
-from diffusers.image_processor import PipelineImageInput, VaeImageProcessor
-from diffusers.loaders import FromSingleFileMixin, ZImageLoraLoaderMixin
-from diffusers.models.autoencoders import AutoencoderKL
-from diffusers.models.transformers import ZImageTransformer2DModel
-from diffusers.pipelines.pipeline_utils import DiffusionPipeline
-from diffusers.pipelines.z_image.pipeline_output import ZImagePipelineOutput
-from diffusers.schedulers import FlowMatchEulerDiscreteScheduler
-from diffusers.utils import logging, replace_example_docstring
-from diffusers.utils.torch_utils import randn_tensor
-
-
-logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
-
-EXAMPLE_DOC_STRING = """
-    Examples:
-        ```py
-        >>> import torch
-        >>> from pipeline_z_image_differential_img2img import ZImageDifferentialImg2ImgPipeline
-        >>> from diffusers.utils import load_image
-
-        >>> pipe = ZImageDifferentialImg2ImgPipeline.from_pretrained("Z-a-o/Z-Image-Turbo", torch_dtype=torch.bfloat16)
-        >>> pipe.to("cuda")
-
-        >>> init_image = load_image(
-        >>>     "https://github.com/exx8/differential-diffusion/blob/main/assets/input.jpg?raw=true",
-        >>> )
-
-        >>> mask = load_image(
-        >>>     "https://github.com/exx8/differential-diffusion/blob/main/assets/map.jpg?raw=true",
-        >>> )
-
-        >>> prompt = "painting of a mountain landscape with a meadow and a forest, meadow background, anime countryside landscape, anime nature wallpap, anime landscape wallpaper, studio ghibli landscape, anime landscape, mountain behind meadow, anime background art, studio ghibli environment, background of flowery hill, anime beautiful peace scene, forrest background, anime scenery, landscape background, background art, anime scenery concept art"
-
-        >>> image = pipe(
-        ...     prompt,
-        ...     image=init_image,
-        ...     mask_image=mask,
-        ...     strength=0.75,
-        ...     num_inference_steps=9,
-        ...     guidance_scale=0.0,
-        ...     generator=torch.Generator("cuda").manual_seed(41),
-        ... ).images[0]
-        >>> image.save("image.png")
-        ```
-"""
-
-
-# Copied from diffusers.pipelines.flux.pipeline_flux.calculate_shift
-def calculate_shift(
-    image_seq_len,
-    base_seq_len: int = 256,
-    max_seq_len: int = 4096,
-    base_shift: float = 0.5,
-    max_shift: float = 1.15,
-):
-    m = (max_shift - base_shift) / (max_seq_len - base_seq_len)
-    b = base_shift - m * base_seq_len
-    mu = image_seq_len * m + b
-    return mu
-
-
-# Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_img2img.retrieve_latents
-def retrieve_latents(
-    encoder_output: torch.Tensor, generator: Optional[torch.Generator] = None, sample_mode: str = "sample"
-):
-    if hasattr(encoder_output, "latent_dist") and sample_mode == "sample":
-        return encoder_output.latent_dist.sample(generator)
-    elif hasattr(encoder_output, "latent_dist") and sample_mode == "argmax":
-        return encoder_output.latent_dist.mode()
-    elif hasattr(encoder_output, "latents"):
-        return encoder_output.latents
-    else:
-        raise AttributeError("Could not access latents of provided encoder_output")
-
-
-# Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.retrieve_timesteps
-def retrieve_timesteps(
-    scheduler,
-    num_inference_steps: Optional[int] = None,
-    device: Optional[Union[str, torch.device]] = None,
-    timesteps: Optional[List[int]] = None,
-    sigmas: Optional[List[float]] = None,
-    **kwargs,
-):
-    r"""
-    Calls the scheduler's `set_timesteps` method and retrieves timesteps from the scheduler after the call. Handles
-    custom timesteps. Any kwargs will be supplied to `scheduler.set_timesteps`.
-
-    Args:
-        scheduler (`SchedulerMixin`):
-            The scheduler to get timesteps from.
-        num_inference_steps (`int`):
-            The number of diffusion steps used when generating samples with a pre-trained model. If used, `timesteps`
-            must be `None`.
-        device (`str` or `torch.device`, *optional*):
-            The device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
-        timesteps (`List[int]`, *optional*):
-            Custom timesteps used to override the timestep spacing strategy of the scheduler. If `timesteps` is passed,
-            `num_inference_steps` and `sigmas` must be `None`.
-        sigmas (`List[float]`, *optional*):
-            Custom sigmas used to override the timestep spacing strategy of the scheduler. If `sigmas` is passed,
-            `num_inference_steps` and `timesteps` must be `None`.
-
-    Returns:
-        `Tuple[torch.Tensor, int]`: A tuple where the first element is the timestep schedule from the scheduler and the
-        second element is the number of inference steps.
-    """
-    if timesteps is not None and sigmas is not None:
-        raise ValueError("Only one of `timesteps` or `sigmas` can be passed. Please choose one to set custom values")
-    if timesteps is not None:
-        accepts_timesteps = "timesteps" in set(inspect.signature(scheduler.set_timesteps).parameters.keys())
-        if not accepts_timesteps:
-            raise ValueError(
-                f"The current scheduler class {scheduler.__class__}'s `set_timesteps` does not support custom"
-                f" timestep schedules. Please check whether you are using the correct scheduler."
-            )
-        scheduler.set_timesteps(timesteps=timesteps, device=device, **kwargs)
-        timesteps = scheduler.timesteps
-        num_inference_steps = len(timesteps)
-    elif sigmas is not None:
-        accept_sigmas = "sigmas" in set(inspect.signature(scheduler.set_timesteps).parameters.keys())
-        if not accept_sigmas:
-            raise ValueError(
-                f"The current scheduler class {scheduler.__class__}'s `set_timesteps` does not support custom"
-                f" sigmas schedules. Please check whether you are using the correct scheduler."
-            )
-        scheduler.set_timesteps(sigmas=sigmas, device=device, **kwargs)
-        timesteps = scheduler.timesteps
-        num_inference_steps = len(timesteps)
-    else:
-        scheduler.set_timesteps(num_inference_steps, device=device, **kwargs)
-        timesteps = scheduler.timesteps
-    return timesteps, num_inference_steps
-
-
-class ZImageDifferentialImg2ImgPipeline(DiffusionPipeline, ZImageLoraLoaderMixin, FromSingleFileMixin):
-    r"""
-    The ZImage pipeline for image-to-image generation.
-
-    Args:
-        scheduler ([`FlowMatchEulerDiscreteScheduler`]):
-            A scheduler to be used in combination with `transformer` to denoise the encoded image latents.
-        vae ([`AutoencoderKL`]):
-            Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.
-        text_encoder ([`PreTrainedModel`]):
-            A text encoder model to encode text prompts.
-        tokenizer ([`AutoTokenizer`]):
-            A tokenizer to tokenize text prompts.
-        transformer ([`ZImageTransformer2DModel`]):
-            A ZImage transformer model to denoise the encoded image latents.
-    """
-
-    model_cpu_offload_seq = "text_encoder->transformer->vae"
-    _optional_components = []
-    _callback_tensor_inputs = ["latents", "prompt_embeds"]
-
-    def __init__(
-        self,
-        scheduler: FlowMatchEulerDiscreteScheduler,
-        vae: AutoencoderKL,
-        text_encoder: PreTrainedModel,
-        tokenizer: AutoTokenizer,
-        transformer: ZImageTransformer2DModel,
-    ):
-        super().__init__()
-
-        self.register_modules(
-            vae=vae,
-            text_encoder=text_encoder,
-            tokenizer=tokenizer,
-            scheduler=scheduler,
-            transformer=transformer,
-        )
-        self.vae_scale_factor = (
-            2 ** (len(self.vae.config.block_out_channels) - 1) if hasattr(self, "vae") and self.vae is not None else 8
-        )
-        latent_channels = self.vae.config.latent_channels if getattr(self, "vae", None) else 16
-        self.image_processor = VaeImageProcessor(vae_scale_factor=self.vae_scale_factor * 2)
-
-        self.mask_processor = VaeImageProcessor(
-            vae_scale_factor=self.vae_scale_factor,
-            vae_latent_channels=latent_channels,
-            do_normalize=False,
-            do_binarize=False,
-            do_convert_grayscale=True,
-        )
-
-    # Copied from diffusers.pipelines.z_image.pipeline_z_image.ZImagePipeline.encode_prompt
-    def encode_prompt(
-        self,
-        prompt: Union[str, List[str]],
-        device: Optional[torch.device] = None,
-        do_classifier_free_guidance: bool = True,
-        negative_prompt: Optional[Union[str, List[str]]] = None,
-        prompt_embeds: Optional[List[torch.FloatTensor]] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
-        max_sequence_length: int = 512,
-    ):
-        prompt = [prompt] if isinstance(prompt, str) else prompt
-        prompt_embeds = self._encode_prompt(
-            prompt=prompt,
-            device=device,
-            prompt_embeds=prompt_embeds,
-            max_sequence_length=max_sequence_length,
-        )
-
-        if do_classifier_free_guidance:
-            if negative_prompt is None:
-                negative_prompt = ["" for _ in prompt]
-            else:
-                negative_prompt = [negative_prompt] if isinstance(negative_prompt, str) else negative_prompt
-            assert len(prompt) == len(negative_prompt)
-            negative_prompt_embeds = self._encode_prompt(
-                prompt=negative_prompt,
-                device=device,
-                prompt_embeds=negative_prompt_embeds,
-                max_sequence_length=max_sequence_length,
-            )
-        else:
-            negative_prompt_embeds = []
-        return prompt_embeds, negative_prompt_embeds
-
-    # Copied from diffusers.pipelines.z_image.pipeline_z_image.ZImagePipeline._encode_prompt
-    def _encode_prompt(
-        self,
-        prompt: Union[str, List[str]],
-        device: Optional[torch.device] = None,
-        prompt_embeds: Optional[List[torch.FloatTensor]] = None,
-        max_sequence_length: int = 512,
-    ) -> List[torch.FloatTensor]:
-        device = device or self._execution_device
-
-        if prompt_embeds is not None:
-            return prompt_embeds
-
-        if isinstance(prompt, str):
-            prompt = [prompt]
-
-        for i, prompt_item in enumerate(prompt):
-            messages = [
-                {"role": "user", "content": prompt_item},
-            ]
-            prompt_item = self.tokenizer.apply_chat_template(
-                messages,
-                tokenize=False,
-                add_generation_prompt=True,
-                enable_thinking=True,
-            )
-            prompt[i] = prompt_item
-
-        text_inputs = self.tokenizer(
-            prompt,
-            padding="max_length",
-            max_length=max_sequence_length,
-            truncation=True,
-            return_tensors="pt",
-        )
-
-        text_input_ids = text_inputs.input_ids.to(device)
-        prompt_masks = text_inputs.attention_mask.to(device).bool()
-
-        prompt_embeds = self.text_encoder(
-            input_ids=text_input_ids,
-            attention_mask=prompt_masks,
-            output_hidden_states=True,
-        ).hidden_states[-2]
-
-        embeddings_list = []
-
-        for i in range(len(prompt_embeds)):
-            embeddings_list.append(prompt_embeds[i][prompt_masks[i]])
-
-        return embeddings_list
-
-    # Copied from diffusers.pipelines.stable_diffusion_3.pipeline_stable_diffusion_3_img2img.StableDiffusion3Img2ImgPipeline.get_timesteps
-    def get_timesteps(self, num_inference_steps, strength, device):
-        # get the original timestep using init_timestep
-        init_timestep = min(num_inference_steps * strength, num_inference_steps)
-
-        t_start = int(max(num_inference_steps - init_timestep, 0))
-        timesteps = self.scheduler.timesteps[t_start * self.scheduler.order :]
-        if hasattr(self.scheduler, "set_begin_index"):
-            self.scheduler.set_begin_index(t_start * self.scheduler.order)
-
-        return timesteps, num_inference_steps - t_start
-
-    @staticmethod
-    def _prepare_latent_image_ids(batch_size, height, width, device, dtype):
-        latent_image_ids = torch.zeros(height // 2, width // 2, 3)
-        latent_image_ids[..., 1] = latent_image_ids[..., 1] + torch.arange(height // 2)[:, None]
-        latent_image_ids[..., 2] = latent_image_ids[..., 2] + torch.arange(width // 2)[None, :]
-
-        latent_image_id_height, latent_image_id_width, latent_image_id_channels = latent_image_ids.shape
-
-        latent_image_ids = latent_image_ids.reshape(
-            latent_image_id_height * latent_image_id_width, latent_image_id_channels
-        )
-
-        return latent_image_ids.to(device=device, dtype=dtype)
-
-    def prepare_latents(
-        self,
-        image,
-        timestep,
-        batch_size,
-        num_channels_latents,
-        height,
-        width,
-        dtype,
-        device,
-        generator,
-        latents=None,
-    ):
-        height = 2 * (int(height) // (self.vae_scale_factor * 2))
-        width = 2 * (int(width) // (self.vae_scale_factor * 2))
-
-        shape = (batch_size, num_channels_latents, height, width)
-        latent_image_ids = self._prepare_latent_image_ids(batch_size, height, width, device, dtype)
-
-        if latents is not None:
-            return latents.to(device=device, dtype=dtype)
-
-        # Encode the input image
-        image = image.to(device=device, dtype=dtype)
-        if image.shape[1] != num_channels_latents:
-            if isinstance(generator, list):
-                image_latents = [
-                    retrieve_latents(self.vae.encode(image[i : i + 1]), generator=generator[i])
-                    for i in range(image.shape[0])
-                ]
-                image_latents = torch.cat(image_latents, dim=0)
-            else:
-                image_latents = retrieve_latents(self.vae.encode(image), generator=generator)
-
-            # Apply scaling (inverse of decoding: decode does latents/scaling_factor + shift_factor)
-            image_latents = (image_latents - self.vae.config.shift_factor) * self.vae.config.scaling_factor
-        else:
-            image_latents = image
-
-        # Handle batch size expansion
-        if batch_size > image_latents.shape[0] and batch_size % image_latents.shape[0] == 0:
-            additional_image_per_prompt = batch_size // image_latents.shape[0]
-            image_latents = torch.cat([image_latents] * additional_image_per_prompt, dim=0)
-        elif batch_size > image_latents.shape[0] and batch_size % image_latents.shape[0] != 0:
-            raise ValueError(
-                f"Cannot duplicate `image` of batch size {image_latents.shape[0]} to {batch_size} text prompts."
-            )
-
-        # Add noise using flow matching scale_noise
-        noise = randn_tensor(shape, generator=generator, device=device, dtype=dtype)
-        latents = self.scheduler.scale_noise(image_latents, timestep, noise)
-
-        return latents, noise, image_latents, latent_image_ids
-
-    def prepare_mask_latents(
-        self,
-        mask,
-        masked_image,
-        batch_size,
-        num_images_per_prompt,
-        height,
-        width,
-        dtype,
-        device,
-        generator,
-    ):
-        height = 2 * (int(height) // (self.vae_scale_factor * 2))
-        width = 2 * (int(width) // (self.vae_scale_factor * 2))
-        # resize the mask to latents shape as we concatenate the mask to the latents
-        # we do that before converting to dtype to avoid breaking in case we're using cpu_offload
-        # and half precision
-        mask = torch.nn.functional.interpolate(mask, size=(height, width))
-        mask = mask.to(device=device, dtype=dtype)
-
-        batch_size = batch_size * num_images_per_prompt
-
-        masked_image = masked_image.to(device=device, dtype=dtype)
-
-        if masked_image.shape[1] == 16:
-            masked_image_latents = masked_image
-        else:
-            masked_image_latents = retrieve_latents(self.vae.encode(masked_image), generator=generator)
-
-        masked_image_latents = (masked_image_latents - self.vae.config.shift_factor) * self.vae.config.scaling_factor
-
-        # duplicate mask and masked_image_latents for each generation per prompt, using mps friendly method
-        if mask.shape[0] < batch_size:
-            if not batch_size % mask.shape[0] == 0:
-                raise ValueError(
-                    "The passed mask and the required batch size don't match. Masks are supposed to be duplicated to"
-                    f" a total batch size of {batch_size}, but {mask.shape[0]} masks were passed. Make sure the number"
-                    " of masks that you pass is divisible by the total requested batch size."
-                )
-            mask = mask.repeat(batch_size // mask.shape[0], 1, 1, 1)
-        if masked_image_latents.shape[0] < batch_size:
-            if not batch_size % masked_image_latents.shape[0] == 0:
-                raise ValueError(
-                    "The passed images and the required batch size don't match. Images are supposed to be duplicated"
-                    f" to a total batch size of {batch_size}, but {masked_image_latents.shape[0]} images were passed."
-                    " Make sure the number of images that you pass is divisible by the total requested batch size."
-                )
-            masked_image_latents = masked_image_latents.repeat(batch_size // masked_image_latents.shape[0], 1, 1, 1)
-
-        # aligning device to prevent device errors when concating it with the latent model input
-        masked_image_latents = masked_image_latents.to(device=device, dtype=dtype)
-
-        return mask, masked_image_latents
-
-    @property
-    def guidance_scale(self):
-        return self._guidance_scale
-
-    @property
-    def do_classifier_free_guidance(self):
-        return self._guidance_scale > 1
-
-    @property
-    def joint_attention_kwargs(self):
-        return self._joint_attention_kwargs
-
-    @property
-    def num_timesteps(self):
-        return self._num_timesteps
-
-    @property
-    def interrupt(self):
-        return self._interrupt
-
-    @torch.no_grad()
-    @replace_example_docstring(EXAMPLE_DOC_STRING)
-    def __call__(
-        self,
-        prompt: Union[str, List[str]] = None,
-        image: PipelineImageInput = None,
-        mask_image: PipelineImageInput = None,
-        strength: float = 0.6,
-        height: Optional[int] = None,
-        width: Optional[int] = None,
-        num_inference_steps: int = 50,
-        sigmas: Optional[List[float]] = None,
-        guidance_scale: float = 5.0,
-        cfg_normalization: bool = False,
-        cfg_truncation: float = 1.0,
-        negative_prompt: Optional[Union[str, List[str]]] = None,
-        num_images_per_prompt: Optional[int] = 1,
-        generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
-        latents: Optional[torch.FloatTensor] = None,
-        prompt_embeds: Optional[List[torch.FloatTensor]] = None,
-        negative_prompt_embeds: Optional[List[torch.FloatTensor]] = None,
-        output_type: Optional[str] = "pil",
-        return_dict: bool = True,
-        joint_attention_kwargs: Optional[Dict[str, Any]] = None,
-        callback_on_step_end: Optional[Callable[[int, int, Dict], None]] = None,
-        callback_on_step_end_tensor_inputs: List[str] = ["latents"],
-        max_sequence_length: int = 512,
-    ):
-        r"""
-        Function invoked when calling the pipeline for image-to-image generation.
-
-        Args:
-            prompt (`str` or `List[str]`, *optional*):
-                The prompt or prompts to guide the image generation. If not defined, one has to pass `prompt_embeds`.
-                instead.
-            image (`torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.Tensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
-                `Image`, numpy array or tensor representing an image batch to be used as the starting point. For both
-                numpy array and pytorch tensor, the expected value range is between `[0, 1]`. If it's a tensor or a
-                list of tensors, the expected shape should be `(B, C, H, W)` or `(C, H, W)`. If it is a numpy array or
-                a list of arrays, the expected shape should be `(B, H, W, C)` or `(H, W, C)`.
-            mask_image (`torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.Tensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
-                `Image`, numpy array or tensor representing an image batch to mask `image`. Black pixels in the mask
-                are repainted while white pixels are preserved. If `mask_image` is a PIL image, it is converted to a
-                single channel (luminance) before use. If it's a numpy array or pytorch tensor, it should contain one
-                color channel (L) instead of 3, so the expected shape for pytorch tensor would be `(B, 1, H, W)`, `(B,
-                H, W)`, `(1, H, W)`, `(H, W)`. And for numpy array would be for `(B, H, W, 1)`, `(B, H, W)`, `(H, W,
-                1)`, or `(H, W)`.
-            strength (`float`, *optional*, defaults to 0.6):
-                Indicates extent to transform the reference `image`. Must be between 0 and 1. `image` is used as a
-                starting point and more noise is added the higher the `strength`. The number of denoising steps depends
-                on the amount of noise initially added. When `strength` is 1, added noise is maximum and the denoising
-                process runs for the full number of iterations specified in `num_inference_steps`. A value of 1
-                essentially ignores `image`.
-            height (`int`, *optional*, defaults to 1024):
-                The height in pixels of the generated image. If not provided, uses the input image height.
-            width (`int`, *optional*, defaults to 1024):
-                The width in pixels of the generated image. If not provided, uses the input image width.
-            num_inference_steps (`int`, *optional*, defaults to 50):
-                The number of denoising steps. More denoising steps usually lead to a higher quality image at the
-                expense of slower inference.
-            sigmas (`List[float]`, *optional*):
-                Custom sigmas to use for the denoising process with schedulers which support a `sigmas` argument in
-                their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is passed
-                will be used.
-            guidance_scale (`float`, *optional*, defaults to 5.0):
-                Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
-                `guidance_scale` is defined as `w` of equation 2. of [Imagen
-                Paper](https://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting `guidance_scale >
-                1`. Higher guidance scale encourages to generate images that are closely linked to the text `prompt`,
-                usually at the expense of lower image quality.
-            cfg_normalization (`bool`, *optional*, defaults to False):
-                Whether to apply configuration normalization.
-            cfg_truncation (`float`, *optional*, defaults to 1.0):
-                The truncation value for configuration.
-            negative_prompt (`str` or `List[str]`, *optional*):
-                The prompt or prompts not to guide the image generation. If not defined, one has to pass
-                `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
-                less than `1`).
-            num_images_per_prompt (`int`, *optional*, defaults to 1):
-                The number of images to generate per prompt.
-            generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
-                One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
-                to make generation deterministic.
-            latents (`torch.FloatTensor`, *optional*):
-                Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
-                generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
-                tensor will be generated by sampling using the supplied random `generator`.
-            prompt_embeds (`List[torch.FloatTensor]`, *optional*):
-                Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
-                provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`List[torch.FloatTensor]`, *optional*):
-                Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
-                weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
-                argument.
-            output_type (`str`, *optional*, defaults to `"pil"`):
-                The output format of the generate image. Choose between
-                [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
-            return_dict (`bool`, *optional*, defaults to `True`):
-                Whether or not to return a [`~pipelines.stable_diffusion.ZImagePipelineOutput`] instead of a plain
-                tuple.
-            joint_attention_kwargs (`dict`, *optional*):
-                A kwargs dictionary that if specified is passed along to the `AttentionProcessor` as defined under
-                `self.processor` in
-                [diffusers.models.attention_processor](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
-            callback_on_step_end (`Callable`, *optional*):
-                A function that calls at the end of each denoising steps during the inference. The function is called
-                with the following arguments: `callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int,
-                callback_kwargs: Dict)`. `callback_kwargs` will include a list of all tensors as specified by
-                `callback_on_step_end_tensor_inputs`.
-            callback_on_step_end_tensor_inputs (`List`, *optional*):
-                The list of tensor inputs for the `callback_on_step_end` function. The tensors specified in the list
-                will be passed as `callback_kwargs` argument. You will only be able to include variables listed in the
-                `._callback_tensor_inputs` attribute of your pipeline class.
-            max_sequence_length (`int`, *optional*, defaults to 512):
-                Maximum sequence length to use with the `prompt`.
-
-        Examples:
-
-        Returns:
-            [`~pipelines.z_image.ZImagePipelineOutput`] or `tuple`: [`~pipelines.z_image.ZImagePipelineOutput`] if
-            `return_dict` is True, otherwise a `tuple`. When returning a tuple, the first element is a list with the
-            generated images.
-        """
-        # 1. Check inputs and validate strength
-        if strength < 0 or strength > 1:
-            raise ValueError(f"The value of strength should be in [0.0, 1.0] but is {strength}")
-
-        # 2. Preprocess image
-        init_image = self.image_processor.preprocess(image)
-        init_image = init_image.to(dtype=torch.float32)
-
-        # Get dimensions from the preprocessed image if not specified
-        if height is None:
-            height = init_image.shape[-2]
-        if width is None:
-            width = init_image.shape[-1]
-
-        vae_scale = self.vae_scale_factor * 2
-        if height % vae_scale != 0:
-            raise ValueError(
-                f"Height must be divisible by {vae_scale} (got {height}). "
-                f"Please adjust the height to a multiple of {vae_scale}."
-            )
-        if width % vae_scale != 0:
-            raise ValueError(
-                f"Width must be divisible by {vae_scale} (got {width}). "
-                f"Please adjust the width to a multiple of {vae_scale}."
-            )
-
-        device = self._execution_device
-
-        self._guidance_scale = guidance_scale
-        self._joint_attention_kwargs = joint_attention_kwargs
-        self._interrupt = False
-        self._cfg_normalization = cfg_normalization
-        self._cfg_truncation = cfg_truncation
-
-        # 3. Define call parameters
-        if prompt is not None and isinstance(prompt, str):
-            batch_size = 1
-        elif prompt is not None and isinstance(prompt, list):
-            batch_size = len(prompt)
-        else:
-            batch_size = len(prompt_embeds)
-
-        # If prompt_embeds is provided and prompt is None, skip encoding
-        if prompt_embeds is not None and prompt is None:
-            if self.do_classifier_free_guidance and negative_prompt_embeds is None:
-                raise ValueError(
-                    "When `prompt_embeds` is provided without `prompt`, "
-                    "`negative_prompt_embeds` must also be provided for classifier-free guidance."
-                )
-        else:
-            (
-                prompt_embeds,
-                negative_prompt_embeds,
-            ) = self.encode_prompt(
-                prompt=prompt,
-                negative_prompt=negative_prompt,
-                do_classifier_free_guidance=self.do_classifier_free_guidance,
-                prompt_embeds=prompt_embeds,
-                negative_prompt_embeds=negative_prompt_embeds,
-                device=device,
-                max_sequence_length=max_sequence_length,
-            )
-
-        # 4. Prepare latent variables
-        num_channels_latents = self.transformer.in_channels
-
-        # Repeat prompt_embeds for num_images_per_prompt
-        if num_images_per_prompt > 1:
-            prompt_embeds = [pe for pe in prompt_embeds for _ in range(num_images_per_prompt)]
-            if self.do_classifier_free_guidance and negative_prompt_embeds:
-                negative_prompt_embeds = [npe for npe in negative_prompt_embeds for _ in range(num_images_per_prompt)]
-
-        actual_batch_size = batch_size * num_images_per_prompt
-
-        # Calculate latent dimensions for image_seq_len
-        latent_height = 2 * (int(height) // (self.vae_scale_factor * 2))
-        latent_width = 2 * (int(width) // (self.vae_scale_factor * 2))
-        image_seq_len = (latent_height // 2) * (latent_width // 2)
-
-        # 5. Prepare timesteps
-        mu = calculate_shift(
-            image_seq_len,
-            self.scheduler.config.get("base_image_seq_len", 256),
-            self.scheduler.config.get("max_image_seq_len", 4096),
-            self.scheduler.config.get("base_shift", 0.5),
-            self.scheduler.config.get("max_shift", 1.15),
-        )
-        self.scheduler.sigma_min = 0.0
-        scheduler_kwargs = {"mu": mu}
-        timesteps, num_inference_steps = retrieve_timesteps(
-            self.scheduler,
-            num_inference_steps,
-            device,
-            sigmas=sigmas,
-            **scheduler_kwargs,
-        )
-
-        # 6. Adjust timesteps based on strength
-        timesteps, num_inference_steps = self.get_timesteps(num_inference_steps, strength, device)
-        if num_inference_steps < 1:
-            raise ValueError(
-                f"After adjusting the num_inference_steps by strength parameter: {strength}, the number of pipeline "
-                f"steps is {num_inference_steps} which is < 1 and not appropriate for this pipeline."
-            )
-        latent_timestep = timesteps[:1].repeat(actual_batch_size)
-
-        # 7. Prepare latents from image
-        latents, noise, original_image_latents, latent_image_ids = self.prepare_latents(
-            init_image,
-            latent_timestep,
-            actual_batch_size,
-            num_channels_latents,
-            height,
-            width,
-            prompt_embeds[0].dtype,
-            device,
-            generator,
-            latents,
-        )
-        resize_mode = "default"
-        crops_coords = None
-
-        # start diff diff preparation
-        original_mask = self.mask_processor.preprocess(
-            mask_image, height=height, width=width, resize_mode=resize_mode, crops_coords=crops_coords
-        )
-
-        masked_image = init_image * original_mask
-        original_mask, _ = self.prepare_mask_latents(
-            original_mask,
-            masked_image,
-            batch_size,
-            num_images_per_prompt,
-            height,
-            width,
-            prompt_embeds[0].dtype,
-            device,
-            generator,
-        )
-        mask_thresholds = torch.arange(num_inference_steps, dtype=original_mask.dtype) / num_inference_steps
-        mask_thresholds = mask_thresholds.reshape(-1, 1, 1, 1).to(device)
-        masks = original_mask > mask_thresholds
-        # end diff diff preparation
-
-        num_warmup_steps = max(len(timesteps) - num_inference_steps * self.scheduler.order, 0)
-        self._num_timesteps = len(timesteps)
-
-        # 8. Denoising loop
-        with self.progress_bar(total=num_inference_steps) as progress_bar:
-            for i, t in enumerate(timesteps):
-                if self.interrupt:
-                    continue
-
-                # broadcast to batch dimension in a way that's compatible with ONNX/Core ML
-                timestep = t.expand(latents.shape[0])
-                timestep = (1000 - timestep) / 1000
-                # Normalized time for time-aware config (0 at start, 1 at end)
-                t_norm = timestep[0].item()
-
-                # Handle cfg truncation
-                current_guidance_scale = self.guidance_scale
-                if (
-                    self.do_classifier_free_guidance
-                    and self._cfg_truncation is not None
-                    and float(self._cfg_truncation) <= 1
-                ):
-                    if t_norm > self._cfg_truncation:
-                        current_guidance_scale = 0.0
-
-                # Run CFG only if configured AND scale is non-zero
-                apply_cfg = self.do_classifier_free_guidance and current_guidance_scale > 0
-
-                if apply_cfg:
-                    latents_typed = latents.to(self.transformer.dtype)
-                    latent_model_input = latents_typed.repeat(2, 1, 1, 1)
-                    prompt_embeds_model_input = prompt_embeds + negative_prompt_embeds
-                    timestep_model_input = timestep.repeat(2)
-                else:
-                    latent_model_input = latents.to(self.transformer.dtype)
-                    prompt_embeds_model_input = prompt_embeds
-                    timestep_model_input = timestep
-
-                latent_model_input = latent_model_input.unsqueeze(2)
-                latent_model_input_list = list(latent_model_input.unbind(dim=0))
-
-                model_out_list = self.transformer(
-                    latent_model_input_list,
-                    timestep_model_input,
-                    prompt_embeds_model_input,
-                )[0]
-
-                if apply_cfg:
-                    # Perform CFG
-                    pos_out = model_out_list[:actual_batch_size]
-                    neg_out = model_out_list[actual_batch_size:]
-
-                    noise_pred = []
-                    for j in range(actual_batch_size):
-                        pos = pos_out[j].float()
-                        neg = neg_out[j].float()
-
-                        pred = pos + current_guidance_scale * (pos - neg)
-
-                        # Renormalization
-                        if self._cfg_normalization and float(self._cfg_normalization) > 0.0:
-                            ori_pos_norm = torch.linalg.vector_norm(pos)
-                            new_pos_norm = torch.linalg.vector_norm(pred)
-                            max_new_norm = ori_pos_norm * float(self._cfg_normalization)
-                            if new_pos_norm > max_new_norm:
-                                pred = pred * (max_new_norm / new_pos_norm)
-
-                        noise_pred.append(pred)
-
-                    noise_pred = torch.stack(noise_pred, dim=0)
-                else:
-                    noise_pred = torch.stack([t.float() for t in model_out_list], dim=0)
-
-                noise_pred = noise_pred.squeeze(2)
-                noise_pred = -noise_pred
-
-                # compute the previous noisy sample x_t -> x_t-1
-                latents = self.scheduler.step(noise_pred.to(torch.float32), t, latents, return_dict=False)[0]
-                assert latents.dtype == torch.float32
-
-                # start diff diff
-                image_latent = original_image_latents
-                latents_dtype = latents.dtype
-                if i < len(timesteps) - 1:
-                    noise_timestep = timesteps[i + 1]
-                    image_latent = self.scheduler.scale_noise(
-                        original_image_latents, torch.tensor([noise_timestep]), noise
-                    )
-
-                    mask = masks[i].to(latents_dtype)
-                    latents = image_latent * mask + latents * (1 - mask)
-                # end diff diff
-
-                if latents.dtype != latents_dtype:
-                    if torch.backends.mps.is_available():
-                        # some platforms (eg. apple mps) misbehave due to a pytorch bug: https://github.com/pytorch/pytorch/pull/99272
-                        latents = latents.to(latents_dtype)
-
-                if callback_on_step_end is not None:
-                    callback_kwargs = {}
-                    for k in callback_on_step_end_tensor_inputs:
-                        callback_kwargs[k] = locals()[k]
-                    callback_outputs = callback_on_step_end(self, i, t, callback_kwargs)
-
-                    latents = callback_outputs.pop("latents", latents)
-                    prompt_embeds = callback_outputs.pop("prompt_embeds", prompt_embeds)
-                    negative_prompt_embeds = callback_outputs.pop("negative_prompt_embeds", negative_prompt_embeds)
-
-                # call the callback, if provided
-                if i == len(timesteps) - 1 or ((i + 1) > num_warmup_steps and (i + 1) % self.scheduler.order == 0):
-                    progress_bar.update()
-
-        if output_type == "latent":
-            image = latents
-
-        else:
-            latents = latents.to(self.vae.dtype)
-            latents = (latents / self.vae.config.scaling_factor) + self.vae.config.shift_factor
-
-            image = self.vae.decode(latents, return_dict=False)[0]
-            image = self.image_processor.postprocess(image, output_type=output_type)
-
-        # Offload all models
-        self.maybe_free_model_hooks()
-
-        if not return_dict:
-            return (image,)
-
-        return ZImagePipelineOutput(images=image)

examples/community/pipline_flux_fill_controlnet_Inpaint.py

@@ -1168,12 +1168,12 @@ class FluxControlNetFillInpaintPipeline(DiffusionPipeline, FluxLoraLoaderMixin,
             generator,
         )
 
-        mask_image_fill = self.mask_processor.preprocess(mask_image, height=height, width=width)
-        masked_image_fill = init_image * (1 - mask_image_fill)
-        masked_image_fill = masked_image_fill.to(dtype=self.vae.dtype, device=device)
-        mask_fill, masked_latents_fill = self.prepare_mask_latents_fill(
-            mask_image_fill,
-            masked_image_fill,
+        mask_imagee = self.mask_processor.preprocess(mask_image, height=height, width=width)
+        masked_imagee = init_image * (1 - mask_imagee)
+        masked_imagee = masked_imagee.to(dtype=self.vae.dtype, device=device)
+        maskkk, masked_image_latentsss = self.prepare_mask_latents_fill(
+            mask_imagee,
+            masked_imagee,
             batch_size,
             num_channels_latents,
             num_images_per_prompt,
@@ -1243,7 +1243,7 @@ class FluxControlNetFillInpaintPipeline(DiffusionPipeline, FluxLoraLoaderMixin,
                 else:
                     guidance = None
 
-                masked_image_latents_fill = torch.cat((masked_latents_fill, mask_fill), dim=-1)
+                masked_image_latents_fill = torch.cat((masked_image_latentsss, maskkk), dim=-1)
                 latent_model_input = torch.cat([latents, masked_image_latents_fill], dim=2)
 
                 noise_pred = self.transformer(

examples/consistency_distillation/train_lcm_distill_lora_sd_wds.py

@@ -74,7 +74,7 @@ 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("0.37.0.dev0")
+check_min_version("0.36.0.dev0")
 
 logger = get_logger(__name__)
 

examples/consistency_distillation/train_lcm_distill_lora_sdxl.py

@@ -67,7 +67,7 @@ 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("0.37.0.dev0")
+check_min_version("0.36.0.dev0")
 
 logger = get_logger(__name__)
 

examples/consistency_distillation/train_lcm_distill_lora_sdxl_wds.py

@@ -80,7 +80,7 @@ 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("0.37.0.dev0")
+check_min_version("0.36.0.dev0")
 
 logger = get_logger(__name__)
 

examples/consistency_distillation/train_lcm_distill_sd_wds.py

@@ -73,7 +73,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.37.0.dev0")
+check_min_version("0.36.0.dev0")
 
 logger = get_logger(__name__)
 

examples/consistency_distillation/train_lcm_distill_sdxl_wds.py

@@ -79,7 +79,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.37.0.dev0")
+check_min_version("0.36.0.dev0")
 
 logger = get_logger(__name__)
 

examples/controlnet/train_controlnet.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("0.37.0.dev0")
+check_min_version("0.36.0.dev0")
 
 logger = get_logger(__name__)
 

examples/controlnet/train_controlnet_flax.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("0.37.0.dev0")
+check_min_version("0.36.0.dev0")
 
 logger = logging.getLogger(__name__)
 

examples/controlnet/train_controlnet_flux.py

@@ -66,7 +66,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.37.0.dev0")
+check_min_version("0.36.0.dev0")
 
 logger = get_logger(__name__)
 if is_torch_npu_available():

examples/controlnet/train_controlnet_sd3.py

@@ -63,7 +63,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.37.0.dev0")
+check_min_version("0.36.0.dev0")
 
 logger = get_logger(__name__)
 

examples/controlnet/train_controlnet_sdxl.py

@@ -62,7 +62,7 @@ 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("0.37.0.dev0")
+check_min_version("0.36.0.dev0")
 
 logger = get_logger(__name__)
 if is_torch_npu_available():

examples/custom_diffusion/train_custom_diffusion.py

@@ -64,7 +64,7 @@ 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("0.37.0.dev0")
+check_min_version("0.36.0.dev0")
 
 logger = get_logger(__name__)
 

examples/dreambooth/README_flux2.md

@@ -1,338 +0,0 @@
-# DreamBooth training example for FLUX.2 [dev]
-
-[DreamBooth](https://huggingface.co/papers/2208.12242) is a method to personalize image generation models given just a few (3~5) images of a subject/concept.
-
-The `train_dreambooth_lora_flux2.py` script shows how to implement the training procedure for [LoRAs](https://huggingface.co/blog/lora) and adapt it for [FLUX.2 [dev]](https://github.com/black-forest-labs/flux2).
-
-> [!NOTE]
-> **Memory consumption**
->
-> Flux can be quite expensive to run on consumer hardware devices and as a result finetuning it comes with high memory requirements -
-> a LoRA with a rank of 16 can exceed XXGB of VRAM for training. below we provide some tips and tricks to reduce memory consumption during training.
-
-> For more tips & guidance on training on a resource-constrained device and general good practices please check out these great guides and trainers for FLUX: 
-> 1) [`@bghira`'s guide](https://github.com/bghira/SimpleTuner/blob/main/documentation/quickstart/FLUX2.md)
-> 2) [`ostris`'s guide](https://github.com/ostris/ai-toolkit?tab=readme-ov-file#flux2-training)
-
-> [!NOTE]
-> **Gated model**
->
-> As the model is gated, before using it with diffusers you first need to go to the [FLUX.2 [dev] Hugging Face page](https://huggingface.co/black-forest-labs/FLUX.2-dev), fill in the form and accept the gate. Once you are in, you need to log in so that your system knows you’ve accepted the gate. Use the command below to log in:
-
-```bash
-hf auth login
-```
-
-This will also allow us to push the trained model parameters to the Hugging Face Hub platform.
-
-## Running locally with PyTorch
-
-### Installing the dependencies
-
-Before running the scripts, make sure to install the library's training dependencies:
-
-**Important**
-
-To make sure you can successfully run the latest versions of the example scripts, we highly recommend **installing from source** and keeping the install up to date as we update the example scripts frequently and install some example-specific requirements. To do this, execute the following steps in a new virtual environment:
-
-```bash
-git clone https://github.com/huggingface/diffusers
-cd diffusers
-pip install -e .
-```
-
-Then cd in the `examples/dreambooth` folder and run
-```bash
-pip install -r requirements_flux.txt
-```
-
-And initialize an [🤗Accelerate](https://github.com/huggingface/accelerate/) environment with:
-
-```bash
-accelerate config
-```
-
-Or for a default accelerate configuration without answering questions about your environment
-
-```bash
-accelerate config default
-```
-
-Or if your environment doesn't support an interactive shell (e.g., a notebook)
-
-```python
-from accelerate.utils import write_basic_config
-write_basic_config()
-```
-
-When running `accelerate config`, if we specify torch compile mode to True there can be dramatic speedups.
-Note also that we use PEFT library as backend for LoRA training, make sure to have `peft>=0.6.0` installed in your environment.
-
-
-### Dog toy example
-
-Now let's get our dataset. For this example we will use some dog images: https://huggingface.co/datasets/diffusers/dog-example.
-
-Let's first download it locally:
-
-```python
-from huggingface_hub import snapshot_download
-
-local_dir = "./dog"
-snapshot_download(
-    "diffusers/dog-example",
-    local_dir=local_dir, repo_type="dataset",
-    ignore_patterns=".gitattributes",
-)
-```
-
-This will also allow us to push the trained LoRA parameters to the Hugging Face Hub platform.
-
-As mentioned, Flux2 LoRA training is *very* memory intensive. Here are memory optimizations we can use (some still experimental) for a more memory efficient training:
-
-## Memory Optimizations
-> [!NOTE] many of these techniques complement each other and can be used together to further reduce memory consumption. 
-> However some techniques may be mutually exclusive so be sure to check before launching a training run.
-### Remote Text Encoder 
-Flux.2 uses  Mistral Small 3.1 as text encoder which is quite large and can take up a lot of memory. To mitigate this, we can use the `--remote_text_encoder` flag to enable remote computation of the prompt embeddings using the HuggingFace Inference API. 
-This way, the text encoder model is not loaded into memory during training.
-> [!NOTE] 
-> to enable remote text encoding you must either be logged in to your HuggingFace account (`hf auth login`) OR pass a token with `--hub_token`.
-### FSDP Text Encoder 
-Flux.2 uses  Mistral Small 3.1 as text encoder which is quite large and can take up a lot of memory. To mitigate this, we can use the `--fsdp_text_encoder` flag to enable distributed computation of the prompt embeddings. 
-This way, it distributes the memory cost across multiple nodes.
-### CPU Offloading 
-To offload parts of the model to CPU memory, you can use `--offload` flag. This will offload the vae and text encoder to CPU memory and only move them to GPU when needed.
-### Latent Caching 
-Pre-encode the training images with the vae, and then delete it to free up some memory. To enable `latent_caching` simply pass `--cache_latents`.
-### QLoRA: Low Precision Training with Quantization
-Perform low precision training using 8-bit or 4-bit quantization to reduce memory usage. You can use the following flags:
-- **FP8 training** with `torchao`: 
-enable FP8 training by passing `--do_fp8_training`. 
-> [!IMPORTANT] Since we are utilizing FP8 tensor cores we need CUDA GPUs with compute capability at least 8.9 or greater. 
-> If you're looking for memory-efficient training on relatively older cards, we encourage you to check out other trainers like SimpleTuner, ai-toolkit, etc.
-- **NF4 training** with `bitsandbytes`: 
-Alternatively, you can use 8-bit or 4-bit quantization with `bitsandbytes` by passing:
-`--bnb_quantization_config_path` to enable 4-bit NF4 quantization.
-### Gradient Checkpointing and Accumulation
-* `--gradient accumulation` refers to the number of updates steps to accumulate before performing a backward/update pass.
-by passing a value > 1 you can reduce the amount of backward/update passes and hence also memory reqs.
-* with `--gradient checkpointing` we can save memory by not storing all intermediate activations during the forward pass.
-Instead, only a subset of these activations (the checkpoints) are stored and the rest is recomputed as needed during the backward pass. Note that this comes at the expanse of a slower backward pass.
-### 8-bit-Adam Optimizer
-When training with `AdamW`(doesn't apply to `prodigy`) You can pass `--use_8bit_adam` to reduce the memory requirements of training. 
-Make sure to install `bitsandbytes` if you want to do so.
-### Image Resolution
-An easy way to mitigate some of the memory requirements is through `--resolution`. `--resolution` refers to the resolution for input images, all the images in the train/validation dataset are resized to this.
-Note that by default, images are resized to resolution of 512, but it's good to keep in mind in case you're accustomed to training on higher resolutions.
-### Precision of saved LoRA layers
-By default, trained transformer layers are saved in the precision dtype in which training was performed. E.g. when training in mixed precision is enabled with `--mixed_precision="bf16"`, final finetuned layers will be saved in `torch.bfloat16` as well. 
-This reduces memory requirements significantly w/o a significant quality loss. Note that if you do wish to save the final layers in float32 at the expanse of more memory usage, you can do so by passing `--upcast_before_saving`.
-
-
-```bash
-export MODEL_NAME="black-forest-labs/FLUX.2-dev"
-export INSTANCE_DIR="dog"
-export OUTPUT_DIR="trained-flux2"
-
-accelerate launch train_dreambooth_lora_flux2.py \
-  --pretrained_model_name_or_path=$MODEL_NAME  \
-  --instance_data_dir=$INSTANCE_DIR \
-  --output_dir=$OUTPUT_DIR \
-  --do_fp8_training \
-  --gradient_checkpointing \
-  --remote_text_encoder \
-  --cache_latents \
-  --instance_prompt="a photo of sks dog" \
-  --resolution=1024 \
-  --train_batch_size=1 \
-  --guidance_scale=1 \
-  --use_8bit_adam \
-  --gradient_accumulation_steps=4 \
-  --optimizer="adamW" \
-  --learning_rate=1e-4 \
-  --report_to="wandb" \
-  --lr_scheduler="constant" \
-  --lr_warmup_steps=100 \
-  --max_train_steps=500 \
-  --validation_prompt="A photo of sks dog in a bucket" \
-  --validation_epochs=25 \
-  --seed="0" \
-  --push_to_hub
-```
-
-To better track our training experiments, we're using the following flags in the command above:
-
-* `report_to="wandb` will ensure the training runs are tracked on [Weights and Biases](https://wandb.ai/site). To use it, be sure to install `wandb` with `pip install wandb`. Don't forget to call `wandb login <your_api_key>` before training if you haven't done it before.
-* `validation_prompt` and `validation_epochs` to allow the script to do a few validation inference runs. This allows us to qualitatively check if the training is progressing as expected.
-
-> [!NOTE]
-> If you want to train using long prompts with the T5 text encoder, you can use `--max_sequence_length` to set the token limit. The default is 77, but it can be increased to as high as 512. Note that this will use more resources and may slow down the training in some cases.
-
-### FSDP on the transformer
-By setting the accelerate configuration with FSDP, the transformer block will be wrapped automatically. E.g. set the configuration to:
-
-```shell
-distributed_type: FSDP
-fsdp_config:
-  fsdp_version: 2
-  fsdp_offload_params: false
-  fsdp_sharding_strategy: HYBRID_SHARD
-  fsdp_auto_wrap_policy: TRANSFOMER_BASED_WRAP
-  fsdp_transformer_layer_cls_to_wrap: Flux2TransformerBlock, Flux2SingleTransformerBlock
-  fsdp_forward_prefetch: true
-  fsdp_sync_module_states: false
-  fsdp_state_dict_type: FULL_STATE_DICT
-  fsdp_use_orig_params: false
-  fsdp_activation_checkpointing: true
-  fsdp_reshard_after_forward: true
-  fsdp_cpu_ram_efficient_loading: false
-```
-
-## LoRA + DreamBooth
-
-[LoRA](https://huggingface.co/docs/peft/conceptual_guides/adapter#low-rank-adaptation-lora) is a popular parameter-efficient fine-tuning technique that allows you to achieve full-finetuning like performance but with a fraction of learnable parameters.
-
-Note also that we use PEFT library as backend for LoRA training, make sure to have `peft>=0.6.0` installed in your environment.
-
-### Prodigy Optimizer
-Prodigy is an adaptive optimizer that dynamically adjusts the learning rate learned parameters based on past gradients, allowing for more efficient convergence. 
-By using prodigy we can "eliminate" the need for manual learning rate tuning. read more [here](https://huggingface.co/blog/sdxl_lora_advanced_script#adaptive-optimizers).
-
-to use prodigy, first make sure to install the prodigyopt library: `pip install prodigyopt`, and then specify -
-```bash
---optimizer="prodigy"
-```
-> [!TIP]
-> When using prodigy it's generally good practice to set- `--learning_rate=1.0`
-
-To perform DreamBooth with LoRA, run:
-
-```bash
-export MODEL_NAME="black-forest-labs/FLUX.2-dev"
-export INSTANCE_DIR="dog"
-export OUTPUT_DIR="trained-flux2-lora"
-
-accelerate launch train_dreambooth_lora_flux2.py \
-  --pretrained_model_name_or_path=$MODEL_NAME  \
-  --instance_data_dir=$INSTANCE_DIR \
-  --output_dir=$OUTPUT_DIR \
-  --do_fp8_training \
-  --gradient_checkpointing \
-  --remote_text_encoder \
-  --cache_latents \
-  --instance_prompt="a photo of sks dog" \
-  --resolution=512 \
-  --train_batch_size=1 \
-  --guidance_scale=1 \
-  --gradient_accumulation_steps=4 \
-  --optimizer="prodigy" \
-  --learning_rate=1. \
-  --report_to="wandb" \
-  --lr_scheduler="constant_with_warmup" \
-  --lr_warmup_steps=100 \
-  --max_train_steps=500 \
-  --validation_prompt="A photo of sks dog in a bucket" \
-  --validation_epochs=25 \
-  --seed="0" \
-  --push_to_hub
-```
-
-### LoRA Rank and Alpha
-Two key LoRA hyperparameters are LoRA rank and LoRA alpha. 
-- `--rank`: Defines the dimension of the trainable LoRA matrices. A higher rank means more expressiveness and capacity to learn (and more parameters).
-- `--lora_alpha`: A scaling factor for the LoRA's output. The LoRA update is scaled by lora_alpha / lora_rank.
-- lora_alpha vs. rank:
-This ratio dictates the LoRA's effective strength:
-lora_alpha == rank: Scaling factor is 1. The LoRA is applied with its learned strength. (e.g., alpha=16, rank=16)
-lora_alpha < rank: Scaling factor < 1. Reduces the LoRA's impact. Useful for subtle changes or to prevent overpowering the base model. (e.g., alpha=8, rank=16)
-lora_alpha > rank: Scaling factor > 1. Amplifies the LoRA's impact. Allows a lower rank LoRA to have a stronger effect. (e.g., alpha=32, rank=16)
-
-> [!TIP]
-> A common starting point is to set `lora_alpha` equal to `rank`. 
-> Some also set `lora_alpha` to be twice the `rank` (e.g., lora_alpha=32 for lora_rank=16) 
-> to give the LoRA updates more influence without increasing parameter count. 
-> If you find your LoRA is "overcooking" or learning too aggressively, consider setting `lora_alpha` to half of `rank` 
-> (e.g., lora_alpha=8 for rank=16). Experimentation is often key to finding the optimal balance for your use case.
-
-### Target Modules
-When LoRA was first adapted from language models to diffusion models, it was applied to the cross-attention layers in the Unet that relate the image representations with the prompts that describe them. 
-More recently, SOTA text-to-image diffusion models replaced the Unet with a diffusion Transformer(DiT). With this change, we may also want to explore 
-applying LoRA training onto different types of layers and blocks. To allow more flexibility and control over the targeted modules we added `--lora_layers`- in which you can specify in a comma separated string
-the exact modules for LoRA training. Here are some examples of target modules you can provide: 
-- for attention only layers: `--lora_layers="attn.to_k,attn.to_q,attn.to_v,attn.to_out.0"`
-- to train the same modules as in the fal trainer: `--lora_layers="attn.to_k,attn.to_q,attn.to_v,attn.to_out.0,attn.add_k_proj,attn.add_q_proj,attn.add_v_proj,attn.to_add_out,ff.net.0.proj,ff.net.2,ff_context.net.0.proj,ff_context.net.2"`
-- to train the same modules as in ostris ai-toolkit / replicate trainer: `--lora_blocks="attn.to_k,attn.to_q,attn.to_v,attn.to_out.0,attn.add_k_proj,attn.add_q_proj,attn.add_v_proj,attn.to_add_out,ff.net.0.proj,ff.net.2,ff_context.net.0.proj,ff_context.net.2,norm1_context.linear, norm1.linear,norm.linear,proj_mlp,proj_out"`
-> [!NOTE]
-> `--lora_layers` can also be used to specify which **blocks** to apply LoRA training to. To do so, simply add a block prefix to each layer in the comma separated string:
-> **single DiT blocks**: to target the ith single transformer block, add the prefix `single_transformer_blocks.i`, e.g. - `single_transformer_blocks.i.attn.to_k`
-> **MMDiT blocks**: to target the ith MMDiT block, add the prefix `transformer_blocks.i`, e.g. - `transformer_blocks.i.attn.to_k` 
-> [!NOTE]
-> keep in mind that while training more layers can improve quality and expressiveness, it also increases the size of the output LoRA weights.
-
-
-
-## Training Image-to-Image
-
-Flux.2 lets us perform image editing as well as image generation. We provide a simple script for image-to-image(I2I) LoRA fine-tuning in [train_dreambooth_lora_flux2_img2img.py](./train_dreambooth_lora_flux2_img2img.py) for both T2I and I2I. The optimizations discussed above apply this script, too.
-
-**important**
-
-**Important**
-To make sure you can successfully run the latest version of the image-to-image example script, we highly recommend installing from source, specifically from the commit mentioned below. To do this, execute the following steps in a new virtual environment:
-
-```bash
-git clone https://github.com/huggingface/diffusers
-cd diffusers
-pip install -e .
-
-To start, you must have a dataset containing triplets:
-
-* Condition image - the input image to be transformed.
-* Target image - the desired output image after transformation.
-* Instruction - a text prompt describing the transformation from the condition image to the target image.
-
-[kontext-community/relighting](https://huggingface.co/datasets/kontext-community/relighting) is a good example of such a dataset. If you are using such a dataset, you can use the command below to launch training:
-
-```bash
-accelerate launch train_dreambooth_lora_flux2_img2img.py \
-  --pretrained_model_name_or_path=black-forest-labs/FLUX.2-dev  \
-  --output_dir="flux2-i2i" \
-  --dataset_name="kontext-community/relighting" \
-  --image_column="output" --cond_image_column="file_name" --caption_column="instruction" \
-  --do_fp8_training \
-  --gradient_checkpointing \
-  --remote_text_encoder \
-  --cache_latents \
-  --resolution=1024 \
-  --train_batch_size=1 \
-  --guidance_scale=1 \
-  --gradient_accumulation_steps=4 \
-  --gradient_checkpointing \
-  --optimizer="adamw" \
-  --use_8bit_adam \
-  --cache_latents \
-  --learning_rate=1e-4 \
-  --lr_scheduler="constant_with_warmup" \
-  --lr_warmup_steps=200 \
-  --max_train_steps=1000 \
-  --rank=16\
-  --seed="0" 
-```
-
-More generally, when performing I2I fine-tuning, we expect you to:
-
-* Have a dataset `kontext-community/relighting`
-* Supply `image_column`, `cond_image_column`, and `caption_column` values when launching training
-
-### Misc notes
-
-* By default, we use `mode` as the value of `--vae_encode_mode` argument. This is because Kontext uses `mode()` of the distribution predicted by the VAE instead of sampling from it.
-### Aspect Ratio Bucketing
-we've added aspect ratio bucketing support which allows training on images with different aspect ratios without cropping them to a single square resolution. This technique helps preserve the original composition of training images and can improve training efficiency.
-
-To enable aspect ratio bucketing, pass `--aspect_ratio_buckets` argument with a semicolon-separated list of height,width pairs, such as:
-
-`--aspect_ratio_buckets="672,1568;688,1504;720,1456;752,1392;800,1328;832,1248;880,1184;944,1104;1024,1024;1104,944;1184,880;1248,832;1328,800;1392,752;1456,720;1504,688;1568,672"
-`
-Since Flux.2 finetuning is still an experimental phase, we encourage you to explore different settings and share your insights! 🤗