up

Fixed latents_to_rgb doc.

Co-authored-by: Álvaro Somoza <asomoza@users.noreply.github.com>

.github/workflows/benchmark.yml

@@ -7,6 +7,7 @@ on:
 
 env:
   DIFFUSERS_IS_CI: yes
+  HF_HUB_ENABLE_HF_TRANSFER: 1
   HF_HOME: /mnt/cache
   OMP_NUM_THREADS: 8
   MKL_NUM_THREADS: 8
@@ -50,7 +51,7 @@ jobs:
 
       - name: Test suite reports artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v4
         with:
           name: benchmark_test_reports
           path: benchmarks/benchmark_outputs

.github/workflows/nightly_tests.yml

@@ -43,7 +43,7 @@ jobs:
 
       - name: Pipeline Tests Artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v4
         with:
           name: test-pipelines.json
           path: reports
@@ -72,7 +72,7 @@ jobs:
         run: |
           python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
           python -m uv pip install -e [quality,test]
-          python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
+          pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
           python -m uv pip install pytest-reportlog
       - name: Environment
         run: |
@@ -95,7 +95,7 @@ jobs:
           cat reports/tests_pipeline_${{ matrix.module }}_cuda_failures_short.txt
       - name: Test suite reports artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v4
         with:
           name: pipeline_${{ matrix.module }}_test_reports
           path: reports
@@ -130,8 +130,8 @@ jobs:
       run: |
         python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python -m uv pip install -e [quality,test]
-        python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
         python -m uv pip install peft@git+https://github.com/huggingface/peft.git
+        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
         python -m uv pip install pytest-reportlog
     - name: Environment
       run: python utils/print_env.py
@@ -169,7 +169,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v4
       with:
         name: torch_${{ matrix.module }}_cuda_test_reports
         path: reports
@@ -201,7 +201,7 @@ jobs:
       run: |
         python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python -m uv pip install -e [quality,test]
-        python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
+        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
         python -m uv pip install pytest-reportlog
 
     - name: Environment
@@ -225,7 +225,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v4
       with:
         name: flax_tpu_test_reports
         path: reports
@@ -257,7 +257,7 @@ jobs:
       run: |
         python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python -m uv pip install -e [quality,test]
-        python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
+        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
         python -m uv pip install pytest-reportlog
     - name: Environment
       run: python utils/print_env.py
@@ -280,9 +280,9 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v4
       with:
-        name: ${{ matrix.config.report }}_test_reports
+        name: tests_onnx_cuda_reports
         path: reports
 
     - name: Generate Report and Notify Channel
@@ -340,7 +340,7 @@ jobs:
 #
 #      - name: Test suite reports artifacts
 #        if: ${{ always() }}
-#        uses: actions/upload-artifact@v2
+#        uses: actions/upload-artifact@v4
 #        with:
 #          name: torch_mps_test_reports
 #          path: reports
@@ -396,7 +396,7 @@ jobs:
 #
 #      - name: Test suite reports artifacts
 #        if: ${{ always() }}
-#        uses: actions/upload-artifact@v2
+#        uses: actions/upload-artifact@v4
 #        with:
 #          name: torch_mps_test_reports
 #          path: reports

.github/workflows/pr_test_fetcher.yml

@@ -171,7 +171,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v4
       with:
         name: pr_${{ matrix.config.report }}_test_reports
         path: reports

.github/workflows/pr_test_peft_backend.yml

@@ -95,7 +95,7 @@ jobs:
         if [ "${{ matrix.lib-versions }}" == "main" ]; then
             python -m pip install -U peft@git+https://github.com/huggingface/peft.git
             python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git
-            python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+            pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
         else
             python -m uv pip install -U peft transformers accelerate
         fi
@@ -110,23 +110,23 @@ jobs:
         python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python -m pytest -n 4 --max-worker-restart=0 --dist=loadfile \
           -s -v \
-          --make-reports=tests_${{ matrix.config.report }} \
+          --make-reports=tests_${{ matrix.lib-versions }} \
           tests/lora/
         python -m pytest -n 4 --max-worker-restart=0 --dist=loadfile \
           -s -v \
-          --make-reports=tests_models_lora_${{ matrix.config.report }} \
+          --make-reports=tests_models_lora_${{ matrix.lib-versions }} \
           tests/models/ -k "lora"
 
 
     - name: Failure short reports
       if: ${{ failure() }}
       run: |
-        cat reports/tests_${{ matrix.config.report }}_failures_short.txt
-        cat reports/tests_models_lora_${{ matrix.config.report }}_failures_short.txt
+        cat reports/tests_${{ matrix.lib-versions }}_failures_short.txt
+        cat reports/tests_models_lora_${{ matrix.lib-versions }}_failures_short.txt
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v4
       with:
-        name: pr_${{ matrix.config.report }}_test_reports
+        name: pr_${{ matrix.lib-versions }}_test_reports
         path: reports

.github/workflows/pr_tests.yml

@@ -22,6 +22,7 @@ concurrency:
 
 env:
   DIFFUSERS_IS_CI: yes
+  HF_HUB_ENABLE_HF_TRANSFER: 1
   OMP_NUM_THREADS: 4
   MKL_NUM_THREADS: 4
   PYTEST_TIMEOUT: 60
@@ -168,9 +169,9 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v4
       with:
-        name: pr_${{ matrix.config.report }}_test_reports
+        name: pr_${{ matrix.config.framework }}_${{ matrix.config.report }}_test_reports
         path: reports
 
   run_staging_tests:
@@ -229,7 +230,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v4
       with:
         name: pr_${{ matrix.config.report }}_test_reports
         path: reports

.github/workflows/push_tests.yml

@@ -1,6 +1,7 @@
 name: Fast GPU Tests on main
 
 on:
+  workflow_dispatch:
   push:
     branches:
       - main
@@ -13,6 +14,7 @@ env:
   DIFFUSERS_IS_CI: yes
   OMP_NUM_THREADS: 8
   MKL_NUM_THREADS: 8
+  HF_HUB_ENABLE_HF_TRANSFER: 1
   PYTEST_TIMEOUT: 600
   PIPELINE_USAGE_CUTOFF: 50000
 
@@ -45,7 +47,7 @@ jobs:
           echo "pipeline_test_matrix=$matrix" >> $GITHUB_OUTPUT
       - name: Pipeline Tests Artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v4
         with:
           name: test-pipelines.json
           path: reports
@@ -75,7 +77,7 @@ jobs:
         run: |
           python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
           python -m uv pip install -e [quality,test]
-          python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
+          pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
       - name: Environment
         run: |
           python utils/print_env.py
@@ -96,7 +98,7 @@ jobs:
           cat reports/tests_pipeline_${{ matrix.module }}_cuda_failures_short.txt
       - name: Test suite reports artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v4
         with:
           name: pipeline_${{ matrix.module }}_test_reports
           path: reports
@@ -126,8 +128,8 @@ jobs:
       run: |
         python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python -m uv pip install -e [quality,test]
-        python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
         python -m uv pip install peft@git+https://github.com/huggingface/peft.git
+        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
 
     - name: Environment
       run: |
@@ -141,20 +143,20 @@ jobs:
       run: |
         python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
           -s -v -k "not Flax and not Onnx" \
-          --make-reports=tests_torch_cuda \
+          --make-reports=tests_torch_cuda_${{ matrix.module }} \
           tests/${{ matrix.module }}
 
     - name: Failure short reports
       if: ${{ failure() }}
       run: |
-        cat reports/tests_torch_cuda_stats.txt
-        cat reports/tests_torch_cuda_failures_short.txt
+        cat reports/tests_torch_cuda_${{ matrix.module }}_stats.txt
+        cat reports/tests_torch_cuda_${{ matrix.module }}_failures_short.txt
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v4
       with:
-        name: torch_cuda_test_reports
+        name: torch_cuda_test_reports_${{ matrix.module }}
         path: reports
 
   flax_tpu_tests:
@@ -176,7 +178,7 @@ jobs:
       run: |
         python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python -m uv pip install -e [quality,test]
-        python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
+        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
 
     - name: Environment
       run: |
@@ -199,7 +201,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v4
       with:
         name: flax_tpu_test_reports
         path: reports
@@ -224,7 +226,7 @@ jobs:
       run: |
         python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python -m uv pip install -e [quality,test]
-        python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
+        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
 
     - name: Environment
       run: |
@@ -247,7 +249,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v4
       with:
         name: onnx_cuda_test_reports
         path: reports
@@ -290,7 +292,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v4
       with:
         name: torch_compile_test_reports
         path: reports
@@ -332,7 +334,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v4
       with:
         name: torch_xformers_test_reports
         path: reports
@@ -383,7 +385,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v4
       with:
         name: examples_test_reports
         path: reports

.github/workflows/push_tests_fast.yml

@@ -18,6 +18,7 @@ env:
   HF_HOME: /mnt/cache
   OMP_NUM_THREADS: 8
   MKL_NUM_THREADS: 8
+  HF_HUB_ENABLE_HF_TRANSFER: 1
   PYTEST_TIMEOUT: 600
   RUN_SLOW: no
 
@@ -119,7 +120,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v4
       with:
         name: pr_${{ matrix.config.report }}_test_reports
         path: reports

.github/workflows/push_tests_mps.yml

@@ -13,6 +13,7 @@ env:
   HF_HOME: /mnt/cache
   OMP_NUM_THREADS: 8
   MKL_NUM_THREADS: 8
+  HF_HUB_ENABLE_HF_TRANSFER: 1
   PYTEST_TIMEOUT: 600
   RUN_SLOW: no
 
@@ -69,7 +70,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v4
       with:
         name: pr_torch_mps_test_reports
         path: reports

.github/workflows/release_tests_fast.yml

@@ -45,7 +45,7 @@ jobs:
           echo "pipeline_test_matrix=$matrix" >> $GITHUB_OUTPUT
       - name: Pipeline Tests Artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v4
         with:
           name: test-pipelines.json
           path: reports
@@ -75,7 +75,7 @@ jobs:
         run: |
           python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
           python -m uv pip install -e [quality,test]
-          python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
+          pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
       - name: Environment
         run: |
           python utils/print_env.py
@@ -96,7 +96,7 @@ jobs:
           cat reports/tests_pipeline_${{ matrix.module }}_cuda_failures_short.txt
       - name: Test suite reports artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v4
         with:
           name: pipeline_${{ matrix.module }}_test_reports
           path: reports
@@ -126,8 +126,8 @@ jobs:
       run: |
         python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python -m uv pip install -e [quality,test]
-        python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
         python -m uv pip install peft@git+https://github.com/huggingface/peft.git
+        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
 
     - name: Environment
       run: |
@@ -141,20 +141,20 @@ jobs:
       run: |
         python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
           -s -v -k "not Flax and not Onnx" \
-          --make-reports=tests_torch_cuda \
+          --make-reports=tests_torch_${{ matrix.module }}_cuda \
           tests/${{ matrix.module }}
 
     - name: Failure short reports
       if: ${{ failure() }}
       run: |
-        cat reports/tests_torch_cuda_stats.txt
-        cat reports/tests_torch_cuda_failures_short.txt
+        cat reports/tests_torch_${{ matrix.module }}_cuda_stats.txt
+        cat reports/tests_torch_${{ matrix.module }}_cuda_failures_short.txt
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v4
       with:
-        name: torch_cuda_test_reports
+        name: torch_cuda_${{ matrix.module }}_test_reports
         path: reports
 
   flax_tpu_tests:
@@ -176,7 +176,7 @@ jobs:
       run: |
         python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python -m uv pip install -e [quality,test]
-        python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
+        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
 
     - name: Environment
       run: |
@@ -199,7 +199,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v4
       with:
         name: flax_tpu_test_reports
         path: reports
@@ -224,7 +224,7 @@ jobs:
       run: |
         python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python -m uv pip install -e [quality,test]
-        python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
+        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
 
     - name: Environment
       run: |
@@ -247,7 +247,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v4
       with:
         name: onnx_cuda_test_reports
         path: reports
@@ -290,7 +290,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v4
       with:
         name: torch_compile_test_reports
         path: reports
@@ -332,7 +332,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v4
       with:
         name: torch_xformers_test_reports
         path: reports
@@ -383,7 +383,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v4
       with:
         name: examples_test_reports
         path: reports

.github/workflows/ssh-runner.yml

@@ -4,8 +4,12 @@ on:
   workflow_dispatch:
     inputs:
       runner_type:
-        description: 'Type of runner to test (a10 or t4)'
+        description: 'Type of runner to test (aws-g6-4xlarge-plus: a10 or aws-g4dn-2xlarge: t4)'
+        type: choice
         required: true
+        options:
+          - aws-g6-4xlarge-plus
+          - aws-g4dn-2xlarge
       docker_image:
         description: 'Name of the Docker image'
         required: true

.github/workflows/stale.yml

@@ -9,6 +9,9 @@ jobs:
     name: Close Stale Issues
     if: github.repository == 'huggingface/diffusers'
     runs-on: ubuntu-latest
+    permissions:
+      issues: write
+      pull-requests: write
     env:
       GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
     steps:

PHILOSOPHY.md

@@ -65,7 +65,7 @@ Pipelines are designed to be easy to use (therefore do not follow [*Simple over
 The following design principles are followed:
 - Pipelines follow the single-file policy. All pipelines can be found in individual directories under src/diffusers/pipelines. One pipeline folder corresponds to one diffusion paper/project/release. Multiple pipeline files can be gathered in one pipeline folder, as it’s done for [`src/diffusers/pipelines/stable-diffusion`](https://github.com/huggingface/diffusers/tree/main/src/diffusers/pipelines/stable_diffusion). If pipelines share similar functionality, one can make use of the [# Copied from mechanism](https://github.com/huggingface/diffusers/blob/125d783076e5bd9785beb05367a2d2566843a271/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py#L251).
 - Pipelines all inherit from [`DiffusionPipeline`].
-- Every pipeline consists of different model and scheduler components, that are documented in the [`model_index.json` file](https://huggingface.co/runwayml/stable-diffusion-v1-5/blob/main/model_index.json), are accessible under the same name as attributes of the pipeline and can be shared between pipelines with [`DiffusionPipeline.components`](https://huggingface.co/docs/diffusers/main/en/api/diffusion_pipeline#diffusers.DiffusionPipeline.components) function.
+- Every pipeline consists of different model and scheduler components, that are documented in the [`model_index.json` file](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5/blob/main/model_index.json), are accessible under the same name as attributes of the pipeline and can be shared between pipelines with [`DiffusionPipeline.components`](https://huggingface.co/docs/diffusers/main/en/api/diffusion_pipeline#diffusers.DiffusionPipeline.components) function.
 - Every pipeline should be loadable via the [`DiffusionPipeline.from_pretrained`](https://huggingface.co/docs/diffusers/main/en/api/diffusion_pipeline#diffusers.DiffusionPipeline.from_pretrained) function.
 - Pipelines should be used **only** for inference.
 - Pipelines should be very readable, self-explanatory, and easy to tweak.

README.md

@@ -73,7 +73,7 @@ Generating outputs is super easy with 🤗 Diffusers. To generate an image from
 from diffusers import DiffusionPipeline
 import torch
 
-pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
+pipeline = DiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16)
 pipeline.to("cuda")
 pipeline("An image of a squirrel in Picasso style").images[0]
 ```
@@ -144,7 +144,7 @@ Also, say 👋 in our public Discord channel <a href="https://discord.gg/G7tWnz9
   <tr style="border-top: 2px solid black">
     <td>Text-to-Image</td>
     <td><a href="https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/text2img">Stable Diffusion Text-to-Image</a></td>
-      <td><a href="https://huggingface.co/runwayml/stable-diffusion-v1-5"> runwayml/stable-diffusion-v1-5 </a></td>
+      <td><a href="https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5"> stable-diffusion-v1-5/stable-diffusion-v1-5 </a></td>
   </tr>
   <tr>
     <td>Text-to-Image</td>
@@ -174,7 +174,7 @@ Also, say 👋 in our public Discord channel <a href="https://discord.gg/G7tWnz9
   <tr>
     <td>Text-guided Image-to-Image</td>
     <td><a href="https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/img2img">Stable Diffusion Image-to-Image</a></td>
-      <td><a href="https://huggingface.co/runwayml/stable-diffusion-v1-5"> runwayml/stable-diffusion-v1-5 </a></td>
+      <td><a href="https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5"> stable-diffusion-v1-5/stable-diffusion-v1-5 </a></td>
   </tr>
   <tr style="border-top: 2px solid black">
     <td>Text-guided Image Inpainting</td>

benchmarks/base_classes.py

@@ -34,7 +34,7 @@ from utils import (  # noqa: E402
 
 
 RESOLUTION_MAPPING = {
-    "runwayml/stable-diffusion-v1-5": (512, 512),
+    "Lykon/DreamShaper": (512, 512),
     "lllyasviel/sd-controlnet-canny": (512, 512),
     "diffusers/controlnet-canny-sdxl-1.0": (1024, 1024),
     "TencentARC/t2iadapter_canny_sd14v1": (512, 512),
@@ -268,7 +268,7 @@ class IPAdapterTextToImageBenchmark(TextToImageBenchmark):
 class ControlNetBenchmark(TextToImageBenchmark):
     pipeline_class = StableDiffusionControlNetPipeline
     aux_network_class = ControlNetModel
-    root_ckpt = "runwayml/stable-diffusion-v1-5"
+    root_ckpt = "Lykon/DreamShaper"
 
     url = "https://huggingface.co/datasets/diffusers/docs-images/resolve/main/benchmarking/canny_image_condition.png"
     image = load_image(url).convert("RGB")
@@ -311,7 +311,7 @@ class ControlNetSDXLBenchmark(ControlNetBenchmark):
 class T2IAdapterBenchmark(ControlNetBenchmark):
     pipeline_class = StableDiffusionAdapterPipeline
     aux_network_class = T2IAdapter
-    root_ckpt = "CompVis/stable-diffusion-v1-4"
+    root_ckpt = "Lykon/DreamShaper"
 
     url = "https://huggingface.co/datasets/diffusers/docs-images/resolve/main/benchmarking/canny_for_adapter.png"
     image = load_image(url).convert("L")

benchmarks/benchmark_ip_adapters.py

@@ -7,7 +7,8 @@ from base_classes import IPAdapterTextToImageBenchmark  # noqa: E402
 
 
 IP_ADAPTER_CKPTS = {
-    "runwayml/stable-diffusion-v1-5": ("h94/IP-Adapter", "ip-adapter_sd15.bin"),
+    # because original SD v1.5 has been taken down.
+    "Lykon/DreamShaper": ("h94/IP-Adapter", "ip-adapter_sd15.bin"),
     "stabilityai/stable-diffusion-xl-base-1.0": ("h94/IP-Adapter", "ip-adapter_sdxl.bin"),
 }
 
@@ -17,7 +18,7 @@ if __name__ == "__main__":
     parser.add_argument(
         "--ckpt",
         type=str,
-        default="runwayml/stable-diffusion-v1-5",
+        default="rstabilityai/stable-diffusion-xl-base-1.0",
         choices=list(IP_ADAPTER_CKPTS.keys()),
     )
     parser.add_argument("--batch_size", type=int, default=1)

benchmarks/benchmark_sd_img.py

@@ -11,9 +11,9 @@ if __name__ == "__main__":
     parser.add_argument(
         "--ckpt",
         type=str,
-        default="runwayml/stable-diffusion-v1-5",
+        default="Lykon/DreamShaper",
         choices=[
-            "runwayml/stable-diffusion-v1-5",
+            "Lykon/DreamShaper",
             "stabilityai/stable-diffusion-2-1",
             "stabilityai/stable-diffusion-xl-refiner-1.0",
             "stabilityai/sdxl-turbo",

benchmarks/benchmark_sd_inpainting.py

@@ -11,9 +11,9 @@ if __name__ == "__main__":
     parser.add_argument(
         "--ckpt",
         type=str,
-        default="runwayml/stable-diffusion-v1-5",
+        default="Lykon/DreamShaper",
         choices=[
-            "runwayml/stable-diffusion-v1-5",
+            "Lykon/DreamShaper",
             "stabilityai/stable-diffusion-2-1",
             "stabilityai/stable-diffusion-xl-base-1.0",
         ],

benchmarks/benchmark_text_to_image.py

@@ -7,7 +7,7 @@ from base_classes import TextToImageBenchmark, TurboTextToImageBenchmark  # noqa
 
 
 ALL_T2I_CKPTS = [
-    "runwayml/stable-diffusion-v1-5",
+    "Lykon/DreamShaper",
     "segmind/SSD-1B",
     "stabilityai/stable-diffusion-xl-base-1.0",
     "kandinsky-community/kandinsky-2-2-decoder",
@@ -21,7 +21,7 @@ if __name__ == "__main__":
     parser.add_argument(
         "--ckpt",
         type=str,
-        default="runwayml/stable-diffusion-v1-5",
+        default="Lykon/DreamShaper",
         choices=ALL_T2I_CKPTS,
     )
     parser.add_argument("--batch_size", type=int, default=1)

docker/diffusers-flax-cpu/Dockerfile

@@ -43,6 +43,7 @@ RUN python3 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
         numpy==1.26.4 \
         scipy \
         tensorboard \
-        transformers
+        transformers \
+        hf_transfer
 
 CMD ["/bin/bash"]

docker/diffusers-flax-tpu/Dockerfile

@@ -45,6 +45,7 @@ RUN python3 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
         numpy==1.26.4 \
         scipy \
         tensorboard \
-        transformers
+        transformers \
+        hf_transfer
 
 CMD ["/bin/bash"]

docker/diffusers-onnxruntime-cpu/Dockerfile

@@ -43,6 +43,7 @@ RUN python3 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
         numpy==1.26.4 \
         scipy \
         tensorboard \
-        transformers
+        transformers \
+        hf_transfer
 
 CMD ["/bin/bash"]

docker/diffusers-onnxruntime-cuda/Dockerfile

@@ -44,6 +44,7 @@ RUN python3.10 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
         numpy==1.26.4 \
         scipy \
         tensorboard \
-        transformers
+        transformers \
+        hf_transfer
 
 CMD ["/bin/bash"]

docker/diffusers-pytorch-compile-cuda/Dockerfile

@@ -44,6 +44,7 @@ RUN python3.10 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
     numpy==1.26.4 \
     scipy \
     tensorboard \
-    transformers
+    transformers \
+    hf_transfer
 
 CMD ["/bin/bash"]

docker/diffusers-pytorch-cpu/Dockerfile

@@ -44,6 +44,7 @@ RUN python3.10 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
         numpy==1.26.4 \
         scipy \
         tensorboard \
-        transformers matplotlib
+        transformers matplotlib  \
+        hf_transfer
 
 CMD ["/bin/bash"]

docker/diffusers-pytorch-cuda/Dockerfile

@@ -45,6 +45,7 @@ RUN python3.10 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
     scipy \
     tensorboard \
     transformers \
-    pytorch-lightning
+    pytorch-lightning  \
+    hf_transfer
 
 CMD ["/bin/bash"]

docker/diffusers-pytorch-xformers-cuda/Dockerfile

@@ -45,6 +45,7 @@ RUN python3.10 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
         scipy \
         tensorboard \
         transformers \
-        xformers
+        xformers  \
+        hf_transfer
 
 CMD ["/bin/bash"]

docs/source/en/_toctree.yml

@@ -56,7 +56,7 @@
   - local: using-diffusers/overview_techniques
     title: Overview
   - local: training/distributed_inference
-    title: Distributed inference with multiple GPUs
+    title: Distributed inference
   - local: using-diffusers/merge_loras
     title: Merge LoRAs
   - local: using-diffusers/scheduler_features
@@ -161,6 +161,8 @@
     title: DeepCache
   - local: optimization/tgate
     title: TGATE
+  - local: optimization/xdit
+    title: xDiT
   - sections:
     - local: using-diffusers/stable_diffusion_jax_how_to
       title: JAX/Flax

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

@@ -22,7 +22,6 @@ The [`~loaders.FromSingleFileMixin.from_single_file`] method allows you to load:
 
 ## Supported pipelines
 
-- [`CogVideoXPipeline`]
 - [`StableDiffusionPipeline`]
 - [`StableDiffusionImg2ImgPipeline`]
 - [`StableDiffusionInpaintPipeline`]
@@ -50,7 +49,6 @@ The [`~loaders.FromSingleFileMixin.from_single_file`] method allows you to load:
 - [`UNet2DConditionModel`]
 - [`StableCascadeUNet`]
 - [`AutoencoderKL`]
-- [`AutoencoderKLCogVideoX`]
 - [`ControlNetModel`]
 - [`SD3Transformer2DModel`]
 - [`FluxTransformer2DModel`]

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

@@ -29,7 +29,7 @@ from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
 url = "https://huggingface.co/lllyasviel/ControlNet-v1-1/blob/main/control_v11p_sd15_canny.pth"  # can also be a local path
 controlnet = ControlNetModel.from_single_file(url)
 
-url = "https://huggingface.co/runwayml/stable-diffusion-v1-5/blob/main/v1-5-pruned.safetensors"  # can also be a local path
+url = "https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5/blob/main/v1-5-pruned.safetensors"  # can also be a local path
 pipe = StableDiffusionControlNetPipeline.from_single_file(url, controlnet=controlnet)
 ```
 

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

@@ -29,6 +29,7 @@ The abstract of the paper is the following:
 | [AnimateDiffSparseControlNetPipeline](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/animatediff/pipeline_animatediff_sparsectrl.py) | *Controlled Video-to-Video Generation with AnimateDiff using SparseCtrl* |
 | [AnimateDiffSDXLPipeline](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/animatediff/pipeline_animatediff_sdxl.py) | *Video-to-Video Generation with AnimateDiff* |
 | [AnimateDiffVideoToVideoPipeline](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/animatediff/pipeline_animatediff_video2video.py) | *Video-to-Video Generation with AnimateDiff* |
+| [AnimateDiffVideoToVideoControlNetPipeline](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/animatediff/pipeline_animatediff_video2video_controlnet.py) | *Video-to-Video Generation with AnimateDiff using ControlNet* |
 
 ## Available checkpoints
 
@@ -518,6 +519,97 @@ Here are some sample outputs:
     </tr>
 </table>
 
+
+
+### AnimateDiffVideoToVideoControlNetPipeline
+
+AnimateDiff can be used together with ControlNets to enhance video-to-video generation by allowing for precise control over the output. ControlNet was introduced in [Adding Conditional Control to Text-to-Image Diffusion Models](https://huggingface.co/papers/2302.05543) by Lvmin Zhang, Anyi Rao, and Maneesh Agrawala, and allows you to condition Stable Diffusion with an additional control image to ensure that the spatial information is preserved throughout the video. 
+
+This pipeline allows you to condition your generation both on the original video and on a sequence of control images.
+
+```python
+import torch
+from PIL import Image
+from tqdm.auto import tqdm
+
+from controlnet_aux.processor import OpenposeDetector
+from diffusers import AnimateDiffVideoToVideoControlNetPipeline
+from diffusers.utils import export_to_gif, load_video
+from diffusers import AutoencoderKL, ControlNetModel, MotionAdapter, LCMScheduler
+
+# Load the ControlNet
+controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-openpose", torch_dtype=torch.float16)
+# Load the motion adapter
+motion_adapter = MotionAdapter.from_pretrained("wangfuyun/AnimateLCM")
+# Load SD 1.5 based finetuned model
+vae = AutoencoderKL.from_pretrained("stabilityai/sd-vae-ft-mse", torch_dtype=torch.float16)
+pipe = AnimateDiffVideoToVideoControlNetPipeline.from_pretrained(
+    "SG161222/Realistic_Vision_V5.1_noVAE",
+    motion_adapter=motion_adapter,
+    controlnet=controlnet,
+    vae=vae,
+).to(device="cuda", dtype=torch.float16)
+
+# Enable LCM to speed up inference
+pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config, beta_schedule="linear")
+pipe.load_lora_weights("wangfuyun/AnimateLCM", weight_name="AnimateLCM_sd15_t2v_lora.safetensors", adapter_name="lcm-lora")
+pipe.set_adapters(["lcm-lora"], [0.8])
+
+video = load_video("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/dance.gif")
+video = [frame.convert("RGB") for frame in video]
+
+prompt = "astronaut in space, dancing"
+negative_prompt = "bad quality, worst quality, jpeg artifacts, ugly"
+
+# Create controlnet preprocessor
+open_pose = OpenposeDetector.from_pretrained("lllyasviel/Annotators").to("cuda")
+
+# Preprocess controlnet images
+conditioning_frames = []
+for frame in tqdm(video):
+    conditioning_frames.append(open_pose(frame))
+
+strength = 0.8
+with torch.inference_mode():
+    video = pipe(
+        video=video,
+        prompt=prompt,
+        negative_prompt=negative_prompt,
+        num_inference_steps=10,
+        guidance_scale=2.0,
+        controlnet_conditioning_scale=0.75,
+        conditioning_frames=conditioning_frames,
+        strength=strength,
+        generator=torch.Generator().manual_seed(42),
+    ).frames[0]
+
+video = [frame.resize(conditioning_frames[0].size) for frame in video]
+export_to_gif(video, f"animatediff_vid2vid_controlnet.gif", fps=8)
+```
+
+Here are some sample outputs:
+
+<table align="center">
+    <tr>
+      <th align="center">Source Video</th>
+      <th align="center">Output Video</th>
+    </tr>
+    <tr>
+        <td align="center">
+          anime girl, dancing
+          <br />
+          <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/dance.gif" alt="anime girl, dancing" />
+        </td>
+        <td align="center">
+          astronaut in space, dancing
+          <br/>
+          <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/animatediff_vid2vid_controlnet.gif" alt="astronaut in space, dancing" />
+        </td>
+    </tr>
+</table>
+
+**The lights and composition were transferred from the Source Video.**
+
 ## Using Motion LoRAs
 
 Motion LoRAs are a collection of LoRAs that work with the `guoyww/animatediff-motion-adapter-v1-5-2` checkpoint. These LoRAs are responsible for adding specific types of motion to the animations.
@@ -822,6 +914,89 @@ export_to_gif(frames, "animatelcm-motion-lora.gif")
     </tr>
 </table>
 
+## Using FreeNoise
+
+[FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling](https://arxiv.org/abs/2310.15169) by Haonan Qiu, Menghan Xia, Yong Zhang, Yingqing He, Xintao Wang, Ying Shan, Ziwei Liu.
+
+FreeNoise is a sampling mechanism that can generate longer videos with short-video generation models by employing noise-rescheduling, temporal attention over sliding windows, and weighted averaging of latent frames. It also can be used with multiple prompts to allow for interpolated video generations. More details are available in the paper.
+
+The currently supported AnimateDiff pipelines that can be used with FreeNoise are:
+- [`AnimateDiffPipeline`]
+- [`AnimateDiffControlNetPipeline`]
+- [`AnimateDiffVideoToVideoPipeline`]
+- [`AnimateDiffVideoToVideoControlNetPipeline`]
+
+In order to use FreeNoise, a single line needs to be added to the inference code after loading your pipelines.
+
+```diff
++ pipe.enable_free_noise()
+```
+
+After this, either a single prompt could be used, or multiple prompts can be passed as a dictionary of integer-string pairs. The integer keys of the dictionary correspond to the frame index at which the influence of that prompt would be maximum. Each frame index should map to a single string prompt. The prompts for intermediate frame indices, that are not passed in the dictionary, are created by interpolating between the frame prompts that are passed. By default, simple linear interpolation is used. However, you can customize this behaviour with a callback to the `prompt_interpolation_callback` parameter when enabling FreeNoise.
+
+Full example:
+
+```python
+import torch
+from diffusers import AutoencoderKL, AnimateDiffPipeline, LCMScheduler, MotionAdapter
+from diffusers.utils import export_to_video, load_image
+
+# Load pipeline
+dtype = torch.float16
+motion_adapter = MotionAdapter.from_pretrained("wangfuyun/AnimateLCM", torch_dtype=dtype)
+vae = AutoencoderKL.from_pretrained("stabilityai/sd-vae-ft-mse", torch_dtype=dtype)
+
+pipe = AnimateDiffPipeline.from_pretrained("emilianJR/epiCRealism", motion_adapter=motion_adapter, vae=vae, torch_dtype=dtype)
+pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config, beta_schedule="linear")
+
+pipe.load_lora_weights(
+    "wangfuyun/AnimateLCM", weight_name="AnimateLCM_sd15_t2v_lora.safetensors", adapter_name="lcm_lora"
+)
+pipe.set_adapters(["lcm_lora"], [0.8])
+
+# Enable FreeNoise for long prompt generation
+pipe.enable_free_noise(context_length=16, context_stride=4)
+pipe.to("cuda")
+
+# Can be a single prompt, or a dictionary with frame timesteps
+prompt = {
+    0: "A caterpillar on a leaf, high quality, photorealistic",
+    40: "A caterpillar transforming into a cocoon, on a leaf, near flowers, photorealistic",
+    80: "A cocoon on a leaf, flowers in the backgrond, photorealistic",
+    120: "A cocoon maturing and a butterfly being born, flowers and leaves visible in the background, photorealistic",
+    160: "A beautiful butterfly, vibrant colors, sitting on a leaf, flowers in the background, photorealistic",
+    200: "A beautiful butterfly, flying away in a forest, photorealistic",
+    240: "A cyberpunk butterfly, neon lights, glowing",
+}
+negative_prompt = "bad quality, worst quality, jpeg artifacts"
+
+# Run inference
+output = pipe(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    num_frames=256,
+    guidance_scale=2.5,
+    num_inference_steps=10,
+    generator=torch.Generator("cpu").manual_seed(0),
+)
+
+# Save video
+frames = output.frames[0]
+export_to_video(frames, "output.mp4", fps=16)
+```
+
+### FreeNoise memory savings
+
+Since FreeNoise processes multiple frames together, there are parts in the modeling where the memory required exceeds that available on normal consumer GPUs. The main memory bottlenecks that we identified are spatial and temporal attention blocks, upsampling and downsampling blocks, resnet blocks and feed-forward layers. Since most of these blocks operate effectively only on the channel/embedding dimension, one can perform chunked inference across the batch dimensions. The batch dimension in AnimateDiff are either spatial (`[B x F, H x W, C]`) or temporal (`B x H x W, F, C`) in nature (note that it may seem counter-intuitive, but the batch dimension here are correct, because spatial blocks process across the `B x F` dimension while the temporal blocks process across the `B x H x W` dimension). We introduce a `SplitInferenceModule` that makes it easier to chunk across any dimension and perform inference. This saves a lot of memory but comes at the cost of requiring more time for inference.
+
+```diff
+# Load pipeline and adapters
+# ...
++ pipe.enable_free_noise_split_inference()
++ pipe.unet.enable_forward_chunking(16)
+```
+
+The call to `pipe.enable_free_noise_split_inference` method accepts two parameters: `spatial_split_size` (defaults to `256`) and `temporal_split_size` (defaults to `16`). These can be configured based on how much VRAM you have available. A lower split size results in lower memory usage but slower inference, whereas a larger split size results in faster inference at the cost of more memory.
 
 ## Using `from_single_file` with the MotionAdapter
 
@@ -866,6 +1041,12 @@ pipe = AnimateDiffPipeline.from_pretrained("emilianJR/epiCRealism", motion_adapt
   - all
   - __call__
 
+## AnimateDiffVideoToVideoControlNetPipeline
+
+[[autodoc]] AnimateDiffVideoToVideoControlNetPipeline
+  - all
+  - __call__
+
 ## AnimateDiffPipelineOutput
 
 [[autodoc]] pipelines.animatediff.AnimateDiffPipelineOutput

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

@@ -29,9 +29,12 @@ Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers.m
 
 This pipeline was contributed by [zRzRzRzRzRzRzR](https://github.com/zRzRzRzRzRzRzR). The original codebase can be found [here](https://huggingface.co/THUDM). The original weights can be found under [hf.co/THUDM](https://huggingface.co/THUDM).
 
-There are two models available that can be used with the CogVideoX pipeline:
-- [`THUDM/CogVideoX-2b`](https://huggingface.co/THUDM/CogVideoX-2b)
-- [`THUDM/CogVideoX-5b`](https://huggingface.co/THUDM/CogVideoX-5b)
+There are two models available that can be used with the text-to-video and video-to-video CogVideoX pipelines:
+- [`THUDM/CogVideoX-2b`](https://huggingface.co/THUDM/CogVideoX-2b): The recommended dtype for running this model is `fp16`.
+- [`THUDM/CogVideoX-5b`](https://huggingface.co/THUDM/CogVideoX-5b): The recommended dtype for running this model is `bf16`.
+
+There is one model available that can be used with the image-to-video CogVideoX pipeline:
+- [`THUDM/CogVideoX-5b-I2V`](https://huggingface.co/THUDM/CogVideoX-5b-I2V): The recommended dtype for running this model is `bf16`.
 
 ## Inference
 
@@ -41,10 +44,15 @@ First, load the pipeline:
 
 ```python
 import torch
-from diffusers import CogVideoXPipeline
-from diffusers.utils import export_to_video
+from diffusers import CogVideoXPipeline, CogVideoXImageToVideoPipeline
+from diffusers.utils import export_to_video,load_image
+pipe = CogVideoXPipeline.from_pretrained("THUDM/CogVideoX-5b").to("cuda") # or "THUDM/CogVideoX-2b" 
+```
 
-pipe = CogVideoXPipeline.from_pretrained("THUDM/CogVideoX-2b").to("cuda")
+If you are using the image-to-video pipeline, load it as follows:
+
+```python
+pipe = CogVideoXImageToVideoPipeline.from_pretrained("THUDM/CogVideoX-5b-I2V").to("cuda")
 ```
 
 Then change the memory layout of the pipelines `transformer` component to `torch.channels_last`:
@@ -53,7 +61,7 @@ Then change the memory layout of the pipelines `transformer` component to `torch
 pipe.transformer.to(memory_format=torch.channels_last)
 ```
 
-Finally, compile the components and run inference:
+Compile the components and run inference:
 
 ```python
 pipe.transformer = torch.compile(pipeline.transformer, mode="max-autotune", fullgraph=True)
@@ -63,7 +71,7 @@ prompt = "A panda, dressed in a small, red jacket and a tiny hat, sits on a wood
 video = pipe(prompt=prompt, guidance_scale=6, num_inference_steps=50).frames[0]
 ```
 
-The [benchmark](https://gist.github.com/a-r-r-o-w/5183d75e452a368fd17448fcc810bd3f) results on an 80GB A100 machine are:
+The [T2V benchmark](https://gist.github.com/a-r-r-o-w/5183d75e452a368fd17448fcc810bd3f) results on an 80GB A100 machine are:
 
 ```
 Without torch.compile(): Average inference time: 96.89 seconds.
@@ -98,6 +106,12 @@ It is also worth noting that torchao quantization is fully compatible with [torc
   - all
   - __call__
 
+## CogVideoXImageToVideoPipeline
+
+[[autodoc]] CogVideoXImageToVideoPipeline
+  - all
+  - __call__
+
 ## CogVideoXVideoToVideoPipeline
 
 [[autodoc]] CogVideoXVideoToVideoPipeline

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

@@ -163,3 +163,28 @@ image.save("flux-fp8-dev.png")
 [[autodoc]] FluxPipeline
 	- all
 	- __call__
+
+## FluxImg2ImgPipeline
+
+[[autodoc]] FluxImg2ImgPipeline
+	- all
+	- __call__
+
+## FluxInpaintPipeline
+
+[[autodoc]] FluxInpaintPipeline
+	- all
+	- __call__
+
+
+## FluxControlNetInpaintPipeline
+
+[[autodoc]] FluxControlNetInpaintPipeline
+	- all
+	- __call__
+
+## FluxControlNetImg2ImgPipeline
+
+[[autodoc]] FluxControlNetImg2ImgPipeline
+	- all
+	- __call__

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

@@ -105,3 +105,11 @@ image.save("kolors_ipa_sample.png")
 
 - all
 - __call__
+
+## KolorsImg2ImgPipeline
+
+[[autodoc]] KolorsImg2ImgPipeline
+
+- all
+- __call__
+

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

@@ -19,7 +19,7 @@ The Stable Diffusion model can also be applied to inpainting which lets you edit
 It is recommended to use this pipeline with checkpoints that have been specifically fine-tuned for inpainting, such
 as [runwayml/stable-diffusion-inpainting](https://huggingface.co/runwayml/stable-diffusion-inpainting). Default
 text-to-image Stable Diffusion checkpoints, such as
-[runwayml/stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5) are also compatible but they might be less performant.
+[stable-diffusion-v1-5/stable-diffusion-v1-5](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) are also compatible but they might be less performant.
 
 <Tip>
 

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

@@ -203,7 +203,7 @@ from diffusers import StableDiffusionImg2ImgPipeline
 import gradio as gr
 
 
-pipe = StableDiffusionImg2ImgPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")
+pipe = StableDiffusionImg2ImgPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5")
 
 gr.Interface.from_pipeline(pipe).launch()
 ```

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

@@ -40,8 +40,9 @@ To generate a video from prompt, run the following Python code:
 ```python
 import torch
 from diffusers import TextToVideoZeroPipeline
+import imageio
 
-model_id = "runwayml/stable-diffusion-v1-5"
+model_id = "stable-diffusion-v1-5/stable-diffusion-v1-5"
 pipe = TextToVideoZeroPipeline.from_pretrained(model_id, torch_dtype=torch.float16).to("cuda")
 
 prompt = "A panda is playing guitar on times square"
@@ -63,7 +64,7 @@ import torch
 from diffusers import TextToVideoZeroPipeline
 import numpy as np
 
-model_id = "runwayml/stable-diffusion-v1-5"
+model_id = "stable-diffusion-v1-5/stable-diffusion-v1-5"
 pipe = TextToVideoZeroPipeline.from_pretrained(model_id, torch_dtype=torch.float16).to("cuda")
 seed = 0
 video_length = 24  #24 ÷ 4fps = 6 seconds
@@ -137,7 +138,7 @@ To generate a video from prompt with additional pose control
     from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
     from diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_zero import CrossFrameAttnProcessor
 
-    model_id = "runwayml/stable-diffusion-v1-5"
+    model_id = "stable-diffusion-v1-5/stable-diffusion-v1-5"
     controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-openpose", torch_dtype=torch.float16)
     pipe = StableDiffusionControlNetPipeline.from_pretrained(
         model_id, controlnet=controlnet, torch_dtype=torch.float16

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

@@ -45,6 +45,14 @@ Many schedulers are implemented from the [k-diffusion](https://github.com/crowso
 | N/A                 | [`DEISMultistepScheduler`]          |                                                                                                               |
 | N/A                 | [`UniPCMultistepScheduler`]         |                                                                                                               |
 
+## Noise schedules and schedule types
+| A1111/k-diffusion        | 🤗 Diffusers                                                               |
+|--------------------------|----------------------------------------------------------------------------|
+| Karras                   | init with `use_karras_sigmas=True`                                         |
+| sgm_uniform              | init with `timestep_spacing="trailing"`                                    |
+| simple                   | init with `timestep_spacing="trailing"`                                    |
+| exponential              | init with `timestep_spacing="linspace"`, `use_exponential_sigmas=True`     |
+
 All schedulers are built from the base [`SchedulerMixin`] class which implements low level utilities shared by all schedulers.
 
 ## SchedulerMixin

docs/source/en/community_projects.md

@@ -75,4 +75,8 @@ Happy exploring, and thank you for being part of the Diffusers community!
     <td><a href="https://github.com/cumulo-autumn/StreamDiffusion"> StreamDiffusion </a></td>
     <td>A Pipeline-Level Solution for Real-Time Interactive Generation</td>
   </tr>
+  <tr style="border-top: 2px solid black">
+    <td><a href="https://github.com/Netwrck/stable-diffusion-server"> Stable Diffusion Server </a></td>
+    <td>A server configured for Inpainting/Generation/img2img with one stable diffusion model</td>
+  </tr>
 </table>

docs/source/en/conceptual/evaluation.md

@@ -92,7 +92,7 @@ images = sd_pipeline(sample_prompts, num_images_per_prompt=1, generator=generato
 
 ![parti-prompts-14](https://huggingface.co/datasets/diffusers/docs-images/resolve/main/evaluation_diffusion_models/parti-prompts-14.png)
 
-We can also set `num_images_per_prompt` accordingly to compare different images for the same prompt. Running the same pipeline but with a different checkpoint ([v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5)), yields:
+We can also set `num_images_per_prompt` accordingly to compare different images for the same prompt. Running the same pipeline but with a different checkpoint ([v1-5](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5)), yields:
 
 ![parti-prompts-15](https://huggingface.co/datasets/diffusers/docs-images/resolve/main/evaluation_diffusion_models/parti-prompts-15.png)
 
@@ -177,10 +177,10 @@ generator = torch.manual_seed(seed)
 images = sd_pipeline(prompts, num_images_per_prompt=1, generator=generator, output_type="np").images
 ```
 
-Then we load the [v1-5 checkpoint](https://huggingface.co/runwayml/stable-diffusion-v1-5) to generate images:
+Then we load the [v1-5 checkpoint](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) to generate images:
 
 ```python
-model_ckpt_1_5 = "runwayml/stable-diffusion-v1-5"
+model_ckpt_1_5 = "stable-diffusion-v1-5/stable-diffusion-v1-5"
 sd_pipeline_1_5 = StableDiffusionPipeline.from_pretrained(model_ckpt_1_5, torch_dtype=weight_dtype).to(device)
 
 images_1_5 = sd_pipeline_1_5(prompts, num_images_per_prompt=1, generator=generator, output_type="np").images
@@ -198,7 +198,7 @@ print(f"CLIP Score with v-1-5: {sd_clip_score_1_5}")
 # CLIP Score with v-1-5: 36.2137
 ```
 
-It seems like the [v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5) checkpoint performs better than its predecessor. Note, however, that the number of prompts we used to compute the CLIP scores is quite low. For a more practical evaluation, this number should be way higher, and the prompts should be diverse.
+It seems like the [v1-5](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) checkpoint performs better than its predecessor. Note, however, that the number of prompts we used to compute the CLIP scores is quite low. For a more practical evaluation, this number should be way higher, and the prompts should be diverse.
 
 <Tip warning={true}>
 

docs/source/en/conceptual/philosophy.md

@@ -65,7 +65,7 @@ Pipelines are designed to be easy to use (therefore do not follow [*Simple over
 The following design principles are followed:
 - Pipelines follow the single-file policy. All pipelines can be found in individual directories under src/diffusers/pipelines. One pipeline folder corresponds to one diffusion paper/project/release. Multiple pipeline files can be gathered in one pipeline folder, as it’s done for [`src/diffusers/pipelines/stable-diffusion`](https://github.com/huggingface/diffusers/tree/main/src/diffusers/pipelines/stable_diffusion). If pipelines share similar functionality, one can make use of the [# Copied from mechanism](https://github.com/huggingface/diffusers/blob/125d783076e5bd9785beb05367a2d2566843a271/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py#L251).
 - Pipelines all inherit from [`DiffusionPipeline`].
-- Every pipeline consists of different model and scheduler components, that are documented in the [`model_index.json` file](https://huggingface.co/runwayml/stable-diffusion-v1-5/blob/main/model_index.json), are accessible under the same name as attributes of the pipeline and can be shared between pipelines with [`DiffusionPipeline.components`](https://huggingface.co/docs/diffusers/main/en/api/diffusion_pipeline#diffusers.DiffusionPipeline.components) function.
+- Every pipeline consists of different model and scheduler components, that are documented in the [`model_index.json` file](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5/blob/main/model_index.json), are accessible under the same name as attributes of the pipeline and can be shared between pipelines with [`DiffusionPipeline.components`](https://huggingface.co/docs/diffusers/main/en/api/diffusion_pipeline#diffusers.DiffusionPipeline.components) function.
 - Every pipeline should be loadable via the [`DiffusionPipeline.from_pretrained`](https://huggingface.co/docs/diffusers/main/en/api/diffusion_pipeline#diffusers.DiffusionPipeline.from_pretrained) function.
 - Pipelines should be used **only** for inference.
 - Pipelines should be very readable, self-explanatory, and easy to tweak.

docs/source/en/optimization/coreml.md

@@ -95,17 +95,17 @@ print(f"Model downloaded at {model_path}")
 Once you have downloaded a snapshot of the model, you can test it using Apple's Python script.
 
 ```shell
-python -m python_coreml_stable_diffusion.pipeline --prompt "a photo of an astronaut riding a horse on mars" -i models/coreml-stable-diffusion-v1-4_original_packages -o </path/to/output/image> --compute-unit CPU_AND_GPU --seed 93
+python -m python_coreml_stable_diffusion.pipeline --prompt "a photo of an astronaut riding a horse on mars" -i ./models/coreml-stable-diffusion-v1-4_original_packages/original/packages -o </path/to/output/image> --compute-unit CPU_AND_GPU --seed 93
 ```
 
 Pass the path of the downloaded checkpoint with `-i` flag to the script. `--compute-unit` indicates the hardware you want to allow for inference. It must be one of the following options: `ALL`, `CPU_AND_GPU`, `CPU_ONLY`, `CPU_AND_NE`. You may also provide an optional output path, and a seed for reproducibility.
 
 The inference script assumes you're using the original version of the Stable Diffusion model, `CompVis/stable-diffusion-v1-4`. If you use another model, you *have* to specify its Hub id in the inference command line, using the `--model-version` option. This works for models already supported and custom models you trained or fine-tuned yourself.
 
-For example, if you want to use [`runwayml/stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5):
+For example, if you want to use [`stable-diffusion-v1-5/stable-diffusion-v1-5`](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5):
 
 ```shell
-python -m python_coreml_stable_diffusion.pipeline --prompt "a photo of an astronaut riding a horse on mars" --compute-unit ALL -o output --seed 93 -i models/coreml-stable-diffusion-v1-5_original_packages --model-version runwayml/stable-diffusion-v1-5
+python -m python_coreml_stable_diffusion.pipeline --prompt "a photo of an astronaut riding a horse on mars" --compute-unit ALL -o output --seed 93 -i models/coreml-stable-diffusion-v1-5_original_packages --model-version stable-diffusion-v1-5/stable-diffusion-v1-5
 ```
 
 ## Core ML inference in Swift

docs/source/en/optimization/deepcache.md

@@ -23,7 +23,7 @@ Then load and enable the [`DeepCacheSDHelper`](https://github.com/horseee/DeepCa
 ```diff
   import torch
   from diffusers import StableDiffusionPipeline
-  pipe = StableDiffusionPipeline.from_pretrained('runwayml/stable-diffusion-v1-5', torch_dtype=torch.float16).to("cuda")
+  pipe = StableDiffusionPipeline.from_pretrained('stable-diffusion-v1-5/stable-diffusion-v1-5', torch_dtype=torch.float16).to("cuda")
 
 + from DeepCache import DeepCacheSDHelper
 + helper = DeepCacheSDHelper(pipe=pipe)

docs/source/en/optimization/fp16.md

@@ -47,7 +47,7 @@ import torch
 from diffusers import DiffusionPipeline
 
 pipe = DiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
     torch_dtype=torch.float16,
     use_safetensors=True,
 )

docs/source/en/optimization/habana.md

@@ -61,7 +61,7 @@ For more information, check out 🤗 Optimum Habana's [documentation](https://hu
 
 We benchmarked Habana's first-generation Gaudi and Gaudi2 with the [Habana/stable-diffusion](https://huggingface.co/Habana/stable-diffusion) and [Habana/stable-diffusion-2](https://huggingface.co/Habana/stable-diffusion-2) Gaudi configurations (mixed precision bf16/fp32) to demonstrate their performance.
 
-For [Stable Diffusion v1.5](https://huggingface.co/runwayml/stable-diffusion-v1-5) on 512x512 images:
+For [Stable Diffusion v1.5](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) on 512x512 images:
 
 |                        | Latency (batch size = 1) | Throughput  |
 | ---------------------- |:------------------------:|:---------------------------:|

docs/source/en/optimization/memory.md

@@ -41,7 +41,7 @@ import torch
 from diffusers import StableDiffusionPipeline
 
 pipe = StableDiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
     torch_dtype=torch.float16,
     use_safetensors=True,
 )
@@ -66,7 +66,7 @@ import torch
 from diffusers import StableDiffusionPipeline, UniPCMultistepScheduler
 
 pipe = StableDiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
     torch_dtype=torch.float16,
     use_safetensors=True,
 )
@@ -92,7 +92,7 @@ import torch
 from diffusers import StableDiffusionPipeline
 
 pipe = StableDiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
     torch_dtype=torch.float16,
     use_safetensors=True,
 )
@@ -140,7 +140,7 @@ import torch
 from diffusers import StableDiffusionPipeline
 
 pipe = StableDiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
     torch_dtype=torch.float16,
     use_safetensors=True,
 )
@@ -201,7 +201,7 @@ def generate_inputs():
 
 
 pipe = StableDiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
     torch_dtype=torch.float16,
     use_safetensors=True,
 ).to("cuda")
@@ -265,7 +265,7 @@ class UNet2DConditionOutput:
 
 
 pipe = StableDiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
     torch_dtype=torch.float16,
     use_safetensors=True,
 ).to("cuda")
@@ -315,7 +315,7 @@ from diffusers import DiffusionPipeline
 import torch
 
 pipe = DiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
     torch_dtype=torch.float16,
     use_safetensors=True,
 ).to("cuda")

docs/source/en/optimization/mps.md

@@ -24,7 +24,7 @@ The `mps` backend uses PyTorch's `.to()` interface to move the Stable Diffusion
 ```python
 from diffusers import DiffusionPipeline
 
-pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")
+pipe = DiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5")
 pipe = pipe.to("mps")
 
 # Recommended if your computer has < 64 GB of RAM
@@ -46,7 +46,7 @@ If you're using **PyTorch 1.13**, you need to "prime" the pipeline with an addit
 ```diff
   from diffusers import DiffusionPipeline
 
-  pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5").to("mps")
+  pipe = DiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5").to("mps")
   pipe.enable_attention_slicing()
 
   prompt = "a photo of an astronaut riding a horse on mars"
@@ -67,7 +67,7 @@ To prevent this from happening, we recommend *attention slicing* to reduce memor
 from diffusers import DiffusionPipeline
 import torch
 
-pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, variant="fp16", use_safetensors=True).to("mps")
+pipeline = DiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16, variant="fp16", use_safetensors=True).to("mps")
 pipeline.enable_attention_slicing()
 ```
 

docs/source/en/optimization/onnx.md

@@ -27,7 +27,7 @@ To load and run inference, use the [`~optimum.onnxruntime.ORTStableDiffusionPipe
 ```python
 from optimum.onnxruntime import ORTStableDiffusionPipeline
 
-model_id = "runwayml/stable-diffusion-v1-5"
+model_id = "stable-diffusion-v1-5/stable-diffusion-v1-5"
 pipeline = ORTStableDiffusionPipeline.from_pretrained(model_id, export=True)
 prompt = "sailing ship in storm by Leonardo da Vinci"
 image = pipeline(prompt).images[0]
@@ -44,7 +44,7 @@ To export the pipeline in the ONNX format offline and use it later for inference
 use the [`optimum-cli export`](https://huggingface.co/docs/optimum/main/en/exporters/onnx/usage_guides/export_a_model#exporting-a-model-to-onnx-using-the-cli) command:
 
 ```bash
-optimum-cli export onnx --model runwayml/stable-diffusion-v1-5 sd_v15_onnx/
+optimum-cli export onnx --model stable-diffusion-v1-5/stable-diffusion-v1-5 sd_v15_onnx/
 ```
 
 Then to perform inference (you don't have to specify `export=True` again):

docs/source/en/optimization/open_vino.md

@@ -29,7 +29,7 @@ To load and run inference, use the [`~optimum.intel.OVStableDiffusionPipeline`].
 ```python
 from optimum.intel import OVStableDiffusionPipeline
 
-model_id = "runwayml/stable-diffusion-v1-5"
+model_id = "stable-diffusion-v1-5/stable-diffusion-v1-5"
 pipeline = OVStableDiffusionPipeline.from_pretrained(model_id, export=True)
 prompt = "sailing ship in storm by Rembrandt"
 image = pipeline(prompt).images[0]

docs/source/en/optimization/tome.md

@@ -28,7 +28,7 @@ You can use ToMe from the [`tomesd`](https://github.com/dbolya/tomesd) library w
   import tomesd
 
   pipeline = StableDiffusionPipeline.from_pretrained(
-        "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True,
+        "stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True,
   ).to("cuda")
 + tomesd.apply_patch(pipeline, ratio=0.5)
 

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

@@ -34,7 +34,7 @@ However, if you want to explicitly enable it, you can set a [`DiffusionPipeline`
   from diffusers import DiffusionPipeline
 + from diffusers.models.attention_processor import AttnProcessor2_0
 
-  pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True).to("cuda")
+  pipe = DiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True).to("cuda")
 + pipe.unet.set_attn_processor(AttnProcessor2_0())
 
   prompt = "a photo of an astronaut riding a horse on mars"
@@ -49,7 +49,7 @@ In some cases - such as making the pipeline more deterministic or converting it
   import torch
   from diffusers import DiffusionPipeline
 
-  pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True).to("cuda")
+  pipe = DiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True).to("cuda")
 + pipe.unet.set_default_attn_processor()
 
   prompt = "a photo of an astronaut riding a horse on mars"
@@ -64,7 +64,7 @@ The `torch.compile` function can often provide an additional speed-up to your Py
 from diffusers import DiffusionPipeline
 import torch
 
-pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True).to("cuda")
+pipe = DiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True).to("cuda")
 pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
 images = pipe(prompt, num_inference_steps=steps, num_images_per_prompt=batch_size).images[0]
 ```
@@ -92,7 +92,7 @@ Expand the dropdown below to find the code used to benchmark each pipeline:
 from diffusers import DiffusionPipeline
 import torch
 
-path = "runwayml/stable-diffusion-v1-5"
+path = "stable-diffusion-v1-5/stable-diffusion-v1-5"
 
 run_compile = True  # Set True / False
 
@@ -122,7 +122,7 @@ url = "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/st
 init_image = load_image(url)
 init_image = init_image.resize((512, 512))
 
-path = "runwayml/stable-diffusion-v1-5"
+path = "stable-diffusion-v1-5/stable-diffusion-v1-5"
 
 run_compile = True  # Set True / False
 
@@ -183,7 +183,7 @@ url = "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/st
 init_image = load_image(url)
 init_image = init_image.resize((512, 512))
 
-path = "runwayml/stable-diffusion-v1-5"
+path = "stable-diffusion-v1-5/stable-diffusion-v1-5"
 
 run_compile = True  # Set True / False
 controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", torch_dtype=torch.float16, use_safetensors=True)

docs/source/en/optimization/xdit.md

@@ -0,0 +1,122 @@
+# xDiT
+
+[xDiT](https://github.com/xdit-project/xDiT) is an inference engine designed for the large scale parallel deployment of Diffusion Transformers (DiTs). xDiT provides a suite of efficient parallel approaches for Diffusion Models, as well as GPU kernel accelerations.
+
+There are four parallel methods supported in xDiT, including [Unified Sequence Parallelism](https://arxiv.org/abs/2405.07719), [PipeFusion](https://arxiv.org/abs/2405.14430), CFG parallelism and data parallelism. The four parallel methods in xDiT can be configured in a hybrid manner, optimizing communication patterns to best suit the underlying network hardware.
+
+Optimization orthogonal to parallelization focuses on accelerating single GPU performance. In addition to utilizing well-known Attention optimization libraries, we leverage compilation acceleration technologies such as torch.compile and onediff.
+
+The overview of xDiT is shown as follows.
+
+<div class="flex justify-center">
+    <img src="https://github.com/xdit-project/xDiT/raw/main/assets/methods/xdit_overview.png">
+</div>
+You can install xDiT using the following command:
+
+
+```bash
+pip install xfuser
+```
+
+Here's an example of using xDiT to accelerate inference of a Diffusers model.
+
+```diff
+ import torch
+ from diffusers import StableDiffusion3Pipeline
+
+ from xfuser import xFuserArgs, xDiTParallel
+ from xfuser.config import FlexibleArgumentParser
+ from xfuser.core.distributed import get_world_group
+
+ def main():
++    parser = FlexibleArgumentParser(description="xFuser Arguments")
++    args = xFuserArgs.add_cli_args(parser).parse_args()
++    engine_args = xFuserArgs.from_cli_args(args)
++    engine_config, input_config = engine_args.create_config()
+
+     local_rank = get_world_group().local_rank
+     pipe = StableDiffusion3Pipeline.from_pretrained(
+         pretrained_model_name_or_path=engine_config.model_config.model,
+         torch_dtype=torch.float16,
+     ).to(f"cuda:{local_rank}")
+    
+# do anything you want with pipeline here
+
++    pipe = xDiTParallel(pipe, engine_config, input_config)
+
+     pipe(
+         height=input_config.height,
+         width=input_config.height,
+         prompt=input_config.prompt,
+         num_inference_steps=input_config.num_inference_steps,
+         output_type=input_config.output_type,
+         generator=torch.Generator(device="cuda").manual_seed(input_config.seed),
+     )
+
++    if input_config.output_type == "pil":
++        pipe.save("results", "stable_diffusion_3")
+
+if __name__ == "__main__":
+    main()
+
+```
+
+As you can see, we only need to use xFuserArgs from xDiT to get configuration parameters, and pass these parameters along with the pipeline object from the Diffusers library into xDiTParallel to complete the parallelization of a specific pipeline in Diffusers.
+
+xDiT runtime parameters can be viewed in the command line using `-h`, and you can refer to this [usage](https://github.com/xdit-project/xDiT?tab=readme-ov-file#2-usage) example for more details.
+
+xDiT needs to be launched using torchrun to support its multi-node, multi-GPU parallel capabilities. For example, the following command can be used for 8-GPU parallel inference:
+
+```bash
+torchrun --nproc_per_node=8 ./inference.py --model models/FLUX.1-dev --data_parallel_degree 2 --ulysses_degree 2 --ring_degree 2 --prompt "A snowy mountain" "A small dog" --num_inference_steps 50
+```
+
+## Supported models
+
+A subset of Diffusers models are supported in xDiT, such as Flux.1, Stable Diffusion 3, etc. The latest supported models can be found [here](https://github.com/xdit-project/xDiT?tab=readme-ov-file#-supported-dits).
+
+## Benchmark
+We tested different models on various machines, and here is some of the benchmark data.
+
+
+### Flux.1-schnell
+<div class="flex justify-center">
+    <img src="https://github.com/xdit-project/xDiT/raw/main/assets/performance/flux/Flux-2k-L40.png">
+</div>
+
+
+<div class="flex justify-center">
+    <img src="https://github.com/xdit-project/xDiT/raw/main/assets/performance/flux/Flux-2K-A100.png">
+</div>
+
+### Stable Diffusion 3
+<div class="flex justify-center">
+    <img src="https://github.com/xdit-project/xDiT/raw/main/assets/performance/sd3/L40-SD3.png">
+</div>
+
+<div class="flex justify-center">
+    <img src="https://github.com/xdit-project/xDiT/raw/main/assets/performance/sd3/A100-SD3.png">
+</div>
+
+### HunyuanDiT
+<div class="flex justify-center">
+    <img src="https://github.com/xdit-project/xDiT/raw/main/assets/performance/hunuyuandit/L40-HunyuanDiT.png">
+</div>
+
+<div class="flex justify-center">
+    <img src="https://github.com/xdit-project/xDiT/raw/main/assets/performance/hunuyuandit/A100-HunyuanDiT.png">
+</div>
+
+<div class="flex justify-center">
+    <img src="https://github.com/xdit-project/xDiT/raw/main/assets/performance/hunuyuandit/T4-HunyuanDiT.png">
+</div>
+
+More detailed performance metric can be found on our [github page](https://github.com/xdit-project/xDiT?tab=readme-ov-file#perf).
+
+## Reference
+
+[xDiT-project](https://github.com/xdit-project/xDiT)
+
+[USP: A Unified Sequence Parallelism Approach for Long Context Generative AI](https://arxiv.org/abs/2405.07719)
+
+[PipeFusion: Displaced Patch Pipeline Parallelism for Inference of Diffusion Transformer Models](https://arxiv.org/abs/2405.14430)

docs/source/en/quicktour.md

@@ -54,7 +54,7 @@ The [`DiffusionPipeline`] is the easiest way to use a pretrained diffusion syste
 
 Start by creating an instance of a [`DiffusionPipeline`] and specify which pipeline checkpoint you would like to download.
 You can use the [`DiffusionPipeline`] for any [checkpoint](https://huggingface.co/models?library=diffusers&sort=downloads) stored on the Hugging Face Hub.
-In this quicktour, you'll load the [`stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5) checkpoint for text-to-image generation.
+In this quicktour, you'll load the [`stable-diffusion-v1-5`](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) checkpoint for text-to-image generation.
 
 <Tip warning={true}>
 
@@ -67,7 +67,7 @@ Load the model with the [`~DiffusionPipeline.from_pretrained`] method:
 ```python
 >>> from diffusers import DiffusionPipeline
 
->>> pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", use_safetensors=True)
+>>> pipeline = DiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", use_safetensors=True)
 ```
 
 The [`DiffusionPipeline`] downloads and caches all modeling, tokenization, and scheduling components. You'll see that the Stable Diffusion pipeline is composed of the [`UNet2DConditionModel`] and [`PNDMScheduler`] among other things:
@@ -124,7 +124,7 @@ You can also use the pipeline locally. The only difference is you need to downlo
 
 ```bash
 !git lfs install
-!git clone https://huggingface.co/runwayml/stable-diffusion-v1-5
+!git clone https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5
 ```
 
 Then load the saved weights into the pipeline:
@@ -142,7 +142,7 @@ Different schedulers come with different denoising speeds and quality trade-offs
 ```py
 >>> from diffusers import EulerDiscreteScheduler
 
->>> pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", use_safetensors=True)
+>>> pipeline = DiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", use_safetensors=True)
 >>> pipeline.scheduler = EulerDiscreteScheduler.from_config(pipeline.scheduler.config)
 ```
 

docs/source/en/stable_diffusion.md

@@ -20,12 +20,12 @@ This is why it's important to get the most *computational* (speed) and *memory*
 
 This tutorial walks you through how to generate faster and better with the [`DiffusionPipeline`].
 
-Begin by loading the [`runwayml/stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5) model:
+Begin by loading the [`stable-diffusion-v1-5/stable-diffusion-v1-5`](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) model:
 
 ```python
 from diffusers import DiffusionPipeline
 
-model_id = "runwayml/stable-diffusion-v1-5"
+model_id = "stable-diffusion-v1-5/stable-diffusion-v1-5"
 pipeline = DiffusionPipeline.from_pretrained(model_id, use_safetensors=True)
 ```
 

docs/source/en/training/adapt_a_model.md

@@ -6,12 +6,12 @@ This guide will show you how to adapt a pretrained text-to-image model for inpai
 
 ## Configure UNet2DConditionModel parameters
 
-A [`UNet2DConditionModel`] by default accepts 4 channels in the [input sample](https://huggingface.co/docs/diffusers/v0.16.0/en/api/models#diffusers.UNet2DConditionModel.in_channels). For example, load a pretrained text-to-image model like [`runwayml/stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5) and take a look at the number of `in_channels`:
+A [`UNet2DConditionModel`] by default accepts 4 channels in the [input sample](https://huggingface.co/docs/diffusers/v0.16.0/en/api/models#diffusers.UNet2DConditionModel.in_channels). For example, load a pretrained text-to-image model like [`stable-diffusion-v1-5/stable-diffusion-v1-5`](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) and take a look at the number of `in_channels`:
 
 ```py
 from diffusers import StableDiffusionPipeline
 
-pipeline = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", use_safetensors=True)
+pipeline = StableDiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", use_safetensors=True)
 pipeline.unet.config["in_channels"]
 4
 ```
@@ -33,7 +33,7 @@ Initialize a [`UNet2DConditionModel`] with the pretrained text-to-image model we
 ```py
 from diffusers import UNet2DConditionModel
 
-model_id = "runwayml/stable-diffusion-v1-5"
+model_id = "stable-diffusion-v1-5/stable-diffusion-v1-5"
 unet = UNet2DConditionModel.from_pretrained(
     model_id,
     subfolder="unet",

docs/source/en/training/controlnet.md

@@ -276,7 +276,7 @@ That's it! You don't need to add any additional parameters to your training comm
 <hfoption id="PyTorch">
 
 ```bash
-export MODEL_DIR="runwayml/stable-diffusion-v1-5"
+export MODEL_DIR="stable-diffusion-v1-5/stable-diffusion-v1-5"
 export OUTPUT_DIR="path/to/save/model"
 
 accelerate launch train_controlnet.py \

docs/source/en/training/create_dataset.md

@@ -78,7 +78,7 @@ Now the dataset is available for training by passing the dataset name to the `--
 
 ```bash
 accelerate launch --mixed_precision="fp16"  train_text_to_image.py \
-  --pretrained_model_name_or_path="runwayml/stable-diffusion-v1-5" \
+  --pretrained_model_name_or_path="stable-diffusion-v1-5/stable-diffusion-v1-5" \
   --dataset_name="name_of_your_dataset" \
   <other-arguments>
 ```

docs/source/en/training/distributed_inference.md

@@ -10,7 +10,7 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
 specific language governing permissions and limitations under the License.
 -->
 
-# Distributed inference with multiple GPUs
+# Distributed inference
 
 On distributed setups, you can run inference across multiple GPUs with 🤗 [Accelerate](https://huggingface.co/docs/accelerate/index) or [PyTorch Distributed](https://pytorch.org/tutorials/beginner/dist_overview.html), which is useful for generating with multiple prompts in parallel.
 
@@ -30,7 +30,7 @@ from accelerate import PartialState
 from diffusers import DiffusionPipeline
 
 pipeline = DiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True
+    "stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True
 )
 distributed_state = PartialState()
 pipeline.to(distributed_state.device)
@@ -66,7 +66,7 @@ import torch.multiprocessing as mp
 from diffusers import DiffusionPipeline
 
 sd = DiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True
+    "stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True
 )
 ```
 
@@ -109,3 +109,131 @@ torchrun run_distributed.py --nproc_per_node=2
 
 > [!TIP]
 > You can use `device_map` within a [`DiffusionPipeline`] to distribute its model-level components on multiple devices. Refer to the [Device placement](../tutorials/inference_with_big_models#device-placement) guide to learn more.
+
+## Model sharding
+
+Modern diffusion systems such as [Flux](../api/pipelines/flux) are very large and have multiple models. For example, [Flux.1-Dev](https://hf.co/black-forest-labs/FLUX.1-dev) is made up of two text encoders - [T5-XXL](https://hf.co/google/t5-v1_1-xxl) and [CLIP-L](https://hf.co/openai/clip-vit-large-patch14) - a [diffusion transformer](../api/models/flux_transformer), and a [VAE](../api/models/autoencoderkl). With a model this size, it can be challenging to run inference on consumer GPUs.
+
+Model sharding is a technique that distributes models across GPUs when the models don't fit on a single GPU. The example below assumes two 16GB GPUs are available for inference.
+
+Start by computing the text embeddings with the text encoders. Keep the text encoders on two GPUs by setting `device_map="balanced"`. The `balanced` strategy evenly distributes the model on all available GPUs. Use the `max_memory` parameter to allocate the maximum amount of memory for each text encoder on each GPU.
+
+> [!TIP]
+> **Only** load the text encoders for this step! The diffusion transformer and VAE are loaded in a later step to preserve memory.
+
+```py
+from diffusers import FluxPipeline
+import torch
+
+prompt = "a photo of a dog with cat-like look"
+
+pipeline = FluxPipeline.from_pretrained(
+    "black-forest-labs/FLUX.1-dev",
+    transformer=None,
+    vae=None,
+    device_map="balanced",
+    max_memory={0: "16GB", 1: "16GB"},
+    torch_dtype=torch.bfloat16
+)
+with torch.no_grad():
+    print("Encoding prompts.")
+    prompt_embeds, pooled_prompt_embeds, text_ids = pipeline.encode_prompt(
+        prompt=prompt, prompt_2=None, max_sequence_length=512
+    )
+```
+
+Once the text embeddings are computed, remove them from the GPU to make space for the diffusion transformer.
+
+```py
+import gc 
+
+def flush():
+    gc.collect()
+    torch.cuda.empty_cache()
+    torch.cuda.reset_max_memory_allocated()
+    torch.cuda.reset_peak_memory_stats()
+
+del pipeline.text_encoder
+del pipeline.text_encoder_2
+del pipeline.tokenizer
+del pipeline.tokenizer_2
+del pipeline
+
+flush()
+```
+
+Load the diffusion transformer next which has 12.5B parameters. This time, set `device_map="auto"` to automatically distribute the model across two 16GB GPUs. The `auto` strategy is backed by [Accelerate](https://hf.co/docs/accelerate/index) and available as a part of the [Big Model Inference](https://hf.co/docs/accelerate/concept_guides/big_model_inference) feature. It starts by distributing a model across the fastest device first (GPU) before moving to slower devices like the CPU and hard drive if needed. The trade-off of storing model parameters on slower devices is slower inference latency.
+
+```py
+from diffusers import FluxTransformer2DModel
+import torch 
+
+transformer = FluxTransformer2DModel.from_pretrained(
+    "black-forest-labs/FLUX.1-dev", 
+    subfolder="transformer",
+    device_map="auto",
+    torch_dtype=torch.bfloat16
+)
+```
+
+> [!TIP]
+> At any point, you can try `print(pipeline.hf_device_map)` to see how the various models are distributed across devices. This is useful for tracking the device placement of the models.
+
+Add the transformer model to the pipeline for denoising, but set the other model-level components like the text encoders and VAE to `None` because you don't need them yet.
+
+```py
+pipeline = FluxPipeline.from_pretrained(
+    "black-forest-labs/FLUX.1-dev", ,
+    text_encoder=None,
+    text_encoder_2=None,
+    tokenizer=None,
+    tokenizer_2=None,
+    vae=None,
+    transformer=transformer,
+    torch_dtype=torch.bfloat16
+)
+
+print("Running denoising.")
+height, width = 768, 1360
+latents = pipeline(
+    prompt_embeds=prompt_embeds,
+    pooled_prompt_embeds=pooled_prompt_embeds,
+    num_inference_steps=50,
+    guidance_scale=3.5,
+    height=height,
+    width=width,
+    output_type="latent",
+).images
+```
+
+Remove the pipeline and transformer from memory as they're no longer needed.
+
+```py
+del pipeline.transformer
+del pipeline
+
+flush()
+```
+
+Finally, decode the latents with the VAE into an image. The VAE is typically small enough to be loaded on a single GPU.
+
+```py
+from diffusers import AutoencoderKL
+from diffusers.image_processor import VaeImageProcessor
+import torch 
+
+vae = AutoencoderKL.from_pretrained(ckpt_id, subfolder="vae", torch_dtype=torch.bfloat16).to("cuda")
+vae_scale_factor = 2 ** (len(vae.config.block_out_channels))
+image_processor = VaeImageProcessor(vae_scale_factor=vae_scale_factor)
+
+with torch.no_grad():
+    print("Running decoding.")
+    latents = FluxPipeline._unpack_latents(latents, height, width, vae_scale_factor)
+    latents = (latents / vae.config.scaling_factor) + vae.config.shift_factor
+
+    image = vae.decode(latents, return_dict=False)[0]
+    image = image_processor.postprocess(image, output_type="pil")
+    image[0].save("split_transformer.png")
+```
+
+By selectively loading and unloading the models you need at a given stage and sharding the largest models across multiple GPUs, it is possible to run inference with large models on consumer GPUs.

docs/source/en/training/dreambooth.md

@@ -315,7 +315,7 @@ That's it! You don't need to add any additional parameters to your training comm
 <hfoption id="PyTorch">
 
 ```bash
-export MODEL_NAME="runwayml/stable-diffusion-v1-5"
+export MODEL_NAME="stable-diffusion-v1-5/stable-diffusion-v1-5"
 export INSTANCE_DIR="./dog"
 export OUTPUT_DIR="path_to_saved_model"
 
@@ -374,7 +374,7 @@ unet = UNet2DConditionModel.from_pretrained("path/to/model/checkpoint-100/unet")
 text_encoder = CLIPTextModel.from_pretrained("path/to/model/checkpoint-100/checkpoint-100/text_encoder")
 
 pipeline = DiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", unet=unet, text_encoder=text_encoder, dtype=torch.float16,
+    "stable-diffusion-v1-5/stable-diffusion-v1-5", unet=unet, text_encoder=text_encoder, dtype=torch.float16,
 ).to("cuda")
 
 image = pipeline("A photo of sks dog in a bucket", num_inference_steps=50, guidance_scale=7.5).images[0]

docs/source/en/training/lcm_distill.md

@@ -193,7 +193,7 @@ Now you're ready to launch the training script and start distilling!
 For this guide, you'll use the `--train_shards_path_or_url` to specify the path to the [Conceptual Captions 12M](https://github.com/google-research-datasets/conceptual-12m) dataset stored on the Hub [here](https://huggingface.co/datasets/laion/conceptual-captions-12m-webdataset). Set the `MODEL_DIR` environment variable to the name of the teacher model and `OUTPUT_DIR` to where you want to save the model.
 
 ```bash
-export MODEL_DIR="runwayml/stable-diffusion-v1-5"
+export MODEL_DIR="stable-diffusion-v1-5/stable-diffusion-v1-5"
 export OUTPUT_DIR="path/to/saved/model"
 
 accelerate launch train_lcm_distill_sd_wds.py \
@@ -225,7 +225,7 @@ from diffusers import UNet2DConditionModel, DiffusionPipeline, LCMScheduler
 import torch
 
 unet = UNet2DConditionModel.from_pretrained("your-username/your-model", torch_dtype=torch.float16, variant="fp16")
-pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", unet=unet, torch_dtype=torch.float16, variant="fp16")
+pipeline = DiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", unet=unet, torch_dtype=torch.float16, variant="fp16")
 
 pipeline.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
 pipeline.to("cuda")

docs/source/en/training/lora.md

@@ -184,7 +184,7 @@ A full training run takes ~5 hours on a 2080 Ti GPU with 11GB of VRAM.
 </Tip>
 
 ```bash
-export MODEL_NAME="runwayml/stable-diffusion-v1-5"
+export MODEL_NAME="stable-diffusion-v1-5/stable-diffusion-v1-5"
 export OUTPUT_DIR="/sddata/finetune/lora/naruto"
 export HUB_MODEL_ID="naruto-lora"
 export DATASET_NAME="lambdalabs/naruto-blip-captions"
@@ -218,7 +218,7 @@ Once training has been completed, you can use your model for inference:
 from diffusers import AutoPipelineForText2Image
 import torch
 
-pipeline = AutoPipelineForText2Image.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16).to("cuda")
+pipeline = AutoPipelineForText2Image.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16).to("cuda")
 pipeline.load_lora_weights("path/to/lora/model", weight_name="pytorch_lora_weights.safetensors")
 image = pipeline("A naruto with blue eyes").images[0]
 ```

docs/source/en/training/text2image.md

@@ -167,7 +167,7 @@ To train on a local dataset, set the `TRAIN_DIR` and `OUTPUT_DIR` environment va
 </Tip>
 
 ```bash
-export MODEL_NAME="runwayml/stable-diffusion-v1-5"
+export MODEL_NAME="stable-diffusion-v1-5/stable-diffusion-v1-5"
 export dataset_name="lambdalabs/naruto-blip-captions"
 
 accelerate launch --mixed_precision="fp16"  train_text_to_image.py \
@@ -201,7 +201,7 @@ To train on a local dataset, set the `TRAIN_DIR` and `OUTPUT_DIR` environment va
 </Tip>
 
 ```bash
-export MODEL_NAME="runwayml/stable-diffusion-v1-5"
+export MODEL_NAME="stable-diffusion-v1-5/stable-diffusion-v1-5"
 export dataset_name="lambdalabs/naruto-blip-captions"
 
 python train_text_to_image_flax.py \

docs/source/en/training/text_inversion.md

@@ -193,7 +193,7 @@ One more thing before you launch the script. If you're interested in following a
 <hfoption id="PyTorch">
 
 ```bash
-export MODEL_NAME="runwayml/stable-diffusion-v1-5"
+export MODEL_NAME="stable-diffusion-v1-5/stable-diffusion-v1-5"
 export DATA_DIR="./cat"
 
 accelerate launch textual_inversion.py \
@@ -248,7 +248,7 @@ After training is complete, you can use your newly trained model for inference l
 from diffusers import StableDiffusionPipeline
 import torch
 
-pipeline = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16).to("cuda")
+pipeline = StableDiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16).to("cuda")
 pipeline.load_textual_inversion("sd-concepts-library/cat-toy")
 image = pipeline("A <cat-toy> train", num_inference_steps=50).images[0]
 image.save("cat-train.png")

docs/source/en/tutorials/inference_with_big_models.md

@@ -90,8 +90,8 @@ from diffusers import DiffusionPipeline
 import torch
 
 pipeline = DiffusionPipeline.from_pretrained(
--    "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True,
-+    "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True, device_map="balanced"
+-    "stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True,
++    "stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True, device_map="balanced"
 )
 image = pipeline("a dog").images[0]
 image
@@ -105,7 +105,7 @@ import torch
 
 max_memory = {0:"1GB", 1:"1GB"}
 pipeline = DiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
     torch_dtype=torch.float16,
     use_safetensors=True,
     device_map="balanced",

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

@@ -109,7 +109,7 @@ Now, you can pass the callback function to the `callback_on_step_end` parameter
 import torch
 from diffusers import StableDiffusionPipeline
 
-pipeline = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
+pipeline = StableDiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16)
 pipeline = pipeline.to("cuda")
 
 prompt = "a photo of an astronaut riding a horse on mars"
@@ -139,7 +139,7 @@ In this example, the diffusion process is stopped after 10 steps even though `nu
 ```python
 from diffusers import StableDiffusionPipeline
 
-pipeline = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")
+pipeline = StableDiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5")
 pipeline.enable_model_cpu_offload()
 num_inference_steps = 50
 
@@ -171,14 +171,13 @@ def latents_to_rgb(latents):
     weights = (
         (60, -60, 25, -70),
         (60,  -5, 15, -50),
-        (60,  10, -5, -35)
+        (60,  10, -5, -35),
     )
 
     weights_tensor = torch.t(torch.tensor(weights, dtype=latents.dtype).to(latents.device))
     biases_tensor = torch.tensor((150, 140, 130), dtype=latents.dtype).to(latents.device)
     rgb_tensor = torch.einsum("...lxy,lr -> ...rxy", latents, weights_tensor) + biases_tensor.unsqueeze(-1).unsqueeze(-1)
-    image_array = rgb_tensor.clamp(0, 255)[0].byte().cpu().numpy()
-    image_array = image_array.transpose(1, 2, 0)
+    image_array = rgb_tensor.clamp(0, 255).byte().cpu().numpy().transpose(1, 2, 0)
 
     return Image.fromarray(image_array)
 ```
@@ -189,7 +188,7 @@ def latents_to_rgb(latents):
 def decode_tensors(pipe, step, timestep, callback_kwargs):
     latents = callback_kwargs["latents"]
 
-    image = latents_to_rgb(latents)
+    image = latents_to_rgb(latents[0])
     image.save(f"{step}.png")
 
     return callback_kwargs

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

@@ -33,7 +33,7 @@ from diffusers import AutoPipelineForText2Image
 import torch
 
 pipeline = AutoPipelineForText2Image.from_pretrained(
-	"runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, variant="fp16"
+	"stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16, variant="fp16"
 ).to("cuda")
 ```
 
@@ -52,18 +52,18 @@ image
 
 ## Popular models
 
-The most common text-to-image models are [Stable Diffusion v1.5](https://huggingface.co/runwayml/stable-diffusion-v1-5), [Stable Diffusion XL (SDXL)](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0), and [Kandinsky 2.2](https://huggingface.co/kandinsky-community/kandinsky-2-2-decoder). There are also ControlNet models or adapters that can be used with text-to-image models for more direct control in generating images. The results from each model are slightly different because of their architecture and training process, but no matter which model you choose, their usage is more or less the same. Let's use the same prompt for each model and compare their results.
+The most common text-to-image models are [Stable Diffusion v1.5](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5), [Stable Diffusion XL (SDXL)](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0), and [Kandinsky 2.2](https://huggingface.co/kandinsky-community/kandinsky-2-2-decoder). There are also ControlNet models or adapters that can be used with text-to-image models for more direct control in generating images. The results from each model are slightly different because of their architecture and training process, but no matter which model you choose, their usage is more or less the same. Let's use the same prompt for each model and compare their results.
 
 ### Stable Diffusion v1.5
 
-[Stable Diffusion v1.5](https://huggingface.co/runwayml/stable-diffusion-v1-5) is a latent diffusion model initialized from [Stable Diffusion v1-4](https://huggingface.co/CompVis/stable-diffusion-v1-4), and finetuned for 595K steps on 512x512 images from the LAION-Aesthetics V2 dataset. You can use this model like:
+[Stable Diffusion v1.5](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) is a latent diffusion model initialized from [Stable Diffusion v1-4](https://huggingface.co/CompVis/stable-diffusion-v1-4), and finetuned for 595K steps on 512x512 images from the LAION-Aesthetics V2 dataset. You can use this model like:
 
 ```py
 from diffusers import AutoPipelineForText2Image
 import torch
 
 pipeline = AutoPipelineForText2Image.from_pretrained(
-	"runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, variant="fp16"
+	"stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16, variant="fp16"
 ).to("cuda")
 generator = torch.Generator("cuda").manual_seed(31)
 image = pipeline("Astronaut in a jungle, cold color palette, muted colors, detailed, 8k", generator=generator).images[0]
@@ -106,7 +106,7 @@ image
 
 ### ControlNet
 
-ControlNet models are auxiliary models or adapters that are finetuned on top of text-to-image models, such as [Stable Diffusion v1.5](https://huggingface.co/runwayml/stable-diffusion-v1-5). Using ControlNet models in combination with text-to-image models offers diverse options for more explicit control over how to generate an image. With ControlNet, you add an additional conditioning input image to the model. For example, if you provide an image of a human pose (usually represented as multiple keypoints that are connected into a skeleton) as a conditioning input, the model generates an image that follows the pose of the image. Check out the more in-depth [ControlNet](controlnet) guide to learn more about other conditioning inputs and how to use them.
+ControlNet models are auxiliary models or adapters that are finetuned on top of text-to-image models, such as [Stable Diffusion v1.5](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5). Using ControlNet models in combination with text-to-image models offers diverse options for more explicit control over how to generate an image. With ControlNet, you add an additional conditioning input image to the model. For example, if you provide an image of a human pose (usually represented as multiple keypoints that are connected into a skeleton) as a conditioning input, the model generates an image that follows the pose of the image. Check out the more in-depth [ControlNet](controlnet) guide to learn more about other conditioning inputs and how to use them.
 
 In this example, let's condition the ControlNet with a human pose estimation image. Load the ControlNet model pretrained on human pose estimations:
 
@@ -125,7 +125,7 @@ Pass the `controlnet` to the [`AutoPipelineForText2Image`], and provide the prom
 
 ```py
 pipeline = AutoPipelineForText2Image.from_pretrained(
-	"runwayml/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16, variant="fp16"
+	"stable-diffusion-v1-5/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16, variant="fp16"
 ).to("cuda")
 generator = torch.Generator("cuda").manual_seed(31)
 image = pipeline("Astronaut in a jungle, cold color palette, muted colors, detailed, 8k", image=pose_image, generator=generator).images[0]
@@ -164,7 +164,7 @@ from diffusers import AutoPipelineForText2Image
 import torch
 
 pipeline = AutoPipelineForText2Image.from_pretrained(
-	"runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, variant="fp16"
+	"stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16, variant="fp16"
 ).to("cuda")
 image = pipeline(
 	"Astronaut in a jungle, cold color palette, muted colors, detailed, 8k", height=768, width=512
@@ -191,7 +191,7 @@ from diffusers import AutoPipelineForText2Image
 import torch
 
 pipeline = AutoPipelineForText2Image.from_pretrained(
-	"runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16
+	"stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16
 ).to("cuda")
 image = pipeline(
 	"Astronaut in a jungle, cold color palette, muted colors, detailed, 8k", guidance_scale=3.5
@@ -223,7 +223,7 @@ from diffusers import AutoPipelineForText2Image
 import torch
 
 pipeline = AutoPipelineForText2Image.from_pretrained(
-	"runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16
+	"stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16
 ).to("cuda")
 image = pipeline(
 	prompt="Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
@@ -254,7 +254,7 @@ from diffusers import AutoPipelineForText2Image
 import torch
 
 pipeline = AutoPipelineForText2Image.from_pretrained(
-	"runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16
+	"stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16
 ).to("cuda")
 generator = torch.Generator(device="cuda").manual_seed(30)
 image = pipeline(
@@ -285,7 +285,7 @@ from diffusers import AutoPipelineForText2Image
 import torch
 
 pipeline = AutoPipelineForText2Image.from_pretrained(
-	"runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16
+	"stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16
 ).to("cuda")
 image = pipeline(
 	prompt_embeds=prompt_embeds, # generated from Compel
@@ -309,7 +309,7 @@ PyTorch 2.0 also supports a more memory-efficient attention mechanism called [*s
 from diffusers import AutoPipelineForText2Image
 import torch
 
-pipeline = AutoPipelineForText2Image.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, variant="fp16").to("cuda")
+pipeline = AutoPipelineForText2Image.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16, variant="fp16").to("cuda")
 pipeline.unet = torch.compile(pipeline.unet, mode="reduce-overhead", fullgraph=True)
 ```
 

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

@@ -84,7 +84,7 @@ import torch
 
 controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", torch_dtype=torch.float16, use_safetensors=True)
 pipe = StableDiffusionControlNetPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16, use_safetensors=True
+    "stable-diffusion-v1-5/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16, use_safetensors=True
 )
 
 pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
@@ -144,7 +144,7 @@ import torch
 
 controlnet = ControlNetModel.from_pretrained("lllyasviel/control_v11f1p_sd15_depth", torch_dtype=torch.float16, use_safetensors=True)
 pipe = StableDiffusionControlNetImg2ImgPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16, use_safetensors=True
+    "stable-diffusion-v1-5/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16, use_safetensors=True
 )
 
 pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
@@ -229,7 +229,7 @@ from diffusers import StableDiffusionControlNetInpaintPipeline, ControlNetModel,
 
 controlnet = ControlNetModel.from_pretrained("lllyasviel/control_v11p_sd15_inpaint", torch_dtype=torch.float16, use_safetensors=True)
 pipe = StableDiffusionControlNetInpaintPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16, use_safetensors=True
+    "stable-diffusion-v1-5/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16, use_safetensors=True
 )
 
 pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
@@ -277,7 +277,7 @@ from PIL import Image
 import cv2
 
 controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", use_safetensors=True)
-pipe = StableDiffusionControlNetPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", controlnet=controlnet, use_safetensors=True).to("cuda")
+pipe = StableDiffusionControlNetPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", controlnet=controlnet, use_safetensors=True).to("cuda")
 
 original_image = load_image("https://huggingface.co/takuma104/controlnet_dev/resolve/main/bird_512x512.png")
 
@@ -454,7 +454,7 @@ image = base(
 
 <Tip>
 
-Replace the SDXL model with a model like [runwayml/stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5) to use multiple conditioning inputs with Stable Diffusion models.
+Replace the SDXL model with a model like [stable-diffusion-v1-5/stable-diffusion-v1-5](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) to use multiple conditioning inputs with Stable Diffusion models.
 
 </Tip>
 

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

@@ -61,7 +61,7 @@ feature_extractor = CLIPImageProcessor.from_pretrained(clip_model_id)
 clip_model = CLIPModel.from_pretrained(clip_model_id)
 
 pipeline = DiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
     custom_pipeline="clip_guided_stable_diffusion",
     clip_model=clip_model,
     feature_extractor=feature_extractor,
@@ -78,7 +78,7 @@ Community pipelines can also be loaded from a local file if you pass a file path
 
 ```py
 pipeline = DiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
     custom_pipeline="./path/to/pipeline_directory/",
     clip_model=clip_model,
     feature_extractor=feature_extractor,
@@ -97,7 +97,7 @@ For example, to load from the main branch:
 
 ```py
 pipeline = DiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
     custom_pipeline="clip_guided_stable_diffusion",
     custom_revision="main",
     clip_model=clip_model,
@@ -113,7 +113,7 @@ For example, to load from a previous version of Diffusers like v0.25.0:
 
 ```py
 pipeline = DiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
     custom_pipeline="clip_guided_stable_diffusion",
     custom_revision="v0.25.0",
     clip_model=clip_model,
@@ -235,7 +235,7 @@ from diffusers import DiffusionPipeline, DDIMScheduler
 from diffusers.utils import load_image
 
 pipeline = DiffusionPipeline.from_pretrained(
-    "Lykon/dreamshaper-8-inpainting",
+    "stable-diffusion-v1-5/stable-diffusion-v1-5-inpainting",
     custom_pipeline="hd_painter"
 )
 pipeline.scheduler = DDIMScheduler.from_config(pipeline.scheduler.config)

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

@@ -30,7 +30,7 @@ import torch
 from diffusers import DiffusionPipeline
 
 pipeline = DiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, safety_checker=None
+    "stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16, safety_checker=None
 ).to("cuda")
 pipeline.enable_freeu(s1=0.9, s2=0.2, b1=1.5, b2=1.6)
 generator = torch.Generator(device="cpu").manual_seed(33)

docs/source/en/using-diffusers/img2img.md

@@ -66,7 +66,7 @@ make_image_grid([init_image, image], rows=1, cols=2)
 
 ## Popular models
 
-The most popular image-to-image models are [Stable Diffusion v1.5](https://huggingface.co/runwayml/stable-diffusion-v1-5), [Stable Diffusion XL (SDXL)](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0), and [Kandinsky 2.2](https://huggingface.co/kandinsky-community/kandinsky-2-2-decoder). The results from the Stable Diffusion and Kandinsky models vary due to their architecture differences and training process; you can generally expect SDXL to produce higher quality images than Stable Diffusion v1.5. Let's take a quick look at how to use each of these models and compare their results.
+The most popular image-to-image models are [Stable Diffusion v1.5](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5), [Stable Diffusion XL (SDXL)](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0), and [Kandinsky 2.2](https://huggingface.co/kandinsky-community/kandinsky-2-2-decoder). The results from the Stable Diffusion and Kandinsky models vary due to their architecture differences and training process; you can generally expect SDXL to produce higher quality images than Stable Diffusion v1.5. Let's take a quick look at how to use each of these models and compare their results.
 
 ### Stable Diffusion v1.5
 
@@ -78,7 +78,7 @@ from diffusers import AutoPipelineForImage2Image
 from diffusers.utils import make_image_grid, load_image
 
 pipeline = AutoPipelineForImage2Image.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
+    "stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
 )
 pipeline.enable_model_cpu_offload()
 # remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
@@ -203,7 +203,7 @@ from diffusers import AutoPipelineForImage2Image
 from diffusers.utils import make_image_grid, load_image
 
 pipeline = AutoPipelineForImage2Image.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
+    "stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
 )
 pipeline.enable_model_cpu_offload()
 # remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
@@ -247,7 +247,7 @@ from diffusers import AutoPipelineForImage2Image
 from diffusers.utils import make_image_grid, load_image
 
 pipeline = AutoPipelineForImage2Image.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
+    "stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
 )
 pipeline.enable_model_cpu_offload()
 # remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
@@ -334,7 +334,7 @@ import torch
 from diffusers.utils import make_image_grid
 
 pipeline = AutoPipelineForText2Image.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
+    "stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
 )
 pipeline.enable_model_cpu_offload()
 # remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
@@ -370,7 +370,7 @@ from diffusers import AutoPipelineForImage2Image
 from diffusers.utils import make_image_grid, load_image
 
 pipeline = AutoPipelineForImage2Image.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
+    "stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
 )
 pipeline.enable_model_cpu_offload()
 # remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
@@ -433,7 +433,7 @@ from diffusers import AutoPipelineForImage2Image
 from diffusers.utils import make_image_grid, load_image
 
 pipeline = AutoPipelineForImage2Image.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
+    "stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
 )
 pipeline.enable_model_cpu_offload()
 # remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
@@ -499,7 +499,7 @@ from diffusers import AutoPipelineForImage2Image
 import torch
 
 pipeline = AutoPipelineForImage2Image.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
+    "stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
 )
 pipeline.enable_model_cpu_offload()
 # remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
@@ -536,7 +536,7 @@ import torch
 
 controlnet = ControlNetModel.from_pretrained("lllyasviel/control_v11f1p_sd15_depth", torch_dtype=torch.float16, variant="fp16", use_safetensors=True)
 pipeline = AutoPipelineForImage2Image.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16, variant="fp16", use_safetensors=True
+    "stable-diffusion-v1-5/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16, variant="fp16", use_safetensors=True
 )
 pipeline.enable_model_cpu_offload()
 # remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed

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

@@ -419,7 +419,7 @@ canny_image = Image.fromarray(image)
 
 controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", torch_dtype=torch.float16)
 pipe = StableDiffusionControlNetPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
     controlnet=controlnet,
     torch_dtype=torch.float16,
     safety_checker=None,

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

@@ -35,7 +35,7 @@ This guide will show you how to perform inference with TCD-LoRAs for a variety o
 
 | Base model                                                                                      | TCD-LoRA checkpoint                                            |
 |-------------------------------------------------------------------------------------------------|----------------------------------------------------------------|
-| [stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5)                  | [TCD-SD15](https://huggingface.co/h1t/TCD-SD15-LoRA)           |
+| [stable-diffusion-v1-5](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5)                  | [TCD-SD15](https://huggingface.co/h1t/TCD-SD15-LoRA)           |
 | [stable-diffusion-2-1-base](https://huggingface.co/stabilityai/stable-diffusion-2-1-base)       | [TCD-SD21-base](https://huggingface.co/h1t/TCD-SD21-base-LoRA) |
 | [stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) | [TCD-SDXL](https://huggingface.co/h1t/TCD-SDXL-LoRA)           |
 

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

@@ -95,7 +95,7 @@ from diffusers import AutoPipelineForInpainting
 from diffusers.utils import load_image
 from PIL import Image
 
-pipeline = AutoPipelineForInpainting.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16).to('cuda')
+pipeline = AutoPipelineForInpainting.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16).to('cuda')
 
 mask = load_image("https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/seashore_mask.png")
 blurred_mask = pipeline.mask_processor.blur(mask, blur_factor=33)
@@ -216,12 +216,13 @@ make_image_grid([init_image, mask_image, image], rows=1, cols=3)
 
 ## Non-inpaint specific checkpoints
 
-So far, this guide has used inpaint specific checkpoints such as [runwayml/stable-diffusion-inpainting](https://huggingface.co/runwayml/stable-diffusion-inpainting). But you can also use regular checkpoints like [runwayml/stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5). Let's compare the results of the two checkpoints.
+
+So far, this guide has used inpaint specific checkpoints such as [stable-diffusion-v1-5/stable-diffusion-inpainting](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-inpainting). But you can also use regular checkpoints like [stable-diffusion-v1-5/stable-diffusion-v1-5](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5). Let's compare the results of the two checkpoints.
 
 The image on the left is generated from a regular checkpoint, and the image on the right is from an inpaint checkpoint. You'll immediately notice the image on the left is not as clean, and you can still see the outline of the area the model is supposed to inpaint. The image on the right is much cleaner and the inpainted area appears more natural.
 
 <hfoptions id="regular-specific">
-<hfoption id="runwayml/stable-diffusion-v1-5">
+<hfoption id="stable-diffusion-v1-5/stable-diffusion-v1-5">
 
 ```py
 import torch
@@ -229,7 +230,7 @@ from diffusers import AutoPipelineForInpainting
 from diffusers.utils import load_image, make_image_grid
 
 pipeline = AutoPipelineForInpainting.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, variant="fp16"
+    "stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16, variant="fp16"
 )
 pipeline.enable_model_cpu_offload()
 # remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
@@ -276,7 +277,7 @@ make_image_grid([init_image, image], rows=1, cols=2)
 <div class="flex gap-4">
   <div>
     <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/non-inpaint-specific.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">runwayml/stable-diffusion-v1-5</figcaption>
+    <figcaption class="mt-2 text-center text-sm text-gray-500">stable-diffusion-v1-5/stable-diffusion-v1-5</figcaption>
   </div>
   <div>
     <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint-specific.png"/>
@@ -287,7 +288,7 @@ make_image_grid([init_image, image], rows=1, cols=2)
 However, for more basic tasks like erasing an object from an image (like the rocks in the road for example), a regular checkpoint yields pretty good results. There isn't as noticeable of difference between the regular and inpaint checkpoint.
 
 <hfoptions id="inpaint">
-<hfoption id="runwayml/stable-diffusion-v1-5">
+<hfoption id="stable-diffusion-v1-5/stable-diffusion-v1-5">
 
 ```py
 import torch
@@ -295,7 +296,7 @@ from diffusers import AutoPipelineForInpainting
 from diffusers.utils import load_image, make_image_grid
 
 pipeline = AutoPipelineForInpainting.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, variant="fp16"
+    "stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16, variant="fp16"
 )
 pipeline.enable_model_cpu_offload()
 # remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
@@ -338,7 +339,7 @@ make_image_grid([init_image, image], rows=1, cols=2)
 <div class="flex gap-4">
   <div>
     <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/regular-inpaint-basic.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">runwayml/stable-diffusion-v1-5</figcaption>
+    <figcaption class="mt-2 text-center text-sm text-gray-500">stable-diffusion-v1-5/stable-diffusion-v1-5</figcaption>
   </div>
   <div>
     <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/specific-inpaint-basic.png"/>
@@ -518,7 +519,7 @@ from diffusers.utils import load_image
 from PIL import Image
 
 generator = torch.Generator(device='cuda').manual_seed(0)
-pipeline = AutoPipelineForInpainting.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16).to('cuda')
+pipeline = AutoPipelineForInpainting.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16).to('cuda')
 
 base = load_image("https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/seashore.png")
 mask = load_image("https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/seashore_mask.png")
@@ -554,7 +555,7 @@ from diffusers import AutoPipelineForText2Image, AutoPipelineForInpainting
 from diffusers.utils import load_image, make_image_grid
 
 pipeline = AutoPipelineForText2Image.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
+    "stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
 )
 pipeline.enable_model_cpu_offload()
 # remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed

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

@@ -380,7 +380,7 @@ from diffusers import StableDiffusionPipeline, DDIMScheduler
 from diffusers.utils import load_image
 
 pipeline = StableDiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
     torch_dtype=torch.float16,
 ).to("cuda")
 pipeline.scheduler = DDIMScheduler.from_config(pipeline.scheduler.config)
@@ -421,7 +421,7 @@ from diffusers.utils import load_image
 from insightface.app import FaceAnalysis
 
 pipeline = StableDiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
     torch_dtype=torch.float16,
 ).to("cuda")
 pipeline.scheduler = DDIMScheduler.from_config(pipeline.scheduler.config)
@@ -617,7 +617,7 @@ controlnet_model_path = "lllyasviel/control_v11f1p_sd15_depth"
 controlnet = ControlNetModel.from_pretrained(controlnet_model_path, torch_dtype=torch.float16)
 
 pipeline = StableDiffusionControlNetPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16)
+    "stable-diffusion-v1-5/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16)
 pipeline.to("cuda")
 pipeline.load_ip_adapter("h94/IP-Adapter", subfolder="models", weight_name="ip-adapter_sd15.bin")
 ```

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

@@ -41,7 +41,7 @@ The [`DiffusionPipeline`] class is a simple and generic way to load the latest t
 ```python
 from diffusers import DiffusionPipeline
 
-pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", use_safetensors=True)
+pipeline = DiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", use_safetensors=True)
 ```
 
 This same checkpoint can also be used for an image-to-image task. The [`DiffusionPipeline`] class can handle any task as long as you provide the appropriate inputs. For example, for an image-to-image task, you need to pass an initial image to the pipeline.
@@ -49,7 +49,7 @@ This same checkpoint can also be used for an image-to-image task. The [`Diffusio
 ```py
 from diffusers import DiffusionPipeline
 
-pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", use_safetensors=True)
+pipeline = DiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", use_safetensors=True)
 
 init_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/img2img-init.png")
 prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
@@ -64,7 +64,7 @@ Checkpoints can be loaded by their specific pipeline class if you already know i
 ```python
 from diffusers import StableDiffusionPipeline
 
-pipeline = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", use_safetensors=True)
+pipeline = StableDiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", use_safetensors=True)
 ```
 
 This same checkpoint may also be used for another task like image-to-image. To differentiate what task you want to use the checkpoint for, you have to use the corresponding task-specific pipeline class. For example, to use the same checkpoint for image-to-image, use the [`StableDiffusionImg2ImgPipeline`] class.
@@ -72,7 +72,7 @@ This same checkpoint may also be used for another task like image-to-image. To d
 ```py
 from diffusers import StableDiffusionImg2ImgPipeline
 
-pipeline = StableDiffusionImg2ImgPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", use_safetensors=True)
+pipeline = StableDiffusionImg2ImgPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", use_safetensors=True)
 ```
 
 </hfoption>
@@ -101,7 +101,7 @@ To load a pipeline locally, use [git-lfs](https://git-lfs.github.com/) to manual
 
 ```bash
 git-lfs install
-git clone https://huggingface.co/runwayml/stable-diffusion-v1-5
+git clone https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5
 ```
 
 This creates a local folder, ./stable-diffusion-v1-5, on your disk and you should pass its path to [`~DiffusionPipeline.from_pretrained`].
@@ -311,7 +311,7 @@ Diffusers implements a [safety checker](https://github.com/huggingface/diffusers
 ```python
 from diffusers import DiffusionPipeline
 
-pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", safety_checker=None, use_safetensors=True)
+pipeline = DiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", safety_checker=None, use_safetensors=True)
 """
 You have disabled the safety checker for <class 'diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline'> by passing `safety_checker=None`. Ensure that you abide by the conditions of the Stable Diffusion license and do not expose unfiltered results in services or applications open to the public. Both the diffusers team and Hugging Face strongly recommend keeping the safety filter enabled in all public-facing circumstances, disabling it only for use cases that involve analyzing network behavior or auditing its results. For more information, please have a look at https://github.com/huggingface/diffusers/pull/254 .
 """
@@ -341,7 +341,7 @@ There are two important arguments for loading variants:
 
   If you only set `torch_dtype=torch.float16`, the default fp32 weights are downloaded first and then converted to fp16.
 
-- `variant` specifies which files should be loaded from the repository. For example, if you want to load a non-EMA variant of a UNet from [runwayml/stable-diffusion-v1-5](https://hf.co/runwayml/stable-diffusion-v1-5/tree/main/unet), set `variant="non_ema"` to download the `non_ema` file.
+- `variant` specifies which files should be loaded from the repository. For example, if you want to load a non-EMA variant of a UNet from [stable-diffusion-v1-5/stable-diffusion-v1-5](https://hf.co/stable-diffusion-v1-5/stable-diffusion-v1-5/tree/main/unet), set `variant="non_ema"` to download the `non_ema` file.
 
 <hfoptions id="variants">
 <hfoption id="fp16">
@@ -351,7 +351,7 @@ from diffusers import DiffusionPipeline
 import torch
 
 pipeline = DiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", variant="fp16", torch_dtype=torch.float16, use_safetensors=True
+    "stable-diffusion-v1-5/stable-diffusion-v1-5", variant="fp16", torch_dtype=torch.float16, use_safetensors=True
 )
 ```
 
@@ -360,7 +360,7 @@ pipeline = DiffusionPipeline.from_pretrained(
 
 ```py
 pipeline = DiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", variant="non_ema", use_safetensors=True
+    "stable-diffusion-v1-5/stable-diffusion-v1-5", variant="non_ema", use_safetensors=True
 )
 ```
 
@@ -375,14 +375,14 @@ Use the `variant` parameter in the [`DiffusionPipeline.save_pretrained`] method
 ```python
 from diffusers import DiffusionPipeline
 
-pipeline.save_pretrained("runwayml/stable-diffusion-v1-5", variant="fp16")
+pipeline.save_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", variant="fp16")
 ```
 
 </hfoption>
 <hfoption id="non_ema">
 
 ```py
-pipeline.save_pretrained("runwayml/stable-diffusion-v1-5", variant="non_ema")
+pipeline.save_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", variant="non_ema")
 ```
 
 </hfoption>
@@ -408,12 +408,12 @@ As a class method, [`DiffusionPipeline.from_pretrained`] is responsible for two
 - Download the latest version of the folder structure required for inference and cache it. If the latest folder structure is available in the local cache, [`DiffusionPipeline.from_pretrained`] reuses the cache and won't redownload the files.
 - Load the cached weights into the correct pipeline [class](../api/pipelines/overview#diffusers-summary) - retrieved from the `model_index.json` file - and return an instance of it.
 
-The pipelines' underlying folder structure corresponds directly with their class instances. For example, the [`StableDiffusionPipeline`] corresponds to the folder structure in [`runwayml/stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5).
+The pipelines' underlying folder structure corresponds directly with their class instances. For example, the [`StableDiffusionPipeline`] corresponds to the folder structure in [`stable-diffusion-v1-5/stable-diffusion-v1-5`](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5).
 
 ```python
 from diffusers import DiffusionPipeline
 
-repo_id = "runwayml/stable-diffusion-v1-5"
+repo_id = "stable-diffusion-v1-5/stable-diffusion-v1-5"
 pipeline = DiffusionPipeline.from_pretrained(repo_id, use_safetensors=True)
 print(pipeline)
 ```
@@ -461,7 +461,7 @@ StableDiffusionPipeline {
 }
 ```
 
-Compare the components of the pipeline instance to the [`runwayml/stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5/tree/main) folder structure, and you'll see there is a separate folder for each of the components in the repository:
+Compare the components of the pipeline instance to the [`stable-diffusion-v1-5/stable-diffusion-v1-5`](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5/tree/main) folder structure, and you'll see there is a separate folder for each of the components in the repository:
 
 ```
 .
@@ -524,7 +524,7 @@ CLIPTokenizer(
 )
 ```
 
-Every pipeline expects a [`model_index.json`](https://huggingface.co/runwayml/stable-diffusion-v1-5/blob/main/model_index.json) file that tells the [`DiffusionPipeline`]:
+Every pipeline expects a [`model_index.json`](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5/blob/main/model_index.json) file that tells the [`DiffusionPipeline`]:
 
 - which pipeline class to load from `_class_name`
 - which version of 🧨 Diffusers was used to create the model in `_diffusers_version`

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

@@ -54,7 +54,7 @@ Because textual inversion creates embeddings, it cannot be used on its own like
 from diffusers import AutoPipelineForText2Image
 import torch
 
-pipeline = AutoPipelineForText2Image.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16).to("cuda")
+pipeline = AutoPipelineForText2Image.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16).to("cuda")
 ```
 
 Now you can load the textual inversion embeddings with the [`~loaders.TextualInversionLoaderMixin.load_textual_inversion`] method and generate some images. Let's load the [sd-concepts-library/gta5-artwork](https://huggingface.co/sd-concepts-library/gta5-artwork) embeddings and you'll need to include the special word `<gta5-artwork>` in your prompt to trigger it:
@@ -269,7 +269,7 @@ from diffusers import AutoPipelineForText2Image
 import torch
 from diffusers.utils import load_image
 
-pipeline = AutoPipelineForText2Image.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16).to("cuda")
+pipeline = AutoPipelineForText2Image.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16).to("cuda")
 ```
 
 Then load the IP-Adapter weights and add it to the pipeline with the [`~loaders.IPAdapterMixin.load_ip_adapter`] method.
@@ -350,7 +350,7 @@ image_encoder = CLIPVisionModelWithProjection.from_pretrained(
 )
 
 pipeline = AutoPipelineForText2Image.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
     image_encoder=image_encoder,
     torch_dtype=torch.float16
 ).to("cuda")

docs/source/en/using-diffusers/other-formats.md

@@ -37,7 +37,7 @@ Make sure you have the [Safetensors](https://hf.co/docs/safetensors) library ins
 
 Safetensors stores weights in a safetensors file. Diffusers loads safetensors files by default if they're available and the Safetensors library is installed. There are two ways safetensors files can be organized:
 
-1. Diffusers-multifolder layout: there may be several separate safetensors files, one for each pipeline component (text encoder, UNet, VAE), organized in subfolders (check out the [runwayml/stable-diffusion-v1-5](https://hf.co/runwayml/stable-diffusion-v1-5/tree/main) repository as an example)
+1. Diffusers-multifolder layout: there may be several separate safetensors files, one for each pipeline component (text encoder, UNet, VAE), organized in subfolders (check out the [stable-diffusion-v1-5/stable-diffusion-v1-5](https://hf.co/stable-diffusion-v1-5/stable-diffusion-v1-5/tree/main) repository as an example)
 2. single-file layout: all the model weights may be saved in a single file (check out the [WarriorMama777/OrangeMixs](https://hf.co/WarriorMama777/OrangeMixs/tree/main/Models/AbyssOrangeMix) repository as an example)
 
 <hfoptions id="safetensors">
@@ -49,7 +49,7 @@ Use the [`~DiffusionPipeline.from_pretrained`] method to load a model with safet
 from diffusers import DiffusionPipeline
 
 pipeline = DiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
     use_safetensors=True
 )
 ```
@@ -118,7 +118,7 @@ Use the [`~loaders.FromSingleFileMixin.from_single_file`] method to directly loa
 from diffusers import StableDiffusionPipeline
 
 pipeline = StableDiffusionPipeline.from_single_file(
-    "https://huggingface.co/runwayml/stable-diffusion-v1-5/blob/main/v1-5-pruned.ckpt"
+    "https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5/blob/main/v1-5-pruned.ckpt"
 )
 ```
 
@@ -314,7 +314,7 @@ Or you could use a ControlNet model in the pipeline.
 ```py
 from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
 
-ckpt_path = "https://huggingface.co/runwayml/stable-diffusion-v1-5/blob/main/v1-5-pruned-emaonly.safetensors"
+ckpt_path = "https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5/blob/main/v1-5-pruned-emaonly.safetensors"
 controlnet = ControlNetModel.from_pretrained("lllyasviel/control_v11p_sd15_canny")
 pipeline = StableDiffusionControlNetPipeline.from_single_file(ckpt_path, controlnet=controlnet)
 ```

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

@@ -121,7 +121,7 @@ Now when you run the same pipeline twice, you'll get identical results.
 import torch
 from diffusers import DDIMScheduler, StableDiffusionPipeline
 
-pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", use_safetensors=True).to("cuda")
+pipe = StableDiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", use_safetensors=True).to("cuda")
 pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config)
 g = torch.Generator(device="cuda")
 
@@ -141,7 +141,7 @@ print("L_inf dist =", abs(result1 - result2).max())
 
 A practical application of creating reproducible pipelines is *deterministic batch generation*. You generate a batch of images and select one image to improve with a more detailed prompt. The main idea is to pass a list of [Generator's](https://pytorch.org/docs/stable/generated/torch.Generator.html) to the pipeline and tie each `Generator` to a seed so you can reuse it.
 
-Let's use the [runwayml/stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5) checkpoint and generate a batch of images.
+Let's use the [stable-diffusion-v1-5/stable-diffusion-v1-5](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) checkpoint and generate a batch of images.
 
 ```py
 import torch
@@ -149,7 +149,7 @@ from diffusers import DiffusionPipeline
 from diffusers.utils import make_image_grid
 
 pipeline = DiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True
+    "stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True
 )
 pipeline = pipeline.to("cuda")
 ```

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

@@ -16,14 +16,14 @@ specific language governing permissions and limitations under the License.
 
 Diffusion pipelines are a collection of interchangeable schedulers and models that can be mixed and matched to tailor a pipeline to a specific use case. The scheduler encapsulates the entire denoising process such as the number of denoising steps and the algorithm for finding the denoised sample. A scheduler is not parameterized or trained so they don't take very much memory. The model is usually only concerned with the forward pass of going from a noisy input to a less noisy sample.
 
-This guide will show you how to load schedulers and models to customize a pipeline. You'll use the [runwayml/stable-diffusion-v1-5](https://hf.co/runwayml/stable-diffusion-v1-5) checkpoint throughout this guide, so let's load it first.
+This guide will show you how to load schedulers and models to customize a pipeline. You'll use the [stable-diffusion-v1-5/stable-diffusion-v1-5](https://hf.co/stable-diffusion-v1-5/stable-diffusion-v1-5) checkpoint throughout this guide, so let's load it first.
 
 ```py
 import torch
 from diffusers import DiffusionPipeline
 
 pipeline = DiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True
+    "stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True
 ).to("cuda")
 ```
 
@@ -56,14 +56,14 @@ For example, to load the [`DDIMScheduler`]:
 ```py
 from diffusers import DDIMScheduler, DiffusionPipeline
 
-ddim = DDIMScheduler.from_pretrained("runwayml/stable-diffusion-v1-5", subfolder="scheduler")
+ddim = DDIMScheduler.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", subfolder="scheduler")
 ```
 
 Then you can pass the newly loaded scheduler to the pipeline.
 
 ```python
 pipeline = DiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", scheduler=ddim, torch_dtype=torch.float16, use_safetensors=True
+    "stable-diffusion-v1-5/stable-diffusion-v1-5", scheduler=ddim, torch_dtype=torch.float16, use_safetensors=True
 ).to("cuda")
 ```
 
@@ -78,7 +78,7 @@ import torch
 from diffusers import DiffusionPipeline
 
 pipeline = DiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True
+    "stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True
 ).to("cuda")
 
 prompt = "A photograph of an astronaut riding a horse on Mars, high resolution, high definition."
@@ -180,11 +180,11 @@ from flax.training.common_utils import shard
 from diffusers import FlaxStableDiffusionPipeline, FlaxDPMSolverMultistepScheduler
 
 scheduler, scheduler_state = FlaxDPMSolverMultistepScheduler.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
     subfolder="scheduler"
 )
 pipeline, params = FlaxStableDiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
     scheduler=scheduler,
     variant="bf16",
     dtype=jax.numpy.bfloat16,
@@ -216,12 +216,12 @@ images = pipeline.numpy_to_pil(np.asarray(images.reshape((num_samples,) + images
 
 Models are loaded from the [`ModelMixin.from_pretrained`] method, which downloads and caches the latest version of the model weights and configurations. If the latest files are available in the local cache, [`~ModelMixin.from_pretrained`] reuses files in the cache instead of re-downloading them.
 
-Models can be loaded from a subfolder with the `subfolder` argument. For example, the model weights for [runwayml/stable-diffusion-v1-5](https://hf.co/runwayml/stable-diffusion-v1-5) are stored in the [unet](https://hf.co/runwayml/stable-diffusion-v1-5/tree/main/unet) subfolder.
+Models can be loaded from a subfolder with the `subfolder` argument. For example, the model weights for [stable-diffusion-v1-5/stable-diffusion-v1-5](https://hf.co/stable-diffusion-v1-5/stable-diffusion-v1-5) are stored in the [unet](https://hf.co/stable-diffusion-v1-5/stable-diffusion-v1-5/tree/main/unet) subfolder.
 
 ```python
 from diffusers import UNet2DConditionModel
 
-unet = UNet2DConditionModel.from_pretrained("runwayml/stable-diffusion-v1-5", subfolder="unet", use_safetensors=True)
+unet = UNet2DConditionModel.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", subfolder="unet", use_safetensors=True)
 ```
 
 They can also be directly loaded from a [repository](https://huggingface.co/google/ddpm-cifar10-32/tree/main).
@@ -238,7 +238,7 @@ To load and save model variants, specify the `variant` argument in [`ModelMixin.
 from diffusers import UNet2DConditionModel
 
 unet = UNet2DConditionModel.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", subfolder="unet", variant="non_ema", use_safetensors=True
+    "stable-diffusion-v1-5/stable-diffusion-v1-5", subfolder="unet", variant="non_ema", use_safetensors=True
 )
 unet.save_pretrained("./local-unet", variant="non_ema")
 ```

docs/source/en/using-diffusers/t2i_adapter.md

@@ -73,7 +73,7 @@ from diffusers import StableDiffusionAdapterPipeline, T2IAdapter
 
 adapter = T2IAdapter.from_pretrained("TencentARC/t2iadapter_canny_sd15v2", torch_dtype=torch.float16)
 pipeline = StableDiffusionAdapterPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
     adapter=adapter,
     torch_dtype=torch.float16,
 )

docs/source/en/using-diffusers/text-img2vid.md

@@ -365,7 +365,7 @@ import torch
 from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
 from diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_zero import CrossFrameAttnProcessor
 
-model_id = "runwayml/stable-diffusion-v1-5"
+model_id = "stable-diffusion-v1-5/stable-diffusion-v1-5"
 controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-openpose", torch_dtype=torch.float16)
 pipeline = StableDiffusionControlNetPipeline.from_pretrained(
     model_id, controlnet=controlnet, torch_dtype=torch.float16
@@ -411,7 +411,7 @@ import torch
 from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
 from diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_zero import CrossFrameAttnProcessor
 
-model_id = "runwayml/stable-diffusion-v1-5"
+model_id = "stable-diffusion-v1-5/stable-diffusion-v1-5"
 controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", torch_dtype=torch.float16)
 pipeline = StableDiffusionControlNetPipeline.from_pretrained(
     model_id, controlnet=controlnet, torch_dtype=torch.float16

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

@@ -31,7 +31,7 @@ from diffusers.utils import make_image_grid
 Pick a Stable Diffusion checkpoint and a pre-learned concept from the [Stable Diffusion Conceptualizer](https://huggingface.co/spaces/sd-concepts-library/stable-diffusion-conceptualizer):
 
 ```py
-pretrained_model_name_or_path = "runwayml/stable-diffusion-v1-5"
+pretrained_model_name_or_path = "stable-diffusion-v1-5/stable-diffusion-v1-5"
 repo_id_embeds = "sd-concepts-library/cat-toy"
 ```
 

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

@@ -366,7 +366,7 @@ from diffusers import StableDiffusionPipeline
 from compel import Compel, DiffusersTextualInversionManager
 
 pipe = StableDiffusionPipeline.from_pretrained(
-  "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16,
+  "stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16,
   use_safetensors=True, variant="fp16").to("cuda")
 pipe.load_textual_inversion("sd-concepts-library/midjourney-style")
 ```

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

@@ -116,7 +116,7 @@ As you can see, this is already more complex than the DDPM pipeline which only c
 
 </Tip>
 
-Now that you know what you need for the Stable Diffusion pipeline, load all these components with the [`~ModelMixin.from_pretrained`] method. You can find them in the pretrained [`runwayml/stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5) checkpoint, and each component is stored in a separate subfolder:
+Now that you know what you need for the Stable Diffusion pipeline, load all these components with the [`~ModelMixin.from_pretrained`] method. You can find them in the pretrained [`stable-diffusion-v1-5/stable-diffusion-v1-5`](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) checkpoint, and each component is stored in a separate subfolder:
 
 ```py
 >>> from PIL import Image

docs/source/ja/quicktour.md

@@ -54,7 +54,7 @@ specific language governing permissions and limitations under the License.
 
 まず、[`DiffusionPipeline`]のインスタンスを作成し、ダウンロードしたいパイプラインのチェックポイントを指定します。
 この[`DiffusionPipeline`]はHugging Face Hubに保存されている任意の[チェックポイント](https://huggingface.co/models?library=diffusers&sort=downloads)を使用することができます。
-この案内では、[`stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5)チェックポイントでテキストから画像へ生成します。
+この案内では、[`stable-diffusion-v1-5`](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5)チェックポイントでテキストから画像へ生成します。
 
 <Tip warning={true}>
 
@@ -67,7 +67,7 @@ specific language governing permissions and limitations under the License.
 ```python
 >>> from diffusers import DiffusionPipeline
 
->>> pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", use_safetensors=True)
+>>> pipeline = DiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", use_safetensors=True)
 ```
 [`DiffusionPipeline`]は全てのモデリング、トークン化、スケジューリングコンポーネントをダウンロードしてキャッシュします。Stable Diffusionパイプラインは[`UNet2DConditionModel`]と[`PNDMScheduler`]などで構成されています：
 
@@ -123,7 +123,7 @@ PyTorchと同じように、ジェネレータオブジェクトをGPUに移す
 
 ```bash
 !git lfs install
-!git clone https://huggingface.co/runwayml/stable-diffusion-v1-5
+!git clone https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5
 ```
 
 保存したウェイトをパイプラインにロードします：
@@ -141,7 +141,7 @@ PyTorchと同じように、ジェネレータオブジェクトをGPUに移す
 ```py
 >>> from diffusers import EulerDiscreteScheduler
 
->>> pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", use_safetensors=True)
+>>> pipeline = DiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", use_safetensors=True)
 >>> pipeline.scheduler = EulerDiscreteScheduler.from_config(pipeline.scheduler.config)
 ```
 

docs/source/ja/stable_diffusion.md

@@ -20,12 +20,12 @@ specific language governing permissions and limitations under the License.
 
 このチュートリアルでは、[`DiffusionPipeline`]を用いて、より速く、より良い計算を行う方法を説明します。
 
-まず、[`runwayml/stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5)モデルをロードします：
+まず、[`stable-diffusion-v1-5/stable-diffusion-v1-5`](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5)モデルをロードします：
 
 ```python
 from diffusers import DiffusionPipeline
 
-model_id = "runwayml/stable-diffusion-v1-5"
+model_id = "stable-diffusion-v1-5/stable-diffusion-v1-5"
 pipeline = DiffusionPipeline.from_pretrained(model_id, use_safetensors=True)
 ```
 

docs/source/ja/tutorials/autopipeline.md

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # AutoPipeline
 
-Diffusersは様々なタスクをこなすことができ、テキストから画像、画像から画像、画像の修復など、複数のタスクに対して同じように事前学習された重みを再利用することができます。しかし、ライブラリや拡散モデルに慣れていない場合、どのタスクにどのパイプラインを使えばいいのかがわかりにくいかもしれません。例えば、 [runwayml/stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5) チェックポイントをテキストから画像に変換するために使用している場合、それぞれ[`StableDiffusionImg2ImgPipeline`]クラスと[`StableDiffusionInpaintPipeline`]クラスでチェックポイントをロードすることで、画像から画像や画像の修復にも使えることを知らない可能性もあります。
+Diffusersは様々なタスクをこなすことができ、テキストから画像、画像から画像、画像の修復など、複数のタスクに対して同じように事前学習された重みを再利用することができます。しかし、ライブラリや拡散モデルに慣れていない場合、どのタスクにどのパイプラインを使えばいいのかがわかりにくいかもしれません。例えば、 [stable-diffusion-v1-5/stable-diffusion-v1-5](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) チェックポイントをテキストから画像に変換するために使用している場合、それぞれ[`StableDiffusionImg2ImgPipeline`]クラスと[`StableDiffusionInpaintPipeline`]クラスでチェックポイントをロードすることで、画像から画像や画像の修復にも使えることを知らない可能性もあります。
 
 `AutoPipeline` クラスは、🤗 Diffusers の様々なパイプラインをよりシンプルするために設計されています。この汎用的でタスク重視のパイプラインによってタスクそのものに集中することができます。`AutoPipeline` は、使用するべき正しいパイプラインクラスを自動的に検出するため、特定のパイプラインクラス名を知らなくても、タスクのチェックポイントを簡単にロードできます。
 
@@ -25,14 +25,14 @@ Diffusersは様々なタスクをこなすことができ、テキストから
 このチュートリアルでは、`AutoPipeline` を使用して、事前に学習された重みが与えられたときに、特定のタスクを読み込むためのパイプラインクラスを自動的に推測する方法を示します。
 
 ## タスクに合わせてAutoPipeline を選択する
-まずはチェックポイントを選ぶことから始めましょう。例えば、 [runwayml/stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5) チェックポイントでテキストから画像への変換したいなら、[`AutoPipelineForText2Image`]を使います:
+まずはチェックポイントを選ぶことから始めましょう。例えば、 [stable-diffusion-v1-5/stable-diffusion-v1-5](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) チェックポイントでテキストから画像への変換したいなら、[`AutoPipelineForText2Image`]を使います:
 
 ```py
 from diffusers import AutoPipelineForText2Image
 import torch
 
 pipeline = AutoPipelineForText2Image.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True
+    "stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True
 ).to("cuda")
 prompt = "peasant and dragon combat, wood cutting style, viking era, bevel with rune"
 
@@ -46,7 +46,7 @@ image
 
 [`AutoPipelineForText2Image`] を具体的に見ていきましょう:
 
-1. [`model_index.json`](https://huggingface.co/runwayml/stable-diffusion-v1-5/blob/main/model_index.json) ファイルから `"stable-diffusion"` クラスを自動的に検出します。
+1. [`model_index.json`](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5/blob/main/model_index.json) ファイルから `"stable-diffusion"` クラスを自動的に検出します。
 2. `"stable-diffusion"` のクラス名に基づいて、テキストから画像へ変換する [`StableDiffusionPipeline`] を読み込みます。
 
 同様に、画像から画像へ変換する場合、[`AutoPipelineForImage2Image`] は `model_index.json` ファイルから `"stable-diffusion"` チェックポイントを検出し、対応する [`StableDiffusionImg2ImgPipeline`] を読み込みます。また、入力画像にノイズの量やバリエーションの追加を決めるための強さなど、パイプラインクラスに固有の追加引数を渡すこともできます:
@@ -59,7 +59,7 @@ from PIL import Image
 from io import BytesIO
 
 pipeline = AutoPipelineForImage2Image.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
     torch_dtype=torch.float16,
     use_safetensors=True,
 ).to("cuda")
@@ -128,7 +128,7 @@ from diffusers import AutoPipelineForText2Image, AutoPipelineForImage2Image
 import torch
 
 pipeline_text2img = AutoPipelineForText2Image.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True
+    "stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True
 )
 print(type(pipeline_text2img))
 "<class 'diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline'>"
@@ -148,7 +148,7 @@ from diffusers import AutoPipelineForText2Image, AutoPipelineForImage2Image
 import torch
 
 pipeline_text2img = AutoPipelineForText2Image.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
     torch_dtype=torch.float16,
     use_safetensors=True,
     requires_safety_checker=False,

docs/source/ko/conceptual/evaluation.md

@@ -88,7 +88,7 @@ images = sd_pipeline(sample_prompts, num_images_per_prompt=1, generator=generato
 ![parti-prompts-14](https://huggingface.co/datasets/diffusers/docs-images/resolve/main/evaluation_diffusion_models/parti-prompts-14.png)
 
 
-`num_images_per_prompt`를 설정하여 동일한 프롬프트에 대해 다른 이미지를 비교할 수도 있습니다. 다른 체크포인트([v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5))로 동일한 파이프라인을 실행하면 다음과 같은 결과가 나옵니다:
+`num_images_per_prompt`를 설정하여 동일한 프롬프트에 대해 다른 이미지를 비교할 수도 있습니다. 다른 체크포인트([v1-5](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5))로 동일한 파이프라인을 실행하면 다음과 같은 결과가 나옵니다:
 
 ![parti-prompts-15](https://huggingface.co/datasets/diffusers/docs-images/resolve/main/evaluation_diffusion_models/parti-prompts-15.png)
 
@@ -170,10 +170,10 @@ generator = torch.manual_seed(seed)
 images = sd_pipeline(prompts, num_images_per_prompt=1, generator=generator, output_type="np").images
 ```
 
-그런 다음 [v1-5 checkpoint](https://huggingface.co/runwayml/stable-diffusion-v1-5)를 로드하여 이미지를 생성합니다:
+그런 다음 [v1-5 checkpoint](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5)를 로드하여 이미지를 생성합니다:
 
 ```python
-model_ckpt_1_5 = "runwayml/stable-diffusion-v1-5"
+model_ckpt_1_5 = "stable-diffusion-v1-5/stable-diffusion-v1-5"
 sd_pipeline_1_5 = StableDiffusionPipeline.from_pretrained(model_ckpt_1_5, torch_dtype=weight_dtype).to(device)
 
 images_1_5 = sd_pipeline_1_5(prompts, num_images_per_prompt=1, generator=generator, output_type="np").images
@@ -191,7 +191,7 @@ print(f"CLIP Score with v-1-5: {sd_clip_score_1_5}")
 # CLIP Score with v-1-5: 36.2137
 ```
 
-[v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5) 체크포인트가 이전 버전보다 더 나은 성능을 보이는 것 같습니다. 그러나 CLIP 점수를 계산하기 위해 사용한 프롬프트의 수가 상당히 적습니다. 보다 실용적인 평가를 위해서는 이 수를 훨씬 높게 설정하고, 프롬프트를 다양하게 사용해야 합니다.
+[v1-5](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) 체크포인트가 이전 버전보다 더 나은 성능을 보이는 것 같습니다. 그러나 CLIP 점수를 계산하기 위해 사용한 프롬프트의 수가 상당히 적습니다. 보다 실용적인 평가를 위해서는 이 수를 훨씬 높게 설정하고, 프롬프트를 다양하게 사용해야 합니다.
 
 <Tip warning={true}>
 

docs/source/ko/conceptual/philosophy.md

@@ -59,7 +59,7 @@ Diffusers에서는 이러한 철학을 파이프라인과 스케줄러에 모두
 다음과 같은 설계 원칙을 따릅니다:
 - 파이프라인은 단일 파일 정책을 따릅니다. 모든 파이프라인은 src/diffusers/pipelines의 개별 디렉토리에 있습니다. 하나의 파이프라인 폴더는 하나의 diffusion 논문/프로젝트/릴리스에 해당합니다. 여러 파이프라인 파일은 하나의 파이프라인 폴더에 모을 수 있습니다. 예를 들어 [`src/diffusers/pipelines/stable-diffusion`](https://github.com/huggingface/diffusers/tree/main/src/diffusers/pipelines/stable_diffusion)에서 그렇게 하고 있습니다. 파이프라인이 유사한 기능을 공유하는 경우, [# Copied from mechanism](https://github.com/huggingface/diffusers/blob/125d783076e5bd9785beb05367a2d2566843a271/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py#L251)을 사용할 수 있습니다.
 - 파이프라인은 모두 [`DiffusionPipeline`]을 상속합니다.
-- 각 파이프라인은 서로 다른 모델 및 스케줄러 구성 요소로 구성되어 있으며, 이는 [`model_index.json` 파일](https://huggingface.co/runwayml/stable-diffusion-v1-5/blob/main/model_index.json)에 문서화되어 있으며, 파이프라인의 속성 이름과 동일한 이름으로 액세스할 수 있으며, [`DiffusionPipeline.components`](https://huggingface.co/docs/diffusers/main/en/api/diffusion_pipeline#diffusers.DiffusionPipeline.components) 함수를 통해 파이프라인 간에 공유할 수 있습니다.
+- 각 파이프라인은 서로 다른 모델 및 스케줄러 구성 요소로 구성되어 있으며, 이는 [`model_index.json` 파일](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5/blob/main/model_index.json)에 문서화되어 있으며, 파이프라인의 속성 이름과 동일한 이름으로 액세스할 수 있으며, [`DiffusionPipeline.components`](https://huggingface.co/docs/diffusers/main/en/api/diffusion_pipeline#diffusers.DiffusionPipeline.components) 함수를 통해 파이프라인 간에 공유할 수 있습니다.
 - 각 파이프라인은 [`DiffusionPipeline.from_pretrained`](https://huggingface.co/docs/diffusers/main/en/api/diffusion_pipeline#diffusers.DiffusionPipeline.from_pretrained) 함수를 통해 로드할 수 있어야 합니다.
 - 파이프라인은 추론에**만** 사용되어야 합니다.
 - 파이프라인은 매우 가독성이 좋고, 이해하기 쉽고, 쉽게 조정할 수 있도록 설계되어야 합니다.

docs/source/ko/optimization/coreml.md

@@ -103,10 +103,10 @@ python -m python_coreml_stable_diffusion.pipeline --prompt "a photo of an astron
 
 추론 스크립트에서는 Stable Diffusion 모델의 원래 버전인 `CompVis/stable-diffusion-v1-4`를 사용한다고 가정합니다. 다른 모델을 사용하는 경우 추론 명령줄에서 `--model-version` 옵션을 사용하여 해당 허브 ID를 *지정*해야 합니다. 이는 이미 지원되는 모델과 사용자가 직접 학습하거나 파인튜닝한 사용자 지정 모델에 적용됩니다.
 
-예를 들어, [`runwayml/stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5)를 사용하려는 경우입니다:
+예를 들어, [`stable-diffusion-v1-5/stable-diffusion-v1-5`](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5)를 사용하려는 경우입니다:
 
 ```shell
-python -m python_coreml_stable_diffusion.pipeline --prompt "a photo of an astronaut riding a horse on mars" --compute-unit ALL -o output --seed 93 -i models/coreml-stable-diffusion-v1-5_original_packages --model-version runwayml/stable-diffusion-v1-5
+python -m python_coreml_stable_diffusion.pipeline --prompt "a photo of an astronaut riding a horse on mars" --compute-unit ALL -o output --seed 93 -i models/coreml-stable-diffusion-v1-5_original_packages --model-version stable-diffusion-v1-5/stable-diffusion-v1-5
 ```
 
 

docs/source/ko/optimization/fp16.md

@@ -64,7 +64,7 @@ torch.backends.cuda.matmul.allow_tf32 = True
 
 ```Python
 pipe = StableDiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
 
     torch_dtype=torch.float16,
 )
@@ -94,7 +94,7 @@ import torch
 from diffusers import StableDiffusionPipeline
 
 pipe = StableDiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
 
     torch_dtype=torch.float16,
 )
@@ -121,7 +121,7 @@ import torch
 from diffusers import StableDiffusionPipeline
 
 pipe = StableDiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
 
     torch_dtype=torch.float16,
 )
@@ -147,7 +147,7 @@ import torch
 from diffusers import StableDiffusionPipeline
 
 pipe = StableDiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
 
     torch_dtype=torch.float16,
 )
@@ -173,7 +173,7 @@ import torch
 from diffusers import StableDiffusionPipeline
 
 pipe = StableDiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
 
     torch_dtype=torch.float16,
 )
@@ -204,7 +204,7 @@ import torch
 from diffusers import StableDiffusionPipeline
 
 pipe = StableDiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
     torch_dtype=torch.float16,
 )
 
@@ -220,7 +220,7 @@ import torch
 from diffusers import StableDiffusionPipeline
 
 pipe = StableDiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
     torch_dtype=torch.float16,
 )
 
@@ -280,7 +280,7 @@ def generate_inputs():
 
 
 pipe = StableDiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
     torch_dtype=torch.float16,
 ).to("cuda")
 unet = pipe.unet
@@ -343,7 +343,7 @@ class UNet2DConditionOutput:
 
 
 pipe = StableDiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
     torch_dtype=torch.float16,
 ).to("cuda")
 
@@ -396,7 +396,7 @@ from diffusers import StableDiffusionPipeline
 import torch
 
 pipe = StableDiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
     torch_dtype=torch.float16,
 ).to("cuda")
 

docs/source/ko/optimization/mps.md

@@ -40,7 +40,7 @@ Diffusers는 Stable Diffusion 추론을 위해 PyTorch `mps`를 사용해 Apple
 # `huggingface-cli login`에 로그인되어 있음을 확인
 from diffusers import DiffusionPipeline
 
-pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")
+pipe = DiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5")
 pipe = pipe.to("mps")
 
 # 컴퓨터가 64GB 이하의 RAM 램일 때 추천

docs/source/ko/optimization/onnx.md

@@ -31,7 +31,7 @@ PyTorch 모델을 불러오고 즉시 ONNX 형식으로 변환하려는 경우 `
 ```python
 from optimum.onnxruntime import ORTStableDiffusionPipeline
 
-model_id = "runwayml/stable-diffusion-v1-5"
+model_id = "stable-diffusion-v1-5/stable-diffusion-v1-5"
 pipe = ORTStableDiffusionPipeline.from_pretrained(model_id, export=True)
 prompt = "a photo of an astronaut riding a horse on mars"
 images = pipe(prompt).images[0]
@@ -42,7 +42,7 @@ pipe.save_pretrained("./onnx-stable-diffusion-v1-5")
 [`optimum-cli export`](https://huggingface.co/docs/optimum/main/en/exporters/onnx/usage_guides/export_a_model#exporting-a-model-to-onnx-using-the-cli) 명령어를 사용할 수 있습니다:
 
 ```bash
-optimum-cli export onnx --model runwayml/stable-diffusion-v1-5 sd_v15_onnx/
+optimum-cli export onnx --model stable-diffusion-v1-5/stable-diffusion-v1-5 sd_v15_onnx/
 ```
 
 그 다음 추론을 수행합니다:

docs/source/ko/optimization/open_vino.md

@@ -30,7 +30,7 @@ OpenVINO 모델을 불러오고 OpenVINO 런타임으로 추론을 실행하려
 ```python
 from optimum.intel.openvino import OVStableDiffusionPipeline
 
-model_id = "runwayml/stable-diffusion-v1-5"
+model_id = "stable-diffusion-v1-5/stable-diffusion-v1-5"
 pipe = OVStableDiffusionPipeline.from_pretrained(model_id, export=True)
 prompt = "a photo of an astronaut riding a horse on mars"
 images = pipe(prompt).images[0]

docs/source/ko/optimization/tome.md

@@ -25,7 +25,7 @@ from diffusers import StableDiffusionPipeline
 import tomesd
 
 pipeline = StableDiffusionPipeline.from_pretrained(
-      "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16
+      "stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16
 ).to("cuda")
 + tomesd.apply_patch(pipeline, ratio=0.5)
 

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

@@ -37,7 +37,7 @@ pip install --upgrade torch diffusers
     import torch
     from diffusers import DiffusionPipeline
 
-    pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
+    pipe = DiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16)
     pipe = pipe.to("cuda")
 
     prompt = "a photo of an astronaut riding a horse on mars"
@@ -51,7 +51,7 @@ pip install --upgrade torch diffusers
     from diffusers import DiffusionPipeline
     + from diffusers.models.attention_processor import AttnProcessor2_0
 
-    pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16).to("cuda")
+    pipe = DiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16).to("cuda")
     + pipe.unet.set_attn_processor(AttnProcessor2_0())
 
     prompt = "a photo of an astronaut riding a horse on mars"
@@ -67,7 +67,7 @@ pip install --upgrade torch diffusers
     from diffusers import DiffusionPipeline
     from diffusers.models.attention_processor import AttnProcessor
 
-    pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16).to("cuda")
+    pipe = DiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16).to("cuda")
     pipe.unet.set_default_attn_processor()
 
     prompt = "a photo of an astronaut riding a horse on mars"
@@ -100,7 +100,7 @@ PyTorch 2.0의 효율적인 어텐션 구현과 `torch.compile`을 사용하여
 from diffusers import DiffusionPipeline
 import torch
 
-path = "runwayml/stable-diffusion-v1-5"
+path = "stable-diffusion-v1-5/stable-diffusion-v1-5"
 
 run_compile = True  # Set True / False
 
@@ -133,7 +133,7 @@ response = requests.get(url)
 init_image = Image.open(BytesIO(response.content)).convert("RGB")
 init_image = init_image.resize((512, 512))
 
-path = "runwayml/stable-diffusion-v1-5"
+path = "stable-diffusion-v1-5/stable-diffusion-v1-5"
 
 run_compile = True  # Set True / False
 
@@ -206,7 +206,7 @@ response = requests.get(url)
 init_image = Image.open(BytesIO(response.content)).convert("RGB")
 init_image = init_image.resize((512, 512))
 
-path = "runwayml/stable-diffusion-v1-5"
+path = "stable-diffusion-v1-5/stable-diffusion-v1-5"
 
 run_compile = True  # Set True / False
 controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", torch_dtype=torch.float16)

docs/source/ko/quicktour.md

@@ -53,7 +53,7 @@ Diffusion 모델은 이미지나 오디오와 같은 관심 샘플들을 생성
 
 먼저 [`DiffusionPipeline`]의 인스턴스를 생성하고 다운로드할 파이프라인 체크포인트를 지정합니다.
 허깅페이스 허브에 저장된 모든 [checkpoint](https://huggingface.co/models?library=diffusers&sort=downloads)에 대해 [`DiffusionPipeline`]을 사용할 수 있습니다.
-이 훑어보기에서는 text-to-image 생성을 위한 [`stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5) 체크포인트를 로드합니다.
+이 훑어보기에서는 text-to-image 생성을 위한 [`stable-diffusion-v1-5`](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) 체크포인트를 로드합니다.
 
 <Tip warning={true}>
 
@@ -66,7 +66,7 @@ Diffusion 모델은 이미지나 오디오와 같은 관심 샘플들을 생성
 ```python
 >>> from diffusers import DiffusionPipeline
 
->>> pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")
+>>> pipeline = DiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5")
 ```
 
 The [`DiffusionPipeline`]은 모든 모델링, 토큰화, 스케줄링 컴포넌트를 다운로드하고 캐시합니다. Stable Diffusion Pipeline은 무엇보다도 [`UNet2DConditionModel`]과 [`PNDMScheduler`]로 구성되어 있음을 알 수 있습니다:
@@ -123,7 +123,7 @@ PyTorch에서와 마찬가지로 제너레이터 객체를 GPU로 이동할 수
 
 ```bash
 !git lfs install
-!git clone https://huggingface.co/runwayml/stable-diffusion-v1-5
+!git clone https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5
 ```
 
 그런 다음 저장된 가중치를 파이프라인에 로드합니다:
@@ -141,7 +141,7 @@ PyTorch에서와 마찬가지로 제너레이터 객체를 GPU로 이동할 수
 ```py
 >>> from diffusers import EulerDiscreteScheduler
 
->>> pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")
+>>> pipeline = DiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5")
 >>> pipeline.scheduler = EulerDiscreteScheduler.from_config(pipeline.scheduler.config)
 ```
 

docs/source/ko/stable_diffusion.md

@@ -20,12 +20,12 @@ specific language governing permissions and limitations under the License.
 
 이 튜토리얼에서는 [`DiffusionPipeline`]을 사용하여 더 빠르고 효과적으로 생성하는 방법을 안내합니다.
 
-[`runwayml/stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5) 모델을 불러와서 시작합니다:
+[`stable-diffusion-v1-5/stable-diffusion-v1-5`](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) 모델을 불러와서 시작합니다:
 
 ```python
 from diffusers import DiffusionPipeline
 
-model_id = "runwayml/stable-diffusion-v1-5"
+model_id = "stable-diffusion-v1-5/stable-diffusion-v1-5"
 pipeline = DiffusionPipeline.from_pretrained(model_id)
 ```
 

docs/source/ko/training/adapt_a_model.md

@@ -18,12 +18,12 @@ specific language governing permissions and limitations under the License.
 
 ## UNet2DConditionModel 파라미터 구성
 
-[`UNet2DConditionModel`]은 [input sample](https://huggingface.co/docs/diffusers/v0.16.0/en/api/models#diffusers.UNet2DConditionModel.in_channels)에서 4개의 채널을 기본적으로 허용합니다. 예를 들어,  [`runwayml/stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5)와 같은 사전학습된 text-to-image 모델을 불러오고 `in_channels`의 수를 확인합니다:
+[`UNet2DConditionModel`]은 [input sample](https://huggingface.co/docs/diffusers/v0.16.0/en/api/models#diffusers.UNet2DConditionModel.in_channels)에서 4개의 채널을 기본적으로 허용합니다. 예를 들어,  [`stable-diffusion-v1-5/stable-diffusion-v1-5`](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5)와 같은 사전학습된 text-to-image 모델을 불러오고 `in_channels`의 수를 확인합니다:
 
 ```py
 from diffusers import StableDiffusionPipeline
 
-pipeline = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")
+pipeline = StableDiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5")
 pipeline.unet.config["in_channels"]
 4
 ```
@@ -45,7 +45,7 @@ pipeline.unet.config["in_channels"]
 ```py
 from diffusers import UNet2DConditionModel
 
-model_id = "runwayml/stable-diffusion-v1-5"
+model_id = "stable-diffusion-v1-5/stable-diffusion-v1-5"
 unet = UNet2DConditionModel.from_pretrained(
     model_id, subfolder="unet", in_channels=9, low_cpu_mem_usage=False, ignore_mismatched_sizes=True
 )

docs/source/ko/training/controlnet.md

@@ -70,7 +70,7 @@ write_basic_config()
 
 원본 데이터셋은 ControlNet [repo](https://huggingface.co/lllyasviel/ControlNet/blob/main/training/fill50k.zip)에 올라와있지만, 우리는 [여기](https://huggingface.co/datasets/fusing/fill50k)에 새롭게 다시 올려서 🤗 Datasets 과 호환가능합니다. 그래서 학습 스크립트 상에서 데이터 불러오기를 다룰 수 있습니다.
 
-우리의 학습 예시는 원래 ControlNet의 학습에 쓰였던 [`runwayml/stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5)을 사용합니다. 그렇지만 ControlNet은 대응되는 어느 Stable Diffusion 모델([`CompVis/stable-diffusion-v1-4`](https://huggingface.co/CompVis/stable-diffusion-v1-4)) 혹은 [`stabilityai/stable-diffusion-2-1`](https://huggingface.co/stabilityai/stable-diffusion-2-1)의 증가를 위해 학습될 수 있습니다.
+우리의 학습 예시는 원래 ControlNet의 학습에 쓰였던 [`stable-diffusion-v1-5/stable-diffusion-v1-5`](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5)을 사용합니다. 그렇지만 ControlNet은 대응되는 어느 Stable Diffusion 모델([`CompVis/stable-diffusion-v1-4`](https://huggingface.co/CompVis/stable-diffusion-v1-4)) 혹은 [`stabilityai/stable-diffusion-2-1`](https://huggingface.co/stabilityai/stable-diffusion-2-1)의 증가를 위해 학습될 수 있습니다.
 
 자체 데이터셋을 사용하기 위해서는 [학습을 위한 데이터셋 생성하기](create_dataset) 가이드를 확인하세요.
 
@@ -89,7 +89,7 @@ wget https://huggingface.co/datasets/huggingface/documentation-images/resolve/ma
 학습 스크립트는 당신의 리포지토리에 `diffusion_pytorch_model.bin` 파일을 생성하고 저장합니다.
 
 ```bash
-export MODEL_DIR="runwayml/stable-diffusion-v1-5"
+export MODEL_DIR="stable-diffusion-v1-5/stable-diffusion-v1-5"
 export OUTPUT_DIR="path to save model"
 
 accelerate launch train_controlnet.py \
@@ -111,7 +111,7 @@ accelerate launch train_controlnet.py \
 더 작은 batch(배치) 크기로 gradient accumulation(기울기 누적)을 하면 학습 요구사항을 ~20 GB VRAM으로 줄일 수 있습니다.
 
 ```bash
-export MODEL_DIR="runwayml/stable-diffusion-v1-5"
+export MODEL_DIR="stable-diffusion-v1-5/stable-diffusion-v1-5"
 export OUTPUT_DIR="path to save model"
 
 accelerate launch train_controlnet.py \
@@ -133,7 +133,7 @@ accelerate launch train_controlnet.py \
 의 설명을 확인하세요. 아래는 예시 명령어입니다:
 
 ```bash
-export MODEL_DIR="runwayml/stable-diffusion-v1-5"
+export MODEL_DIR="stable-diffusion-v1-5/stable-diffusion-v1-5"
 export OUTPUT_DIR="path to save model"
 
 accelerate launch --mixed_precision="fp16" --multi_gpu train_controlnet.py \
@@ -181,7 +181,7 @@ accelerate launch --mixed_precision="fp16" --multi_gpu train_controlnet.py \
 이제 학습 스크립트를 시작할 수 있습니다:
 
 ```bash
-export MODEL_DIR="runwayml/stable-diffusion-v1-5"
+export MODEL_DIR="stable-diffusion-v1-5/stable-diffusion-v1-5"
 export OUTPUT_DIR="path to save model"
 
 accelerate launch train_controlnet.py \
@@ -209,7 +209,7 @@ accelerate launch train_controlnet.py \
 - 기울기를 `None`으로 설정
 
 ```bash
-export MODEL_DIR="runwayml/stable-diffusion-v1-5"
+export MODEL_DIR="stable-diffusion-v1-5/stable-diffusion-v1-5"
 export OUTPUT_DIR="path to save model"
 
 accelerate launch train_controlnet.py \
@@ -275,7 +275,7 @@ Pytorch와 같은 버전의 CUDA toolchain이 필요합니다. 8-비트 optimize
 호환되지 않는 것 같습니다.
 
 ```bash
-export MODEL_DIR="runwayml/stable-diffusion-v1-5"
+export MODEL_DIR="stable-diffusion-v1-5/stable-diffusion-v1-5"
 export OUTPUT_DIR="path to save model"
 
 accelerate launch train_controlnet.py \

docs/source/ko/training/create_dataset.md

@@ -86,7 +86,7 @@ dataset.push_to_hub("name_of_your_dataset", private=True)
 
 ```bash
 accelerate launch --mixed_precision="fp16"  train_text_to_image.py \
-  --pretrained_model_name_or_path="runwayml/stable-diffusion-v1-5" \
+  --pretrained_model_name_or_path="stable-diffusion-v1-5/stable-diffusion-v1-5" \
   --dataset_name="name_of_your_dataset" \
   <other-arguments>
 ```