Update docs/source/en/modular_diffusers/custom_blocks.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
update
2025-11-14 10:35:13 +05:30 · 2025-11-07 16:02:16 +01:00 · 2025-11-07 15:58:13 +01:00 · 2025-11-07 08:49:41 +01:00 · 2025-11-07 08:42:18 +01:00 · 2025-11-07 07:51:54 +01:00
267 changed files with 18489 additions and 1486 deletions
@@ -7,7 +7,7 @@ on:

 env:
  DIFFUSERS_IS_CI: yes
-  HF_HUB_ENABLE_HF_TRANSFER: 1
+  HF_XET_HIGH_PERFORMANCE: 1
  HF_HOME: /mnt/cache
  OMP_NUM_THREADS: 8
  MKL_NUM_THREADS: 8
@@ -42,18 +42,39 @@ jobs:
          CHANGED_FILES: ${{ steps.file_changes.outputs.all }}
        run: |
          echo "$CHANGED_FILES"
-          for FILE in $CHANGED_FILES; do 
+          ALLOWED_IMAGES=(
+            diffusers-pytorch-cpu
+            diffusers-pytorch-cuda
+            diffusers-pytorch-xformers-cuda
+            diffusers-pytorch-minimum-cuda
+            diffusers-doc-builder
+          )
+
+          declare -A IMAGES_TO_BUILD=()
+
+          for FILE in $CHANGED_FILES; do
            # skip anything that isn't still on disk
-            if [[ ! -f "$FILE" ]]; then
+            if [[ ! -e "$FILE" ]]; then
              echo "Skipping removed file $FILE"
              continue
-            fi           
-            if [[ "$FILE" == docker/*Dockerfile ]]; then
-              DOCKER_PATH="${FILE%/Dockerfile}"
-              DOCKER_TAG=$(basename "$DOCKER_PATH")
-              echo "Building Docker image for $DOCKER_TAG"
-              docker build -t "$DOCKER_TAG" "$DOCKER_PATH"
            fi
+
+            for IMAGE in "${ALLOWED_IMAGES[@]}"; do
+              if [[ "$FILE" == docker/${IMAGE}/* ]]; then
+                IMAGES_TO_BUILD["$IMAGE"]=1
+              fi
+            done
+          done
+
+          if [[ ${#IMAGES_TO_BUILD[@]} -eq 0 ]]; then
+            echo "No relevant Docker changes detected."
+            exit 0
+          fi
+
+          for IMAGE in "${!IMAGES_TO_BUILD[@]}"; do
+            DOCKER_PATH="docker/${IMAGE}"
+            echo "Building Docker image for $IMAGE"
+            docker build -t "$IMAGE" "$DOCKER_PATH"
          done
        if: steps.file_changes.outputs.all != ''

@@ -7,7 +7,7 @@ on:

 env:
  DIFFUSERS_IS_CI: yes
-  HF_HUB_ENABLE_HF_TRANSFER: 1
+  HF_XET_HIGH_PERFORMANCE: 1
  OMP_NUM_THREADS: 8
  MKL_NUM_THREADS: 8
  PYTEST_TIMEOUT: 600
@@ -26,7 +26,7 @@ concurrency:

 env:
  DIFFUSERS_IS_CI: yes
-  HF_HUB_ENABLE_HF_TRANSFER: 1
+  HF_XET_HIGH_PERFORMANCE: 1
  OMP_NUM_THREADS: 4
  MKL_NUM_THREADS: 4
  PYTEST_TIMEOUT: 60
@@ -22,7 +22,7 @@ concurrency:

 env:
  DIFFUSERS_IS_CI: yes
-  HF_HUB_ENABLE_HF_TRANSFER: 1
+  HF_XET_HIGH_PERFORMANCE: 1
  OMP_NUM_THREADS: 4
  MKL_NUM_THREADS: 4
  PYTEST_TIMEOUT: 60
@@ -24,7 +24,7 @@ env:
  DIFFUSERS_IS_CI: yes
  OMP_NUM_THREADS: 8
  MKL_NUM_THREADS: 8
-  HF_HUB_ENABLE_HF_TRANSFER: 1
+  HF_XET_HIGH_PERFORMANCE: 1
  PYTEST_TIMEOUT: 600
  PIPELINE_USAGE_CUTOFF: 1000000000 # set high cutoff so that only always-test pipelines run

@@ -14,7 +14,7 @@ env:
  DIFFUSERS_IS_CI: yes
  OMP_NUM_THREADS: 8
  MKL_NUM_THREADS: 8
-  HF_HUB_ENABLE_HF_TRANSFER: 1
+  HF_XET_HIGH_PERFORMANCE: 1
  PYTEST_TIMEOUT: 600
  PIPELINE_USAGE_CUTOFF: 50000

@@ -18,7 +18,7 @@ env:
  HF_HOME: /mnt/cache
  OMP_NUM_THREADS: 8
  MKL_NUM_THREADS: 8
-  HF_HUB_ENABLE_HF_TRANSFER: 1
+  HF_XET_HIGH_PERFORMANCE: 1
  PYTEST_TIMEOUT: 600
  RUN_SLOW: no

@@ -8,7 +8,7 @@ env:
  HF_HOME: /mnt/cache
  OMP_NUM_THREADS: 8
  MKL_NUM_THREADS: 8
-  HF_HUB_ENABLE_HF_TRANSFER: 1
+  HF_XET_HIGH_PERFORMANCE: 1
  PYTEST_TIMEOUT: 600
  RUN_SLOW: no

@@ -171,7 +171,7 @@ Also, say 👋 in our public Discord channel <a href="https://discord.gg/G7tWnz9
  <tr style="border-top: 2px solid black">
    <td>Text-guided Image Inpainting</td>
    <td><a href="https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/inpaint">Stable Diffusion Inpainting</a></td>
-      <td><a href="https://huggingface.co/runwayml/stable-diffusion-inpainting"> runwayml/stable-diffusion-inpainting </a></td>
+      <td><a href="https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-inpainting"> stable-diffusion-v1-5/stable-diffusion-inpainting </a></td>
  </tr>
  <tr style="border-top: 2px solid black">
    <td>Image Variation</td>
@@ -33,7 +33,7 @@ RUN uv pip install --no-cache-dir "git+https://github.com/huggingface/diffusers.
 RUN uv pip install --no-cache-dir \
    accelerate \
    numpy==1.26.4 \
-    hf_transfer \
+    hf_xet \
    setuptools==69.5.1 \
    bitsandbytes \
    torchao \
@@ -44,6 +44,6 @@ RUN python3 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
        scipy \
        tensorboard \
        transformers \
-        hf_transfer
+        hf_xet

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

 CMD ["/bin/bash"]
@@ -31,7 +31,7 @@ RUN uv pip install --no-cache-dir "git+https://github.com/huggingface/diffusers.
 RUN uv pip install --no-cache-dir \
    accelerate \
    numpy==1.26.4 \
-    hf_transfer
+    hf_xet

 RUN apt-get clean && rm -rf /var/lib/apt/lists/* && apt-get autoremove && apt-get autoclean

@@ -44,6 +44,6 @@ RUN uv pip install --no-cache-dir \
    accelerate \
    numpy==1.26.4 \
    pytorch-lightning \
-    hf_transfer
+    hf_xet

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

 CMD ["/bin/bash"]
@@ -44,7 +44,7 @@ RUN uv pip install --no-cache-dir \
    accelerate \
    numpy==1.26.4 \
    pytorch-lightning \
-    hf_transfer \
+    hf_xet \
    xformers

 CMD ["/bin/bash"]
@@ -1,5 +1,4 @@
- title: Get started
-  sections:
+- sections:
  - local: index
    title: Diffusers
  - local: installation
@@ -8,9 +7,8 @@
    title: Quickstart
  - local: stable_diffusion
    title: Basic performance
-
- title: Pipelines
-  isExpanded: false
+  title: Get started
+- isExpanded: false
  sections:
  - local: using-diffusers/loading
    title: DiffusionPipeline
@@ -28,9 +26,8 @@
    title: Model formats
  - local: using-diffusers/push_to_hub
    title: Sharing pipelines and models
-
- title: Adapters
-  isExpanded: false
+  title: Pipelines
+- isExpanded: false
  sections:
  - local: tutorials/using_peft_for_inference
    title: LoRA
@@ -44,9 +41,8 @@
    title: DreamBooth
  - local: using-diffusers/textual_inversion_inference
    title: Textual inversion
-
- title: Inference
-  isExpanded: false
+  title: Adapters
+- isExpanded: false
  sections:
  - local: using-diffusers/weighted_prompts
    title: Prompting
@@ -56,9 +52,8 @@
    title: Batch inference
  - local: training/distributed_inference
    title: Distributed inference
-
- title: Inference optimization
-  isExpanded: false
+  title: Inference
+- isExpanded: false
  sections:
  - local: optimization/fp16
    title: Accelerate inference
@@ -70,8 +65,7 @@
    title: Reduce memory usage
  - local: optimization/speed-memory-optims
    title: Compiling and offloading quantized models
-  - title: Community optimizations
-    sections:
+  - sections:
    - local: optimization/pruna
      title: Pruna
    - local: optimization/xformers
@@ -90,9 +84,9 @@
      title: ParaAttention
    - local: using-diffusers/image_quality
      title: FreeU
-
- title: Hybrid Inference
-  isExpanded: false
+    title: Community optimizations
+  title: Inference optimization
+- isExpanded: false
  sections:
  - local: hybrid_inference/overview
    title: Overview
@@ -102,9 +96,8 @@
    title: VAE Encode
  - local: hybrid_inference/api_reference
    title: API Reference
-
- title: Modular Diffusers
-  isExpanded: false
+  title: Hybrid Inference
+- isExpanded: false
  sections:
  - local: modular_diffusers/overview
    title: Overview
@@ -126,9 +119,10 @@
    title: ComponentsManager
  - local: modular_diffusers/guiders
    title: Guiders
-
- title: Training
-  isExpanded: false
+  - local: modular_diffusers/custom_blocks
+    title: Building Custom Blocks
+  title: Modular Diffusers
+- isExpanded: false
  sections:
  - local: training/overview
    title: Overview
@@ -138,8 +132,7 @@
    title: Adapt a model to a new task
  - local: tutorials/basic_training
    title: Train a diffusion model
-  - title: Models
-    sections:
+  - sections:
    - local: training/unconditional_training
      title: Unconditional image generation
    - local: training/text2image
@@ -158,8 +151,8 @@
      title: InstructPix2Pix
    - local: training/cogvideox
      title: CogVideoX
-  - title: Methods
-    sections:
+    title: Models
+  - sections:
    - local: training/text_inversion
      title: Textual Inversion
    - local: training/dreambooth
@@ -172,9 +165,9 @@
      title: Latent Consistency Distillation
    - local: training/ddpo
      title: Reinforcement learning training with DDPO
-
- title: Quantization
-  isExpanded: false
+    title: Methods
+  title: Training
+- isExpanded: false
  sections:
  - local: quantization/overview
    title: Getting started
@@ -188,9 +181,8 @@
    title: quanto
  - local: quantization/modelopt
    title: NVIDIA ModelOpt
-
- title: Model accelerators and hardware
-  isExpanded: false
+  title: Quantization
+- isExpanded: false
  sections:
  - local: optimization/onnx
    title: ONNX
@@ -204,9 +196,8 @@
    title: Intel Gaudi
  - local: optimization/neuron
    title: AWS Neuron
-
- title: Specific pipeline examples
-  isExpanded: false
+  title: Model accelerators and hardware
+- isExpanded: false
  sections:
  - local: using-diffusers/consisid
    title: ConsisID
@@ -232,12 +223,10 @@
    title: Stable Video Diffusion
  - local: using-diffusers/marigold_usage
    title: Marigold Computer Vision
-
- title: Resources
-  isExpanded: false
+  title: Specific pipeline examples
+- isExpanded: false
  sections:
-  - title: Task recipes
-    sections:
+  - sections:
    - local: using-diffusers/unconditional_image_generation
      title: Unconditional image generation
    - local: using-diffusers/conditional_image_generation
@@ -252,6 +241,7 @@
      title: Video generation
    - local: using-diffusers/depth2img
      title: Depth-to-image
+    title: Task recipes
  - local: using-diffusers/write_own_pipeline
    title: Understanding pipelines, models and schedulers
  - local: community_projects
@@ -266,12 +256,10 @@
    title: Diffusers' Ethical Guidelines
  - local: conceptual/evaluation
    title: Evaluating Diffusion Models
-
- title: API
-  isExpanded: false
+  title: Resources
+- isExpanded: false
  sections:
-  - title: Main Classes
-    sections:
+  - sections:
    - local: api/configuration
      title: Configuration
    - local: api/logging
@@ -282,8 +270,8 @@
      title: Quantization
    - local: api/parallel
      title: Parallel inference
-  - title: Modular
-    sections:
+    title: Main Classes
+  - sections:
    - local: api/modular_diffusers/pipeline
      title: Pipeline
    - local: api/modular_diffusers/pipeline_blocks
@@ -294,8 +282,8 @@
      title: Components and configs
    - local: api/modular_diffusers/guiders
      title: Guiders
-  - title: Loaders
-    sections:
+    title: Modular
+  - sections:
    - local: api/loaders/ip_adapter
      title: IP-Adapter
    - local: api/loaders/lora
@@ -310,14 +298,13 @@
      title: SD3Transformer2D
    - local: api/loaders/peft
      title: PEFT
-  - title: Models
-    sections:
+    title: Loaders
+  - sections:
    - local: api/models/overview
      title: Overview
    - local: api/models/auto_model
      title: AutoModel
-    - title: ControlNets
-      sections:
+    - sections:
      - local: api/models/controlnet
        title: ControlNetModel
      - local: api/models/controlnet_union
@@ -332,12 +319,14 @@
        title: SD3ControlNetModel
      - local: api/models/controlnet_sparsectrl
        title: SparseControlNetModel
-    - title: Transformers
-      sections:
+      title: ControlNets
+    - sections:
      - local: api/models/allegro_transformer3d
        title: AllegroTransformer3DModel
      - local: api/models/aura_flow_transformer2d
        title: AuraFlowTransformer2DModel
+      - local: api/models/transformer_bria_fibo
+        title: BriaFiboTransformer2DModel
      - local: api/models/bria_transformer
        title: BriaTransformer2DModel
      - local: api/models/chroma_transformer
@@ -362,6 +351,8 @@
        title: HiDreamImageTransformer2DModel
      - local: api/models/hunyuan_transformer2d
        title: HunyuanDiT2DModel
+      - local: api/models/hunyuanimage_transformer_2d
+        title: HunyuanImageTransformer2DModel
      - local: api/models/hunyuan_video_transformer_3d
        title: HunyuanVideoTransformer3DModel
      - local: api/models/latte_transformer3d
@@ -384,6 +375,8 @@
        title: QwenImageTransformer2DModel
      - local: api/models/sana_transformer2d
        title: SanaTransformer2DModel
+      - local: api/models/sana_video_transformer3d
+        title: SanaVideoTransformer3DModel
      - local: api/models/sd3_transformer2d
        title: SD3Transformer2DModel
      - local: api/models/skyreels_v2_transformer_3d
@@ -396,8 +389,8 @@
        title: TransformerTemporalModel
      - local: api/models/wan_transformer_3d
        title: WanTransformer3DModel
-    - title: UNets
-      sections:
+      title: Transformers
+    - sections:
      - local: api/models/stable_cascade_unet
        title: StableCascadeUNet
      - local: api/models/unet
@@ -412,8 +405,8 @@
        title: UNetMotionModel
      - local: api/models/uvit2d
        title: UViT2DModel
-    - title: VAEs
-      sections:
+      title: UNets
+    - sections:
      - local: api/models/asymmetricautoencoderkl
        title: AsymmetricAutoencoderKL
      - local: api/models/autoencoder_dc
@@ -426,6 +419,10 @@
        title: AutoencoderKLCogVideoX
      - local: api/models/autoencoderkl_cosmos
        title: AutoencoderKLCosmos
+      - local: api/models/autoencoder_kl_hunyuanimage
+        title: AutoencoderKLHunyuanImage
+      - local: api/models/autoencoder_kl_hunyuanimage_refiner
+        title: AutoencoderKLHunyuanImageRefiner
      - local: api/models/autoencoder_kl_hunyuan_video
        title: AutoencoderKLHunyuanVideo
      - local: api/models/autoencoderkl_ltx_video
@@ -446,210 +443,228 @@
        title: Tiny AutoEncoder
      - local: api/models/vq
        title: VQModel
-  - title: Pipelines
-    sections:
+      title: VAEs
+    title: Models
+  - sections:
    - local: api/pipelines/overview
      title: Overview
-    - local: api/pipelines/allegro
-      title: Allegro
-    - local: api/pipelines/amused
-      title: aMUSEd
-    - local: api/pipelines/animatediff
-      title: AnimateDiff
-    - local: api/pipelines/attend_and_excite
-      title: Attend-and-Excite
-    - local: api/pipelines/audioldm
-      title: AudioLDM
-    - local: api/pipelines/audioldm2
-      title: AudioLDM 2
-    - local: api/pipelines/aura_flow
-      title: AuraFlow
+    - sections:
+      - local: api/pipelines/audioldm
+        title: AudioLDM
+      - local: api/pipelines/audioldm2
+        title: AudioLDM 2
+      - local: api/pipelines/dance_diffusion
+        title: Dance Diffusion
+      - local: api/pipelines/musicldm
+        title: MusicLDM
+      - local: api/pipelines/stable_audio
+        title: Stable Audio
+      title: Audio
    - local: api/pipelines/auto_pipeline
      title: AutoPipeline
-    - local: api/pipelines/blip_diffusion
-      title: BLIP-Diffusion
-    - local: api/pipelines/bria_3_2
-      title: Bria 3.2
-    - local: api/pipelines/chroma
-      title: Chroma
-    - local: api/pipelines/cogvideox
-      title: CogVideoX
-    - local: api/pipelines/cogview3
-      title: CogView3
-    - local: api/pipelines/cogview4
-      title: CogView4
-    - local: api/pipelines/consisid
-      title: ConsisID
-    - local: api/pipelines/consistency_models
-      title: Consistency Models
-    - local: api/pipelines/controlnet
-      title: ControlNet
-    - local: api/pipelines/controlnet_flux
-      title: ControlNet with Flux.1
-    - local: api/pipelines/controlnet_hunyuandit
-      title: ControlNet with Hunyuan-DiT
-    - local: api/pipelines/controlnet_sd3
-      title: ControlNet with Stable Diffusion 3
-    - local: api/pipelines/controlnet_sdxl
-      title: ControlNet with Stable Diffusion XL
-    - local: api/pipelines/controlnet_sana
-      title: ControlNet-Sana
-    - local: api/pipelines/controlnetxs
-      title: ControlNet-XS
-    - local: api/pipelines/controlnetxs_sdxl
-      title: ControlNet-XS with Stable Diffusion XL
-    - local: api/pipelines/controlnet_union
-      title: ControlNetUnion
-    - local: api/pipelines/cosmos
-      title: Cosmos
-    - local: api/pipelines/dance_diffusion
-      title: Dance Diffusion
-    - local: api/pipelines/ddim
-      title: DDIM
-    - local: api/pipelines/ddpm
-      title: DDPM
-    - local: api/pipelines/deepfloyd_if
-      title: DeepFloyd IF
-    - local: api/pipelines/diffedit
-      title: DiffEdit
-    - local: api/pipelines/dit
-      title: DiT
-    - local: api/pipelines/easyanimate
-      title: EasyAnimate
-    - local: api/pipelines/flux
-      title: Flux
-    - local: api/pipelines/control_flux_inpaint
-      title: FluxControlInpaint
-    - local: api/pipelines/framepack
-      title: Framepack
-    - local: api/pipelines/hidream
-      title: HiDream-I1
-    - local: api/pipelines/hunyuandit
-      title: Hunyuan-DiT
-    - local: api/pipelines/hunyuan_video
-      title: HunyuanVideo
-    - local: api/pipelines/i2vgenxl
-      title: I2VGen-XL
-    - local: api/pipelines/pix2pix
-      title: InstructPix2Pix
-    - local: api/pipelines/kandinsky
-      title: Kandinsky 2.1
-    - local: api/pipelines/kandinsky_v22
-      title: Kandinsky 2.2
-    - local: api/pipelines/kandinsky3
-      title: Kandinsky 3
-    - local: api/pipelines/kolors
-      title: Kolors
-    - local: api/pipelines/latent_consistency_models
-      title: Latent Consistency Models
-    - local: api/pipelines/latent_diffusion
-      title: Latent Diffusion
-    - local: api/pipelines/latte
-      title: Latte
-    - local: api/pipelines/ledits_pp
-      title: LEDITS++
-    - local: api/pipelines/ltx_video
-      title: LTXVideo
-    - local: api/pipelines/lumina2
-      title: Lumina 2.0
-    - local: api/pipelines/lumina
-      title: Lumina-T2X
-    - local: api/pipelines/marigold
-      title: Marigold
-    - local: api/pipelines/mochi
-      title: Mochi
-    - local: api/pipelines/panorama
-      title: MultiDiffusion
-    - local: api/pipelines/musicldm
-      title: MusicLDM
-    - local: api/pipelines/omnigen
-      title: OmniGen
-    - local: api/pipelines/pag
-      title: PAG
-    - local: api/pipelines/paint_by_example
-      title: Paint by Example
-    - local: api/pipelines/pia
-      title: Personalized Image Animator (PIA)
-    - local: api/pipelines/pixart
-      title: PixArt-α
-    - local: api/pipelines/pixart_sigma
-      title: PixArt-Σ
-    - local: api/pipelines/qwenimage
-      title: QwenImage
-    - local: api/pipelines/sana
-      title: Sana
-    - local: api/pipelines/sana_sprint
-      title: Sana Sprint
-    - local: api/pipelines/self_attention_guidance
-      title: Self-Attention Guidance
-    - local: api/pipelines/semantic_stable_diffusion
-      title: Semantic Guidance
-    - local: api/pipelines/shap_e
-      title: Shap-E
-    - local: api/pipelines/skyreels_v2
-      title: SkyReels-V2
-    - local: api/pipelines/stable_audio
-      title: Stable Audio
-    - local: api/pipelines/stable_cascade
-      title: Stable Cascade
-    - title: Stable Diffusion
-      sections:
-      - local: api/pipelines/stable_diffusion/overview
-        title: Overview
-      - local: api/pipelines/stable_diffusion/depth2img
-        title: Depth-to-image
-      - local: api/pipelines/stable_diffusion/gligen
-        title: GLIGEN (Grounded Language-to-Image Generation)
-      - local: api/pipelines/stable_diffusion/image_variation
-        title: Image variation
-      - local: api/pipelines/stable_diffusion/img2img
-        title: Image-to-image
+    - sections:
+      - local: api/pipelines/amused
+        title: aMUSEd
+      - local: api/pipelines/animatediff
+        title: AnimateDiff
+      - local: api/pipelines/attend_and_excite
+        title: Attend-and-Excite
+      - local: api/pipelines/aura_flow
+        title: AuraFlow
+      - local: api/pipelines/blip_diffusion
+        title: BLIP-Diffusion
+      - local: api/pipelines/bria_3_2
+        title: Bria 3.2
+      - local: api/pipelines/bria_fibo
+        title: Bria Fibo
+      - local: api/pipelines/chroma
+        title: Chroma
+      - local: api/pipelines/cogview3
+        title: CogView3
+      - local: api/pipelines/cogview4
+        title: CogView4
+      - local: api/pipelines/consistency_models
+        title: Consistency Models
+      - local: api/pipelines/controlnet
+        title: ControlNet
+      - local: api/pipelines/controlnet_flux
+        title: ControlNet with Flux.1
+      - local: api/pipelines/controlnet_hunyuandit
+        title: ControlNet with Hunyuan-DiT
+      - local: api/pipelines/controlnet_sd3
+        title: ControlNet with Stable Diffusion 3
+      - local: api/pipelines/controlnet_sdxl
+        title: ControlNet with Stable Diffusion XL
+      - local: api/pipelines/controlnet_sana
+        title: ControlNet-Sana
+      - local: api/pipelines/controlnetxs
+        title: ControlNet-XS
+      - local: api/pipelines/controlnetxs_sdxl
+        title: ControlNet-XS with Stable Diffusion XL
+      - local: api/pipelines/controlnet_union
+        title: ControlNetUnion
+      - local: api/pipelines/cosmos
+        title: Cosmos
+      - local: api/pipelines/ddim
+        title: DDIM
+      - local: api/pipelines/ddpm
+        title: DDPM
+      - local: api/pipelines/deepfloyd_if
+        title: DeepFloyd IF
+      - local: api/pipelines/diffedit
+        title: DiffEdit
+      - local: api/pipelines/dit
+        title: DiT
+      - local: api/pipelines/easyanimate
+        title: EasyAnimate
+      - local: api/pipelines/flux
+        title: Flux
+      - local: api/pipelines/control_flux_inpaint
+        title: FluxControlInpaint
+      - local: api/pipelines/hidream
+        title: HiDream-I1
+      - local: api/pipelines/hunyuandit
+        title: Hunyuan-DiT
+      - local: api/pipelines/pix2pix
+        title: InstructPix2Pix
+      - local: api/pipelines/kandinsky
+        title: Kandinsky 2.1
+      - local: api/pipelines/kandinsky_v22
+        title: Kandinsky 2.2
+      - local: api/pipelines/kandinsky3
+        title: Kandinsky 3
+      - local: api/pipelines/kolors
+        title: Kolors
+      - local: api/pipelines/latent_consistency_models
+        title: Latent Consistency Models
+      - local: api/pipelines/latent_diffusion
+        title: Latent Diffusion
+      - local: api/pipelines/ledits_pp
+        title: LEDITS++
+      - local: api/pipelines/lumina2
+        title: Lumina 2.0
+      - local: api/pipelines/lumina
+        title: Lumina-T2X
+      - local: api/pipelines/marigold
+        title: Marigold
+      - local: api/pipelines/panorama
+        title: MultiDiffusion
+      - local: api/pipelines/omnigen
+        title: OmniGen
+      - local: api/pipelines/pag
+        title: PAG
+      - local: api/pipelines/paint_by_example
+        title: Paint by Example
+      - local: api/pipelines/pixart
+        title: PixArt-α
+      - local: api/pipelines/pixart_sigma
+        title: PixArt-Σ
+      - local: api/pipelines/prx
+        title: PRX
+      - local: api/pipelines/qwenimage
+        title: QwenImage
+      - local: api/pipelines/sana
+        title: Sana
+      - local: api/pipelines/sana_sprint
+        title: Sana Sprint
+      - local: api/pipelines/sana_video
+        title: Sana Video
+      - local: api/pipelines/self_attention_guidance
+        title: Self-Attention Guidance
+      - local: api/pipelines/semantic_stable_diffusion
+        title: Semantic Guidance
+      - local: api/pipelines/shap_e
+        title: Shap-E
+      - local: api/pipelines/stable_cascade
+        title: Stable Cascade
+      - sections:
+        - local: api/pipelines/stable_diffusion/overview
+          title: Overview
+        - local: api/pipelines/stable_diffusion/depth2img
+          title: Depth-to-image
+        - local: api/pipelines/stable_diffusion/gligen
+          title: GLIGEN (Grounded Language-to-Image Generation)
+        - local: api/pipelines/stable_diffusion/image_variation
+          title: Image variation
+        - local: api/pipelines/stable_diffusion/img2img
+          title: Image-to-image
+        - local: api/pipelines/stable_diffusion/inpaint
+          title: Inpainting
+        - local: api/pipelines/stable_diffusion/k_diffusion
+          title: K-Diffusion
+        - local: api/pipelines/stable_diffusion/latent_upscale
+          title: Latent upscaler
+        - local: api/pipelines/stable_diffusion/ldm3d_diffusion
+          title: LDM3D Text-to-(RGB, Depth), Text-to-(RGB-pano, Depth-pano), LDM3D
+            Upscaler
+        - local: api/pipelines/stable_diffusion/stable_diffusion_safe
+          title: Safe Stable Diffusion
+        - local: api/pipelines/stable_diffusion/sdxl_turbo
+          title: SDXL Turbo
+        - local: api/pipelines/stable_diffusion/stable_diffusion_2
+          title: Stable Diffusion 2
+        - local: api/pipelines/stable_diffusion/stable_diffusion_3
+          title: Stable Diffusion 3
+        - local: api/pipelines/stable_diffusion/stable_diffusion_xl
+          title: Stable Diffusion XL
+        - local: api/pipelines/stable_diffusion/upscale
+          title: Super-resolution
+        - local: api/pipelines/stable_diffusion/adapter
+          title: T2I-Adapter
+        - local: api/pipelines/stable_diffusion/text2img
+          title: Text-to-image
+        title: Stable Diffusion
+      - local: api/pipelines/stable_unclip
+        title: Stable unCLIP
+      - local: api/pipelines/unclip
+        title: unCLIP
+      - local: api/pipelines/unidiffuser
+        title: UniDiffuser
+      - local: api/pipelines/value_guided_sampling
+        title: Value-guided sampling
+      - local: api/pipelines/visualcloze
+        title: VisualCloze
+      - local: api/pipelines/wuerstchen
+        title: Wuerstchen
+      title: Image
+    - sections:
+      - local: api/pipelines/allegro
+        title: Allegro
+      - local: api/pipelines/cogvideox
+        title: CogVideoX
+      - local: api/pipelines/consisid
+        title: ConsisID
+      - local: api/pipelines/framepack
+        title: Framepack
+      - local: api/pipelines/hunyuanimage21
+        title: HunyuanImage2.1
+      - local: api/pipelines/hunyuan_video
+        title: HunyuanVideo
+      - local: api/pipelines/i2vgenxl
+        title: I2VGen-XL
+      - local: api/pipelines/kandinsky5_video
+        title: Kandinsky 5.0 Video
+      - local: api/pipelines/latte
+        title: Latte
+      - local: api/pipelines/ltx_video
+        title: LTXVideo
+      - local: api/pipelines/mochi
+        title: Mochi
+      - local: api/pipelines/pia
+        title: Personalized Image Animator (PIA)
+      - local: api/pipelines/skyreels_v2
+        title: SkyReels-V2
      - local: api/pipelines/stable_diffusion/svd
-        title: Image-to-video
-      - local: api/pipelines/stable_diffusion/inpaint
-        title: Inpainting
-      - local: api/pipelines/stable_diffusion/k_diffusion
-        title: K-Diffusion
-      - local: api/pipelines/stable_diffusion/latent_upscale
-        title: Latent upscaler
-      - local: api/pipelines/stable_diffusion/ldm3d_diffusion
-        title: LDM3D Text-to-(RGB, Depth), Text-to-(RGB-pano, Depth-pano), LDM3D Upscaler
-      - local: api/pipelines/stable_diffusion/stable_diffusion_safe
-        title: Safe Stable Diffusion
-      - local: api/pipelines/stable_diffusion/sdxl_turbo
-        title: SDXL Turbo
-      - local: api/pipelines/stable_diffusion/stable_diffusion_2
-        title: Stable Diffusion 2
-      - local: api/pipelines/stable_diffusion/stable_diffusion_3
-        title: Stable Diffusion 3
-      - local: api/pipelines/stable_diffusion/stable_diffusion_xl
-        title: Stable Diffusion XL
-      - local: api/pipelines/stable_diffusion/upscale
-        title: Super-resolution
-      - local: api/pipelines/stable_diffusion/adapter
-        title: T2I-Adapter
-      - local: api/pipelines/stable_diffusion/text2img
-        title: Text-to-image
-    - local: api/pipelines/stable_unclip
-      title: Stable unCLIP
-    - local: api/pipelines/text_to_video
-      title: Text-to-video
-    - local: api/pipelines/text_to_video_zero
-      title: Text2Video-Zero
-    - local: api/pipelines/unclip
-      title: unCLIP
-    - local: api/pipelines/unidiffuser
-      title: UniDiffuser
-    - local: api/pipelines/value_guided_sampling
-      title: Value-guided sampling
-    - local: api/pipelines/visualcloze
-      title: VisualCloze
-    - local: api/pipelines/wan
-      title: Wan
-    - local: api/pipelines/wuerstchen
-      title: Wuerstchen
-  - title: Schedulers
-    sections:
+        title: Stable Video Diffusion
+      - local: api/pipelines/text_to_video
+        title: Text-to-video
+      - local: api/pipelines/text_to_video_zero
+        title: Text2Video-Zero
+      - local: api/pipelines/wan
+        title: Wan
+      title: Video
+    title: Pipelines
+  - sections:
    - local: api/schedulers/overview
      title: Overview
    - local: api/schedulers/cm_stochastic_iterative
@@ -718,8 +733,8 @@
      title: UniPCMultistepScheduler
    - local: api/schedulers/vq_diffusion
      title: VQDiffusionScheduler
-  - title: Internal classes
-    sections:
+    title: Schedulers
+  - sections:
    - local: api/internal_classes_overview
      title: Overview
    - local: api/attnprocessor
@@ -736,3 +751,5 @@
      title: VAE Image Processor
    - local: api/video_processor
      title: Video Processor
+    title: Internal classes
+  title: API
@@ -107,6 +107,9 @@ LoRA is a fast and lightweight training method that inserts and trains a signifi

 [[autodoc]] loaders.lora_pipeline.QwenImageLoraLoaderMixin

+## KandinskyLoraLoaderMixin
+[[autodoc]] loaders.lora_pipeline.KandinskyLoraLoaderMixin
+
 ## LoraBaseMixin

 [[autodoc]] loaders.lora_base.LoraBaseMixin
@@ -39,7 +39,7 @@ mask_url = "https://huggingface.co/datasets/hf-internal-testing/diffusers-images
 original_image = load_image(img_url).resize((512, 512))
 mask_image = load_image(mask_url).resize((512, 512))

-pipe = StableDiffusionInpaintPipeline.from_pretrained("runwayml/stable-diffusion-inpainting")
+pipe = StableDiffusionInpaintPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-inpainting")
 pipe.vae = AsymmetricAutoencoderKL.from_pretrained("cross-attention/asymmetric-autoencoder-kl-x-1-5")
 pipe.to("cuda")

@@ -0,0 +1,32 @@
+<!-- Copyright 2025 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License. -->
+
+# AutoencoderKLHunyuanImage
+
+The 2D variational autoencoder (VAE) model with KL loss used in [HunyuanImage2.1].
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import AutoencoderKLHunyuanImage
+
+vae = AutoencoderKLHunyuanImage.from_pretrained("hunyuanvideo-community/HunyuanImage-2.1-Diffusers", subfolder="vae", torch_dtype=torch.bfloat16)
+```
+
+## AutoencoderKLHunyuanImage
+
+[[autodoc]] AutoencoderKLHunyuanImage
+  - decode
+  - all
+
+## DecoderOutput
+
+[[autodoc]] models.autoencoders.vae.DecoderOutput
@@ -0,0 +1,32 @@
+<!-- Copyright 2025 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License. -->
+
+# AutoencoderKLHunyuanImageRefiner
+
+The 3D variational autoencoder (VAE) model with KL loss used in [HunyuanImage2.1](https://github.com/Tencent-Hunyuan/HunyuanImage-2.1) for its refiner pipeline.
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import AutoencoderKLHunyuanImageRefiner
+
+vae = AutoencoderKLHunyuanImageRefiner.from_pretrained("hunyuanvideo-community/HunyuanImage-2.1-Refiner-Diffusers", subfolder="vae", torch_dtype=torch.bfloat16)
+```
+
+## AutoencoderKLHunyuanImageRefiner
+
+[[autodoc]] AutoencoderKLHunyuanImageRefiner
+  - decode
+  - all
+
+## DecoderOutput
+
+[[autodoc]] models.autoencoders.vae.DecoderOutput
@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.

 # ChromaTransformer2DModel

-A modified flux Transformer model from [Chroma](https://huggingface.co/lodestones/Chroma)
+A modified flux Transformer model from [Chroma](https://huggingface.co/lodestones/Chroma1-HD)

 ## ChromaTransformer2DModel

@@ -0,0 +1,30 @@
+<!-- Copyright 2025 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License. -->
+
+# HunyuanImageTransformer2DModel
+
+A Diffusion Transformer model for [HunyuanImage2.1](https://github.com/Tencent-Hunyuan/HunyuanImage-2.1).
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import HunyuanImageTransformer2DModel
+
+transformer = HunyuanImageTransformer2DModel.from_pretrained("hunyuanvideo-community/HunyuanImage-2.1-Diffusers", subfolder="transformer", torch_dtype=torch.bfloat16)
+```
+
+## HunyuanImageTransformer2DModel
+
+[[autodoc]] HunyuanImageTransformer2DModel
+
+## Transformer2DModelOutput
+
+[[autodoc]] models.modeling_outputs.Transformer2DModelOutput
@@ -0,0 +1,36 @@
+<!-- Copyright 2025 The SANA-Video Authors and HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License. -->
+
+# SanaVideoTransformer3DModel
+
+A Diffusion Transformer model for 3D data (video) from [SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer](https://huggingface.co/papers/2509.24695) from NVIDIA and MIT HAN Lab, by Junsong Chen, Yuyang Zhao, Jincheng Yu, Ruihang Chu, Junyu Chen, Shuai Yang, Xianbang Wang, Yicheng Pan, Daquan Zhou, Huan Ling, Haozhe Liu, Hongwei Yi, Hao Zhang, Muyang Li, Yukang Chen, Han Cai, Sanja Fidler, Ping Luo, Song Han, Enze Xie.
+
+The abstract from the paper is:
+
+*We introduce SANA-Video, a small diffusion model that can efficiently generate videos up to 720x1280 resolution and minute-length duration. SANA-Video synthesizes high-resolution, high-quality and long videos with strong text-video alignment at a remarkably fast speed, deployable on RTX 5090 GPU. Two core designs ensure our efficient, effective and long video generation: (1) Linear DiT: We leverage linear attention as the core operation, which is more efficient than vanilla attention given the large number of tokens processed in video generation. (2) Constant-Memory KV cache for Block Linear Attention: we design block-wise autoregressive approach for long video generation by employing a constant-memory state, derived from the cumulative properties of linear attention. This KV cache provides the Linear DiT with global context at a fixed memory cost, eliminating the need for a traditional KV cache and enabling efficient, minute-long video generation. In addition, we explore effective data filters and model training strategies, narrowing the training cost to 12 days on 64 H100 GPUs, which is only 1% of the cost of MovieGen. Given its low cost, SANA-Video achieves competitive performance compared to modern state-of-the-art small diffusion models (e.g., Wan 2.1-1.3B and SkyReel-V2-1.3B) while being 16x faster in measured latency. Moreover, SANA-Video can be deployed on RTX 5090 GPUs with NVFP4 precision, accelerating the inference speed of generating a 5-second 720p video from 71s to 29s (2.4x speedup). In summary, SANA-Video enables low-cost, high-quality video generation.*
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import SanaVideoTransformer3DModel
+import torch
+
+transformer = SanaVideoTransformer3DModel.from_pretrained("Efficient-Large-Model/SANA-Video_2B_480p_diffusers", subfolder="transformer", torch_dtype=torch.bfloat16)
+```
+
+## SanaVideoTransformer3DModel
+
+[[autodoc]] SanaVideoTransformer3DModel
+
+## Transformer2DModelOutput
+
+[[autodoc]] models.modeling_outputs.Transformer2DModelOutput
+
@@ -0,0 +1,19 @@
+<!--Copyright 2025 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# BriaFiboTransformer2DModel
+
+A modified flux Transformer model from [Bria](https://huggingface.co/briaai/FIBO)
+
+## BriaFiboTransformer2DModel
+
+[[autodoc]] BriaFiboTransformer2DModel
@@ -0,0 +1,45 @@
+<!--Copyright 2025 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# Bria Fibo
+
+Text-to-image models have mastered imagination - but not control. FIBO changes that.
+
+FIBO is trained on structured JSON captions up to 1,000+ words and designed to understand and control different visual parameters such as lighting, composition, color, and camera settings, enabling precise and reproducible outputs.
+
+With only 8 billion parameters, FIBO provides a new level of image quality, prompt adherence and proffesional control.
+
+FIBO is trained exclusively on a structured prompt and will not work with freeform text prompts.
+you can use the [FIBO-VLM-prompt-to-JSON](https://huggingface.co/briaai/FIBO-VLM-prompt-to-JSON) model or the [FIBO-gemini-prompt-to-JSON](https://huggingface.co/briaai/FIBO-gemini-prompt-to-JSON)  to convert your freeform text prompt to a structured JSON prompt.
+
+its not recommended to use freeform text prompts directly with FIBO, as it will not produce the best results.
+
+you can learn more about FIBO in  [Bria Fibo Hugging Face page](https://huggingface.co/briaai/FIBO).
+
+
+## Usage
+
+_As the model is gated, before using it with diffusers you first need to go to the [Bria Fibo Hugging Face page](https://huggingface.co/briaai/FIBO), fill in the form and accept the gate. Once you are in, you need to login so that your system knows you’ve accepted the gate._
+
+Use the command below to log in:
+
+```bash
+hf auth login
+```
+
+
+## BriaPipeline
+
+[[autodoc]] BriaPipeline
+	- all
+	- __call__
+
@@ -19,20 +19,21 @@ specific language governing permissions and limitations under the License.

 Chroma is a text to image generation model based on Flux.

-Original model checkpoints for Chroma can be found [here](https://huggingface.co/lodestones/Chroma).
+Original model checkpoints for Chroma can be found here:
+* High-resolution finetune: [lodestones/Chroma1-HD](https://huggingface.co/lodestones/Chroma1-HD)
+* Base model: [lodestones/Chroma1-Base](https://huggingface.co/lodestones/Chroma1-Base)
+* Original repo with progress checkpoints: [lodestones/Chroma](https://huggingface.co/lodestones/Chroma) (loading this repo with `from_pretrained` will load a Diffusers-compatible version of the `unlocked-v37` checkpoint)

 > [!TIP]
 > Chroma can use all the same optimizations as Flux.

 ## Inference

-The Diffusers version of Chroma is based on the [`unlocked-v37`](https://huggingface.co/lodestones/Chroma/blob/main/chroma-unlocked-v37.safetensors) version of the original model, which is available in the [Chroma repository](https://huggingface.co/lodestones/Chroma).
-
 ```python
 import torch
 from diffusers import ChromaPipeline

-pipe = ChromaPipeline.from_pretrained("lodestones/Chroma", torch_dtype=torch.bfloat16)
+pipe = ChromaPipeline.from_pretrained("lodestones/Chroma1-HD", torch_dtype=torch.bfloat16)
 pipe.enable_model_cpu_offload()

 prompt = [
@@ -63,10 +64,10 @@ Then run the following example
 import torch
 from diffusers import ChromaTransformer2DModel, ChromaPipeline

-model_id = "lodestones/Chroma"
+model_id = "lodestones/Chroma1-HD"
 dtype = torch.bfloat16

-transformer = ChromaTransformer2DModel.from_single_file("https://huggingface.co/lodestones/Chroma/blob/main/chroma-unlocked-v37.safetensors", torch_dtype=dtype)
+transformer = ChromaTransformer2DModel.from_single_file("https://huggingface.co/lodestones/Chroma1-HD/blob/main/Chroma1-HD.safetensors", torch_dtype=dtype)

 pipe = ChromaPipeline.from_pretrained(model_id, transformer=transformer, torch_dtype=dtype)
 pipe.enable_model_cpu_offload()
@@ -0,0 +1,152 @@
+<!-- Copyright 2025 The HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License. -->
+
+# HunyuanImage2.1
+
+
+HunyuanImage-2.1 is a 17B text-to-image model that is capable of generating 2K (2048 x 2048) resolution images
+
+HunyuanImage-2.1 comes in the following variants:
+
+| model type | model id |
+|:----------:|:--------:|
+| HunyuanImage-2.1 | [hunyuanvideo-community/HunyuanImage-2.1-Diffusers](https://huggingface.co/hunyuanvideo-community/HunyuanImage-2.1-Diffusers) |
+| HunyuanImage-2.1-Distilled | [hunyuanvideo-community/HunyuanImage-2.1-Distilled-Diffusers](https://huggingface.co/hunyuanvideo-community/HunyuanImage-2.1-Distilled-Diffusers) |
+| HunyuanImage-2.1-Refiner | [hunyuanvideo-community/HunyuanImage-2.1-Refiner-Diffusers](https://huggingface.co/hunyuanvideo-community/HunyuanImage-2.1-Refiner-Diffusers) |
+
+> [!TIP]
+> [Caching](../../optimization/cache) may also speed up inference by storing and reusing intermediate outputs.
+
+## HunyuanImage-2.1
+
+HunyuanImage-2.1 applies [Adaptive Projected Guidance (APG)](https://huggingface.co/papers/2410.02416) combined with Classifier-Free Guidance (CFG) in the denoising loop. `HunyuanImagePipeline` has a `guider` component (read more about [Guider](../modular_diffusers/guiders.md)) and does not take a `guidance_scale` parameter at runtime. To change guider-related parameters, e.g., `guidance_scale`, you can update the `guider` configuration instead.
+
+```python
+import torch
+from diffusers import HunyuanImagePipeline
+
+pipe = HunyuanImagePipeline.from_pretrained(
+    "hunyuanvideo-community/HunyuanImage-2.1-Diffusers", 
+    torch_dtype=torch.bfloat16
+)
+pipe = pipe.to("cuda")
+``` 
+
+You can inspect the `guider` object:
+
+```py
+>>> pipe.guider
+AdaptiveProjectedMixGuidance {
+  "_class_name": "AdaptiveProjectedMixGuidance",
+  "_diffusers_version": "0.36.0.dev0",
+  "adaptive_projected_guidance_momentum": -0.5,
+  "adaptive_projected_guidance_rescale": 10.0,
+  "adaptive_projected_guidance_scale": 10.0,
+  "adaptive_projected_guidance_start_step": 5,
+  "enabled": true,
+  "eta": 0.0,
+  "guidance_rescale": 0.0,
+  "guidance_scale": 3.5,
+  "start": 0.0,
+  "stop": 1.0,
+  "use_original_formulation": false
+}
+
+State:
+  step: None
+  num_inference_steps: None
+  timestep: None
+  count_prepared: 0
+  enabled: True
+  num_conditions: 2
+  momentum_buffer: None
+  is_apg_enabled: False
+  is_cfg_enabled: True
+```
+
+To update the guider with a different configuration, use the `new()` method. For example, to generate an image with `guidance_scale=5.0` while keeping all other default guidance parameters:
+
+```py
+import torch
+from diffusers import HunyuanImagePipeline
+
+pipe = HunyuanImagePipeline.from_pretrained(
+    "hunyuanvideo-community/HunyuanImage-2.1-Diffusers", 
+    torch_dtype=torch.bfloat16
+)
+pipe = pipe.to("cuda")
+
+# Update the guider configuration
+pipe.guider = pipe.guider.new(guidance_scale=5.0)
+
+prompt = (
+    "A cute, cartoon-style anthropomorphic penguin plush toy with fluffy fur, standing in a painting studio, "
+    "wearing a red knitted scarf and a red beret with the word 'Tencent' on it, holding a paintbrush with a "
+    "focused expression as it paints an oil painting of the Mona Lisa, rendered in a photorealistic photographic style."
+)
+
+image = pipe(
+    prompt=prompt, 
+    num_inference_steps=50, 
+    height=2048, 
+    width=2048,
+).images[0]
+image.save("image.png")
+```
+
+
+## HunyuanImage-2.1-Distilled
+
+use `distilled_guidance_scale` with the guidance-distilled checkpoint, 
+
+```py
+import torch
+from diffusers import HunyuanImagePipeline
+pipe = HunyuanImagePipeline.from_pretrained("hunyuanvideo-community/HunyuanImage-2.1-Distilled-Diffusers", torch_dtype=torch.bfloat16)
+pipe = pipe.to("cuda")
+
+prompt = (
+    "A cute, cartoon-style anthropomorphic penguin plush toy with fluffy fur, standing in a painting studio, "
+    "wearing a red knitted scarf and a red beret with the word 'Tencent' on it, holding a paintbrush with a "
+    "focused expression as it paints an oil painting of the Mona Lisa, rendered in a photorealistic photographic style."
+)
+
+out = pipe(
+    prompt,
+    num_inference_steps=8,
+    distilled_guidance_scale=3.25,
+    height=2048,
+    width=2048,
+    generator=generator,
+).images[0]
+
+```
+
+
+## HunyuanImagePipeline
+
+[[autodoc]] HunyuanImagePipeline
+  - all
+  - __call__
+
+## HunyuanImageRefinerPipeline
+
+[[autodoc]] HunyuanImageRefinerPipeline
+  - all
+  - __call__
+
+
+## HunyuanImagePipelineOutput
+
+[[autodoc]] pipelines.hunyuan_image.pipeline_output.HunyuanImagePipelineOutput
@@ -0,0 +1,149 @@
+<!--Copyright 2025 The HuggingFace Team. All rights reserved.
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+http://www.apache.org/licenses/LICENSE-2.0
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# Kandinsky 5.0 Video
+
+Kandinsky 5.0 Video is created by the Kandinsky team: Alexey Letunovskiy, Maria Kovaleva, Ivan Kirillov, Lev Novitskiy, Denis Koposov, Dmitrii Mikhailov, Anna Averchenkova, Andrey Shutkin, Julia Agafonova, Olga Kim, Anastasiia Kargapoltseva, Nikita Kiselev, Anna Dmitrienko,  Anastasia Maltseva, Kirill Chernyshev, Ilia Vasiliev, Viacheslav Vasilev, Vladimir Polovnikov, Yury Kolabushin, Alexander Belykh, Mikhail Mamaev, Anastasia Aliaskina, Tatiana Nikulina, Polina Gavrilova, Vladimir Arkhipkin, Vladimir Korviakov, Nikolai Gerasimenko, Denis Parkhomenko, Denis Dimitrov
+
+
+Kandinsky 5.0 is a family of diffusion models for Video & Image generation. Kandinsky 5.0 T2V Lite is a lightweight video generation model (2B parameters) that ranks #1 among open-source models in its class. It outperforms larger models and offers the best understanding of Russian concepts in the open-source ecosystem.
+
+The model introduces several key innovations:
+- **Latent diffusion pipeline** with **Flow Matching** for improved training stability
+- **Diffusion Transformer (DiT)** as the main generative backbone with cross-attention to text embeddings
+- Dual text encoding using **Qwen2.5-VL** and **CLIP** for comprehensive text understanding
+- **HunyuanVideo 3D VAE** for efficient video encoding and decoding
+- **Sparse attention mechanisms** (NABLA) for efficient long-sequence processing
+
+The original codebase can be found at [ai-forever/Kandinsky-5](https://github.com/ai-forever/Kandinsky-5).
+
+> [!TIP]
+> Check out the [AI Forever](https://huggingface.co/ai-forever) organization on the Hub for the official model checkpoints for text-to-video generation, including pretrained, SFT, no-CFG, and distilled variants.
+
+## Available Models
+
+Kandinsky 5.0 T2V Lite comes in several variants optimized for different use cases:
+
+| model_id | Description | Use Cases |
+|------------|-------------|-----------|
+| **ai-forever/Kandinsky-5.0-T2V-Lite-sft-5s-Diffusers** | 5 second Supervised Fine-Tuned model | Highest generation quality |
+| **ai-forever/Kandinsky-5.0-T2V-Lite-sft-10s-Diffusers** | 10 second Supervised Fine-Tuned model | Highest generation quality |
+| **ai-forever/Kandinsky-5.0-T2V-Lite-nocfg-5s-Diffusers** | 5 second Classifier-Free Guidance distilled | 2× faster inference |
+| **ai-forever/Kandinsky-5.0-T2V-Lite-nocfg-10s-Diffusers** | 10 second Classifier-Free Guidance distilled | 2× faster inference |
+| **ai-forever/Kandinsky-5.0-T2V-Lite-distilled16steps-5s-Diffusers** | 5 second Diffusion distilled to 16 steps | 6× faster inference, minimal quality loss |
+| **ai-forever/Kandinsky-5.0-T2V-Lite-distilled16steps-10s-Diffusers** | 10 second Diffusion distilled to 16 steps | 6× faster inference, minimal quality loss |
+| **ai-forever/Kandinsky-5.0-T2V-Lite-pretrain-5s-Diffusers** | 5 second Base pretrained model | Research and fine-tuning |
+| **ai-forever/Kandinsky-5.0-T2V-Lite-pretrain-10s-Diffusers** | 10 second Base pretrained model | Research and fine-tuning |
+
+All models are available in 5-second and 10-second video generation versions.
+
+## Kandinsky5T2VPipeline
+
+[[autodoc]] Kandinsky5T2VPipeline
+    - all
+    - __call__
+
+## Usage Examples
+
+### Basic Text-to-Video Generation
+
+```python
+import torch
+from diffusers import Kandinsky5T2VPipeline
+from diffusers.utils import export_to_video
+
+# Load the pipeline
+model_id = "ai-forever/Kandinsky-5.0-T2V-Lite-sft-5s-Diffusers"
+pipe = Kandinsky5T2VPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
+pipe = pipe.to("cuda")
+
+# Generate video
+prompt = "A cat and a dog baking a cake together in a kitchen."
+negative_prompt = "Static, 2D cartoon, cartoon, 2d animation, paintings, images, worst quality, low quality, ugly, deformed, walking backwards"
+
+output = pipe(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    height=512,
+    width=768,
+    num_frames=121,  # ~5 seconds at 24fps
+    num_inference_steps=50,
+    guidance_scale=5.0,
+).frames[0]
+
+export_to_video(output, "output.mp4", fps=24, quality=9)
+```
+
+### 10 second Models
+**⚠️ Warning!** all 10 second models should be used with Flex attention and max-autotune-no-cudagraphs compilation:
+
+```python
+pipe = Kandinsky5T2VPipeline.from_pretrained(
+    "ai-forever/Kandinsky-5.0-T2V-Lite-sft-10s-Diffusers", 
+    torch_dtype=torch.bfloat16
+)
+pipe = pipe.to("cuda")
+
+pipe.transformer.set_attention_backend(
+    "flex"
+)                                       # <--- Sett attention bakend to Flex
+pipe.transformer.compile(
+    mode="max-autotune-no-cudagraphs", 
+    dynamic=True
+)                                       # <--- Compile with max-autotune-no-cudagraphs
+
+prompt = "A cat and a dog baking a cake together in a kitchen."
+negative_prompt = "Static, 2D cartoon, cartoon, 2d animation, paintings, images, worst quality, low quality, ugly, deformed, walking backwards"
+
+output = pipe(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    height=512,
+    width=768,
+    num_frames=241,
+    num_inference_steps=50,
+    guidance_scale=5.0,
+).frames[0]
+
+export_to_video(output, "output.mp4", fps=24, quality=9)
+```
+
+### Diffusion Distilled model
+**⚠️ Warning!** all nocfg and diffusion distilled models should be infered wothout CFG (```guidance_scale=1.0```):
+
+```python
+model_id = "ai-forever/Kandinsky-5.0-T2V-Lite-distilled16steps-5s-Diffusers"
+pipe = Kandinsky5T2VPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
+pipe = pipe.to("cuda")
+
+output = pipe(
+    prompt="A beautiful sunset over mountains",
+    num_inference_steps=16,  # <--- Model is distilled in 16 steps
+    guidance_scale=1.0,      # <--- no CFG
+).frames[0]
+
+export_to_video(output, "output.mp4", fps=24, quality=9)
+```
+
+
+## Citation
+```bibtex
+@misc{kandinsky2025,
+    author = {Alexey Letunovskiy and Maria Kovaleva and Ivan Kirillov and Lev Novitskiy and Denis Koposov and
+              Dmitrii Mikhailov and Anna Averchenkova and Andrey Shutkin and Julia Agafonova and Olga Kim and
+              Anastasiia Kargapoltseva and Nikita Kiselev and Vladimir Arkhipkin and Vladimir Korviakov and
+              Nikolai Gerasimenko and Denis Parkhomenko and Anna Dmitrienko and Anastasia Maltseva and
+              Kirill Chernyshev and Ilia Vasiliev and Viacheslav Vasilev and Vladimir Polovnikov and
+              Yury Kolabushin and Alexander Belykh and Mikhail Mamaev and Anastasia Aliaskina and
+              Tatiana Nikulina and Polina Gavrilova and Denis Dimitrov},
+    title = {Kandinsky 5.0: A family of diffusion models for Video & Image generation},
+    howpublished = {\url{https://github.com/ai-forever/Kandinsky-5}},
+    year = 2025
+}
+```
@@ -0,0 +1,131 @@
+<!-- Copyright 2025 The HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License. -->
+
+# PRX
+
+
+PRX generates high-quality images from text using a simplified MMDIT architecture where text tokens don't update through transformer blocks. It employs flow matching with discrete scheduling for efficient sampling and uses Google's T5Gemma-2B-2B-UL2 model for multi-language text encoding. The ~1.3B parameter transformer delivers fast inference without sacrificing quality. You can choose between Flux VAE (8x compression, 16 latent channels) for balanced quality and speed or DC-AE (32x compression, 32 latent channels) for latent compression and faster processing.
+
+## Available models
+
+PRX offers multiple variants with different VAE configurations, each optimized for specific resolutions. Base models excel with detailed prompts, capturing complex compositions and subtle details. Fine-tuned models trained on the [Alchemist dataset](https://huggingface.co/datasets/yandex/alchemist) improve aesthetic quality, especially with simpler prompts.
+
+
+| Model | Resolution | Fine-tuned | Distilled | Description | Suggested prompts | Suggested parameters | Recommended dtype |
+|:-----:|:-----------------:|:----------:|:----------:|:----------:|:----------:|:----------:|:----------:|
+| [`Photoroom/prx-256-t2i`](https://huggingface.co/Photoroom/prx-256-t2i)| 256 | No | No | Base model pre-trained at 256 with Flux VAE|Works best with detailed prompts in natural language|28 steps, cfg=5.0| `torch.bfloat16` |
+| [`Photoroom/prx-256-t2i-sft`](https://huggingface.co/Photoroom/prx-256-t2i-sft)| 512 | Yes | No | Fine-tuned on the [Alchemist dataset](https://huggingface.co/datasets/yandex/alchemist) dataset with Flux VAE | Can handle less detailed prompts|28 steps, cfg=5.0| `torch.bfloat16` |
+| [`Photoroom/prx-512-t2i`](https://huggingface.co/Photoroom/prx-512-t2i)| 512 | No | No | Base model pre-trained at 512 with Flux VAE |Works best with detailed prompts in natural language|28 steps, cfg=5.0| `torch.bfloat16` |
+| [`Photoroom/prx-512-t2i-sft`](https://huggingface.co/Photoroom/prx-512-t2i-sft)| 512 | Yes | No | Fine-tuned on the [Alchemist dataset](https://huggingface.co/datasets/yandex/alchemist) dataset with Flux VAE | Can handle less detailed prompts in natural language|28 steps, cfg=5.0| `torch.bfloat16` |
+| [`Photoroom/prx-512-t2i-sft-distilled`](https://huggingface.co/Photoroom/prx-512-t2i-sft-distilled)| 512 | Yes | Yes | 8-step distilled model from [`Photoroom/prx-512-t2i-sft`](https://huggingface.co/Photoroom/prx-512-t2i-sft) | Can handle less detailed prompts in natural language|8 steps, cfg=1.0| `torch.bfloat16` |
+| [`Photoroom/prx-512-t2i-dc-ae`](https://huggingface.co/Photoroom/prx-512-t2i-dc-ae)| 512 | No | No | Base model pre-trained at 512 with [Deep Compression Autoencoder (DC-AE)](https://hanlab.mit.edu/projects/dc-ae)|Works best with detailed prompts in natural language|28 steps, cfg=5.0| `torch.bfloat16` |
+| [`Photoroom/prx-512-t2i-dc-ae-sft`](https://huggingface.co/Photoroom/prx-512-t2i-dc-ae-sft)| 512 | Yes | No | Fine-tuned on the [Alchemist dataset](https://huggingface.co/datasets/yandex/alchemist) dataset with [Deep Compression Autoencoder (DC-AE)](https://hanlab.mit.edu/projects/dc-ae) | Can handle less detailed prompts in natural language|28 steps, cfg=5.0| `torch.bfloat16` |
+| [`Photoroom/prx-512-t2i-dc-ae-sft-distilled`](https://huggingface.co/Photoroom/prx-512-t2i-dc-ae-sft-distilled)| 512 | Yes | Yes | 8-step distilled model from [`Photoroom/prx-512-t2i-dc-ae-sft-distilled`](https://huggingface.co/Photoroom/prx-512-t2i-dc-ae-sft-distilled) | Can handle less detailed prompts in natural language|8 steps, cfg=1.0| `torch.bfloat16` |s
+
+Refer to [this](https://huggingface.co/collections/Photoroom/prx-models-68e66254c202ebfab99ad38e) collection for more information.
+
+## Loading the pipeline
+
+Load the pipeline with [`~DiffusionPipeline.from_pretrained`].
+
+```py
+from diffusers.pipelines.prx import PRXPipeline
+
+# Load pipeline - VAE and text encoder will be loaded from HuggingFace
+pipe = PRXPipeline.from_pretrained("Photoroom/prx-512-t2i-sft", torch_dtype=torch.bfloat16)
+pipe.to("cuda")
+
+prompt = "A front-facing portrait of a lion the golden savanna at sunset."
+image = pipe(prompt, num_inference_steps=28, guidance_scale=5.0).images[0]
+image.save("prx_output.png")
+```
+
+### Manual Component Loading
+
+Load components individually to customize the pipeline for instance to use quantized models.
+
+```py
+import torch
+from diffusers.pipelines.prx import PRXPipeline
+from diffusers.models import AutoencoderKL, AutoencoderDC
+from diffusers.models.transformers.transformer_prx import PRXTransformer2DModel
+from diffusers.schedulers import FlowMatchEulerDiscreteScheduler
+from transformers import T5GemmaModel, GemmaTokenizerFast
+from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig
+from transformers import BitsAndBytesConfig as BitsAndBytesConfig
+
+quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
+# Load transformer
+transformer = PRXTransformer2DModel.from_pretrained(
+    "checkpoints/prx-512-t2i-sft",
+    subfolder="transformer",
+    quantization_config=quant_config,
+    torch_dtype=torch.bfloat16,
+)
+
+# Load scheduler
+scheduler = FlowMatchEulerDiscreteScheduler.from_pretrained(
+    "checkpoints/prx-512-t2i-sft", subfolder="scheduler"
+)
+
+# Load T5Gemma text encoder
+t5gemma_model = T5GemmaModel.from_pretrained("google/t5gemma-2b-2b-ul2",
+                                            quantization_config=quant_config,
+                                            torch_dtype=torch.bfloat16)
+text_encoder = t5gemma_model.encoder.to(dtype=torch.bfloat16)
+tokenizer = GemmaTokenizerFast.from_pretrained("google/t5gemma-2b-2b-ul2")
+tokenizer.model_max_length = 256
+
+# Load VAE - choose either Flux VAE or DC-AE
+# Flux VAE
+vae = AutoencoderKL.from_pretrained("black-forest-labs/FLUX.1-dev",
+                                    subfolder="vae",
+                                    quantization_config=quant_config,
+                                    torch_dtype=torch.bfloat16)
+
+pipe = PRXPipeline(
+    transformer=transformer,
+    scheduler=scheduler,
+    text_encoder=text_encoder,
+    tokenizer=tokenizer,
+    vae=vae
+)
+pipe.to("cuda")
+```
+
+
+## Memory Optimization
+
+For memory-constrained environments:
+
+```py
+import torch
+from diffusers.pipelines.prx import PRXPipeline
+
+pipe = PRXPipeline.from_pretrained("Photoroom/prx-512-t2i-sft", torch_dtype=torch.bfloat16)
+pipe.enable_model_cpu_offload()  # Offload components to CPU when not in use
+
+# Or use sequential CPU offload for even lower memory
+pipe.enable_sequential_cpu_offload()
+```
+
+## PRXPipeline
+
+[[autodoc]] PRXPipeline
+  - all
+  - __call__
+
+## PRXPipelineOutput
+
+[[autodoc]] pipelines.prx.pipeline_output.PRXPipelineOutput
@@ -24,9 +24,6 @@ The abstract from the paper is:

 *This paper presents SANA-Sprint, an efficient diffusion model for ultra-fast text-to-image (T2I) generation. SANA-Sprint is built on a pre-trained foundation model and augmented with hybrid distillation, dramatically reducing inference steps from 20 to 1-4. We introduce three key innovations: (1) We propose a training-free approach that transforms a pre-trained flow-matching model for continuous-time consistency distillation (sCM), eliminating costly training from scratch and achieving high training efficiency. Our hybrid distillation strategy combines sCM with latent adversarial distillation (LADD): sCM ensures alignment with the teacher model, while LADD enhances single-step generation fidelity. (2) SANA-Sprint is a unified step-adaptive model that achieves high-quality generation in 1-4 steps, eliminating step-specific training and improving efficiency. (3) We integrate ControlNet with SANA-Sprint for real-time interactive image generation, enabling instant visual feedback for user interaction. SANA-Sprint establishes a new Pareto frontier in speed-quality tradeoffs, achieving state-of-the-art performance with 7.59 FID and 0.74 GenEval in only 1 step — outperforming FLUX-schnell (7.94 FID / 0.71 GenEval) while being 10× faster (0.1s vs 1.1s on H100). It also achieves 0.1s (T2I) and 0.25s (ControlNet) latency for 1024×1024 images on H100, and 0.31s (T2I) on an RTX 4090, showcasing its exceptional efficiency and potential for AI-powered consumer applications (AIPC). Code and pre-trained models will be open-sourced.*

-> [!TIP]
-> Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
-
 This pipeline was contributed by [lawrence-cj](https://github.com/lawrence-cj), [shuchen Xue](https://github.com/scxue) and [Enze Xie](https://github.com/xieenze). The original codebase can be found [here](https://github.com/NVlabs/Sana). The original weights can be found under [hf.co/Efficient-Large-Model](https://huggingface.co/Efficient-Large-Model/).

 Available models:
@@ -0,0 +1,102 @@
+<!-- Copyright 2025 The SANA-Video Authors and HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License. -->
+
+# SanaVideoPipeline
+
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+  <img alt="MPS" src="https://img.shields.io/badge/MPS-000000?style=flat&logo=apple&logoColor=white%22">
+</div>
+
+[SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer](https://huggingface.co/papers/2509.24695) from NVIDIA and MIT HAN Lab, by Junsong Chen, Yuyang Zhao, Jincheng Yu, Ruihang Chu, Junyu Chen, Shuai Yang, Xianbang Wang, Yicheng Pan, Daquan Zhou, Huan Ling, Haozhe Liu, Hongwei Yi, Hao Zhang, Muyang Li, Yukang Chen, Han Cai, Sanja Fidler, Ping Luo, Song Han, Enze Xie.
+
+The abstract from the paper is:
+
+*We introduce SANA-Video, a small diffusion model that can efficiently generate videos up to 720x1280 resolution and minute-length duration. SANA-Video synthesizes high-resolution, high-quality and long videos with strong text-video alignment at a remarkably fast speed, deployable on RTX 5090 GPU. Two core designs ensure our efficient, effective and long video generation: (1) Linear DiT: We leverage linear attention as the core operation, which is more efficient than vanilla attention given the large number of tokens processed in video generation. (2) Constant-Memory KV cache for Block Linear Attention: we design block-wise autoregressive approach for long video generation by employing a constant-memory state, derived from the cumulative properties of linear attention. This KV cache provides the Linear DiT with global context at a fixed memory cost, eliminating the need for a traditional KV cache and enabling efficient, minute-long video generation. In addition, we explore effective data filters and model training strategies, narrowing the training cost to 12 days on 64 H100 GPUs, which is only 1% of the cost of MovieGen. Given its low cost, SANA-Video achieves competitive performance compared to modern state-of-the-art small diffusion models (e.g., Wan 2.1-1.3B and SkyReel-V2-1.3B) while being 16x faster in measured latency. Moreover, SANA-Video can be deployed on RTX 5090 GPUs with NVFP4 precision, accelerating the inference speed of generating a 5-second 720p video from 71s to 29s (2.4x speedup). In summary, SANA-Video enables low-cost, high-quality video generation. [this https URL](https://github.com/NVlabs/SANA).*
+
+This pipeline was contributed by SANA Team. The original codebase can be found [here](https://github.com/NVlabs/Sana). The original weights can be found under [hf.co/Efficient-Large-Model](https://hf.co/collections/Efficient-Large-Model/sana-video).
+
+Available models:
+
+| Model | Recommended dtype |
+|:-----:|:-----------------:|
+| [`Efficient-Large-Model/SANA-Video_2B_480p_diffusers`](https://huggingface.co/Efficient-Large-Model/ANA-Video_2B_480p_diffusers) | `torch.bfloat16` |
+
+Refer to [this](https://huggingface.co/collections/Efficient-Large-Model/sana-video) collection for more information.
+
+Note: The recommended dtype mentioned is for the transformer weights. The text encoder and VAE weights must stay in `torch.bfloat16` or `torch.float32` for the model to work correctly. Please refer to the inference example below to see how to load the model with the recommended dtype. 
+
+## Quantization
+
+Quantization helps reduce the memory requirements of very large models by storing model weights in a lower precision data type. However, quantization may have varying impact on video quality depending on the video model.
+
+Refer to the [Quantization](../../quantization/overview) overview to learn more about supported quantization backends and selecting a quantization backend that supports your use case. The example below demonstrates how to load a quantized [`SanaVideoPipeline`] for inference with bitsandbytes.
+
+```py
+import torch
+from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, SanaVideoTransformer3DModel, SanaVideoPipeline
+from transformers import BitsAndBytesConfig as BitsAndBytesConfig, AutoModel
+
+quant_config = BitsAndBytesConfig(load_in_8bit=True)
+text_encoder_8bit = AutoModel.from_pretrained(
+    "Efficient-Large-Model/SANA-Video_2B_480p_diffusers",
+    subfolder="text_encoder",
+    quantization_config=quant_config,
+    torch_dtype=torch.float16,
+)
+
+quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
+transformer_8bit = SanaVideoTransformer3DModel.from_pretrained(
+    "Efficient-Large-Model/SANA-Video_2B_480p_diffusers",
+    subfolder="transformer",
+    quantization_config=quant_config,
+    torch_dtype=torch.float16,
+)
+
+pipeline = SanaVideoPipeline.from_pretrained(
+    "Efficient-Large-Model/SANA-Video_2B_480p_diffusers",
+    text_encoder=text_encoder_8bit,
+    transformer=transformer_8bit,
+    torch_dtype=torch.float16,
+    device_map="balanced",
+)
+
+model_score = 30
+prompt = "Evening, backlight, side lighting, soft light, high contrast, mid-shot, centered composition, clean solo shot, warm color. A young Caucasian man stands in a forest, golden light glimmers on his hair as sunlight filters through the leaves. He wears a light shirt, wind gently blowing his hair and collar, light dances across his face with his movements. The background is blurred, with dappled light and soft tree shadows in the distance. The camera focuses on his lifted gaze, clear and emotional."
+negative_prompt = "A chaotic sequence with misshapen, deformed limbs in heavy motion blur, sudden disappearance, jump cuts, jerky movements, rapid shot changes, frames out of sync, inconsistent character shapes, temporal artifacts, jitter, and ghosting effects, creating a disorienting visual experience."
+motion_prompt = f" motion score: {model_score}."
+prompt = prompt + motion_prompt
+
+output = pipeline(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    height=480,
+    width=832,
+    num_frames=81,
+    guidance_scale=6.0,
+    num_inference_steps=50
+).frames[0]
+export_to_video(output, "sana-video-output.mp4", fps=16)
+```
+
+## SanaVideoPipeline
+
+[[autodoc]] SanaVideoPipeline
+  - all
+  - __call__
+
+
+## SanaVideoPipelineOutput
+
+[[autodoc]] pipelines.sana.pipeline_sana_video.SanaVideoPipelineOutput
@@ -21,7 +21,7 @@ The Stable Diffusion model can also infer depth based on an image using [MiDaS](
 > [!TIP]
 > Make sure to check out the Stable Diffusion [Tips](overview#tips) section to learn how to explore the tradeoff between scheduler speed and quality, and how to reuse pipeline components efficiently!
 >
-> If you're interested in using one of the official checkpoints for a task, explore the [CompVis](https://huggingface.co/CompVis), [Runway](https://huggingface.co/runwayml), and [Stability AI](https://huggingface.co/stabilityai) Hub organizations!
+> If you're interested in using one of the official checkpoints for a task, explore the [CompVis](https://huggingface.co/CompVis) and [Stability AI](https://huggingface.co/stabilityai) Hub organizations!

 ## StableDiffusionDepth2ImgPipeline

@@ -21,14 +21,14 @@ The Stable Diffusion model can also be applied to inpainting which lets you edit
 ## Tips

 It is recommended to use this pipeline with checkpoints that have been specifically fine-tuned for inpainting, such
-as [runwayml/stable-diffusion-inpainting](https://huggingface.co/runwayml/stable-diffusion-inpainting). Default
+as [stable-diffusion-v1-5/stable-diffusion-inpainting](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-inpainting). Default
 text-to-image Stable Diffusion checkpoints, such as
 [stable-diffusion-v1-5/stable-diffusion-v1-5](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) are also compatible but they might be less performant.

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

 ## StableDiffusionInpaintPipeline

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

 ## StableDiffusionLatentUpscalePipeline

@@ -22,7 +22,7 @@ Stable Diffusion is trained on 512x512 images from a subset of the LAION-5B data

 For more details about how Stable Diffusion works and how it differs from the base latent diffusion model, take a look at the Stability AI [announcement](https://stability.ai/blog/stable-diffusion-announcement) and our own [blog post](https://huggingface.co/blog/stable_diffusion#how-does-stable-diffusion-work) for more technical details.

-You can find the original codebase for Stable Diffusion v1.0 at [CompVis/stable-diffusion](https://github.com/CompVis/stable-diffusion) and Stable Diffusion v2.0 at [Stability-AI/stablediffusion](https://github.com/Stability-AI/stablediffusion) as well as their original scripts for various tasks. Additional official checkpoints for the different Stable Diffusion versions and tasks can be found on the [CompVis](https://huggingface.co/CompVis), [Runway](https://huggingface.co/runwayml), and [Stability AI](https://huggingface.co/stabilityai) Hub organizations. Explore these organizations to find the best checkpoint for your use-case!
+You can find the original codebase for Stable Diffusion v1.0 at [CompVis/stable-diffusion](https://github.com/CompVis/stable-diffusion) and Stable Diffusion v2.0 at [Stability-AI/stablediffusion](https://github.com/Stability-AI/stablediffusion) as well as their original scripts for various tasks. Additional official checkpoints for the different Stable Diffusion versions and tasks can be found on the [CompVis](https://huggingface.co/CompVis) and [Stability AI](https://huggingface.co/stabilityai) Hub organizations. Explore these organizations to find the best checkpoint for your use-case!

 The table below summarizes the available Stable Diffusion pipelines, their supported tasks, and an interactive demo:

@@ -64,7 +64,7 @@ The table below summarizes the available Stable Diffusion pipelines, their suppo
            <a href="./inpaint">StableDiffusionInpaint</a>
            </td>
            <td class="px-4 py-2 text-gray-700">inpainting</td>
-            <td class="px-4 py-2"><a href="https://huggingface.co/spaces/runwayml/stable-diffusion-inpainting"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue"/></a>
+            <td class="px-4 py-2"><a href="https://huggingface.co/spaces/stable-diffusion-v1-5/stable-diffusion-inpainting"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue"/></a>
            </td>
        </tr>
        <tr>
@@ -36,7 +36,7 @@ Here are some examples for how to use Stable Diffusion 2 for each task:
 > [!TIP]
 > Make sure to check out the Stable Diffusion [Tips](overview#tips) section to learn how to explore the tradeoff between scheduler speed and quality, and how to reuse pipeline components efficiently!
 >
-> If you're interested in using one of the official checkpoints for a task, explore the [CompVis](https://huggingface.co/CompVis), [Runway](https://huggingface.co/runwayml), and [Stability AI](https://huggingface.co/stabilityai) Hub organizations!
+> If you're interested in using one of the official checkpoints for a task, explore the [CompVis](https://huggingface.co/CompVis) and [Stability AI](https://huggingface.co/stabilityai) Hub organizations!

 ## Text-to-image

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

 ## StableDiffusionPipeline

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

 ## StableDiffusionUpscalePipeline

@@ -0,0 +1,492 @@
+<!--Copyright 2025 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+
+# Building Custom Blocks
+
+[ModularPipelineBlocks](./pipeline_block) are the fundamental building blocks of a [`ModularPipeline`]. You can create custom blocks by defining their inputs, outputs, and computation logic. This guide demonstrates how to create and use a custom block.
+
+> [!TIP]
+> Explore the [Modular Diffusers Custom Blocks](https://huggingface.co/collections/diffusers/modular-diffusers-custom-blocks) collection for official custom modular blocks like Nano Banana.
+
+## Project Structure
+
+Your custom block project should use the following structure:
+
+```shell
+.
+├── block.py
+└── modular_config.json
+```
+
+- `block.py` contains the custom block implementation
+- `modular_config.json` contains the metadata needed to load the block
+
+## Example: Florence 2 Inpainting Block
+
+In this example we will create a custom block that uses the [Florence 2](https://huggingface.co/docs/transformers/model_doc/florence2) model to process an input image and generate a mask for inpainting.
+
+The first step is to define the components that the block will use. In this case, we will need to use the `Florence2ForConditionalGeneration` model and its corresponding processor `AutoProcessor`. When defining components, we must specify the name of the component within our pipeline, model class via `type_hint`, and provide a `pretrained_model_name_or_path` for the component if we intend to load the model weights from a specific repository on the Hub.
+
+```py
+# Inside block.py
+from diffusers.modular_pipelines import (
+    ModularPipelineBlocks,
+    ComponentSpec,
+)
+from transformers import AutoProcessor, Florence2ForConditionalGeneration
+
+
+class Florence2ImageAnnotatorBlock(ModularPipelineBlocks):
+
+    @property
+    def expected_components(self):
+        return [
+            ComponentSpec(
+                name="image_annotator",
+                type_hint=Florence2ForConditionalGeneration,
+                pretrained_model_name_or_path="florence-community/Florence-2-base-ft",
+            ),
+            ComponentSpec(
+                name="image_annotator_processor",
+                type_hint=AutoProcessor,
+                pretrained_model_name_or_path="florence-community/Florence-2-base-ft",
+            ),
+        ]
+```
+
+Next, we define the inputs and outputs of the block. The inputs include the image to be annotated, the annotation task, and the annotation prompt. The outputs include the generated mask image and annotations.
+
+```py
+from typing import List, Union
+from PIL import Image, ImageDraw
+import torch
+import numpy as np
+
+from diffusers.modular_pipelines import (
+    PipelineState,
+    ModularPipelineBlocks,
+    InputParam,
+    ComponentSpec,
+    OutputParam,
+)
+from transformers import AutoProcessor, Florence2ForConditionalGeneration
+
+
+class Florence2ImageAnnotatorBlock(ModularPipelineBlocks):
+
+    @property
+    def expected_components(self):
+        return [
+            ComponentSpec(
+                name="image_annotator",
+                type_hint=Florence2ForConditionalGeneration,
+                pretrained_model_name_or_path="florence-community/Florence-2-base-ft",
+            ),
+            ComponentSpec(
+                name="image_annotator_processor",
+                type_hint=AutoProcessor,
+                pretrained_model_name_or_path="florence-community/Florence-2-base-ft",
+            ),
+        ]
+
+    @property
+    def inputs(self) -> List[InputParam]:
+        return [
+            InputParam(
+                "image",
+                type_hint=Union[Image.Image, List[Image.Image]],
+                required=True,
+                description="Image(s) to annotate",
+            ),
+            InputParam(
+                "annotation_task",
+                type_hint=Union[str, List[str]],
+                required=True,
+                default="<REFERRING_EXPRESSION_SEGMENTATION>",
+                description="""Annotation Task to perform on the image.
+                Supported Tasks:
+
+                <OD>
+                <REFERRING_EXPRESSION_SEGMENTATION>
+                <CAPTION>
+                <DETAILED_CAPTION>
+                <MORE_DETAILED_CAPTION>
+                <DENSE_REGION_CAPTION>
+                <CAPTION_TO_PHRASE_GROUNDING>
+                <OPEN_VOCABULARY_DETECTION>
+
+                """,
+            ),
+            InputParam(
+                "annotation_prompt",
+                type_hint=Union[str, List[str]],
+                required=True,
+                description="""Annotation Prompt to provide more context to the task.
+                Can be used to detect or segment out specific elements in the image
+                """,
+            ),
+            InputParam(
+                "annotation_output_type",
+                type_hint=str,
+                required=True,
+                default="mask_image",
+                description="""Output type from annotation predictions. Availabe options are
+                mask_image:
+                    -black and white mask image for the given image based on the task type
+                mask_overlay:
+                    - mask overlayed on the original image
+                bounding_box:
+                    - bounding boxes drawn on the original image
+                """,
+            ),
+            InputParam(
+                "annotation_overlay",
+                type_hint=bool,
+                required=True,
+                default=False,
+                description="",
+            ),
+        ]
+
+    @property
+    def intermediate_outputs(self) -> List[OutputParam]:
+        return [
+            OutputParam(
+                "mask_image",
+                type_hint=Image,
+                description="Inpainting Mask for input Image(s)",
+            ),
+            OutputParam(
+                "annotations",
+                type_hint=dict,
+                description="Annotations Predictions for input Image(s)",
+            ),
+            OutputParam(
+                "image",
+                type_hint=Image,
+                description="Annotated input Image(s)",
+            ),
+        ]
+
+```
+
+Now we implement the `__call__` method, which contains the logic for processing the input image and generating the mask.
+
+```py
+from typing import List, Union
+from PIL import Image, ImageDraw
+import torch
+import numpy as np
+
+from diffusers.modular_pipelines import (
+    PipelineState,
+    ModularPipelineBlocks,
+    InputParam,
+    ComponentSpec,
+    OutputParam,
+)
+from transformers import AutoProcessor, Florence2ForConditionalGeneration
+
+
+class Florence2ImageAnnotatorBlock(ModularPipelineBlocks):
+
+    @property
+    def expected_components(self):
+        return [
+            ComponentSpec(
+                name="image_annotator",
+                type_hint=Florence2ForConditionalGeneration,
+                pretrained_model_name_or_path="florence-community/Florence-2-base-ft",
+            ),
+            ComponentSpec(
+                name="image_annotator_processor",
+                type_hint=AutoProcessor,
+                pretrained_model_name_or_path="florence-community/Florence-2-base-ft",
+            ),
+        ]
+
+    @property
+    def inputs(self) -> List[InputParam]:
+        return [
+            InputParam(
+                "image",
+                type_hint=Union[Image.Image, List[Image.Image]],
+                required=True,
+                description="Image(s) to annotate",
+            ),
+            InputParam(
+                "annotation_task",
+                type_hint=Union[str, List[str]],
+                required=True,
+                default="<REFERRING_EXPRESSION_SEGMENTATION>",
+                description="""Annotation Task to perform on the image.
+                Supported Tasks:
+
+                <OD>
+                <REFERRING_EXPRESSION_SEGMENTATION>
+                <CAPTION>
+                <DETAILED_CAPTION>
+                <MORE_DETAILED_CAPTION>
+                <DENSE_REGION_CAPTION>
+                <CAPTION_TO_PHRASE_GROUNDING>
+                <OPEN_VOCABULARY_DETECTION>
+
+                """,
+            ),
+            InputParam(
+                "annotation_prompt",
+                type_hint=Union[str, List[str]],
+                required=True,
+                description="""Annotation Prompt to provide more context to the task.
+                Can be used to detect or segment out specific elements in the image
+                """,
+            ),
+            InputParam(
+                "annotation_output_type",
+                type_hint=str,
+                required=True,
+                default="mask_image",
+                description="""Output type from annotation predictions. Availabe options are
+                mask_image:
+                    -black and white mask image for the given image based on the task type
+                mask_overlay:
+                    - mask overlayed on the original image
+                bounding_box:
+                    - bounding boxes drawn on the original image
+                """,
+            ),
+            InputParam(
+                "annotation_overlay",
+                type_hint=bool,
+                required=True,
+                default=False,
+                description="",
+            ),
+        ]
+
+    @property
+    def intermediate_outputs(self) -> List[OutputParam]:
+        return [
+            OutputParam(
+                "mask_image",
+                type_hint=Image,
+                description="Inpainting Mask for input Image(s)",
+            ),
+            OutputParam(
+                "annotations",
+                type_hint=dict,
+                description="Annotations Predictions for input Image(s)",
+            ),
+            OutputParam(
+                "image",
+                type_hint=Image,
+                description="Annotated input Image(s)",
+            ),
+        ]
+
+    def get_annotations(self, components, images, prompts, task):
+        task_prompts = [task + prompt for prompt in prompts]
+
+        inputs = components.image_annotator_processor(
+            text=task_prompts, images=images, return_tensors="pt"
+        ).to(components.image_annotator.device, components.image_annotator.dtype)
+
+        generated_ids = components.image_annotator.generate(
+            input_ids=inputs["input_ids"],
+            pixel_values=inputs["pixel_values"],
+            max_new_tokens=1024,
+            early_stopping=False,
+            do_sample=False,
+            num_beams=3,
+        )
+        annotations = components.image_annotator_processor.batch_decode(
+            generated_ids, skip_special_tokens=False
+        )
+        outputs = []
+        for image, annotation in zip(images, annotations):
+            outputs.append(
+                components.image_annotator_processor.post_process_generation(
+                    annotation, task=task, image_size=(image.width, image.height)
+                )
+            )
+        return outputs
+
+    def prepare_mask(self, images, annotations, overlay=False, fill="white"):
+        masks = []
+        for image, annotation in zip(images, annotations):
+            mask_image = image.copy() if overlay else Image.new("L", image.size, 0)
+            draw = ImageDraw.Draw(mask_image)
+
+            for _, _annotation in annotation.items():
+                if "polygons" in _annotation:
+                    for polygon in _annotation["polygons"]:
+                        polygon = np.array(polygon).reshape(-1, 2)
+                        if len(polygon) < 3:
+                            continue
+                        polygon = polygon.reshape(-1).tolist()
+                        draw.polygon(polygon, fill=fill)
+
+                elif "bbox" in _annotation:
+                    bbox = _annotation["bbox"]
+                    draw.rectangle(bbox, fill="white")
+
+            masks.append(mask_image)
+
+        return masks
+
+    def prepare_bounding_boxes(self, images, annotations):
+        outputs = []
+        for image, annotation in zip(images, annotations):
+            image_copy = image.copy()
+            draw = ImageDraw.Draw(image_copy)
+            for _, _annotation in annotation.items():
+                bbox = _annotation["bbox"]
+                label = _annotation["label"]
+
+                draw.rectangle(bbox, outline="red", width=3)
+                draw.text((bbox[0], bbox[1] - 20), label, fill="red")
+
+            outputs.append(image_copy)
+
+        return outputs
+
+    def prepare_inputs(self, images, prompts):
+        prompts = prompts or ""
+
+        if isinstance(images, Image.Image):
+            images = [images]
+        if isinstance(prompts, str):
+            prompts = [prompts]
+
+        if len(images) != len(prompts):
+            raise ValueError("Number of images and annotation prompts must match.")
+
+        return images, prompts
+
+    @torch.no_grad()
+    def __call__(self, components, state: PipelineState) -> PipelineState:
+        block_state = self.get_block_state(state)
+        images, annotation_task_prompt = self.prepare_inputs(
+            block_state.image, block_state.annotation_prompt
+        )
+        task = block_state.annotation_task
+        fill = block_state.fill
+
+        annotations = self.get_annotations(
+            components, images, annotation_task_prompt, task
+        )
+        block_state.annotations = annotations
+        if block_state.annotation_output_type == "mask_image":
+            block_state.mask_image = self.prepare_mask(images, annotations)
+        else:
+            block_state.mask_image = None
+
+        if block_state.annotation_output_type == "mask_overlay":
+            block_state.image = self.prepare_mask(images, annotations, overlay=True, fill=fill)
+
+        elif block_state.annotation_output_type == "bounding_box":
+            block_state.image = self.prepare_bounding_boxes(images, annotations)
+
+        self.set_block_state(state, block_state)
+
+        return components, state
+
+```
+
+Once we have defined our custom block, we can save it to the Hub, using either the CLI or the [`push_to_hub`] method. This will make it easy to share and reuse our custom block with other pipelines.
+
+<hfoptions id="share">
+<hfoption id="hf CLI">
+
+```shell
+# In the folder with the `block.py` file, run:
+diffusers-cli custom_block
+```
+
+Then upload the block to the Hub:
+
+```shell
+hf upload <your repo id> . .
+```
+</hfoption>
+<hfoption id="push_to_hub">
+
+```py
+from block import Florence2ImageAnnotatorBlock
+block = Florence2ImageAnnotatorBlock()
+block.push_to_hub("<your repo id>")
+```
+
+</hfoption>
+</hfoptions>
+
+## Using Custom Blocks
+
+Load the custom block with [`~ModularPipelineBlocks.from_pretrained`] and set `trust_remote_code=True`.
+
+```py
+import torch
+from diffusers.modular_pipelines import ModularPipelineBlocks, SequentialPipelineBlocks
+from diffusers.modular_pipelines.stable_diffusion_xl import INPAINT_BLOCKS
+from diffusers.utils import load_image
+
+# Fetch the Florence2 image annotator block that will create our mask
+image_annotator_block = ModularPipelineBlocks.from_pretrained("diffusers/florence-2-custom-block", trust_remote_code=True)
+
+my_blocks = INPAINT_BLOCKS.copy()
+# insert the annotation block before the image encoding step
+my_blocks.insert("image_annotator", image_annotator_block, 1)
+
+# Create our initial set of inpainting blocks
+blocks = SequentialPipelineBlocks.from_blocks_dict(my_blocks)
+
+repo_id = "diffusers/modular-stable-diffusion-xl-base-1.0"
+pipe = blocks.init_pipeline(repo_id)
+pipe.load_components(torch_dtype=torch.float16, device_map="cuda", trust_remote_code=True)
+
+image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg?download=true")
+image = image.resize((1024, 1024))
+
+prompt = ["A red car"]
+annotation_task = "<REFERRING_EXPRESSION_SEGMENTATION>"
+annotation_prompt = ["the car"]
+
+output = pipe(
+    prompt=prompt,
+    image=image,
+    annotation_task=annotation_task,
+    annotation_prompt=annotation_prompt,
+    annotation_output_type="mask_image",
+    num_inference_steps=35,
+    guidance_scale=7.5,
+    strength=0.95,
+    output="images"
+)
+output[0].save("florence-inpainting.png")
+```
+
+## Editing Custom Blocks
+
+By default, custom blocks are saved in your cache directory. Use the `local_dir` argument to download and edit a custom block in a specific folder.
+
+```py
+import torch
+from diffusers.modular_pipelines import ModularPipelineBlocks, SequentialPipelineBlocks
+from diffusers.modular_pipelines.stable_diffusion_xl import INPAINT_BLOCKS
+from diffusers.utils import load_image
+
+# Fetch the Florence2 image annotator block that will create our mask
+image_annotator_block = ModularPipelineBlocks.from_pretrained("diffusers/florence-2-custom-block", trust_remote_code=True, local_dir="/my-local-folder")
+```
+
+Any changes made to the block files in this folder will be reflected when you load the block again.
@@ -21,6 +21,7 @@ Refer to the table below for an overview of the available attention families and
 | attention family | main feature |
 |---|---|
 | FlashAttention | minimizes memory reads/writes through tiling and recomputation |
+| AI Tensor Engine for ROCm | FlashAttention implementation optimized for AMD ROCm accelerators |
 | SageAttention | quantizes attention to int8 |
 | PyTorch native | built-in PyTorch implementation using [scaled_dot_product_attention](./fp16#scaled-dot-product-attention) |
 | xFormers | memory-efficient attention with support for various attention kernels |
@@ -139,6 +140,7 @@ Refer to the table below for a complete list of available attention backends and
 | `_native_xla` | [PyTorch native](https://docs.pytorch.org/docs/stable/generated/torch.nn.attention.SDPBackend.html#torch.nn.attention.SDPBackend) | XLA-optimized attention |
 | `flash` | [FlashAttention](https://github.com/Dao-AILab/flash-attention) | FlashAttention-2 |
 | `flash_varlen` | [FlashAttention](https://github.com/Dao-AILab/flash-attention) | Variable length FlashAttention |
+| `aiter` | [AI Tensor Engine for ROCm](https://github.com/ROCm/aiter) | FlashAttention for AMD ROCm |
 | `_flash_3` | [FlashAttention](https://github.com/Dao-AILab/flash-attention) | FlashAttention-3 |
 | `_flash_varlen_3` | [FlashAttention](https://github.com/Dao-AILab/flash-attention) | Variable length FlashAttention-3 |
 | `_flash_3_hub` | [FlashAttention](https://github.com/Dao-AILab/flash-attention) | FlashAttention-3 from kernels |
@@ -16,12 +16,12 @@ pipeline.unet.config["in_channels"]
 4
 ```

-Inpainting requires 9 channels in the input sample. You can check this value in a pretrained inpainting model like [`runwayml/stable-diffusion-inpainting`](https://huggingface.co/runwayml/stable-diffusion-inpainting):
+Inpainting requires 9 channels in the input sample. You can check this value in a pretrained inpainting model like [`stable-diffusion-v1-5/stable-diffusion-inpainting`](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-inpainting):

 ```py
 from diffusers import StableDiffusionPipeline

-pipeline = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-inpainting", use_safetensors=True)
+pipeline = StableDiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-inpainting", use_safetensors=True)
 pipeline.unet.config["in_channels"]
 9
 ```
@@ -215,7 +215,7 @@ from diffusers import AutoPipelineForInpainting, LCMScheduler
 from diffusers.utils import load_image, make_image_grid

 pipe = AutoPipelineForInpainting.from_pretrained(
-    "runwayml/stable-diffusion-inpainting",
+    "stable-diffusion-v1-5/stable-diffusion-inpainting",
    torch_dtype=torch.float16,
    variant="fp16",
 ).to("cuda")
@@ -112,7 +112,7 @@ blurred_mask

 ## Popular models

-[Stable Diffusion Inpainting](https://huggingface.co/runwayml/stable-diffusion-inpainting), [Stable Diffusion XL (SDXL) Inpainting](https://huggingface.co/diffusers/stable-diffusion-xl-1.0-inpainting-0.1), and [Kandinsky 2.2 Inpainting](https://huggingface.co/kandinsky-community/kandinsky-2-2-decoder-inpaint) are among the most popular models for inpainting. SDXL typically produces higher resolution images than Stable Diffusion v1.5, and Kandinsky 2.2 is also capable of generating high-quality images.
+[Stable Diffusion Inpainting](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-inpainting), [Stable Diffusion XL (SDXL) Inpainting](https://huggingface.co/diffusers/stable-diffusion-xl-1.0-inpainting-0.1), and [Kandinsky 2.2 Inpainting](https://huggingface.co/kandinsky-community/kandinsky-2-2-decoder-inpaint) are among the most popular models for inpainting. SDXL typically produces higher resolution images than Stable Diffusion v1.5, and Kandinsky 2.2 is also capable of generating high-quality images.

 ### Stable Diffusion Inpainting

@@ -124,7 +124,7 @@ from diffusers import AutoPipelineForInpainting
 from diffusers.utils import load_image, make_image_grid

 pipeline = AutoPipelineForInpainting.from_pretrained(
-    "runwayml/stable-diffusion-inpainting", torch_dtype=torch.float16, variant="fp16"
+    "stable-diffusion-v1-5/stable-diffusion-inpainting", torch_dtype=torch.float16, variant="fp16"
 )
 pipeline.enable_model_cpu_offload()
 # remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
@@ -244,7 +244,7 @@ make_image_grid([init_image, image], rows=1, cols=2)
 ```

 </hfoption>
-<hfoption id="runwayml/stable-diffusion-inpainting">
+<hfoption id="stable-diffusion-v1-5/stable-diffusion-inpainting">

 ```py
 import torch
@@ -252,7 +252,7 @@ from diffusers import AutoPipelineForInpainting
 from diffusers.utils import load_image, make_image_grid

 pipeline = AutoPipelineForInpainting.from_pretrained(
-    "runwayml/stable-diffusion-inpainting", torch_dtype=torch.float16, variant="fp16"
+    "stable-diffusion-v1-5/stable-diffusion-inpainting", torch_dtype=torch.float16, variant="fp16"
 )
 pipeline.enable_model_cpu_offload()
 # remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
@@ -278,7 +278,7 @@ make_image_grid([init_image, image], rows=1, cols=2)
  </div>
  <div>
    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint-specific.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">runwayml/stable-diffusion-inpainting</figcaption>
+    <figcaption class="mt-2 text-center text-sm text-gray-500">stable-diffusion-v1-5/stable-diffusion-inpainting</figcaption>
  </div>
 </div>

@@ -308,7 +308,7 @@ make_image_grid([init_image, image], rows=1, cols=2)
 ```

 </hfoption>
-<hfoption id="runwayml/stable-diffusion-inpaint">
+<hfoption id="stable-diffusion-v1-5/stable-diffusion-inpaint">

 ```py
 import torch
@@ -316,7 +316,7 @@ from diffusers import AutoPipelineForInpainting
 from diffusers.utils import load_image, make_image_grid

 pipeline = AutoPipelineForInpainting.from_pretrained(
-    "runwayml/stable-diffusion-inpainting", torch_dtype=torch.float16, variant="fp16"
+    "stable-diffusion-v1-5/stable-diffusion-inpainting", torch_dtype=torch.float16, variant="fp16"
 )
 pipeline.enable_model_cpu_offload()
 # remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
@@ -340,7 +340,7 @@ make_image_grid([init_image, image], rows=1, cols=2)
  </div>
  <div>
    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/specific-inpaint-basic.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">runwayml/stable-diffusion-inpainting</figcaption>
+    <figcaption class="mt-2 text-center text-sm text-gray-500">stable-diffusion-v1-5/stable-diffusion-inpainting</figcaption>
  </div>
 </div>

@@ -358,7 +358,7 @@ from diffusers.utils import load_image, make_image_grid

 device = "cuda"
 pipeline = AutoPipelineForInpainting.from_pretrained(
-    "runwayml/stable-diffusion-inpainting",
+    "stable-diffusion-v1-5/stable-diffusion-inpainting",
    torch_dtype=torch.float16,
    variant="fp16"
 )
@@ -396,7 +396,7 @@ from diffusers import AutoPipelineForInpainting
 from diffusers.utils import load_image, make_image_grid

 pipeline = AutoPipelineForInpainting.from_pretrained(
-    "runwayml/stable-diffusion-inpainting", torch_dtype=torch.float16, variant="fp16"
+    "stable-diffusion-v1-5/stable-diffusion-inpainting", torch_dtype=torch.float16, variant="fp16"
 )
 pipeline.enable_model_cpu_offload()
 # remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
@@ -441,7 +441,7 @@ from diffusers import AutoPipelineForInpainting
 from diffusers.utils import load_image, make_image_grid

 pipeline = AutoPipelineForInpainting.from_pretrained(
-    "runwayml/stable-diffusion-inpainting", torch_dtype=torch.float16, variant="fp16"
+    "stable-diffusion-v1-5/stable-diffusion-inpainting", torch_dtype=torch.float16, variant="fp16"
 )
 pipeline.enable_model_cpu_offload()
 # remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
@@ -481,7 +481,7 @@ from diffusers import AutoPipelineForInpainting
 from diffusers.utils import load_image, make_image_grid

 pipeline = AutoPipelineForInpainting.from_pretrained(
-    "runwayml/stable-diffusion-inpainting", torch_dtype=torch.float16, variant="fp16"
+    "stable-diffusion-v1-5/stable-diffusion-inpainting", torch_dtype=torch.float16, variant="fp16"
 )
 pipeline.enable_model_cpu_offload()
 # remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
@@ -606,7 +606,7 @@ from diffusers import AutoPipelineForInpainting, AutoPipelineForImage2Image
 from diffusers.utils import load_image, make_image_grid

 pipeline = AutoPipelineForInpainting.from_pretrained(
-    "runwayml/stable-diffusion-inpainting", torch_dtype=torch.float16, variant="fp16"
+    "stable-diffusion-v1-5/stable-diffusion-inpainting", torch_dtype=torch.float16, variant="fp16"
 )
 pipeline.enable_model_cpu_offload()
 # remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
@@ -683,7 +683,7 @@ from diffusers import AutoPipelineForInpainting
 from diffusers.utils import make_image_grid

 pipeline = AutoPipelineForInpainting.from_pretrained(
-    "runwayml/stable-diffusion-inpainting", torch_dtype=torch.float16,
+    "stable-diffusion-v1-5/stable-diffusion-inpainting", torch_dtype=torch.float16,
 )
 pipeline.enable_model_cpu_offload()
 # remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
@@ -714,7 +714,7 @@ controlnet = ControlNetModel.from_pretrained("lllyasviel/control_v11p_sd15_inpai

 # pass ControlNet to the pipeline
 pipeline = StableDiffusionControlNetInpaintPipeline.from_pretrained(
-    "runwayml/stable-diffusion-inpainting", controlnet=controlnet, torch_dtype=torch.float16, variant="fp16"
+    "stable-diffusion-v1-5/stable-diffusion-inpainting", controlnet=controlnet, torch_dtype=torch.float16, variant="fp16"
 )
 pipeline.enable_model_cpu_offload()
 # remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
@@ -173,7 +173,7 @@ mask_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data
 init_image = download_image(img_url).resize((512, 512))
 mask_image = download_image(mask_url).resize((512, 512))

-path = "runwayml/stable-diffusion-inpainting"
+path = "stable-diffusion-v1-5/stable-diffusion-inpainting"

 run_compile = True  # Set True / False

@@ -28,12 +28,12 @@ pipeline.unet.config["in_channels"]
 4
 ```

-인페인팅은 입력 샘플에 9개의 채널이 필요합니다. [`runwayml/stable-diffusion-inpainting`](https://huggingface.co/runwayml/stable-diffusion-inpainting)와 같은 사전학습된 인페인팅 모델에서 이 값을 확인할 수 있습니다:
+인페인팅은 입력 샘플에 9개의 채널이 필요합니다. [`stable-diffusion-v1-5/stable-diffusion-inpainting`](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-inpainting)와 같은 사전학습된 인페인팅 모델에서 이 값을 확인할 수 있습니다:

 ```py
 from diffusers import StableDiffusionPipeline

-pipeline = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-inpainting")
+pipeline = StableDiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-inpainting")
 pipeline.unet.config["in_channels"]
 9
 ```
@@ -14,7 +14,7 @@ specific language governing permissions and limitations under the License.

 [[open-in-colab]]

-[`StableDiffusionInpaintPipeline`]은 마스크와 텍스트 프롬프트를 제공하여 이미지의 특정 부분을 편집할 수 있도록 합니다. 이 기능은 인페인팅 작업을 위해 특별히 훈련된 [`runwayml/stable-diffusion-inpainting`](https://huggingface.co/runwayml/stable-diffusion-inpainting)과 같은 Stable Diffusion 버전을 사용합니다.
+[`StableDiffusionInpaintPipeline`]은 마스크와 텍스트 프롬프트를 제공하여 이미지의 특정 부분을 편집할 수 있도록 합니다. 이 기능은 인페인팅 작업을 위해 특별히 훈련된 [`stable-diffusion-v1-5/stable-diffusion-inpainting`](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-inpainting)과 같은 Stable Diffusion 버전을 사용합니다.

 먼저 [`StableDiffusionInpaintPipeline`] 인스턴스를 불러옵니다:

@@ -27,7 +27,7 @@ from io import BytesIO
 from diffusers import StableDiffusionInpaintPipeline

 pipeline = StableDiffusionInpaintPipeline.from_pretrained(
-    "runwayml/stable-diffusion-inpainting",
+    "stable-diffusion-v1-5/stable-diffusion-inpainting",
    torch_dtype=torch.float16,
 )
 pipeline = pipeline.to("cuda")
@@ -61,12 +61,3 @@ image = pipe(prompt=prompt, image=init_image, mask_image=mask_image).images[0]

 > [!WARNING]
 > 이전의 실험적인 인페인팅 구현에서는 품질이 낮은 다른 프로세스를 사용했습니다. 이전 버전과의 호환성을 보장하기 위해 새 모델이 포함되지 않은 사전학습된 파이프라인을 불러오면 이전 인페인팅 방법이 계속 적용됩니다.
-
-아래 Space에서 이미지 인페인팅을 직접 해보세요!
-
-<iframe
-  src="https://runwayml-stable-diffusion-inpainting.hf.space"
-  frameborder="0"
-  width="850"
-  height="500"
-></iframe>
@@ -16,12 +16,12 @@ pipeline.unet.config["in_channels"]
 4
 ```

-而图像修复任务需要输入样本具有9个通道。您可以在 [`runwayml/stable-diffusion-inpainting`](https://huggingface.co/runwayml/stable-diffusion-inpainting) 这样的预训练修复模型中验证此参数：
+而图像修复任务需要输入样本具有9个通道。您可以在 [`stable-diffusion-v1-5/stable-diffusion-inpainting`](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-inpainting) 这样的预训练修复模型中验证此参数：

 ```python
 from diffusers import StableDiffusionPipeline

-pipeline = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-inpainting", use_safetensors=True)
+pipeline = StableDiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-inpainting", use_safetensors=True)
 pipeline.unet.config["in_channels"]
 9
 ```
@@ -1328,7 +1328,7 @@ model = CLIPSegForImageSegmentation.from_pretrained("CIDAS/clipseg-rd64-refined"

 # Load Stable Diffusion Inpainting Pipeline with custom pipeline
 pipe = DiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-inpainting",
+    "stable-diffusion-v1-5/stable-diffusion-inpainting",
    custom_pipeline="text_inpainting",
    segmentation_model=model,
    segmentation_processor=processor
@@ -126,7 +126,7 @@ EXAMPLE_DOC_STRING = """
        ...     "lllyasviel/control_v11p_sd15_inpaint", torch_dtype=torch.float16
        ... )
        >>> pipe = StableDiffusionControlNetInpaintPipeline.from_pretrained(
-        ...     "runwayml/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16
+        ...     "stable-diffusion-v1-5/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16
        ... )

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

        >>> pipe = AdaptiveMaskInpaintPipeline.from_pretrained(
-        ...     "runwayml/stable-diffusion-inpainting", torch_dtype=torch.float16
+        ...     "stable-diffusion-v1-5/stable-diffusion-inpainting", torch_dtype=torch.float16
        ... )
        >>> pipe = pipe.to("cuda")

@@ -1095,7 +1095,7 @@ class AdaptiveMaskInpaintPipeline(

        # 8. Check that sizes of mask, masked image and latents match
        if num_channels_unet == 9:
-            # default case for runwayml/stable-diffusion-inpainting
+            # default case for stable-diffusion-v1-5/stable-diffusion-inpainting
            num_channels_mask = mask.shape[1]
            num_channels_masked_image = masked_image_latents.shape[1]
            if num_channels_latents + num_channels_mask + num_channels_masked_image != self.unet.config.in_channels:
@@ -62,7 +62,7 @@ class ComposableStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin)
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
        safety_checker ([`StableDiffusionSafetyChecker`]):
            Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
+            Please, refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for details.
        feature_extractor ([`CLIPImageProcessor`]):
            Model that extracts features from generated images to be used as inputs for the `safety_checker`.
    """
@@ -145,8 +145,8 @@ class ComposableStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin)
                "The configuration file of the unet has set the default `sample_size` to smaller than"
                " 64 which seems highly unlikely. If your checkpoint is a fine-tuned version of any of the"
                " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
-                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
+                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                " in the config might lead to incorrect results in future versions. If you have downloaded this"
                " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"
@@ -1276,7 +1276,7 @@ class FrescoV2VPipeline(StableDiffusionControlNetImg2ImgPipeline):
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
        safety_checker ([`StableDiffusionSafetyChecker`]):
            Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for more details
            about a model's potential harms.
        feature_extractor ([`~transformers.CLIPImageProcessor`]):
            A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
@@ -678,7 +678,7 @@ class StableDiffusionHDPainterPipeline(StableDiffusionInpaintPipeline):

        # 8. Check that sizes of mask, masked image and latents match
        if num_channels_unet == 9:
-            # default case for runwayml/stable-diffusion-inpainting
+            # default case for stable-diffusion-v1-5/stable-diffusion-inpainting
            num_channels_mask = mask.shape[1]
            num_channels_masked_image = masked_image_latents.shape[1]
            if num_channels_latents + num_channels_mask + num_channels_masked_image != self.unet.config.in_channels:
@@ -78,7 +78,7 @@ class ImageToImageInpaintingPipeline(DiffusionPipeline):
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
        safety_checker ([`StableDiffusionSafetyChecker`]):
            Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
+            Please, refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for details.
        feature_extractor ([`CLIPImageProcessor`]):
            Model that extracts features from generated images to be used as inputs for the `safety_checker`.
    """
@@ -86,7 +86,7 @@ class InstaFlowPipeline(
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
        safety_checker ([`StableDiffusionSafetyChecker`]):
            Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for more details
            about a model's potential harms.
        feature_extractor ([`~transformers.CLIPImageProcessor`]):
            A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
@@ -165,8 +165,8 @@ class InstaFlowPipeline(
                "The configuration file of the unet has set the default `sample_size` to smaller than"
                " 64 which seems highly unlikely. If your checkpoint is a fine-tuned version of any of the"
                " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
-                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
+                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                " in the config might lead to incorrect results in future versions. If you have downloaded this"
                " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"
@@ -166,7 +166,7 @@ class IPAdapterFaceIDStableDiffusionPipeline(
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
        safety_checker ([`StableDiffusionSafetyChecker`]):
            Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for more details
            about a model's potential harms.
        feature_extractor ([`~transformers.CLIPImageProcessor`]):
            A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
@@ -247,8 +247,8 @@ class IPAdapterFaceIDStableDiffusionPipeline(
                "The configuration file of the unet has set the default `sample_size` to smaller than"
                " 64 which seems highly unlikely. If your checkpoint is a fine-tuned version of any of the"
                " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
-                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
+                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                " in the config might lead to incorrect results in future versions. If you have downloaded this"
                " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"
@@ -414,7 +414,7 @@ class StableDiffusionHighResFixPipeline(StableDiffusionPipeline):
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
        safety_checker ([`StableDiffusionSafetyChecker`]):
            Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for more details
            about a model's potential harms.
        feature_extractor ([`~transformers.CLIPImageProcessor`]):
            A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
@@ -222,7 +222,7 @@ class LatentConsistencyModelWalkPipeline(
            supports [`LCMScheduler`].
        safety_checker ([`StableDiffusionSafetyChecker`]):
            Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for more details
            about a model's potential harms.
        feature_extractor ([`~transformers.CLIPImageProcessor`]):
            A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
@@ -302,7 +302,7 @@ class LLMGroundedDiffusionPipeline(
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
        safety_checker ([`StableDiffusionSafetyChecker`]):
            Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for more details
            about a model's potential harms.
        feature_extractor ([`~transformers.CLIPImageProcessor`]):
            A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
@@ -392,8 +392,8 @@ class LLMGroundedDiffusionPipeline(
                "The configuration file of the unet has set the default `sample_size` to smaller than"
                " 64 which seems highly unlikely. If your checkpoint is a fine-tuned version of any of the"
                " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
-                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
+                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                " in the config might lead to incorrect results in future versions. If you have downloaded this"
                " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"
@@ -552,8 +552,8 @@ class StableDiffusionLongPromptWeightingPipeline(
                "The configuration file of the unet has set the default `sample_size` to smaller than"
                " 64 which seems highly unlikely. If your checkpoint is a fine-tuned version of any of the"
                " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
-                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
+                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                " in the config might lead to incorrect results in future versions. If you have downloaded this"
                " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"
@@ -1765,7 +1765,7 @@ class SDXLLongPromptWeightingPipeline(

            # Check that sizes of mask, masked image and latents match
            if num_channels_unet == 9:
-                # default case for runwayml/stable-diffusion-inpainting
+                # default case for stable-diffusion-v1-5/stable-diffusion-inpainting
                num_channels_mask = mask.shape[1]
                num_channels_masked_image = masked_image_latents.shape[1]
                if num_channels_latents + num_channels_mask + num_channels_masked_image != num_channels_unet:
@@ -3729,8 +3729,8 @@ class MatryoshkaPipeline(
                "The configuration file of the unet has set the default `sample_size` to smaller than"
                " 64 which seems highly unlikely. If your checkpoint is a fine-tuned version of any of the"
                " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
-                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
+                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                " in the config might lead to incorrect results in future versions. If you have downloaded this"
                " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"
@@ -78,7 +78,7 @@ class MultilingualStableDiffusion(DiffusionPipeline, StableDiffusionMixin):
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
        safety_checker ([`StableDiffusionSafetyChecker`]):
            Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
+            Please, refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for details.
        feature_extractor ([`CLIPImageProcessor`]):
            Model that extracts features from generated images to be used as inputs for the `safety_checker`.
    """
@@ -1607,7 +1607,7 @@ class KolorsControlNetInpaintPipeline(

        # 9. Check that sizes of mask, masked image and latents match
        if num_channels_unet == 9:
-            # default case for runwayml/stable-diffusion-inpainting
+            # default case for stable-diffusion-v1-5/stable-diffusion-inpainting
            num_channels_mask = mask.shape[1]
            num_channels_masked_image = masked_image_latents.shape[1]
            if num_channels_latents + num_channels_mask + num_channels_masked_image != self.unet.config.in_channels:
@@ -135,7 +135,7 @@ class FabricPipeline(DiffusionPipeline):
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
        safety_checker ([`StableDiffusionSafetyChecker`]):
            Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for more details
            about a model's potential harms.
    """

@@ -163,8 +163,8 @@ class FabricPipeline(DiffusionPipeline):
                "The configuration file of the unet has set the default `sample_size` to smaller than"
                " 64 which seems highly unlikely. If your checkpoint is a fine-tuned version of any of the"
                " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
-                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
+                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                " in the config might lead to incorrect results in future versions. If you have downloaded this"
                " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"
@@ -1487,7 +1487,7 @@ class KolorsInpaintPipeline(

        # 8. Check that sizes of mask, masked image and latents match
        if num_channels_unet == 9:
-            # default case for runwayml/stable-diffusion-inpainting
+            # default case for stable-diffusion-v1-5/stable-diffusion-inpainting
            num_channels_mask = mask.shape[1]
            num_channels_masked_image = masked_image_latents.shape[1]
            if num_channels_latents + num_channels_mask + num_channels_masked_image != self.unet.config.in_channels:
@@ -106,7 +106,7 @@ class Prompt2PromptPipeline(
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
        safety_checker ([`StableDiffusionSafetyChecker`]):
            Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for more details
            about a model's potential harms.
        feature_extractor ([`~transformers.CLIPImageProcessor`]):
            A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
@@ -187,8 +187,8 @@ class Prompt2PromptPipeline(
                "The configuration file of the unet has set the default `sample_size` to smaller than"
                " 64 which seems highly unlikely. If your checkpoint is a fine-tuned version of any of the"
                " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
-                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
+                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                " in the config might lead to incorrect results in future versions. If you have downloaded this"
                " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"
@@ -1730,7 +1730,7 @@ class StyleAlignedSDXLPipeline(

            # Check that sizes of mask, masked image and latents match
            if num_channels_unet == 9:
-                # default case for runwayml/stable-diffusion-inpainting
+                # default case for stable-diffusion-v1-5/stable-diffusion-inpainting
                num_channels_mask = mask.shape[1]
                num_channels_masked_image = masked_image_latents.shape[1]
                if num_channels_latents + num_channels_mask + num_channels_masked_image != num_channels_unet:
@@ -59,7 +59,7 @@ EXAMPLE_DOC_STRING = """
        >>> import torch
        >>> from diffusers import StableDiffusionPipeline

-        >>> pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
+        >>> pipe = StableDiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16)
        >>> pipe = pipe.to("cuda")

        >>> prompt = "a photo of an astronaut riding a horse on mars"
@@ -392,7 +392,7 @@ class StableDiffusionBoxDiffPipeline(
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
        safety_checker ([`StableDiffusionSafetyChecker`]):
            Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for more details
            about a model's potential harms.
        feature_extractor ([`~transformers.CLIPImageProcessor`]):
            A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
@@ -473,8 +473,8 @@ class StableDiffusionBoxDiffPipeline(
                "The configuration file of the unet has set the default `sample_size` to smaller than"
                " 64 which seems highly unlikely. If your checkpoint is a fine-tuned version of any of the"
                " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
-                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
+                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                " in the config might lead to incorrect results in future versions. If you have downloaded this"
                " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"
@@ -42,7 +42,7 @@ EXAMPLE_DOC_STRING = """
        ```py
        >>> import torch
        >>> from diffusers import StableDiffusionPipeline
-        >>> pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
+        >>> pipe = StableDiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16)
        >>> pipe = pipe.to("cuda")
        >>> prompt = "a photo of an astronaut riding a horse on mars"
        >>> image = pipe(prompt).images[0]
@@ -359,7 +359,7 @@ class StableDiffusionPAGPipeline(
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
        safety_checker ([`StableDiffusionSafetyChecker`]):
            Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for more details
            about a model's potential harms.
        feature_extractor ([`~transformers.CLIPImageProcessor`]):
            A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
@@ -440,8 +440,8 @@ class StableDiffusionPAGPipeline(
                "The configuration file of the unet has set the default `sample_size` to smaller than"
                " 64 which seems highly unlikely. If your checkpoint is a fine-tuned version of any of the"
                " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
-                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
+                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                " in the config might lead to incorrect results in future versions. If you have downloaded this"
                " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"
@@ -100,7 +100,7 @@ class StableDiffusionUpscaleLDM3DPipeline(
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
        safety_checker ([`StableDiffusionSafetyChecker`]):
            Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for more details
            about a model's potential harms.
        feature_extractor ([`~transformers.CLIPImageProcessor`]):
            A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
@@ -2042,7 +2042,7 @@ class StableDiffusionXL_AE_Pipeline(

        # 8. Check that sizes of mask, masked image and latents match
        if num_channels_unet == 9:
-            # default case for runwayml/stable-diffusion-inpainting
+            # default case for stable-diffusion-v1-5/stable-diffusion-inpainting
            num_channels_mask = mask.shape[1]
            num_channels_masked_image = masked_image_latents.shape[1]
            if num_channels_latents + num_channels_mask + num_channels_masked_image != self.unet.config.in_channels:
@@ -188,7 +188,7 @@ class StableDiffusionXLControlNetAdapterPipeline(
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
        safety_checker ([`StableDiffusionSafetyChecker`]):
            Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
+            Please, refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for details.
        feature_extractor ([`CLIPImageProcessor`]):
            Model that extracts features from generated images to be used as inputs for the `safety_checker`.
    """
@@ -330,7 +330,7 @@ class StableDiffusionXLControlNetAdapterInpaintPipeline(
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
        safety_checker ([`StableDiffusionSafetyChecker`]):
            Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
+            Please, refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for details.
        feature_extractor ([`CLIPImageProcessor`]):
            Model that extracts features from generated images to be used as inputs for the `safety_checker`.
        requires_aesthetics_score (`bool`, *optional*, defaults to `"False"`):
@@ -1569,7 +1569,7 @@ class StableDiffusionXLControlNetAdapterInpaintPipeline(

        # 8. Check that sizes of mask, masked image and latents match
        if num_channels_unet == 9:
-            # default case for runwayml/stable-diffusion-inpainting
+            # default case for stable-diffusion-v1-5/stable-diffusion-inpainting
            num_channels_mask = mask.shape[1]
            num_channels_masked_image = masked_image_latents.shape[1]
            if num_channels_latents + num_channels_mask + num_channels_masked_image != self.unet.config.in_channels:
@@ -46,7 +46,7 @@ EXAMPLE_DOC_STRING = """
        >>> import torch
        >>> from diffusers import StableDiffusionPipeline

-        >>> pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
+        >>> pipe = StableDiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16)
        >>> pipe = pipe.to("cuda")

        >>> prompt = "a photo of an astronaut riding a horse on mars"
@@ -86,7 +86,7 @@ class Zero1to3StableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin):
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
        safety_checker ([`StableDiffusionSafetyChecker`]):
            Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
+            Please, refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for details.
        feature_extractor ([`CLIPImageProcessor`]):
            Model that extracts features from generated images to be used as inputs for the `safety_checker`.
        cc_projection ([`CCProjection`]):
@@ -164,8 +164,8 @@ class Zero1to3StableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin):
                "The configuration file of the unet has set the default `sample_size` to smaller than"
                " 64 which seems highly unlikely. If your checkpoint is a fine-tuned version of any of the"
                " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
-                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
+                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                " in the config might lead to incorrect results in future versions. If you have downloaded this"
                " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"
@@ -288,7 +288,7 @@ class RerenderAVideoPipeline(StableDiffusionControlNetImg2ImgPipeline):
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
        safety_checker ([`StableDiffusionSafetyChecker`]):
            Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
+            Please, refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for details.
        feature_extractor ([`CLIPImageProcessor`]):
            Model that extracts features from generated images to be used as inputs for the `safety_checker`.
    """
@@ -54,7 +54,7 @@ EXAMPLE_DOC_STRING = """
        >>> # load control net and stable diffusion v1-5
        >>> controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", torch_dtype=torch.float16)
        >>> pipe = StableDiffusionControlNetImg2ImgPipeline.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
        ... )

        >>> # speed up diffusion process with faster scheduler and memory optimization
@@ -158,7 +158,7 @@ EXAMPLE_DOC_STRING = """
        >>> # load control net and stable diffusion v1-5
        >>> controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", torch_dtype=torch.float16)
        >>> pipe = StableDiffusionControlNetImg2ImgPipeline.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
        ... )

        >>> # speed up diffusion process with faster scheduler and memory optimization
@@ -64,7 +64,7 @@ class StableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin):
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
        safety_checker ([`StableDiffusionSafetyChecker`]):
            Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
+            Please, refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for details.
        feature_extractor ([`CLIPImageProcessor`]):
            Model that extracts features from generated images to be used as inputs for the `safety_checker`.
    """
@@ -114,7 +114,7 @@ class SdeDragPipeline(DiffusionPipeline):
        >>> from diffusers import DDIMScheduler, DiffusionPipeline

        >>> # Load the pipeline
-        >>> model_path = "runwayml/stable-diffusion-v1-5"
+        >>> model_path = "stable-diffusion-v1-5/stable-diffusion-v1-5"
        >>> scheduler = DDIMScheduler.from_pretrained(model_path, subfolder="scheduler")
        >>> pipe = DiffusionPipeline.from_pretrained(model_path, scheduler=scheduler, custom_pipeline="sde_drag")
        >>> pipe.to('cuda')
@@ -46,7 +46,7 @@ class StableDiffusionComparisonPipeline(DiffusionPipeline, StableDiffusionMixin)
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
        safety_checker ([`StableDiffusionMegaSafetyChecker`]):
            Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
+            Please, refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for details.
        feature_extractor ([`CLIPImageProcessor`]):
            Model that extracts features from generated images to be used as inputs for the `safety_checker`.
    """
@@ -36,7 +36,7 @@ EXAMPLE_DOC_STRING = """
        >>> controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", torch_dtype=torch.float16)

        >>> pipe_controlnet = StableDiffusionControlNetImg2ImgPipeline.from_pretrained(
-                "runwayml/stable-diffusion-v1-5",
+                "stable-diffusion-v1-5/stable-diffusion-v1-5",
                controlnet=controlnet,
                safety_checker=None,
                torch_dtype=torch.float16
@@ -81,7 +81,7 @@ EXAMPLE_DOC_STRING = """
        >>> controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-seg", torch_dtype=torch.float16)

        >>> pipe = StableDiffusionControlNetInpaintPipeline.from_pretrained(
-                "runwayml/stable-diffusion-inpainting", controlnet=controlnet, safety_checker=None, torch_dtype=torch.float16
+                "stable-diffusion-v1-5/stable-diffusion-inpainting", controlnet=controlnet, safety_checker=None, torch_dtype=torch.float16
            )

        >>> pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
@@ -80,7 +80,7 @@ EXAMPLE_DOC_STRING = """
        >>> controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-seg", torch_dtype=torch.float16)

        >>> pipe = StableDiffusionControlNetInpaintImg2ImgPipeline.from_pretrained(
-                "runwayml/stable-diffusion-inpainting", controlnet=controlnet, safety_checker=None, torch_dtype=torch.float16
+                "stable-diffusion-v1-5/stable-diffusion-inpainting", controlnet=controlnet, safety_checker=None, torch_dtype=torch.float16
            )

        >>> pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
@@ -37,7 +37,7 @@ EXAMPLE_DOC_STRING = """

        >>> controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", torch_dtype=torch.float16)
        >>> pipe = StableDiffusionControlNetReferencePipeline.from_pretrained(
-                "runwayml/stable-diffusion-v1-5",
+                "stable-diffusion-v1-5/stable-diffusion-v1-5",
                controlnet=controlnet,
                safety_checker=None,
                torch_dtype=torch.float16
@@ -43,7 +43,7 @@ EXAMPLE_DOC_STRING = """
        >>> import torch
        >>> from diffusers import StableDiffusionPipeline

-        >>> pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", custom_pipeline="stable_diffusion_ipex")
+        >>> pipe = DiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", custom_pipeline="stable_diffusion_ipex")

        >>> # For Float32
        >>> pipe.prepare_for_ipex(prompt, dtype=torch.float32, height=512, width=512) #value of image height/width should be consistent with the pipeline inference
@@ -85,7 +85,7 @@ class StableDiffusionIPEXPipeline(
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
        safety_checker ([`StableDiffusionSafetyChecker`]):
            Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
+            Please, refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for details.
        feature_extractor ([`CLIPImageProcessor`]):
            Model that extracts features from generated images to be used as inputs for the `safety_checker`.
    """
@@ -161,8 +161,8 @@ class StableDiffusionIPEXPipeline(
                "The configuration file of the unet has set the default `sample_size` to smaller than"
                " 64 which seems highly unlikely. If your checkpoint is a fine-tuned version of any of the"
                " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
-                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
+                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                " in the config might lead to incorrect results in future versions. If you have downloaded this"
                " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"
@@ -47,7 +47,7 @@ class StableDiffusionMegaPipeline(DiffusionPipeline, StableDiffusionMixin):
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
        safety_checker ([`StableDiffusionMegaSafetyChecker`]):
            Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
+            Please, refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for details.
        feature_extractor ([`CLIPImageProcessor`]):
            Model that extracts features from generated images to be used as inputs for the `safety_checker`.
    """
@@ -46,7 +46,7 @@ EXAMPLE_DOC_STRING = """
        >>> input_image = load_image("https://hf.co/datasets/huggingface/documentation-images/resolve/main/diffusers/input_image_vermeer.png")

        >>> pipe = StableDiffusionReferencePipeline.from_pretrained(
-                "runwayml/stable-diffusion-v1-5",
+                "stable-diffusion-v1-5/stable-diffusion-v1-5",
                safety_checker=None,
                torch_dtype=torch.float16
                ).to('cuda:0')
@@ -112,7 +112,7 @@ class StableDiffusionReferencePipeline(
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
        safety_checker ([`StableDiffusionSafetyChecker`]):
            Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
+            Please, refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for details.
        feature_extractor ([`CLIPImageProcessor`]):
            Model that extracts features from generated images to be used as inputs for the `safety_checker`.
    """
@@ -194,8 +194,8 @@ class StableDiffusionReferencePipeline(
                "The configuration file of the unet has set the default `sample_size` to smaller than"
                " 64 which seems highly unlikely .If you're checkpoint is a fine-tuned version of any of the"
                " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
-                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
+                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                " in the config might lead to incorrect results in future versions. If you have downloaded this"
                " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"
@@ -167,7 +167,7 @@ class StableDiffusionRepaintPipeline(
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
        safety_checker ([`StableDiffusionSafetyChecker`]):
            Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
+            Please, refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for details.
        feature_extractor ([`CLIPImageProcessor`]):
            Model that extracts features from generated images to be used as inputs for the `safety_checker`.
    """
@@ -249,8 +249,8 @@ class StableDiffusionRepaintPipeline(
                "The configuration file of the unet has set the default `sample_size` to smaller than"
                " 64 which seems highly unlikely .If you're checkpoint is a fine-tuned version of any of the"
                " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
-                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
+                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                " in the config might lead to incorrect results in future versions. If you have downloaded this"
                " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"
@@ -678,7 +678,7 @@ class TensorRTStableDiffusionImg2ImgPipeline(DiffusionPipeline):
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
        safety_checker ([`StableDiffusionSafetyChecker`]):
            Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
+            Please, refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for details.
        feature_extractor ([`CLIPImageProcessor`]):
            Model that extracts features from generated images to be used as inputs for the `safety_checker`.
    """
@@ -766,8 +766,8 @@ class TensorRTStableDiffusionImg2ImgPipeline(DiffusionPipeline):
                "The configuration file of the unet has set the default `sample_size` to smaller than"
                " 64 which seems highly unlikely. If your checkpoint is a fine-tuned version of any of the"
                " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
-                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
+                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                " in the config might lead to incorrect results in future versions. If you have downloaded this"
                " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"
@@ -682,7 +682,7 @@ class TensorRTStableDiffusionInpaintPipeline(DiffusionPipeline):
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
        safety_checker ([`StableDiffusionSafetyChecker`]):
            Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
+            Please, refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for details.
        feature_extractor ([`CLIPImageProcessor`]):
            Model that extracts features from generated images to be used as inputs for the `safety_checker`.
    """
@@ -770,8 +770,8 @@ class TensorRTStableDiffusionInpaintPipeline(DiffusionPipeline):
                "The configuration file of the unet has set the default `sample_size` to smaller than"
                " 64 which seems highly unlikely. If your checkpoint is a fine-tuned version of any of the"
                " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
-                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
+                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                " in the config might lead to incorrect results in future versions. If you have downloaded this"
                " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"
@@ -594,7 +594,7 @@ class TensorRTStableDiffusionPipeline(DiffusionPipeline):
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
        safety_checker ([`StableDiffusionSafetyChecker`]):
            Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
+            Please, refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for details.
        feature_extractor ([`CLIPImageProcessor`]):
            Model that extracts features from generated images to be used as inputs for the `safety_checker`.
    """
@@ -682,8 +682,8 @@ class TensorRTStableDiffusionPipeline(DiffusionPipeline):
                "The configuration file of the unet has set the default `sample_size` to smaller than"
                " 64 which seems highly unlikely. If your checkpoint is a fine-tuned version of any of the"
                " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
-                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
+                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- stable-diffusion-v1-5/stable-diffusion-v1-5"
+                " \n- stable-diffusion-v1-5/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
                " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
                " in the config might lead to incorrect results in future versions. If you have downloaded this"
                " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"
@@ -52,7 +52,7 @@ class TextInpainting(DiffusionPipeline, StableDiffusionMixin):
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
        safety_checker ([`StableDiffusionSafetyChecker`]):
            Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
+            Please, refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for details.
        feature_extractor ([`CLIPImageProcessor`]):
            Model that extracts features from generated images to be used as inputs for the `safety_checker`.
    """
@@ -1223,7 +1223,7 @@ class AnyTextPipeline(
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
        safety_checker ([`StableDiffusionSafetyChecker`]):
            Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for more details
            about a model's potential harms.
        feature_extractor ([`~transformers.CLIPImageProcessor`]):
            A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
@@ -5,7 +5,7 @@ This script was added by @thedarkzeno .
 Please note that this script is not actively maintained, you can open an issue and tag @thedarkzeno or @patil-suraj though.

 ```bash
-export MODEL_NAME="runwayml/stable-diffusion-inpainting"
+export MODEL_NAME="stable-diffusion-v1-5/stable-diffusion-inpainting"
 export INSTANCE_DIR="path-to-instance-images"
 export OUTPUT_DIR="path-to-save-model"

@@ -29,7 +29,7 @@ Prior-preservation is used to avoid overfitting and language-drift. Refer to the
 According to the paper, it's recommended to generate `num_epochs * num_samples` images for prior-preservation. 200-300 works well for most cases.

 ```bash
-export MODEL_NAME="runwayml/stable-diffusion-inpainting"
+export MODEL_NAME="stable-diffusion-v1-5/stable-diffusion-inpainting"
 export INSTANCE_DIR="path-to-instance-images"
 export CLASS_DIR="path-to-class-images"
 export OUTPUT_DIR="path-to-save-model"
@@ -60,7 +60,7 @@ With the help of gradient checkpointing and the 8-bit optimizer from bitsandbyte
 To install `bitandbytes` please refer to this [readme](https://github.com/TimDettmers/bitsandbytes#requirements--installation).

 ```bash
-export MODEL_NAME="runwayml/stable-diffusion-inpainting"
+export MODEL_NAME="stable-diffusion-v1-5/stable-diffusion-inpainting"
 export INSTANCE_DIR="path-to-instance-images"
 export CLASS_DIR="path-to-class-images"
 export OUTPUT_DIR="path-to-save-model"
@@ -92,7 +92,7 @@ Pass the `--train_text_encoder` argument to the script to enable training `text_
 ___Note: Training text encoder requires more memory, with this option the training won't fit on 16GB GPU. It needs at least 24GB VRAM.___

 ```bash
-export MODEL_NAME="runwayml/stable-diffusion-inpainting"
+export MODEL_NAME="stable-diffusion-v1-5/stable-diffusion-inpainting"
 export INSTANCE_DIR="path-to-instance-images"
 export CLASS_DIR="path-to-class-images"
 export OUTPUT_DIR="path-to-save-model"
@@ -55,7 +55,7 @@ The Accelerate launch command is used to train a model using multiple GPUs and m
 ```
 accelerate launch --mixed_precision "fp16" \
 tutorial_train_ip-adapter.py \
--pretrained_model_name_or_path="runwayml/stable-diffusion-v1-5/" \
+--pretrained_model_name_or_path="stable-diffusion-v1-5/stable-diffusion-v1-5/" \
 --image_encoder_path="{image_encoder_path}" \
 --data_json_file="{data.json}" \
 --data_root_path="{image_path}" \
@@ -73,7 +73,7 @@ tutorial_train_ip-adapter.py \
 ```
 accelerate launch --num_processes 8 --multi_gpu --mixed_precision "fp16" \
  tutorial_train_ip-adapter.py \
-  --pretrained_model_name_or_path="runwayml/stable-diffusion-v1-5/" \
+  --pretrained_model_name_or_path="stable-diffusion-v1-5/stable-diffusion-v1-5/" \
  --image_encoder_path="{image_encoder_path}" \
  --data_json_file="{data.json}" \
  --data_root_path="{image_path}" \
@@ -27,7 +27,7 @@ You can build multiple datasets for every subject and upload them to the 🤗 hu
 Before launching the training script, make sure to select the inpainting the target model, the output directory and the 🤗 datasets.

 ```bash
-export MODEL_NAME="runwayml/stable-diffusion-inpainting"
+export MODEL_NAME="stable-diffusion-v1-5/stable-diffusion-inpainting"
 export OUTPUT_DIR="path-to-save-model"

 export DATASET_1="gzguevara/mr_potato_head_masked"
@@ -177,7 +177,7 @@ class PromptDiffusionPipeline(
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
        safety_checker ([`StableDiffusionSafetyChecker`]):
            Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
+            Please refer to the [model card](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) for more details
            about a model's potential harms.
        feature_extractor ([`~transformers.CLIPImageProcessor`]):
            A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
@@ -238,7 +238,7 @@ def parse_args() -> argparse.Namespace:

 # EXAMPLE USAGE:
 #
-# python vae_roundtrip.py --use_cuda --pretrained_model_name_or_path "runwayml/stable-diffusion-v1-5" --subfolder "vae" --input_image "foo.png"
+# python vae_roundtrip.py --use_cuda --pretrained_model_name_or_path "stable-diffusion-v1-5/stable-diffusion-v1-5" --subfolder "vae" --input_image "foo.png"
 #
 # python vae_roundtrip.py --use_cuda --pretrained_model_name_or_path "madebyollin/taesd" --use_tiny_nn --input_image "foo.png"
 #
--- a/Show More
+++ b/Show More