ability to delete a single adapter.

.github/workflows/build_docker_images.yml

@@ -34,7 +34,7 @@ jobs:
         id: file_changes
         uses: jitterbit/get-changed-files@v1
         with:
-          format: "space-delimited"
+          format: 'space-delimited'
           token: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Build Changed Docker Images
@@ -67,7 +67,6 @@ jobs:
           - diffusers-pytorch-cuda
           - diffusers-pytorch-compile-cuda
           - diffusers-pytorch-xformers-cuda
-          - diffusers-pytorch-minimum-cuda
           - diffusers-flax-cpu
           - diffusers-flax-tpu
           - diffusers-onnxruntime-cpu

.github/workflows/nightly_tests.yml

@@ -235,73 +235,15 @@ jobs:
         run: |
           pip install slack_sdk tabulate
           python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
-          
-  torch_minimum_version_cuda_tests:
-    name: Torch Minimum Version CUDA Tests
-    runs-on:
-      group: aws-g4dn-2xlarge
-    container:
-      image: diffusers/diffusers-pytorch-minimum-cuda
-      options: --shm-size "16gb" --ipc host --gpus 0
-    defaults:
-      run:
-        shell: bash
-    steps:
-      - name: Checkout diffusers
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 2
 
-      - name: Install dependencies
-        run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          python -m uv pip install -e [quality,test]
-          python -m uv pip install peft@git+https://github.com/huggingface/peft.git
-          pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-
-      - name: Environment
-        run: |
-          python utils/print_env.py
-
-      - name: Run PyTorch CUDA tests
-        env:
-          HF_TOKEN: ${{ secrets.HF_TOKEN }}
-          # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
-          CUBLAS_WORKSPACE_CONFIG: :16:8
-        run: |
-          python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            -s -v -k "not Flax and not Onnx" \
-            --make-reports=tests_torch_minimum_version_cuda \
-            tests/models/test_modeling_common.py \
-            tests/pipelines/test_pipelines_common.py \
-            tests/pipelines/test_pipeline_utils.py \
-            tests/pipelines/test_pipelines.py \
-            tests/pipelines/test_pipelines_auto.py \
-            tests/schedulers/test_schedulers.py \
-            tests/others
-
-      - name: Failure short reports
-        if: ${{ failure() }}
-        run: |
-          cat reports/tests_torch_minimum_version_cuda_stats.txt
-          cat reports/tests_torch_minimum_version_cuda_failures_short.txt
-
-      - name: Test suite reports artifacts
-        if: ${{ always() }}
-        uses: actions/upload-artifact@v4
-        with:
-          name: torch_minimum_version_cuda_test_reports
-          path: reports
- 
   run_flax_tpu_tests:
     name: Nightly Flax TPU Tests
-    runs-on:
-      group: gcp-ct5lp-hightpu-8t
+    runs-on: docker-tpu
     if: github.event_name == 'schedule'
 
     container:
       image: diffusers/diffusers-flax-tpu
-      options: --shm-size "16gb" --ipc host --privileged ${{ vars.V5_LITEPOD_8_ENV}} -v /mnt/hf_cache:/mnt/hf_cache
+      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --privileged
     defaults:
       run:
         shell: bash
@@ -414,10 +356,6 @@ jobs:
         config:
           - backend: "bitsandbytes"
             test_location: "bnb"
-          - backend: "gguf"
-            test_location: "gguf"
-          - backend: "torchao"
-            test_location: "torchao"
     runs-on:
       group: aws-g6e-xlarge-plus
     container:
@@ -581,4 +519,4 @@ jobs:
 #        if: always()
 #        run: |
 #          pip install slack_sdk tabulate
-#          python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
+#          python utils/log_reports.py >> $GITHUB_STEP_SUMMARY

.github/workflows/pr_tests.yml

@@ -266,7 +266,6 @@ jobs:
         # TODO (sayakpaul, DN6): revisit `--no-deps`
         python -m pip install -U peft@git+https://github.com/huggingface/peft.git --no-deps
         python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git --no-deps
-        python -m uv pip install -U tokenizers
         pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git --no-deps
 
     - name: Environment

.github/workflows/push_tests.yml

@@ -161,11 +161,10 @@ jobs:
 
   flax_tpu_tests:
     name: Flax TPU Tests
-    runs-on:
-      group: gcp-ct5lp-hightpu-8t
+    runs-on: docker-tpu
     container:
       image: diffusers/diffusers-flax-tpu
-      options: --shm-size "16gb" --ipc host --privileged ${{ vars.V5_LITEPOD_8_ENV}} -v /mnt/hf_cache:/mnt/hf_cache 
+      options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/ --privileged
     defaults:
       run:
         shell: bash

.github/workflows/push_tests_mps.yml

@@ -46,7 +46,7 @@ jobs:
       shell: arch -arch arm64 bash {0}
       run: |
         ${CONDA_RUN} python -m pip install --upgrade pip uv
-        ${CONDA_RUN} python -m uv pip install -e ".[quality,test]"
+        ${CONDA_RUN} python -m uv pip install -e [quality,test]
         ${CONDA_RUN} python -m uv pip install torch torchvision torchaudio
         ${CONDA_RUN} python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
         ${CONDA_RUN} python -m uv pip install transformers --upgrade

.github/workflows/pypi_publish.yaml

@@ -68,7 +68,7 @@ jobs:
       - name: Test installing diffusers and importing
         run: |
           pip install diffusers && pip uninstall diffusers -y
-          pip install -i https://test.pypi.org/simple/ diffusers
+          pip install -i https://testpypi.python.org/pypi diffusers
           python -c "from diffusers import __version__; print(__version__)"
           python -c "from diffusers import DiffusionPipeline; pipe = DiffusionPipeline.from_pretrained('fusing/unet-ldm-dummy-update'); pipe()"
           python -c "from diffusers import DiffusionPipeline; pipe = DiffusionPipeline.from_pretrained('hf-internal-testing/tiny-stable-diffusion-pipe', safety_checker=None); pipe('ah suh du')"

.github/workflows/release_tests_fast.yml

@@ -157,63 +157,6 @@ jobs:
         name: torch_cuda_${{ matrix.module }}_test_reports
         path: reports
 
-  torch_minimum_version_cuda_tests:
-    name: Torch Minimum Version CUDA Tests
-    runs-on:
-      group: aws-g4dn-2xlarge
-    container:
-      image: diffusers/diffusers-pytorch-minimum-cuda
-      options: --shm-size "16gb" --ipc host --gpus 0
-    defaults:
-      run:
-        shell: bash
-    steps:
-      - name: Checkout diffusers
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 2
-
-      - name: Install dependencies
-        run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          python -m uv pip install -e [quality,test]
-          python -m uv pip install peft@git+https://github.com/huggingface/peft.git
-          pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-
-      - name: Environment
-        run: |
-          python utils/print_env.py
-
-      - name: Run PyTorch CUDA tests
-        env:
-          HF_TOKEN: ${{ secrets.HF_TOKEN }}
-          # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
-          CUBLAS_WORKSPACE_CONFIG: :16:8
-        run: |
-          python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            -s -v -k "not Flax and not Onnx" \
-            --make-reports=tests_torch_minimum_cuda \
-            tests/models/test_modeling_common.py \
-            tests/pipelines/test_pipelines_common.py \
-            tests/pipelines/test_pipeline_utils.py \
-            tests/pipelines/test_pipelines.py \
-            tests/pipelines/test_pipelines_auto.py \
-            tests/schedulers/test_schedulers.py \
-            tests/others
-
-      - name: Failure short reports
-        if: ${{ failure() }}
-        run: |
-          cat reports/tests_torch_minimum_version_cuda_stats.txt
-          cat reports/tests_torch_minimum_version_cuda_failures_short.txt
-
-      - name: Test suite reports artifacts
-        if: ${{ always() }}
-        uses: actions/upload-artifact@v4
-        with:
-          name: torch_minimum_version_cuda_test_reports
-          path: reports
-          
   flax_tpu_tests:
     name: Flax TPU Tests
     runs-on: docker-tpu

docker/diffusers-pytorch-minimum-cuda/Dockerfile

@@ -1,53 +0,0 @@
-FROM nvidia/cuda:12.1.0-runtime-ubuntu20.04
-LABEL maintainer="Hugging Face"
-LABEL repository="diffusers"
-
-ENV DEBIAN_FRONTEND=noninteractive
-ENV MINIMUM_SUPPORTED_TORCH_VERSION="2.1.0"
-ENV MINIMUM_SUPPORTED_TORCHVISION_VERSION="0.16.0"
-ENV MINIMUM_SUPPORTED_TORCHAUDIO_VERSION="2.1.0"
-
-RUN apt-get -y update \
-    && apt-get install -y software-properties-common \
-    && add-apt-repository ppa:deadsnakes/ppa
-
-RUN apt install -y bash \
-    build-essential \
-    git \
-    git-lfs \
-    curl \
-    ca-certificates \
-    libsndfile1-dev \
-    libgl1 \
-    python3.10 \
-    python3.10-dev \
-    python3-pip \
-    python3.10-venv && \
-    rm -rf /var/lib/apt/lists
-
-# make sure to use venv
-RUN python3.10 -m venv /opt/venv
-ENV PATH="/opt/venv/bin:$PATH"
-
-# pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
-RUN python3.10 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
-    python3.10 -m uv pip install --no-cache-dir \
-    torch==$MINIMUM_SUPPORTED_TORCH_VERSION \
-    torchvision==$MINIMUM_SUPPORTED_TORCHVISION_VERSION \
-    torchaudio==$MINIMUM_SUPPORTED_TORCHAUDIO_VERSION \
-    invisible_watermark && \
-    python3.10 -m pip install --no-cache-dir \
-    accelerate \
-    datasets \
-    hf-doc-builder \
-    huggingface-hub \
-    hf_transfer \
-    Jinja2 \
-    librosa \
-    numpy==1.26.4 \
-    scipy \
-    tensorboard \
-    transformers \
-    hf_transfer
-
-CMD ["/bin/bash"]

docs/source/en/_toctree.yml

@@ -48,7 +48,7 @@
   - local: using-diffusers/inpaint
     title: Inpainting
   - local: using-diffusers/text-img2vid
-    title: Video generation
+    title: Text or image-to-video
   - local: using-diffusers/depth2img
     title: Depth-to-image
   title: Generative tasks
@@ -157,10 +157,6 @@
     title: Getting Started
   - local: quantization/bitsandbytes
     title: bitsandbytes
-  - local: quantization/gguf
-    title: gguf
-  - local: quantization/torchao
-    title: torchao
   title: Quantization Methods
 - sections:
   - local: optimization/fp16
@@ -238,8 +234,6 @@
       title: Textual Inversion
     - local: api/loaders/unet
       title: UNet
-    - local: api/loaders/transformer_sd3
-      title: SD3Transformer2D
     - local: api/loaders/peft
       title: PEFT
     title: Loaders
@@ -276,14 +270,10 @@
         title: FluxTransformer2DModel
       - local: api/models/hunyuan_transformer2d
         title: HunyuanDiT2DModel
-      - local: api/models/hunyuan_video_transformer_3d
-        title: HunyuanVideoTransformer3DModel
       - local: api/models/latte_transformer3d
         title: LatteTransformer3DModel
       - local: api/models/lumina_nextdit2d
         title: LuminaNextDiT2DModel
-      - local: api/models/ltx_video_transformer3d
-        title: LTXVideoTransformer3DModel
       - local: api/models/mochi_transformer3d
         title: MochiTransformer3DModel
       - local: api/models/pixart_transformer2d
@@ -292,8 +282,6 @@
         title: PriorTransformer
       - local: api/models/sd3_transformer2d
         title: SD3Transformer2DModel
-      - local: api/models/sana_transformer2d
-        title: SanaTransformer2DModel
       - local: api/models/stable_audio_transformer
         title: StableAudioDiTModel
       - local: api/models/transformer2d
@@ -324,10 +312,6 @@
         title: AutoencoderKLAllegro
       - local: api/models/autoencoderkl_cogvideox
         title: AutoencoderKLCogVideoX
-      - local: api/models/autoencoder_kl_hunyuan_video
-        title: AutoencoderKLHunyuanVideo
-      - local: api/models/autoencoderkl_ltx_video
-        title: AutoencoderKLLTXVideo
       - local: api/models/autoencoderkl_mochi
         title: AutoencoderKLMochi
       - local: api/models/asymmetricautoencoderkl
@@ -402,12 +386,8 @@
       title: DiT
     - local: api/pipelines/flux
       title: Flux
-    - local: api/pipelines/control_flux_inpaint
-      title: FluxControlInpaint
     - 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
@@ -428,8 +408,6 @@
       title: Latte
     - local: api/pipelines/ledits_pp
       title: LEDITS++
-    - local: api/pipelines/ltx_video
-      title: LTXVideo
     - local: api/pipelines/lumina
       title: Lumina-T2X
     - local: api/pipelines/marigold
@@ -450,8 +428,6 @@
       title: PixArt-α
     - local: api/pipelines/pixart_sigma
       title: PixArt-Σ
-    - local: api/pipelines/sana
-      title: Sana
     - local: api/pipelines/self_attention_guidance
       title: Self-Attention Guidance
     - local: api/pipelines/semantic_stable_diffusion

docs/source/en/api/attnprocessor.md

@@ -15,135 +15,40 @@ specific language governing permissions and limitations under the License.
 An attention processor is a class for applying different types of attention mechanisms.
 
 ## AttnProcessor
-
 [[autodoc]] models.attention_processor.AttnProcessor
 
+## AttnProcessor2_0
 [[autodoc]] models.attention_processor.AttnProcessor2_0
 
+## AttnAddedKVProcessor
 [[autodoc]] models.attention_processor.AttnAddedKVProcessor
 
+## AttnAddedKVProcessor2_0
 [[autodoc]] models.attention_processor.AttnAddedKVProcessor2_0
 
-[[autodoc]] models.attention_processor.AttnProcessorNPU
-
-[[autodoc]] models.attention_processor.FusedAttnProcessor2_0
-
-## Allegro
-
-[[autodoc]] models.attention_processor.AllegroAttnProcessor2_0
-
-## AuraFlow
-
-[[autodoc]] models.attention_processor.AuraFlowAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.FusedAuraFlowAttnProcessor2_0
-
-## CogVideoX
-
-[[autodoc]] models.attention_processor.CogVideoXAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.FusedCogVideoXAttnProcessor2_0
-
 ## CrossFrameAttnProcessor
-
 [[autodoc]] pipelines.text_to_video_synthesis.pipeline_text_to_video_zero.CrossFrameAttnProcessor
 
-## Custom Diffusion
-
+## CustomDiffusionAttnProcessor
 [[autodoc]] models.attention_processor.CustomDiffusionAttnProcessor
 
+## CustomDiffusionAttnProcessor2_0
 [[autodoc]] models.attention_processor.CustomDiffusionAttnProcessor2_0
 
+## CustomDiffusionXFormersAttnProcessor
 [[autodoc]] models.attention_processor.CustomDiffusionXFormersAttnProcessor
 
-## Flux
-
-[[autodoc]] models.attention_processor.FluxAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.FusedFluxAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.FluxSingleAttnProcessor2_0
-
-## Hunyuan
-
-[[autodoc]] models.attention_processor.HunyuanAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.FusedHunyuanAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.PAGHunyuanAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.PAGCFGHunyuanAttnProcessor2_0
-
-## IdentitySelfAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.PAGIdentitySelfAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.PAGCFGIdentitySelfAttnProcessor2_0
-
-## IP-Adapter
-
-[[autodoc]] models.attention_processor.IPAdapterAttnProcessor
-
-[[autodoc]] models.attention_processor.IPAdapterAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.SD3IPAdapterJointAttnProcessor2_0
-
-## JointAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.JointAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.PAGJointAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.PAGCFGJointAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.FusedJointAttnProcessor2_0
-
-## LoRA
-
-[[autodoc]] models.attention_processor.LoRAAttnProcessor
-
-[[autodoc]] models.attention_processor.LoRAAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.LoRAAttnAddedKVProcessor
-
-[[autodoc]] models.attention_processor.LoRAXFormersAttnProcessor
-
-## Lumina-T2X
-
-[[autodoc]] models.attention_processor.LuminaAttnProcessor2_0
-
-## Mochi
-
-[[autodoc]] models.attention_processor.MochiAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.MochiVaeAttnProcessor2_0
-
-## Sana
-
-[[autodoc]] models.attention_processor.SanaLinearAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.SanaMultiscaleAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.PAGCFGSanaLinearAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.PAGIdentitySanaLinearAttnProcessor2_0
-
-## Stable Audio
-
-[[autodoc]] models.attention_processor.StableAudioAttnProcessor2_0
+## FusedAttnProcessor2_0
+[[autodoc]] models.attention_processor.FusedAttnProcessor2_0
 
 ## SlicedAttnProcessor
-
 [[autodoc]] models.attention_processor.SlicedAttnProcessor
 
+## SlicedAttnAddedKVProcessor
 [[autodoc]] models.attention_processor.SlicedAttnAddedKVProcessor
 
 ## XFormersAttnProcessor
-
 [[autodoc]] models.attention_processor.XFormersAttnProcessor
 
-[[autodoc]] models.attention_processor.XFormersAttnAddedKVProcessor
-
-## XLAFlashAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.XLAFlashAttnProcessor2_0
+## AttnProcessorNPU
+[[autodoc]] models.attention_processor.AttnProcessorNPU

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

@@ -24,12 +24,6 @@ Learn how to load an IP-Adapter checkpoint and image in the IP-Adapter [loading]
 
 [[autodoc]] loaders.ip_adapter.IPAdapterMixin
 
-## SD3IPAdapterMixin
-
-[[autodoc]] loaders.ip_adapter.SD3IPAdapterMixin
-    - all
-    - is_ip_adapter_active
-
 ## IPAdapterMaskProcessor
 
 [[autodoc]] image_processor.IPAdapterMaskProcessor

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

@@ -17,9 +17,6 @@ LoRA is a fast and lightweight training method that inserts and trains a signifi
 - [`StableDiffusionLoraLoaderMixin`] provides functions for loading and unloading, fusing and unfusing, enabling and disabling, and more functions for managing LoRA weights. This class can be used with any model.
 - [`StableDiffusionXLLoraLoaderMixin`] is a [Stable Diffusion (SDXL)](../../api/pipelines/stable_diffusion/stable_diffusion_xl) version of the [`StableDiffusionLoraLoaderMixin`] class for loading and saving LoRA weights. It can only be used with the SDXL model.
 - [`SD3LoraLoaderMixin`] provides similar functions for [Stable Diffusion 3](https://huggingface.co/blog/sd3).
-- [`FluxLoraLoaderMixin`] provides similar functions for [Flux](https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux).
-- [`CogVideoXLoraLoaderMixin`] provides similar functions for [CogVideoX](https://huggingface.co/docs/diffusers/main/en/api/pipelines/cogvideox).
-- [`Mochi1LoraLoaderMixin`] provides similar functions for [Mochi](https://huggingface.co/docs/diffusers/main/en/api/pipelines/mochi).
 - [`AmusedLoraLoaderMixin`] is for the [`AmusedPipeline`].
 - [`LoraBaseMixin`] provides a base class with several utility methods to fuse, unfuse, unload, LoRAs and more.
 
@@ -41,18 +38,6 @@ To learn more about how to load LoRA weights, see the [LoRA](../../using-diffuse
 
 [[autodoc]] loaders.lora_pipeline.SD3LoraLoaderMixin
 
-## FluxLoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.FluxLoraLoaderMixin
-
-## CogVideoXLoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.CogVideoXLoraLoaderMixin
-
-## Mochi1LoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.Mochi1LoraLoaderMixin
-
 ## AmusedLoraLoaderMixin
 
 [[autodoc]] loaders.lora_pipeline.AmusedLoraLoaderMixin

docs/source/en/api/loaders/transformer_sd3.md

@@ -1,29 +0,0 @@
-<!--Copyright 2024 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.
--->
-
-# SD3Transformer2D
-
-This class is useful when *only* loading weights into a [`SD3Transformer2DModel`]. If you need to load weights into the text encoder or a text encoder and SD3Transformer2DModel, check [`SD3LoraLoaderMixin`](lora#diffusers.loaders.SD3LoraLoaderMixin) class instead.
-
-The [`SD3Transformer2DLoadersMixin`] class currently only loads IP-Adapter weights, but will be used in the future to save weights and load LoRAs.
-
-<Tip>
-
-To learn more about how to load LoRA weights, see the [LoRA](../../using-diffusers/loading_adapters#lora) loading guide.
-
-</Tip>
-
-## SD3Transformer2DLoadersMixin
-
-[[autodoc]] loaders.transformer_sd3.SD3Transformer2DLoadersMixin
-    - all
-    - _load_ip_adapter_weights

docs/source/en/api/models/allegro_transformer3d.md

@@ -18,7 +18,7 @@ The model can be loaded with the following code snippet.
 ```python
 from diffusers import AllegroTransformer3DModel
 
-transformer = AllegroTransformer3DModel.from_pretrained("rhymes-ai/Allegro", subfolder="transformer", torch_dtype=torch.bfloat16).to("cuda")
+vae = AllegroTransformer3DModel.from_pretrained("rhymes-ai/Allegro", subfolder="transformer", torch_dtype=torch.bfloat16).to("cuda")
 ```
 
 ## AllegroTransformer3DModel

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

@@ -29,8 +29,6 @@ The following DCAE models are released and supported in Diffusers.
 | [`mit-han-lab/dc-ae-f128c512-in-1.0-diffusers`](https://huggingface.co/mit-han-lab/dc-ae-f128c512-in-1.0-diffusers) | [`mit-han-lab/dc-ae-f128c512-in-1.0`](https://huggingface.co/mit-han-lab/dc-ae-f128c512-in-1.0)
 | [`mit-han-lab/dc-ae-f128c512-mix-1.0-diffusers`](https://huggingface.co/mit-han-lab/dc-ae-f128c512-mix-1.0-diffusers) | [`mit-han-lab/dc-ae-f128c512-mix-1.0`](https://huggingface.co/mit-han-lab/dc-ae-f128c512-mix-1.0)
 
-This model was contributed by [lawrence-cj](https://github.com/lawrence-cj).
-
 Load a model in Diffusers format with [`~ModelMixin.from_pretrained`].
 
 ```python

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

@@ -1,32 +0,0 @@
-<!-- Copyright 2024 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. -->
-
-# AutoencoderKLHunyuanVideo
-
-The 3D variational autoencoder (VAE) model with KL loss used in [HunyuanVideo](https://github.com/Tencent/HunyuanVideo/), which was introduced in [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://huggingface.co/papers/2412.03603) by Tencent.
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import AutoencoderKLHunyuanVideo
-
-vae = AutoencoderKLHunyuanVideo.from_pretrained("hunyuanvideo-community/HunyuanVideo", subfolder="vae", torch_dtype=torch.float16)
-```
-
-## AutoencoderKLHunyuanVideo
-
-[[autodoc]] AutoencoderKLHunyuanVideo
-  - decode
-  - all
-
-## DecoderOutput
-
-[[autodoc]] models.autoencoders.vae.DecoderOutput

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

@@ -1,37 +0,0 @@
-<!-- Copyright 2024 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. -->
-
-# AutoencoderKLLTXVideo
-
-The 3D variational autoencoder (VAE) model with KL loss used in [LTX](https://huggingface.co/Lightricks/LTX-Video) was introduced by Lightricks.
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import AutoencoderKLLTXVideo
-
-vae = AutoencoderKLLTXVideo.from_pretrained("Lightricks/LTX-Video", subfolder="vae", torch_dtype=torch.float32).to("cuda")
-```
-
-## AutoencoderKLLTXVideo
-
-[[autodoc]] AutoencoderKLLTXVideo
-    - decode
-    - encode
-    - all
-
-## AutoencoderKLOutput
-
-[[autodoc]] models.autoencoders.autoencoder_kl.AutoencoderKLOutput
-
-## DecoderOutput
-
-[[autodoc]] models.autoencoders.vae.DecoderOutput

docs/source/en/api/models/cogvideox_transformer3d.md

@@ -18,7 +18,7 @@ The model can be loaded with the following code snippet.
 ```python
 from diffusers import CogVideoXTransformer3DModel
 
-transformer = CogVideoXTransformer3DModel.from_pretrained("THUDM/CogVideoX-2b", subfolder="transformer", torch_dtype=torch.float16).to("cuda")
+vae = CogVideoXTransformer3DModel.from_pretrained("THUDM/CogVideoX-2b", subfolder="transformer", torch_dtype=torch.float16).to("cuda")
 ```
 
 ## CogVideoXTransformer3DModel

docs/source/en/api/models/cogview3plus_transformer2d.md

@@ -18,7 +18,7 @@ The model can be loaded with the following code snippet.
 ```python
 from diffusers import CogView3PlusTransformer2DModel
 
-transformer = CogView3PlusTransformer2DModel.from_pretrained("THUDM/CogView3Plus-3b", subfolder="transformer", torch_dtype=torch.bfloat16).to("cuda")
+vae = CogView3PlusTransformer2DModel.from_pretrained("THUDM/CogView3Plus-3b", subfolder="transformer", torch_dtype=torch.bfloat16).to("cuda")
 ```
 
 ## CogView3PlusTransformer2DModel

docs/source/en/api/models/hunyuan_video_transformer_3d.md

@@ -1,30 +0,0 @@
-<!-- Copyright 2024 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. -->
-
-# HunyuanVideoTransformer3DModel
-
-A Diffusion Transformer model for 3D video-like data was introduced in [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://huggingface.co/papers/2412.03603) by Tencent.
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import HunyuanVideoTransformer3DModel
-
-transformer = HunyuanVideoTransformer3DModel.from_pretrained("hunyuanvideo-community/HunyuanVideo", subfolder="transformer", torch_dtype=torch.bfloat16)
-```
-
-## HunyuanVideoTransformer3DModel
-
-[[autodoc]] HunyuanVideoTransformer3DModel
-
-## Transformer2DModelOutput
-
-[[autodoc]] models.modeling_outputs.Transformer2DModelOutput

docs/source/en/api/models/ltx_video_transformer3d.md

@@ -1,30 +0,0 @@
-<!-- Copyright 2024 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. -->
-
-# LTXVideoTransformer3DModel
-
-A Diffusion Transformer model for 3D data from [LTX](https://huggingface.co/Lightricks/LTX-Video) was introduced by Lightricks.
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import LTXVideoTransformer3DModel
-
-transformer = LTXVideoTransformer3DModel.from_pretrained("Lightricks/LTX-Video", subfolder="transformer", torch_dtype=torch.bfloat16).to("cuda")
-```
-
-## LTXVideoTransformer3DModel
-
-[[autodoc]] LTXVideoTransformer3DModel
-
-## Transformer2DModelOutput
-
-[[autodoc]] models.modeling_outputs.Transformer2DModelOutput

docs/source/en/api/models/mochi_transformer3d.md

@@ -18,7 +18,7 @@ The model can be loaded with the following code snippet.
 ```python
 from diffusers import MochiTransformer3DModel
 
-transformer = MochiTransformer3DModel.from_pretrained("genmo/mochi-1-preview", subfolder="transformer", torch_dtype=torch.float16).to("cuda")
+vae = MochiTransformer3DModel.from_pretrained("genmo/mochi-1-preview", subfolder="transformer", torch_dtype=torch.float16).to("cuda")
 ```
 
 ## MochiTransformer3DModel

docs/source/en/api/models/sana_transformer2d.md

@@ -1,34 +0,0 @@
-<!-- Copyright 2024 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. -->
-
-# SanaTransformer2DModel
-
-A Diffusion Transformer model for 2D data from [SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers](https://huggingface.co/papers/2410.10629) was introduced from NVIDIA and MIT HAN Lab, by Enze Xie, Junsong Chen, Junyu Chen, Han Cai, Haotian Tang, Yujun Lin, Zhekai Zhang, Muyang Li, Ligeng Zhu, Yao Lu, Song Han.
-
-The abstract from the paper is:
-
-*We introduce Sana, a text-to-image framework that can efficiently generate images up to 4096×4096 resolution. Sana can synthesize high-resolution, high-quality images with strong text-image alignment at a remarkably fast speed, deployable on laptop GPU. Core designs include: (1) Deep compression autoencoder: unlike traditional AEs, which compress images only 8×, we trained an AE that can compress images 32×, effectively reducing the number of latent tokens. (2) Linear DiT: we replace all vanilla attention in DiT with linear attention, which is more efficient at high resolutions without sacrificing quality. (3) Decoder-only text encoder: we replaced T5 with modern decoder-only small LLM as the text encoder and designed complex human instruction with in-context learning to enhance the image-text alignment. (4) Efficient training and sampling: we propose Flow-DPM-Solver to reduce sampling steps, with efficient caption labeling and selection to accelerate convergence. As a result, Sana-0.6B is very competitive with modern giant diffusion model (e.g. Flux-12B), being 20 times smaller and 100+ times faster in measured throughput. Moreover, Sana-0.6B can be deployed on a 16GB laptop GPU, taking less than 1 second to generate a 1024×1024 resolution image. Sana enables content creation at low cost. Code and model will be publicly released.*
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import SanaTransformer2DModel
-
-transformer = SanaTransformer2DModel.from_pretrained("Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers", subfolder="transformer", torch_dtype=torch.bfloat16)
-```
-
-## SanaTransformer2DModel
-
-[[autodoc]] SanaTransformer2DModel
-
-## Transformer2DModelOutput
-
-[[autodoc]] models.modeling_outputs.Transformer2DModelOutput

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

@@ -19,55 +19,10 @@ The abstract from the paper is:
 
 <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.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers.md) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading.md#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 
-## 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 [`AllegroPipeline`] for inference with bitsandbytes.
-
-```py
-import torch
-from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, AllegroTransformer3DModel, AllegroPipeline
-from diffusers.utils import export_to_video
-from transformers import BitsAndBytesConfig as BitsAndBytesConfig, T5EncoderModel
-
-quant_config = BitsAndBytesConfig(load_in_8bit=True)
-text_encoder_8bit = T5EncoderModel.from_pretrained(
-    "rhymes-ai/Allegro",
-    subfolder="text_encoder",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
-
-quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
-transformer_8bit = AllegroTransformer3DModel.from_pretrained(
-    "rhymes-ai/Allegro",
-    subfolder="transformer",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
-
-pipeline = AllegroPipeline.from_pretrained(
-    "rhymes-ai/Allegro",
-    text_encoder=text_encoder_8bit,
-    transformer=transformer_8bit,
-    torch_dtype=torch.float16,
-    device_map="balanced",
-)
-
-prompt = (
-    "A seaside harbor with bright sunlight and sparkling seawater, with many boats in the water. From an aerial view, "
-    "the boats vary in size and color, some moving and some stationary. Fishing boats in the water suggest that this "
-    "location might be a popular spot for docking fishing boats."
-)
-video = pipeline(prompt, guidance_scale=7.5, max_sequence_length=512).frames[0]
-export_to_video(video, "harbor.mp4", fps=15)
-```
-
 ## AllegroPipeline
 
 [[autodoc]] AllegroPipeline

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

@@ -803,7 +803,7 @@ FreeInit is not really free - the improved quality comes at the cost of extra co
 
 <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.
+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-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

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

@@ -22,7 +22,7 @@ You can find additional information about Attend-and-Excite on the [project page
 
 <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.
+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-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

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

@@ -37,7 +37,7 @@ During inference:
 
 <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.
+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-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/audioldm2.md

@@ -60,7 +60,7 @@ The following example demonstrates how to construct good music and speech genera
 
 <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.
+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-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

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

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # AuraFlow
 
-AuraFlow is inspired by [Stable Diffusion 3](../pipelines/stable_diffusion/stable_diffusion_3) and is by far the largest text-to-image generation model that comes with an Apache 2.0 license. This model achieves state-of-the-art results on the [GenEval](https://github.com/djghosh13/geneval) benchmark.
+AuraFlow is inspired by [Stable Diffusion 3](../pipelines/stable_diffusion/stable_diffusion_3.md) and is by far the largest text-to-image generation model that comes with an Apache 2.0 license. This model achieves state-of-the-art results on the [GenEval](https://github.com/djghosh13/geneval) benchmark.
 
 It was developed by the Fal team and more details about it can be found in [this blog post](https://blog.fal.ai/auraflow/).
 
@@ -22,73 +22,6 @@ AuraFlow can be quite expensive to run on consumer hardware devices. However, yo
 
 </Tip>
 
-## 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 [`AuraFlowPipeline`] for inference with bitsandbytes.
-
-```py
-import torch
-from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, AuraFlowTransformer2DModel, AuraFlowPipeline
-from transformers import BitsAndBytesConfig as BitsAndBytesConfig, T5EncoderModel
-
-quant_config = BitsAndBytesConfig(load_in_8bit=True)
-text_encoder_8bit = T5EncoderModel.from_pretrained(
-    "fal/AuraFlow",
-    subfolder="text_encoder",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
-
-quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
-transformer_8bit = AuraFlowTransformer2DModel.from_pretrained(
-    "fal/AuraFlow",
-    subfolder="transformer",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
-
-pipeline = AuraFlowPipeline.from_pretrained(
-    "fal/AuraFlow",
-    text_encoder=text_encoder_8bit,
-    transformer=transformer_8bit,
-    torch_dtype=torch.float16,
-    device_map="balanced",
-)
-
-prompt = "a tiny astronaut hatching from an egg on the moon"
-image = pipeline(prompt).images[0]
-image.save("auraflow.png")
-```
-
-Loading [GGUF checkpoints](https://huggingface.co/docs/diffusers/quantization/gguf) are also supported:
-
-```py
-import torch
-from diffusers import (
-    AuraFlowPipeline,
-    GGUFQuantizationConfig,
-    AuraFlowTransformer2DModel,
-)
-
-transformer = AuraFlowTransformer2DModel.from_single_file(
-    "https://huggingface.co/city96/AuraFlow-v0.3-gguf/blob/main/aura_flow_0.3-Q2_K.gguf",
-    quantization_config=GGUFQuantizationConfig(compute_dtype=torch.bfloat16),
-    torch_dtype=torch.bfloat16,
-)
-
-pipeline = AuraFlowPipeline.from_pretrained(
-    "fal/AuraFlow-v0.3",
-    transformer=transformer,
-    torch_dtype=torch.bfloat16,
-)
-
-prompt = "a cute pony in a field of flowers"
-image = pipeline(prompt).images[0]
-image.save("auraflow.png")
-```
-
 ## AuraFlowPipeline
 
 [[autodoc]] AuraFlowPipeline

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

@@ -25,7 +25,7 @@ The original codebase can be found at [salesforce/LAVIS](https://github.com/sale
 
 <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.
+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-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

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

@@ -23,7 +23,7 @@ The abstract from the paper is:
 
 <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.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers.md) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading.md#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 
@@ -112,46 +112,13 @@ CogVideoX-2b requires about 19 GB of GPU memory to decode 49 frames (6 seconds o
   - With enabling cpu offloading and tiling, memory usage is `11 GB`
 - `pipe.vae.enable_slicing()`
 
-## Quantization
+### Quantized inference
 
-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.
+[torchao](https://github.com/pytorch/ao) and [optimum-quanto](https://github.com/huggingface/optimum-quanto/) can be used to quantize the text encoder, transformer and VAE modules to lower the memory requirements. This makes it possible to run the model on a free-tier T4 Colab or lower VRAM GPUs!
 
-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 [`CogVideoXPipeline`] for inference with bitsandbytes.
-
-```py
-import torch
-from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, CogVideoXTransformer3DModel, CogVideoXPipeline
-from diffusers.utils import export_to_video
-from transformers import BitsAndBytesConfig as BitsAndBytesConfig, T5EncoderModel
-
-quant_config = BitsAndBytesConfig(load_in_8bit=True)
-text_encoder_8bit = T5EncoderModel.from_pretrained(
-    "THUDM/CogVideoX-2b",
-    subfolder="text_encoder",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
-
-quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
-transformer_8bit = CogVideoXTransformer3DModel.from_pretrained(
-    "THUDM/CogVideoX-2b",
-    subfolder="transformer",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
-
-pipeline = CogVideoXPipeline.from_pretrained(
-    "THUDM/CogVideoX-2b",
-    text_encoder=text_encoder_8bit,
-    transformer=transformer_8bit,
-    torch_dtype=torch.float16,
-    device_map="balanced",
-)
-
-prompt = "A detailed wooden toy ship with intricately carved masts and sails is seen gliding smoothly over a plush, blue carpet that mimics the waves of the sea. The ship's hull is painted a rich brown, with tiny windows. The carpet, soft and textured, provides a perfect backdrop, resembling an oceanic expanse. Surrounding the ship are various other toys and children's items, hinting at a playful environment. The scene captures the innocence and imagination of childhood, with the toy ship's journey symbolizing endless adventures in a whimsical, indoor setting."
-video = pipeline(prompt=prompt, guidance_scale=6, num_inference_steps=50).frames[0]
-export_to_video(video, "ship.mp4", fps=8)
-```
+It is also worth noting that torchao quantization is fully compatible with [torch.compile](/optimization/torch2.0#torchcompile), which allows for much faster inference speed. Additionally, models can be serialized and stored in a quantized datatype to save disk space with torchao. Find examples and benchmarks in the gists below.
+- [torchao](https://gist.github.com/a-r-r-o-w/4d9732d17412888c885480c6521a9897)
+- [quanto](https://gist.github.com/a-r-r-o-w/31be62828b00a9292821b85c1017effa)
 
 ## CogVideoXPipeline
 

docs/source/en/api/pipelines/cogview3.md

@@ -23,7 +23,7 @@ The abstract from the paper is:
 
 <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.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers.md) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading.md#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

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

@@ -1,89 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team, The Black Forest 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.
--->
-
-# FluxControlInpaint
-
-FluxControlInpaintPipeline is an implementation of Inpainting for Flux.1 Depth/Canny models. It is a pipeline that allows you to inpaint images using the Flux.1 Depth/Canny models. The pipeline takes an image and a mask as input and returns the inpainted image.
-
-FLUX.1 Depth and Canny [dev] is a 12 billion parameter rectified flow transformer capable of generating an image based on a text description while following the structure of a given input image. **This is not a ControlNet model**.
-
-| Control type | Developer | Link |
-| -------- | ---------- | ---- |
-| Depth | [Black Forest Labs](https://huggingface.co/black-forest-labs) | [Link](https://huggingface.co/black-forest-labs/FLUX.1-Depth-dev) |
-| Canny | [Black Forest Labs](https://huggingface.co/black-forest-labs) | [Link](https://huggingface.co/black-forest-labs/FLUX.1-Canny-dev) |
-
-
-<Tip>
-
-Flux can be quite expensive to run on consumer hardware devices. However, you can perform a suite of optimizations to run it faster and in a more memory-friendly manner. Check out [this section](https://huggingface.co/blog/sd3#memory-optimizations-for-sd3) for more details. Additionally, Flux can benefit from quantization for memory efficiency with a trade-off in inference latency. Refer to [this blog post](https://huggingface.co/blog/quanto-diffusers) to learn more. For an exhaustive list of resources, check out [this gist](https://gist.github.com/sayakpaul/b664605caf0aa3bf8585ab109dd5ac9c).
-
-</Tip>
-
-```python
-import torch
-from diffusers import FluxControlInpaintPipeline
-from diffusers.models.transformers import FluxTransformer2DModel
-from transformers import T5EncoderModel
-from diffusers.utils import load_image, make_image_grid
-from image_gen_aux import DepthPreprocessor # https://github.com/huggingface/image_gen_aux
-from PIL import Image
-import numpy as np
-
-pipe = FluxControlInpaintPipeline.from_pretrained(
-    "black-forest-labs/FLUX.1-Depth-dev",
-    torch_dtype=torch.bfloat16,
-)
-# use following lines if you have GPU constraints
-# ---------------------------------------------------------------
-transformer = FluxTransformer2DModel.from_pretrained(
-    "sayakpaul/FLUX.1-Depth-dev-nf4", subfolder="transformer", torch_dtype=torch.bfloat16
-)
-text_encoder_2 = T5EncoderModel.from_pretrained(
-    "sayakpaul/FLUX.1-Depth-dev-nf4", subfolder="text_encoder_2", torch_dtype=torch.bfloat16
-)
-pipe.transformer = transformer
-pipe.text_encoder_2 = text_encoder_2
-pipe.enable_model_cpu_offload()
-# ---------------------------------------------------------------
-pipe.to("cuda")
-
-prompt = "a blue robot singing opera with human-like expressions"
-image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/robot.png")
-
-head_mask = np.zeros_like(image)
-head_mask[65:580,300:642] = 255
-mask_image = Image.fromarray(head_mask)
-
-processor = DepthPreprocessor.from_pretrained("LiheYoung/depth-anything-large-hf")
-control_image = processor(image)[0].convert("RGB")
-
-output = pipe(
-    prompt=prompt,
-    image=image,
-    control_image=control_image,
-    mask_image=mask_image,
-    num_inference_steps=30,
-    strength=0.9,
-    guidance_scale=10.0,
-    generator=torch.Generator().manual_seed(42),
-).images[0]
-make_image_grid([image, control_image, mask_image, output.resize(image.size)], rows=1, cols=4).save("output.png")
-```
-
-## FluxControlInpaintPipeline
-[[autodoc]] FluxControlInpaintPipeline
-	- all
-	- __call__
-
-
-## FluxPipelineOutput
-[[autodoc]] pipelines.flux.pipeline_output.FluxPipelineOutput

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

@@ -26,7 +26,7 @@ The original codebase can be found at [lllyasviel/ControlNet](https://github.com
 
 <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.
+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-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

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

@@ -42,7 +42,7 @@ XLabs ControlNets are also supported, which was contributed by the [XLabs team](
 
 <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.
+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-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

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

@@ -26,7 +26,7 @@ This code is implemented by Tencent Hunyuan Team. You can find pre-trained check
 
 <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.
+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-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/controlnet_sd3.md

@@ -36,7 +36,7 @@ This controlnet code is mainly implemented by [The InstantX Team](https://huggin
 
 <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.
+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-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

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

@@ -32,7 +32,7 @@ If you don't see a checkpoint you're interested in, you can train your own SDXL
 
 <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.
+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-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

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

@@ -26,7 +26,7 @@ This model was contributed by [UmerHA](https://twitter.com/UmerHAdil). ❤️
 
 <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.
+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-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

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

@@ -32,7 +32,7 @@ This model was contributed by [UmerHA](https://twitter.com/UmerHAdil). ❤️
 
 <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.
+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-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

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

@@ -19,7 +19,7 @@ Dance Diffusion is the first in a suite of generative audio tools for producers
 
 <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.
+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-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

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

@@ -22,7 +22,7 @@ The original codebase can be found at [hohonathanho/diffusion](https://github.co
 
 <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.
+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-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

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

@@ -22,7 +22,7 @@ The original codebase can be found at [facebookresearch/dit](https://github.com/
 
 <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.
+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-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

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

@@ -268,47 +268,6 @@ images = pipe(
 images[0].save("flux-redux.png")
 ```
 
-## Combining Flux Turbo LoRAs with Flux Control, Fill, and Redux
-
-We can combine Flux Turbo LoRAs with Flux Control and other pipelines like Fill and Redux to enable few-steps' inference. The example below shows how to do that for Flux Control LoRA for depth and turbo LoRA from [`ByteDance/Hyper-SD`](https://hf.co/ByteDance/Hyper-SD).
-
-```py
-from diffusers import FluxControlPipeline
-from image_gen_aux import DepthPreprocessor
-from diffusers.utils import load_image
-from huggingface_hub import hf_hub_download
-import torch
-
-control_pipe = FluxControlPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
-control_pipe.load_lora_weights("black-forest-labs/FLUX.1-Depth-dev-lora", adapter_name="depth")
-control_pipe.load_lora_weights(
-    hf_hub_download("ByteDance/Hyper-SD", "Hyper-FLUX.1-dev-8steps-lora.safetensors"), adapter_name="hyper-sd"
-)
-control_pipe.set_adapters(["depth", "hyper-sd"], adapter_weights=[0.85, 0.125])
-control_pipe.enable_model_cpu_offload()
-
-prompt = "A robot made of exotic candies and chocolates of different kinds. The background is filled with confetti and celebratory gifts."
-control_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/robot.png")
-
-processor = DepthPreprocessor.from_pretrained("LiheYoung/depth-anything-large-hf")
-control_image = processor(control_image)[0].convert("RGB")
-
-image = control_pipe(
-    prompt=prompt,
-    control_image=control_image,
-    height=1024,
-    width=1024,
-    num_inference_steps=8,
-    guidance_scale=10.0,
-    generator=torch.Generator().manual_seed(42),
-).images[0]
-image.save("output.png")
-```
-
-## Note about `unload_lora_weights()` when using Flux LoRAs
-
-When unloading the Control LoRA weights, call `pipe.unload_lora_weights(reset_to_overwritten_params=True)` to reset the `pipe.transformer` completely back to its original form. The resultant pipeline can then be used with methods like [`DiffusionPipeline.from_pipe`]. More details about this argument are available in [this PR](https://github.com/huggingface/diffusers/pull/10397).
-
 ## Running FP16 inference
 
 Flux can generate high-quality images with FP16 (i.e. to accelerate inference on Turing/Volta GPUs) but produces different outputs compared to FP32/BF16. The issue is that some activations in the text encoders have to be clipped when running in FP16, which affects the overall image. Forcing text encoders to run with FP32 inference thus removes this output difference. See [here](https://github.com/huggingface/diffusers/pull/9097#issuecomment-2272292516) for details.
@@ -338,46 +297,6 @@ out = pipe(
 out.save("image.png")
 ```
 
-## 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 [`FluxPipeline`] for inference with bitsandbytes.
-
-```py
-import torch
-from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, FluxTransformer2DModel, FluxPipeline
-from transformers import BitsAndBytesConfig as BitsAndBytesConfig, T5EncoderModel
-
-quant_config = BitsAndBytesConfig(load_in_8bit=True)
-text_encoder_8bit = T5EncoderModel.from_pretrained(
-    "black-forest-labs/FLUX.1-dev",
-    subfolder="text_encoder_2",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
-
-quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
-transformer_8bit = FluxTransformer2DModel.from_pretrained(
-    "black-forest-labs/FLUX.1-dev",
-    subfolder="transformer",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
-
-pipeline = FluxPipeline.from_pretrained(
-    "black-forest-labs/FLUX.1-dev",
-    text_encoder_2=text_encoder_8bit,
-    transformer=transformer_8bit,
-    torch_dtype=torch.float16,
-    device_map="balanced",
-)
-
-prompt = "a tiny astronaut hatching from an egg on the moon"
-image = pipeline(prompt, guidance_scale=3.5, height=768, width=1360, num_inference_steps=50).images[0]
-image.save("flux.png")
-```
-
 ## Single File Loading for the `FluxTransformer2DModel`
 
 The `FluxTransformer2DModel` supports loading checkpoints in the original format shipped by Black Forest Labs. This is also useful when trying to load finetunes or quantized versions of the models that have been published by the community.

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

@@ -1,74 +0,0 @@
-<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License. -->
-
-# HunyuanVideo
-
-[HunyuanVideo](https://www.arxiv.org/abs/2412.03603) by Tencent.
-
-*Recent advancements in video generation have significantly impacted daily life for both individuals and industries. However, the leading video generation models remain closed-source, resulting in a notable performance gap between industry capabilities and those available to the public. In this report, we introduce HunyuanVideo, an innovative open-source video foundation model that demonstrates performance in video generation comparable to, or even surpassing, that of leading closed-source models. HunyuanVideo encompasses a comprehensive framework that integrates several key elements, including data curation, advanced architectural design, progressive model scaling and training, and an efficient infrastructure tailored for large-scale model training and inference. As a result, we successfully trained a video generative model with over 13 billion parameters, making it the largest among all open-source models. We conducted extensive experiments and implemented a series of targeted designs to ensure high visual quality, motion dynamics, text-video alignment, and advanced filming techniques. According to evaluations by professionals, HunyuanVideo outperforms previous state-of-the-art models, including Runway Gen-3, Luma 1.6, and three top-performing Chinese video generative models. By releasing the code for the foundation model and its applications, we aim to bridge the gap between closed-source and open-source communities. This initiative will empower individuals within the community to experiment with their ideas, fostering a more dynamic and vibrant video generation ecosystem. The code is publicly available at [this https URL](https://github.com/tencent/HunyuanVideo).*
-
-<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.
-
-</Tip>
-
-Recommendations for inference:
-- Both text encoders should be in `torch.float16`.
-- Transformer should be in `torch.bfloat16`.
-- VAE should be in `torch.float16`.
-- `num_frames` should be of the form `4 * k + 1`, for example `49` or `129`.
-- For smaller resolution videos, try lower values of `shift` (between `2.0` to `5.0`) in the [Scheduler](https://huggingface.co/docs/diffusers/main/en/api/schedulers/flow_match_euler_discrete#diffusers.FlowMatchEulerDiscreteScheduler.shift). For larger resolution images, try higher values (between `7.0` and `12.0`). The default value is `7.0` for HunyuanVideo.
-- For more information about supported resolutions and other details, please refer to the original repository [here](https://github.com/Tencent/HunyuanVideo/).
-
-## 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 [`HunyuanVideoPipeline`] for inference with bitsandbytes.
-
-```py
-import torch
-from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, HunyuanVideoTransformer3DModel, HunyuanVideoPipeline
-from diffusers.utils import export_to_video
-
-quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
-transformer_8bit = HunyuanVideoTransformer3DModel.from_pretrained(
-    "hunyuanvideo-community/HunyuanVideo",
-    subfolder="transformer",
-    quantization_config=quant_config,
-    torch_dtype=torch.bfloat16,
-)
-
-pipeline = HunyuanVideoPipeline.from_pretrained(
-    "hunyuanvideo-community/HunyuanVideo",
-    transformer=transformer_8bit,
-    torch_dtype=torch.float16,
-    device_map="balanced",
-)
-
-prompt = "A cat walks on the grass, realistic style."
-video = pipeline(prompt=prompt, num_frames=61, num_inference_steps=30).frames[0]
-export_to_video(video, "cat.mp4", fps=15)
-```
-
-## HunyuanVideoPipeline
-
-[[autodoc]] HunyuanVideoPipeline
-  - all
-  - __call__
-
-## HunyuanVideoPipelineOutput
-
-[[autodoc]] pipelines.hunyuan_video.pipeline_output.HunyuanVideoPipelineOutput

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

@@ -30,7 +30,7 @@ HunyuanDiT has the following components:
 
 <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.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers.md) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading.md#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/i2vgenxl.md

@@ -22,7 +22,7 @@ The original codebase can be found [here](https://github.com/ali-vilab/i2vgen-xl
 
 <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. Also, to know more about reducing the memory usage of this pipeline, refer to the ["Reduce memory usage"] section [here](../../using-diffusers/svd#reduce-memory-usage).
+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-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines. Also, to know more about reducing the memory usage of this pipeline, refer to the ["Reduce memory usage"] section [here](../../using-diffusers/svd#reduce-memory-usage).
 
 </Tip>
 

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

@@ -25,7 +25,7 @@ Check out the [Kandinsky Community](https://huggingface.co/kandinsky-community)
 
 <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.
+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-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/kandinsky3.md

@@ -32,7 +32,7 @@ Check out the [Kandinsky Community](https://huggingface.co/kandinsky-community)
 
 <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.
+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-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/kandinsky_v22.md

@@ -25,7 +25,7 @@ Check out the [Kandinsky Community](https://huggingface.co/kandinsky-community)
 
 <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.
+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-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

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

@@ -22,7 +22,7 @@ The original codebase can be found at [CompVis/latent-diffusion](https://github.
 
 <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.
+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-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

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

@@ -28,7 +28,7 @@ This pipeline was contributed by [maxin-cn](https://github.com/maxin-cn). The or
 
 <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.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers.md) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading.md#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 
@@ -70,47 +70,6 @@ Without torch.compile(): Average inference time: 16.246 seconds.
 With torch.compile(): Average inference time: 14.573 seconds.
 ```
 
-## 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 [`LattePipeline`] for inference with bitsandbytes.
-
-```py
-import torch
-from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, LatteTransformer3DModel, LattePipeline
-from diffusers.utils import export_to_gif
-from transformers import BitsAndBytesConfig as BitsAndBytesConfig, T5EncoderModel
-
-quant_config = BitsAndBytesConfig(load_in_8bit=True)
-text_encoder_8bit = T5EncoderModel.from_pretrained(
-    "maxin-cn/Latte-1",
-    subfolder="text_encoder",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
-
-quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
-transformer_8bit = LatteTransformer3DModel.from_pretrained(
-    "maxin-cn/Latte-1",
-    subfolder="transformer",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
-
-pipeline = LattePipeline.from_pretrained(
-    "maxin-cn/Latte-1",
-    text_encoder=text_encoder_8bit,
-    transformer=transformer_8bit,
-    torch_dtype=torch.float16,
-    device_map="balanced",
-)
-
-prompt = "A small cactus with a happy face in the Sahara desert."
-video = pipeline(prompt).frames[0]
-export_to_gif(video, "latte.gif")
-```
-
 ## LattePipeline
 
 [[autodoc]] LattePipeline

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

@@ -1,197 +0,0 @@
-<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License. -->
-
-# LTX Video
-
-[LTX Video](https://huggingface.co/Lightricks/LTX-Video) is the first DiT-based video generation model capable of generating high-quality videos in real-time. It produces 24 FPS videos at a 768x512 resolution faster than they can be watched. Trained on a large-scale dataset of diverse videos, the model generates high-resolution videos with realistic and varied content. We provide a model for both text-to-video as well as image + text-to-video usecases.
-
-<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.
-
-</Tip>
-
-Available models:
-
-|  Model name   | Recommended dtype |
-|:-------------:|:-----------------:|
-| [`LTX Video 0.9.0`](https://huggingface.co/Lightricks/LTX-Video/blob/main/ltx-video-2b-v0.9.safetensors) | `torch.bfloat16` |
-| [`LTX Video 0.9.1`](https://huggingface.co/Lightricks/LTX-Video/blob/main/ltx-video-2b-v0.9.1.safetensors) | `torch.bfloat16` |
-
-Note: The recommended dtype is for the transformer component. The VAE and text encoders can be either `torch.float32`, `torch.bfloat16` or `torch.float16` but the recommended dtype is `torch.bfloat16` as used in the original repository.
-
-## Loading Single Files
-
-Loading the original LTX Video checkpoints is also possible with [`~ModelMixin.from_single_file`]. We recommend using `from_single_file` for the Lightricks series of models, as they plan to release multiple models in the future in the single file format.
-
-```python
-import torch
-from diffusers import AutoencoderKLLTXVideo, LTXImageToVideoPipeline, LTXVideoTransformer3DModel
-
-# `single_file_url` could also be https://huggingface.co/Lightricks/LTX-Video/ltx-video-2b-v0.9.1.safetensors
-single_file_url = "https://huggingface.co/Lightricks/LTX-Video/ltx-video-2b-v0.9.safetensors"
-transformer = LTXVideoTransformer3DModel.from_single_file(
-  single_file_url, torch_dtype=torch.bfloat16
-)
-vae = AutoencoderKLLTXVideo.from_single_file(single_file_url, torch_dtype=torch.bfloat16)
-pipe = LTXImageToVideoPipeline.from_pretrained(
-  "Lightricks/LTX-Video", transformer=transformer, vae=vae, torch_dtype=torch.bfloat16
-)
-
-# ... inference code ...
-```
-
-Alternatively, the pipeline can be used to load the weights with [`~FromSingleFileMixin.from_single_file`].
-
-```python
-import torch
-from diffusers import LTXImageToVideoPipeline
-from transformers import T5EncoderModel, T5Tokenizer
-
-single_file_url = "https://huggingface.co/Lightricks/LTX-Video/ltx-video-2b-v0.9.safetensors"
-text_encoder = T5EncoderModel.from_pretrained(
-  "Lightricks/LTX-Video", subfolder="text_encoder", torch_dtype=torch.bfloat16
-)
-tokenizer = T5Tokenizer.from_pretrained(
-  "Lightricks/LTX-Video", subfolder="tokenizer", torch_dtype=torch.bfloat16
-)
-pipe = LTXImageToVideoPipeline.from_single_file(
-  single_file_url, text_encoder=text_encoder, tokenizer=tokenizer, torch_dtype=torch.bfloat16
-)
-```
-
-Loading [LTX GGUF checkpoints](https://huggingface.co/city96/LTX-Video-gguf) are also supported:
-
-```py
-import torch
-from diffusers.utils import export_to_video
-from diffusers import LTXPipeline, LTXVideoTransformer3DModel, GGUFQuantizationConfig
-
-ckpt_path = (
-    "https://huggingface.co/city96/LTX-Video-gguf/blob/main/ltx-video-2b-v0.9-Q3_K_S.gguf"
-)
-transformer = LTXVideoTransformer3DModel.from_single_file(
-    ckpt_path,
-    quantization_config=GGUFQuantizationConfig(compute_dtype=torch.bfloat16),
-    torch_dtype=torch.bfloat16,
-)
-pipe = LTXPipeline.from_pretrained(
-    "Lightricks/LTX-Video",
-    transformer=transformer,
-    torch_dtype=torch.bfloat16,
-)
-pipe.enable_model_cpu_offload()
-
-prompt = "A woman with long brown hair and light skin smiles at another woman with long blonde hair. The woman with brown hair wears a black jacket and has a small, barely noticeable mole on her right cheek. The camera angle is a close-up, focused on the woman with brown hair's face. The lighting is warm and natural, likely from the setting sun, casting a soft glow on the scene. The scene appears to be real-life footage"
-negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted"
-
-video = pipe(
-    prompt=prompt,
-    negative_prompt=negative_prompt,
-    width=704,
-    height=480,
-    num_frames=161,
-    num_inference_steps=50,
-).frames[0]
-export_to_video(video, "output_gguf_ltx.mp4", fps=24)
-```
-
-Make sure to read the [documentation on GGUF](../../quantization/gguf) to learn more about our GGUF support.
-
-<!-- TODO(aryan): Update this when official weights are supported -->
-
-Loading and running inference with [LTX Video 0.9.1](https://huggingface.co/Lightricks/LTX-Video/blob/main/ltx-video-2b-v0.9.1.safetensors) weights.
-
-```python
-import torch
-from diffusers import LTXPipeline
-from diffusers.utils import export_to_video
-
-pipe = LTXPipeline.from_pretrained("a-r-r-o-w/LTX-Video-0.9.1-diffusers", torch_dtype=torch.bfloat16)
-pipe.to("cuda")
-
-prompt = "A woman with long brown hair and light skin smiles at another woman with long blonde hair. The woman with brown hair wears a black jacket and has a small, barely noticeable mole on her right cheek. The camera angle is a close-up, focused on the woman with brown hair's face. The lighting is warm and natural, likely from the setting sun, casting a soft glow on the scene. The scene appears to be real-life footage"
-negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted"
-
-video = pipe(
-    prompt=prompt,
-    negative_prompt=negative_prompt,
-    width=768,
-    height=512,
-    num_frames=161,
-    decode_timestep=0.03,
-    decode_noise_scale=0.025,
-    num_inference_steps=50,
-).frames[0]
-export_to_video(video, "output.mp4", fps=24)
-```
-
-Refer to [this section](https://huggingface.co/docs/diffusers/main/en/api/pipelines/cogvideox#memory-optimization) to learn more about optimizing memory consumption.
-
-## 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 [`LTXPipeline`] for inference with bitsandbytes.
-
-```py
-import torch
-from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, LTXVideoTransformer3DModel, LTXPipeline
-from diffusers.utils import export_to_video
-from transformers import BitsAndBytesConfig as BitsAndBytesConfig, T5EncoderModel
-
-quant_config = BitsAndBytesConfig(load_in_8bit=True)
-text_encoder_8bit = T5EncoderModel.from_pretrained(
-    "Lightricks/LTX-Video",
-    subfolder="text_encoder",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
-
-quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
-transformer_8bit = LTXVideoTransformer3DModel.from_pretrained(
-    "Lightricks/LTX-Video",
-    subfolder="transformer",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
-
-pipeline = LTXPipeline.from_pretrained(
-    "Lightricks/LTX-Video",
-    text_encoder=text_encoder_8bit,
-    transformer=transformer_8bit,
-    torch_dtype=torch.float16,
-    device_map="balanced",
-)
-
-prompt = "A detailed wooden toy ship with intricately carved masts and sails is seen gliding smoothly over a plush, blue carpet that mimics the waves of the sea. The ship's hull is painted a rich brown, with tiny windows. The carpet, soft and textured, provides a perfect backdrop, resembling an oceanic expanse. Surrounding the ship are various other toys and children's items, hinting at a playful environment. The scene captures the innocence and imagination of childhood, with the toy ship's journey symbolizing endless adventures in a whimsical, indoor setting."
-video = pipeline(prompt=prompt, num_frames=161, num_inference_steps=50).frames[0]
-export_to_video(video, "ship.mp4", fps=24)
-```
-
-## LTXPipeline
-
-[[autodoc]] LTXPipeline
-  - all
-  - __call__
-
-## LTXImageToVideoPipeline
-
-[[autodoc]] LTXImageToVideoPipeline
-  - all
-  - __call__
-
-## LTXPipelineOutput
-
-[[autodoc]] pipelines.ltx.pipeline_output.LTXPipelineOutput

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

@@ -47,7 +47,7 @@ This pipeline was contributed by [PommesPeter](https://github.com/PommesPeter).
 
 <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.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers.md) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading.md#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 
@@ -82,46 +82,6 @@ pipeline.vae.decode = torch.compile(pipeline.vae.decode, mode="max-autotune", fu
 image = pipeline(prompt="Upper body of a young woman in a Victorian-era outfit with brass goggles and leather straps. Background shows an industrial revolution cityscape with smoky skies and tall, metal structures").images[0]
 ```
 
-## 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 [`LuminaText2ImgPipeline`] for inference with bitsandbytes.
-
-```py
-import torch
-from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, Transformer2DModel, LuminaText2ImgPipeline
-from transformers import BitsAndBytesConfig as BitsAndBytesConfig, T5EncoderModel
-
-quant_config = BitsAndBytesConfig(load_in_8bit=True)
-text_encoder_8bit = T5EncoderModel.from_pretrained(
-    "Alpha-VLLM/Lumina-Next-SFT-diffusers",
-    subfolder="text_encoder",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
-
-quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
-transformer_8bit = Transformer2DModel.from_pretrained(
-    "Alpha-VLLM/Lumina-Next-SFT-diffusers",
-    subfolder="transformer",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
-
-pipeline = LuminaText2ImgPipeline.from_pretrained(
-    "Alpha-VLLM/Lumina-Next-SFT-diffusers",
-    text_encoder=text_encoder_8bit,
-    transformer=transformer_8bit,
-    torch_dtype=torch.float16,
-    device_map="balanced",
-)
-
-prompt = "a tiny astronaut hatching from an egg on the moon"
-image = pipeline(prompt).images[0]
-image.save("lumina.png")
-```
-
 ## LuminaText2ImgPipeline
 
 [[autodoc]] LuminaText2ImgPipeline

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

@@ -43,7 +43,7 @@ The original checkpoints can be found under the [PRS-ETH](https://huggingface.co
 
 <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. Also, to know more about reducing the memory usage of this pipeline, refer to the ["Reduce memory usage"] section [here](../../using-diffusers/svd#reduce-memory-usage).
+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-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines. Also, to know more about reducing the memory usage of this pipeline, refer to the ["Reduce memory usage"] section [here](../../using-diffusers/svd#reduce-memory-usage).
 
 </Tip>
 

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

@@ -13,257 +13,18 @@
 # limitations under the License.
 -->
 
-# Mochi 1 Preview
+# Mochi
 
-> [!TIP]
-> Only a research preview of the model weights is available at the moment.
-
-[Mochi 1](https://huggingface.co/genmo/mochi-1-preview) is a video generation model by Genmo with a strong focus on prompt adherence and motion quality. The model features a 10B parameter Asmmetric Diffusion Transformer (AsymmDiT) architecture, and uses non-square QKV and output projection layers to reduce inference memory requirements. A single T5-XXL model is used to encode prompts.
+[Mochi 1 Preview](https://huggingface.co/genmo/mochi-1-preview) from Genmo.
 
 *Mochi 1 preview is an open state-of-the-art video generation model with high-fidelity motion and strong prompt adherence in preliminary evaluation. This model dramatically closes the gap between closed and open video generation systems. The model is released under a permissive Apache 2.0 license.*
 
-> [!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.
-
-## 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 [`MochiPipeline`] for inference with bitsandbytes.
-
-```py
-import torch
-from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, MochiTransformer3DModel, MochiPipeline
-from diffusers.utils import export_to_video
-from transformers import BitsAndBytesConfig as BitsAndBytesConfig, T5EncoderModel
-
-quant_config = BitsAndBytesConfig(load_in_8bit=True)
-text_encoder_8bit = T5EncoderModel.from_pretrained(
-    "genmo/mochi-1-preview",
-    subfolder="text_encoder",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
-
-quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
-transformer_8bit = MochiTransformer3DModel.from_pretrained(
-    "genmo/mochi-1-preview",
-    subfolder="transformer",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
-
-pipeline = MochiPipeline.from_pretrained(
-    "genmo/mochi-1-preview",
-    text_encoder=text_encoder_8bit,
-    transformer=transformer_8bit,
-    torch_dtype=torch.float16,
-    device_map="balanced",
-)
-
-video = pipeline(
-  "Close-up of a cats eye, with the galaxy reflected in the cats eye. Ultra high resolution 4k.",
-  num_inference_steps=28,
-  guidance_scale=3.5
-).frames[0]
-export_to_video(video, "cat.mp4")
-```
-
-## Generating videos with Mochi-1 Preview
-
-The following example will download the full precision `mochi-1-preview` weights and produce the highest quality results but will require at least 42GB VRAM to run.
-
-```python
-import torch
-from diffusers import MochiPipeline
-from diffusers.utils import export_to_video
-
-pipe = MochiPipeline.from_pretrained("genmo/mochi-1-preview")
-
-# Enable memory savings
-pipe.enable_model_cpu_offload()
-pipe.enable_vae_tiling()
-
-prompt = "Close-up of a chameleon's eye, with its scaly skin changing color. Ultra high resolution 4k."
-
-with torch.autocast("cuda", torch.bfloat16, cache_enabled=False):
-      frames = pipe(prompt, num_frames=85).frames[0]
-
-export_to_video(frames, "mochi.mp4", fps=30)
-```
-
-## Using a lower precision variant to save memory
-
-The following example will use the `bfloat16` variant of the model and requires 22GB VRAM to run. There is a slight drop in the quality of the generated video as a result.
-
-```python
-import torch
-from diffusers import MochiPipeline
-from diffusers.utils import export_to_video
-
-pipe = MochiPipeline.from_pretrained("genmo/mochi-1-preview", variant="bf16", torch_dtype=torch.bfloat16)
-
-# Enable memory savings
-pipe.enable_model_cpu_offload()
-pipe.enable_vae_tiling()
-
-prompt = "Close-up of a chameleon's eye, with its scaly skin changing color. Ultra high resolution 4k."
-frames = pipe(prompt, num_frames=85).frames[0]
-
-export_to_video(frames, "mochi.mp4", fps=30)
-```
-
-## Reproducing the results from the Genmo Mochi repo
-
-The [Genmo Mochi implementation](https://github.com/genmoai/mochi/tree/main) uses different precision values for each stage in the inference process. The text encoder and VAE use `torch.float32`, while the DiT uses `torch.bfloat16` with the [attention kernel](https://pytorch.org/docs/stable/generated/torch.nn.attention.sdpa_kernel.html#torch.nn.attention.sdpa_kernel) set to `EFFICIENT_ATTENTION`. Diffusers pipelines currently do not support setting different `dtypes` for different stages of the pipeline. In order to run inference in the same way as the the original implementation, please refer to the following example.
-
 <Tip>
-The original Mochi implementation zeros out empty prompts. However, enabling this option and placing the entire pipeline under autocast can lead to numerical overflows with the T5 text encoder.
 
-When enabling `force_zeros_for_empty_prompt`, it is recommended to run the text encoding step outside the autocast context in full precision.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers.md) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading.md#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
 </Tip>
 
-<Tip>
-Decoding the latents in full precision is very memory intensive. You will need at least 70GB VRAM to generate the 163 frames in this example. To reduce memory, either reduce the number of frames or run the decoding step in `torch.bfloat16`.
-</Tip>
-
-```python
-import torch
-from torch.nn.attention import SDPBackend, sdpa_kernel
-
-from diffusers import MochiPipeline
-from diffusers.utils import export_to_video
-from diffusers.video_processor import VideoProcessor
-
-pipe = MochiPipeline.from_pretrained("genmo/mochi-1-preview", force_zeros_for_empty_prompt=True)
-pipe.enable_vae_tiling()
-pipe.enable_model_cpu_offload()
-
-prompt =  "An aerial shot of a parade of elephants walking across the African savannah. The camera showcases the herd and the surrounding landscape."
-
-with torch.no_grad():
-    prompt_embeds, prompt_attention_mask, negative_prompt_embeds, negative_prompt_attention_mask = (
-        pipe.encode_prompt(prompt=prompt)
-    )
-
-with torch.autocast("cuda", torch.bfloat16):
-    with sdpa_kernel(SDPBackend.EFFICIENT_ATTENTION):
-        frames = pipe(
-            prompt_embeds=prompt_embeds,
-            prompt_attention_mask=prompt_attention_mask,
-            negative_prompt_embeds=negative_prompt_embeds,
-            negative_prompt_attention_mask=negative_prompt_attention_mask,
-            guidance_scale=4.5,
-            num_inference_steps=64,
-            height=480,
-            width=848,
-            num_frames=163,
-            generator=torch.Generator("cuda").manual_seed(0),
-            output_type="latent",
-            return_dict=False,
-        )[0]
-
-video_processor = VideoProcessor(vae_scale_factor=8)
-has_latents_mean = hasattr(pipe.vae.config, "latents_mean") and pipe.vae.config.latents_mean is not None
-has_latents_std = hasattr(pipe.vae.config, "latents_std") and pipe.vae.config.latents_std is not None
-if has_latents_mean and has_latents_std:
-    latents_mean = (
-        torch.tensor(pipe.vae.config.latents_mean).view(1, 12, 1, 1, 1).to(frames.device, frames.dtype)
-    )
-    latents_std = (
-        torch.tensor(pipe.vae.config.latents_std).view(1, 12, 1, 1, 1).to(frames.device, frames.dtype)
-    )
-    frames = frames * latents_std / pipe.vae.config.scaling_factor + latents_mean
-else:
-    frames = frames / pipe.vae.config.scaling_factor
-
-with torch.no_grad():
-    video = pipe.vae.decode(frames.to(pipe.vae.dtype), return_dict=False)[0]
-
-video = video_processor.postprocess_video(video)[0]
-export_to_video(video, "mochi.mp4", fps=30)
-```
-
-## Running inference with multiple GPUs
-
-It is possible to split the large Mochi transformer across multiple GPUs using the `device_map` and `max_memory` options in `from_pretrained`. In the following example we split the model across two GPUs, each with 24GB of VRAM.
-
-```python
-import torch
-from diffusers import MochiPipeline, MochiTransformer3DModel
-from diffusers.utils import export_to_video
-
-model_id = "genmo/mochi-1-preview"
-transformer = MochiTransformer3DModel.from_pretrained(
-    model_id,
-    subfolder="transformer",
-    device_map="auto",
-    max_memory={0: "24GB", 1: "24GB"}
-)
-
-pipe = MochiPipeline.from_pretrained(model_id,  transformer=transformer)
-pipe.enable_model_cpu_offload()
-pipe.enable_vae_tiling()
-
-with torch.autocast(device_type="cuda", dtype=torch.bfloat16, cache_enabled=False):
-    frames = pipe(
-        prompt="Close-up of a chameleon's eye, with its scaly skin changing color. Ultra high resolution 4k.",
-        negative_prompt="",
-        height=480,
-        width=848,
-        num_frames=85,
-        num_inference_steps=50,
-        guidance_scale=4.5,
-        num_videos_per_prompt=1,
-        generator=torch.Generator(device="cuda").manual_seed(0),
-        max_sequence_length=256,
-        output_type="pil",
-    ).frames[0]
-
-export_to_video(frames, "output.mp4", fps=30)
-```
-
-## Using single file loading with the Mochi Transformer
-
-You can use `from_single_file` to load the Mochi transformer in its original format.
-
-<Tip>
-Diffusers currently doesn't support using the FP8 scaled versions of the Mochi single file checkpoints.
-</Tip>
-
-```python
-import torch
-from diffusers import MochiPipeline, MochiTransformer3DModel
-from diffusers.utils import export_to_video
-
-model_id = "genmo/mochi-1-preview"
-
-ckpt_path = "https://huggingface.co/Comfy-Org/mochi_preview_repackaged/blob/main/split_files/diffusion_models/mochi_preview_bf16.safetensors"
-
-transformer = MochiTransformer3DModel.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16)
-
-pipe = MochiPipeline.from_pretrained(model_id,  transformer=transformer)
-pipe.enable_model_cpu_offload()
-pipe.enable_vae_tiling()
-
-with torch.autocast(device_type="cuda", dtype=torch.bfloat16, cache_enabled=False):
-    frames = pipe(
-        prompt="Close-up of a chameleon's eye, with its scaly skin changing color. Ultra high resolution 4k.",
-        negative_prompt="",
-        height=480,
-        width=848,
-        num_frames=85,
-        num_inference_steps=50,
-        guidance_scale=4.5,
-        num_videos_per_prompt=1,
-        generator=torch.Generator(device="cuda").manual_seed(0),
-        max_sequence_length=256,
-        output_type="pil",
-    ).frames[0]
-
-export_to_video(frames, "output.mp4", fps=30)
-```
-
 ## MochiPipeline
 
 [[autodoc]] MochiPipeline

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

@@ -42,7 +42,7 @@ During inference:
 
 <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.
+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-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

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

@@ -26,7 +26,7 @@ Paint by Example is supported by the official [Fantasy-Studio/Paint-by-Example](
 
 <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.
+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-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

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

@@ -37,7 +37,7 @@ But with circular padding, the right and the left parts are matching (`circular_
 
 <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.
+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-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/pix2pix.md

@@ -22,7 +22,7 @@ You can find additional information about InstructPix2Pix on the [project page](
 
 <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.
+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-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

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

@@ -31,7 +31,7 @@ Some notes about this pipeline:
 
 <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.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers.md) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading.md#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

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

@@ -1,107 +0,0 @@
-<!-- Copyright 2024 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. -->
-
-# SanaPipeline
-
-[SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers](https://huggingface.co/papers/2410.10629) from NVIDIA and MIT HAN Lab, by Enze Xie, Junsong Chen, Junyu Chen, Han Cai, Haotian Tang, Yujun Lin, Zhekai Zhang, Muyang Li, Ligeng Zhu, Yao Lu, Song Han.
-
-The abstract from the paper is:
-
-*We introduce Sana, a text-to-image framework that can efficiently generate images up to 4096×4096 resolution. Sana can synthesize high-resolution, high-quality images with strong text-image alignment at a remarkably fast speed, deployable on laptop GPU. Core designs include: (1) Deep compression autoencoder: unlike traditional AEs, which compress images only 8×, we trained an AE that can compress images 32×, effectively reducing the number of latent tokens. (2) Linear DiT: we replace all vanilla attention in DiT with linear attention, which is more efficient at high resolutions without sacrificing quality. (3) Decoder-only text encoder: we replaced T5 with modern decoder-only small LLM as the text encoder and designed complex human instruction with in-context learning to enhance the image-text alignment. (4) Efficient training and sampling: we propose Flow-DPM-Solver to reduce sampling steps, with efficient caption labeling and selection to accelerate convergence. As a result, Sana-0.6B is very competitive with modern giant diffusion model (e.g. Flux-12B), being 20 times smaller and 100+ times faster in measured throughput. Moreover, Sana-0.6B can be deployed on a 16GB laptop GPU, taking less than 1 second to generate a 1024×1024 resolution image. Sana enables content creation at low cost. Code and model will be publicly released.*
-
-<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.
-
-</Tip>
-
-This pipeline was contributed by [lawrence-cj](https://github.com/lawrence-cj) and [chenjy2003](https://github.com/chenjy2003). 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:
-
-| Model | Recommended dtype |
-|:-----:|:-----------------:|
-| [`Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers`](https://huggingface.co/Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers) | `torch.bfloat16` |
-| [`Efficient-Large-Model/Sana_1600M_1024px_diffusers`](https://huggingface.co/Efficient-Large-Model/Sana_1600M_1024px_diffusers) | `torch.float16` |
-| [`Efficient-Large-Model/Sana_1600M_1024px_MultiLing_diffusers`](https://huggingface.co/Efficient-Large-Model/Sana_1600M_1024px_MultiLing_diffusers) | `torch.float16` |
-| [`Efficient-Large-Model/Sana_1600M_512px_diffusers`](https://huggingface.co/Efficient-Large-Model/Sana_1600M_512px_diffusers) | `torch.float16` |
-| [`Efficient-Large-Model/Sana_1600M_512px_MultiLing_diffusers`](https://huggingface.co/Efficient-Large-Model/Sana_1600M_512px_MultiLing_diffusers) | `torch.float16` |
-| [`Efficient-Large-Model/Sana_600M_1024px_diffusers`](https://huggingface.co/Efficient-Large-Model/Sana_600M_1024px_diffusers) | `torch.float16` |
-| [`Efficient-Large-Model/Sana_600M_512px_diffusers`](https://huggingface.co/Efficient-Large-Model/Sana_600M_512px_diffusers) | `torch.float16` |
-
-Refer to [this](https://huggingface.co/collections/Efficient-Large-Model/sana-673efba2a57ed99843f11f9e) 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. 
-
-<Tip>
-
-Make sure to pass the `variant` argument for downloaded checkpoints to use lower disk space. Set it to `"fp16"` for models with recommended dtype as `torch.float16`, and `"bf16"` for models with recommended dtype as `torch.bfloat16`. By default, `torch.float32` weights are downloaded, which use twice the amount of disk storage. Additionally, `torch.float32` weights can be downcasted on-the-fly by specifying the `torch_dtype` argument. Read about it in the [docs](https://huggingface.co/docs/diffusers/v0.31.0/en/api/pipelines/overview#diffusers.DiffusionPipeline.from_pretrained).
-
-</Tip>
-
-## 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 [`SanaPipeline`] for inference with bitsandbytes.
-
-```py
-import torch
-from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, SanaTransformer2DModel, SanaPipeline
-from transformers import BitsAndBytesConfig as BitsAndBytesConfig, AutoModel
-
-quant_config = BitsAndBytesConfig(load_in_8bit=True)
-text_encoder_8bit = AutoModel.from_pretrained(
-    "Efficient-Large-Model/Sana_1600M_1024px_diffusers",
-    subfolder="text_encoder",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
-
-quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
-transformer_8bit = SanaTransformer2DModel.from_pretrained(
-    "Efficient-Large-Model/Sana_1600M_1024px_diffusers",
-    subfolder="transformer",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
-
-pipeline = SanaPipeline.from_pretrained(
-    "Efficient-Large-Model/Sana_1600M_1024px_diffusers",
-    text_encoder=text_encoder_8bit,
-    transformer=transformer_8bit,
-    torch_dtype=torch.float16,
-    device_map="balanced",
-)
-
-prompt = "a tiny astronaut hatching from an egg on the moon"
-image = pipeline(prompt).images[0]
-image.save("sana.png")
-```
-
-## SanaPipeline
-
-[[autodoc]] SanaPipeline
-  - all
-  - __call__
-
-## SanaPAGPipeline
-
-[[autodoc]] SanaPAGPipeline
-  - all
-  - __call__
-
-## SanaPipelineOutput
-
-[[autodoc]] pipelines.sana.pipeline_output.SanaPipelineOutput

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

@@ -22,7 +22,7 @@ You can find additional information about Self-Attention Guidance on the [projec
 
 <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.
+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-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

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

@@ -21,7 +21,7 @@ The abstract from the paper is:
 
 <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.
+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-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

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

@@ -19,7 +19,7 @@ The original codebase can be found at [openai/shap-e](https://github.com/openai/
 
 <Tip>
 
-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.
+See the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

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

@@ -35,57 +35,6 @@ During inference:
 * The _quality_ of the generated audio sample can be controlled by the `num_inference_steps` argument; higher steps give higher quality audio at the expense of slower inference.
 * Multiple waveforms can be generated in one go: set `num_waveforms_per_prompt` to a value greater than 1 to enable. Automatic scoring will be performed between the generated waveforms and prompt text, and the audios ranked from best to worst accordingly.
 
-## 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 [`StableAudioPipeline`] for inference with bitsandbytes.
-
-```py
-import torch
-from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, StableAudioDiTModel, StableAudioPipeline
-from diffusers.utils import export_to_video
-from transformers import BitsAndBytesConfig as BitsAndBytesConfig, T5EncoderModel
-
-quant_config = BitsAndBytesConfig(load_in_8bit=True)
-text_encoder_8bit = T5EncoderModel.from_pretrained(
-    "stabilityai/stable-audio-open-1.0",
-    subfolder="text_encoder",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
-
-quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
-transformer_8bit = StableAudioDiTModel.from_pretrained(
-    "stabilityai/stable-audio-open-1.0",
-    subfolder="transformer",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
-
-pipeline = StableAudioPipeline.from_pretrained(
-    "stabilityai/stable-audio-open-1.0",
-    text_encoder=text_encoder_8bit,
-    transformer=transformer_8bit,
-    torch_dtype=torch.float16,
-    device_map="balanced",
-)
-
-prompt = "The sound of a hammer hitting a wooden surface."
-negative_prompt = "Low quality."
-audio = pipeline(
-    prompt,
-    negative_prompt=negative_prompt,
-    num_inference_steps=200,
-    audio_end_in_s=10.0,
-    num_waveforms_per_prompt=3,
-    generator=generator,
-).audios
-
-output = audio[0].T.float().cpu().numpy()
-sf.write("hammer.wav", output, pipeline.vae.sampling_rate)
-```
-
 
 ## StableAudioPipeline
 [[autodoc]] StableAudioPipeline

docs/source/en/api/pipelines/stable_diffusion/stable_diffusion_3.md

@@ -59,76 +59,9 @@ image.save("sd3_hello_world.png")
 - [`stabilityai/stable-diffusion-3.5-large`](https://huggingface.co/stabilityai/stable-diffusion-3-5-large)
 - [`stabilityai/stable-diffusion-3.5-large-turbo`](https://huggingface.co/stabilityai/stable-diffusion-3-5-large-turbo)
 
-## Image Prompting with IP-Adapters
-
-An IP-Adapter lets you prompt SD3 with images, in addition to the text prompt. This is especially useful when describing complex concepts that are difficult to articulate through text alone and you have reference images. To load and use an IP-Adapter, you need:
-
-- `image_encoder`: Pre-trained vision model used to obtain image features, usually a CLIP image encoder.
-- `feature_extractor`: Image processor that prepares the input image for the chosen `image_encoder`.
-- `ip_adapter_id`: Checkpoint containing parameters of image cross attention layers and image projection. 
-
-IP-Adapters are trained for a specific model architecture, so they also work in finetuned variations of the base model. You can use the [`~SD3IPAdapterMixin.set_ip_adapter_scale`] function to adjust how strongly the output aligns with the image prompt. The higher the value, the more closely the model follows the image prompt. A default value of 0.5 is typically a good balance, ensuring the model considers both the text and image prompts equally.
-
-```python
-import torch
-from PIL import Image
-
-from diffusers import StableDiffusion3Pipeline
-from transformers import SiglipVisionModel, SiglipImageProcessor
-
-image_encoder_id = "google/siglip-so400m-patch14-384"
-ip_adapter_id = "InstantX/SD3.5-Large-IP-Adapter"
-
-feature_extractor = SiglipImageProcessor.from_pretrained(
-    image_encoder_id,
-    torch_dtype=torch.float16
-)
-image_encoder = SiglipVisionModel.from_pretrained(
-    image_encoder_id,
-    torch_dtype=torch.float16
-).to( "cuda")
-
-pipe = StableDiffusion3Pipeline.from_pretrained(
-    "stabilityai/stable-diffusion-3.5-large",
-    torch_dtype=torch.float16,
-    feature_extractor=feature_extractor,
-    image_encoder=image_encoder,
-).to("cuda")
-
-pipe.load_ip_adapter(ip_adapter_id)
-pipe.set_ip_adapter_scale(0.6)
-
-ref_img = Image.open("image.jpg").convert('RGB')
-
-image = pipe(
-    width=1024,
-    height=1024,
-    prompt="a cat",
-    negative_prompt="lowres, low quality, worst quality",
-    num_inference_steps=24,
-    guidance_scale=5.0,
-    ip_adapter_image=ref_img
-).images[0]
-
-image.save("result.jpg")
-```
-
-<div class="justify-center">
-    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/sd3_ip_adapter_example.png"/>
-    <figcaption class="mt-2 text-sm text-center text-gray-500">IP-Adapter examples with prompt "a cat"</figcaption>
-</div>
-
-
-<Tip>
-
-Check out [IP-Adapter](../../../using-diffusers/ip_adapter) to learn more about how IP-Adapters work.
-
-</Tip>
-
-
 ## Memory Optimisations for SD3
 
-SD3 uses three text encoders, one of which is the very large T5-XXL model. This makes it challenging to run the model on GPUs with less than 24GB of VRAM, even when using `fp16` precision. The following section outlines a few memory optimizations in Diffusers that make it easier to run SD3 on low resource hardware.
+SD3 uses three text encoders, one if which is the very large T5-XXL model. This makes it challenging to run the model on GPUs with less than 24GB of VRAM, even when using `fp16` precision. The following section outlines a few memory optimizations in Diffusers that make it easier to run SD3 on low resource hardware.
 
 ### Running Inference with Model Offloading
 
@@ -268,46 +201,6 @@ image.save("sd3_hello_world.png")
 
 Check out the full script [here](https://gist.github.com/sayakpaul/508d89d7aad4f454900813da5d42ca97).
 
-## 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 [`StableDiffusion3Pipeline`] for inference with bitsandbytes.
-
-```py
-import torch
-from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, SD3Transformer2DModel, StableDiffusion3Pipeline
-from transformers import BitsAndBytesConfig as BitsAndBytesConfig, T5EncoderModel
-
-quant_config = BitsAndBytesConfig(load_in_8bit=True)
-text_encoder_8bit = T5EncoderModel.from_pretrained(
-    "stabilityai/stable-diffusion-3.5-large",
-    subfolder="text_encoder_3",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
-
-quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
-transformer_8bit = SD3Transformer2DModel.from_pretrained(
-    "stabilityai/stable-diffusion-3.5-large",
-    subfolder="transformer",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
-
-pipeline = StableDiffusion3Pipeline.from_pretrained(
-    "stabilityai/stable-diffusion-3.5-large",
-    text_encoder=text_encoder_8bit,
-    transformer=transformer_8bit,
-    torch_dtype=torch.float16,
-    device_map="balanced",
-)
-
-prompt = "a tiny astronaut hatching from an egg on the moon"
-image = pipeline(prompt, num_inference_steps=28, guidance_scale=7.0).images[0]
-image.save("sd3.png")
-```
-
 ## Using Long Prompts with the T5 Text Encoder
 
 By default, the T5 Text Encoder prompt uses a maximum sequence length of `256`. This can be adjusted by setting the `max_sequence_length` to accept fewer or more tokens. Keep in mind that longer sequences require additional resources and result in longer generation times, such as during batch inference.

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

@@ -97,7 +97,7 @@ image
 
 <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.
+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-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

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

@@ -175,7 +175,7 @@ Check out the [Text or image-to-video](text-img2vid) guide for more details abou
 
 <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.
+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-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

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

@@ -284,7 +284,7 @@ You can filter out some available DreamBooth-trained models with [this link](htt
 
 <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.
+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-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

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

@@ -19,7 +19,7 @@ You can find lucidrains' DALL-E 2 recreation at [lucidrains/DALLE2-pytorch](http
 
 <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.
+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-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

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

@@ -192,7 +192,7 @@ print(final_prompt)
 
 <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.
+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-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

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

@@ -30,7 +30,7 @@ The script to run the model is available [here](https://github.com/huggingface/d
 
 <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.
+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-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/quantization.md

@@ -28,13 +28,6 @@ Learn how to quantize models in the [Quantization](../quantization/overview) gui
 
 [[autodoc]] BitsAndBytesConfig
 
-## GGUFQuantizationConfig
-
-[[autodoc]] GGUFQuantizationConfig
-## TorchAoConfig
-
-[[autodoc]] TorchAoConfig
-
 ## DiffusersQuantizer
 
 [[autodoc]] quantizers.base.DiffusersQuantizer

docs/source/en/community_projects.md

@@ -79,8 +79,4 @@ Happy exploring, and thank you for being part of the Diffusers community!
     <td><a href="https://github.com/Netwrck/stable-diffusion-server"> Stable Diffusion Server </a></td>
     <td>A server configured for Inpainting/Generation/img2img with one stable diffusion model</td>
   </tr>
-  <tr style="border-top: 2px solid black">
-    <td><a href="https://github.com/suzukimain/auto_diffusers"> Model Search </a></td>
-    <td>Search models on Civitai and Hugging Face</td>
-  </tr>
 </table>

docs/source/en/quantization/gguf.md

@@ -1,69 +0,0 @@
-<!--Copyright 2024 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.
-
--->
-
-# GGUF
-
-The GGUF file format is typically used to store models for inference with [GGML](https://github.com/ggerganov/ggml) and supports a variety of block wise quantization options. Diffusers supports loading checkpoints prequantized and saved in the GGUF format via `from_single_file` loading with Model classes. Loading GGUF checkpoints via Pipelines is currently not supported.
-
-The following example will load the [FLUX.1 DEV](https://huggingface.co/black-forest-labs/FLUX.1-dev) transformer model using the GGUF Q2_K quantization variant.
-
-Before starting please install gguf in your environment
-
-```shell
-pip install -U gguf
-```
-
-Since GGUF is a single file format, use [`~FromSingleFileMixin.from_single_file`] to load the model and pass in the [`GGUFQuantizationConfig`].
-
-When using GGUF checkpoints, the quantized weights remain in a low memory `dtype`(typically `torch.uint8`) and are dynamically dequantized and cast to the configured `compute_dtype` during each module's forward pass through the model. The `GGUFQuantizationConfig` allows you to set the `compute_dtype`.
-
-The functions used for dynamic dequantizatation are based on the great work done by [city96](https://github.com/city96/ComfyUI-GGUF), who created the Pytorch ports of the original [`numpy`](https://github.com/ggerganov/llama.cpp/blob/master/gguf-py/gguf/quants.py) implementation by [compilade](https://github.com/compilade).
-
-```python
-import torch
-
-from diffusers import FluxPipeline, FluxTransformer2DModel, GGUFQuantizationConfig
-
-ckpt_path = (
-    "https://huggingface.co/city96/FLUX.1-dev-gguf/blob/main/flux1-dev-Q2_K.gguf"
-)
-transformer = FluxTransformer2DModel.from_single_file(
-    ckpt_path,
-    quantization_config=GGUFQuantizationConfig(compute_dtype=torch.bfloat16),
-    torch_dtype=torch.bfloat16,
-)
-pipe = FluxPipeline.from_pretrained(
-    "black-forest-labs/FLUX.1-dev",
-    transformer=transformer,
-    torch_dtype=torch.bfloat16,
-)
-pipe.enable_model_cpu_offload()
-prompt = "A cat holding a sign that says hello world"
-image = pipe(prompt, generator=torch.manual_seed(0)).images[0]
-image.save("flux-gguf.png")
-```
-
-## Supported Quantization Types
-
-- BF16
-- Q4_0
-- Q4_1
-- Q5_0
-- Q5_1
-- Q8_0
-- Q2_K
-- Q3_K
-- Q4_K
-- Q5_K
-- Q6_K
-

docs/source/en/quantization/overview.md

@@ -17,7 +17,7 @@ Quantization techniques focus on representing data with less information while a
 
 <Tip>
 
-Interested in adding a new quantization method to Diffusers? Refer to the [Contribute new quantization method guide](https://huggingface.co/docs/transformers/main/en/quantization/contribute) to learn more about adding a new quantization method.
+Interested in adding a new quantization method to Transformers? Refer to the [Contribute new quantization method guide](https://huggingface.co/docs/transformers/main/en/quantization/contribute) to learn more about adding a new quantization method.
 
 </Tip>
 
@@ -32,9 +32,4 @@ If you are new to the quantization field, we recommend you to check out these be
 
 ## When to use what?
 
-Diffusers currently supports the following quantization methods.
-- [BitsandBytes](./bitsandbytes)
-- [TorchAO](./torchao)
-- [GGUF](./gguf)
-
-[This resource](https://huggingface.co/docs/transformers/main/en/quantization/overview#when-to-use-what) provides a good overview of the pros and cons of different quantization techniques.
+This section will be expanded once Diffusers has multiple quantization backends. Currently, we only support `bitsandbytes`. [This resource](https://huggingface.co/docs/transformers/main/en/quantization/overview#when-to-use-what) provides a good overview of the pros and cons of different quantization techniques. 

docs/source/en/quantization/torchao.md

@@ -1,156 +0,0 @@
-<!-- Copyright 2024 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. -->
-
-# torchao
-
-[TorchAO](https://github.com/pytorch/ao) is an architecture optimization library for PyTorch. It provides high-performance dtypes, optimization techniques, and kernels for inference and training, featuring composability with native PyTorch features like [torch.compile](https://pytorch.org/tutorials/intermediate/torch_compile_tutorial.html), FullyShardedDataParallel (FSDP), and more.
-
-Before you begin, make sure you have Pytorch 2.5+ and TorchAO installed.
-
-```bash
-pip install -U torch torchao
-```
-
-
-Quantize a model by passing [`TorchAoConfig`] to [`~ModelMixin.from_pretrained`] (you can also load pre-quantized models). This works for any model in any modality, as long as it supports loading with [Accelerate](https://hf.co/docs/accelerate/index) and contains `torch.nn.Linear` layers.
-
-The example below only quantizes the weights to int8.
-
-```python
-import torch
-from diffusers import FluxPipeline, FluxTransformer2DModel, TorchAoConfig
-
-model_id = "black-forest-labs/FLUX.1-dev"
-dtype = torch.bfloat16
-
-quantization_config = TorchAoConfig("int8wo")
-transformer = FluxTransformer2DModel.from_pretrained(
-    model_id,
-    subfolder="transformer",
-    quantization_config=quantization_config,
-    torch_dtype=dtype,
-)
-pipe = FluxPipeline.from_pretrained(
-    model_id,
-    transformer=transformer,
-    torch_dtype=dtype,
-)
-pipe.to("cuda")
-
-# Without quantization: ~31.447 GB
-# With quantization: ~20.40 GB
-print(f"Pipeline memory usage: {torch.cuda.max_memory_reserved() / 1024**3:.3f} GB")
-
-prompt = "A cat holding a sign that says hello world"
-image = pipe(
-    prompt, num_inference_steps=50, guidance_scale=4.5, max_sequence_length=512
-).images[0]
-image.save("output.png")
-```
-
-TorchAO is fully compatible with [torch.compile](./optimization/torch2.0#torchcompile), setting it apart from other quantization methods. This makes it easy to speed up inference with just one line of code.
-
-```python
-# In the above code, add the following after initializing the transformer
-transformer = torch.compile(transformer, mode="max-autotune", fullgraph=True)
-```
-
-For speed and memory benchmarks on Flux and CogVideoX, please refer to the table [here](https://github.com/huggingface/diffusers/pull/10009#issue-2688781450). You can also find some torchao [benchmarks](https://github.com/pytorch/ao/tree/main/torchao/quantization#benchmarks) numbers for various hardware.
-
-torchao also supports an automatic quantization API through [autoquant](https://github.com/pytorch/ao/blob/main/torchao/quantization/README.md#autoquantization). Autoquantization determines the best quantization strategy applicable to a model by comparing the performance of each technique on chosen input types and shapes. Currently, this can be used directly on the underlying modeling components. Diffusers will also expose an autoquant configuration option in the future.
-
-The `TorchAoConfig` class accepts three parameters:
-- `quant_type`: A string value mentioning one of the quantization types below.
-- `modules_to_not_convert`: A list of module full/partial module names for which quantization should not be performed. For example, to not perform any quantization of the [`FluxTransformer2DModel`]'s first block, one would specify: `modules_to_not_convert=["single_transformer_blocks.0"]`.
-- `kwargs`: A dict of keyword arguments to pass to the underlying quantization method which will be invoked based on `quant_type`.
-
-## Supported quantization types
-
-torchao supports weight-only quantization and weight and dynamic-activation quantization for int8, float3-float8, and uint1-uint7.
-
-Weight-only quantization stores the model weights in a specific low-bit data type but performs computation with a higher-precision data type, like `bfloat16`. This lowers the memory requirements from model weights but retains the memory peaks for activation computation.
-
-Dynamic activation quantization stores the model weights in a low-bit dtype, while also quantizing the activations on-the-fly to save additional memory. This lowers the memory requirements from model weights, while also lowering the memory overhead from activation computations. However, this may come at a quality tradeoff at times, so it is recommended to test different models thoroughly.
-
-The quantization methods supported are as follows:
-
-| **Category** | **Full Function Names** | **Shorthands** |
-|--------------|-------------------------|----------------|
-| **Integer quantization** | `int4_weight_only`, `int8_dynamic_activation_int4_weight`, `int8_weight_only`, `int8_dynamic_activation_int8_weight` | `int4wo`, `int4dq`, `int8wo`, `int8dq` |
-| **Floating point 8-bit quantization** | `float8_weight_only`, `float8_dynamic_activation_float8_weight`, `float8_static_activation_float8_weight` | `float8wo`, `float8wo_e5m2`, `float8wo_e4m3`, `float8dq`, `float8dq_e4m3`, `float8_e4m3_tensor`, `float8_e4m3_row` |
-| **Floating point X-bit quantization** | `fpx_weight_only` | `fpX_eAwB` where `X` is the number of bits (1-7), `A` is exponent bits, and `B` is mantissa bits. Constraint: `X == A + B + 1` |
-| **Unsigned Integer quantization** | `uintx_weight_only` | `uint1wo`, `uint2wo`, `uint3wo`, `uint4wo`, `uint5wo`, `uint6wo`, `uint7wo` |
-
-Some quantization methods are aliases (for example, `int8wo` is the commonly used shorthand for `int8_weight_only`). This allows using the quantization methods described in the torchao docs as-is, while also making it convenient to remember their shorthand notations.
-
-Refer to the official torchao documentation for a better understanding of the available quantization methods and the exhaustive list of configuration options available.
-
-## Serializing and Deserializing quantized models
-
-To serialize a quantized model in a given dtype, first load the model with the desired quantization dtype and then save it using the [`~ModelMixin.save_pretrained`] method.
-
-```python
-import torch
-from diffusers import FluxTransformer2DModel, TorchAoConfig
-
-quantization_config = TorchAoConfig("int8wo")
-transformer = FluxTransformer2DModel.from_pretrained(
-    "black-forest-labs/Flux.1-Dev",
-    subfolder="transformer",
-    quantization_config=quantization_config,
-    torch_dtype=torch.bfloat16,
-)
-transformer.save_pretrained("/path/to/flux_int8wo", safe_serialization=False)
-```
-
-To load a serialized quantized model, use the [`~ModelMixin.from_pretrained`] method.
-
-```python
-import torch
-from diffusers import FluxPipeline, FluxTransformer2DModel
-
-transformer = FluxTransformer2DModel.from_pretrained("/path/to/flux_int8wo", torch_dtype=torch.bfloat16, use_safetensors=False)
-pipe = FluxPipeline.from_pretrained("black-forest-labs/Flux.1-Dev", transformer=transformer, torch_dtype=torch.bfloat16)
-pipe.to("cuda")
-
-prompt = "A cat holding a sign that says hello world"
-image = pipe(prompt, num_inference_steps=30, guidance_scale=7.0).images[0]
-image.save("output.png")
-```
-
-Some quantization methods, such as `uint4wo`, cannot be loaded directly and may result in an `UnpicklingError` when trying to load the models, but work as expected when saving them. In order to work around this, one can load the state dict manually into the model. Note, however, that this requires using `weights_only=False` in `torch.load`, so it should be run only if the weights were obtained from a trustable source.
-
-```python
-import torch
-from accelerate import init_empty_weights
-from diffusers import FluxPipeline, FluxTransformer2DModel, TorchAoConfig
-
-# Serialize the model
-transformer = FluxTransformer2DModel.from_pretrained(
-    "black-forest-labs/Flux.1-Dev",
-    subfolder="transformer",
-    quantization_config=TorchAoConfig("uint4wo"),
-    torch_dtype=torch.bfloat16,
-)
-transformer.save_pretrained("/path/to/flux_uint4wo", safe_serialization=False, max_shard_size="50GB")
-# ...
-
-# Load the model
-state_dict = torch.load("/path/to/flux_uint4wo/diffusion_pytorch_model.bin", weights_only=False, map_location="cpu")
-with init_empty_weights():
-    transformer = FluxTransformer2DModel.from_config("/path/to/flux_uint4wo/config.json")
-transformer.load_state_dict(state_dict, strict=True, assign=True)
-```
-
-## Resources
-
-- [TorchAO Quantization API](https://github.com/pytorch/ao/blob/main/torchao/quantization/README.md)
-- [Diffusers-TorchAO examples](https://github.com/sayakpaul/diffusers-torchao)

docs/source/en/tutorials/using_peft_for_inference.md

@@ -56,7 +56,7 @@ image
 
 With the `adapter_name` parameter, it is really easy to use another adapter for inference! Load the [nerijs/pixel-art-xl](https://huggingface.co/nerijs/pixel-art-xl) adapter that has been fine-tuned to generate pixel art images and call it `"pixel"`.
 
-The pipeline automatically sets the first loaded adapter (`"toy"`) as the active adapter, but you can activate the `"pixel"` adapter with the [`~loaders.peft.PeftAdapterMixin.set_adapters`] method:
+The pipeline automatically sets the first loaded adapter (`"toy"`) as the active adapter, but you can activate the `"pixel"` adapter with the [`~diffusers.loaders.UNet2DConditionLoadersMixin.set_adapters`] method:
 
 ```python
 pipe.load_lora_weights("nerijs/pixel-art-xl", weight_name="pixel-art-xl.safetensors", adapter_name="pixel")
@@ -85,7 +85,7 @@ By default, if the most up-to-date versions of PEFT and Transformers are detecte
 
 You can also merge different adapter checkpoints for inference to blend their styles together.
 
-Once again, use the [`~loaders.peft.PeftAdapterMixin.set_adapters`] method to activate the `pixel` and `toy` adapters and specify the weights for how they should be merged.
+Once again, use the [`~diffusers.loaders.UNet2DConditionLoadersMixin.set_adapters`] method to activate the `pixel` and `toy` adapters and specify the weights for how they should be merged.
 
 ```python
 pipe.set_adapters(["pixel", "toy"], adapter_weights=[0.5, 1.0])
@@ -114,7 +114,7 @@ Impressive! As you can see, the model generated an image that mixed the characte
 > [!TIP]
 > Through its PEFT integration, Diffusers also offers more efficient merging methods which you can learn about in the [Merge LoRAs](../using-diffusers/merge_loras) guide!
 
-To return to only using one adapter, use the [`~loaders.peft.PeftAdapterMixin.set_adapters`] method to activate the `"toy"` adapter:
+To return to only using one adapter, use the [`~diffusers.loaders.UNet2DConditionLoadersMixin.set_adapters`] method to activate the `"toy"` adapter:
 
 ```python
 pipe.set_adapters("toy")
@@ -127,7 +127,7 @@ image = pipe(
 image
 ```
 
-Or to disable all adapters entirely, use the [`~loaders.peft.PeftAdapterMixin.disable_lora`] method to return the base model.
+Or to disable all adapters entirely, use the [`~diffusers.loaders.UNet2DConditionLoadersMixin.disable_lora`] method to return the base model.
 
 ```python
 pipe.disable_lora()
@@ -140,8 +140,7 @@ image
 ![no-lora](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/peft_integration/diffusers_peft_lora_inference_20_1.png)
 
 ### Customize adapters strength
-
-For even more customization, you can control how strongly the adapter affects each part of the pipeline. For this, pass a dictionary with the control strengths (called "scales") to [`~loaders.peft.PeftAdapterMixin.set_adapters`].
+For even more customization, you can control how strongly the adapter affects each part of the pipeline. For this, pass a dictionary with the control strengths (called "scales") to [`~diffusers.loaders.UNet2DConditionLoadersMixin.set_adapters`].
 
 For example, here's how you can turn on the adapter for the `down` parts, but turn it off for the `mid` and `up` parts:
 ```python
@@ -196,7 +195,7 @@ image
 
 ![block-lora-mixed](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/peft_integration/diffusers_peft_lora_inference_block_mixed.png)
 
-## Manage adapters
+## Manage active adapters
 
 You have attached multiple adapters in this tutorial, and if you're feeling a bit lost on what adapters have been attached to the pipeline's components, use the [`~diffusers.loaders.StableDiffusionLoraLoaderMixin.get_active_adapters`] method to check the list of active adapters:
 
@@ -213,11 +212,3 @@ list_adapters_component_wise = pipe.get_list_adapters()
 list_adapters_component_wise
 {"text_encoder": ["toy", "pixel"], "unet": ["toy", "pixel"], "text_encoder_2": ["toy", "pixel"]}
 ```
-
-The [`~loaders.peft.PeftAdapterMixin.delete_adapters`] function completely removes an adapter and their LoRA layers from a model.
-
-```py
-pipe.delete_adapters("toy")
-pipe.get_active_adapters()
-["pixel"]
-```

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

@@ -1,4 +1,4 @@
- <!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--Copyright 2024 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
@@ -10,20 +10,31 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
 specific language governing permissions and limitations under the License.
 -->
 
-# Video generation
+# Text or image-to-video
 
-Video generation models include a temporal dimension to bring images, or frames, together to create a video. These models are trained on large-scale datasets of high-quality text-video pairs to learn how to combine the modalities to ensure the generated video is coherent and realistic.
+Driven by the success of text-to-image diffusion models, generative video models are able to generate short clips of video from a text prompt or an initial image. These models extend a pretrained diffusion model to generate videos by adding some type of temporal and/or spatial convolution layer to the architecture. A mixed dataset of images and videos are used to train the model which learns to output a series of video frames based on the text or image conditioning.
 
-[Explore](https://huggingface.co/models?other=video-generation) some of the more popular open-source video generation models available from Diffusers below.
+This guide will show you how to generate videos, how to configure video model parameters, and how to control video generation.
 
-<hfoptions id="popular-models">
-<hfoption id="CogVideoX">
+## Popular models
 
-[CogVideoX](https://huggingface.co/collections/THUDM/cogvideo-66c08e62f1685a3ade464cce) uses a 3D causal Variational Autoencoder (VAE) to compress videos along the spatial and temporal dimensions, and it includes a stack of expert transformer blocks with a 3D full attention mechanism to better capture visual, semantic, and motion information in the data.
+> [!TIP]
+> Discover other cool and trending video generation models on the Hub [here](https://huggingface.co/models?pipeline_tag=text-to-video&sort=trending)!
 
-The CogVideoX family also includes models capable of generating videos from images and videos in addition to text. The image-to-video models are indicated by **I2V** in the checkpoint name, and they should be used with the [`CogVideoXImageToVideoPipeline`]. The regular checkpoints support video-to-video through the [`CogVideoXVideoToVideoPipeline`].
+[Stable Video Diffusions (SVD)](https://huggingface.co/stabilityai/stable-video-diffusion-img2vid), [I2VGen-XL](https://huggingface.co/ali-vilab/i2vgen-xl/), [AnimateDiff](https://huggingface.co/guoyww/animatediff), and [ModelScopeT2V](https://huggingface.co/ali-vilab/text-to-video-ms-1.7b) are popular models used for video diffusion. Each model is distinct. For example, AnimateDiff inserts a motion modeling module into a frozen text-to-image model to generate personalized animated images, whereas SVD is entirely pretrained from scratch with a three-stage training process to generate short high-quality videos.
 
-The example below demonstrates how to generate a video from an image and text prompt with [THUDM/CogVideoX-5b-I2V](https://huggingface.co/THUDM/CogVideoX-5b-I2V).
+[CogVideoX](https://huggingface.co/collections/THUDM/cogvideo-66c08e62f1685a3ade464cce) is another popular video generation model. The model is a multidimensional transformer that integrates text, time, and space. It employs full attention in the attention module and includes an expert block at the layer level to spatially align text and video.
+
+### CogVideoX
+ 
+[CogVideoX](../api/pipelines/cogvideox) uses a 3D Variational Autoencoder (VAE) to compress videos along the spatial and temporal dimensions.
+
+Begin by loading the [`CogVideoXPipeline`] and passing an initial text or image to generate a video.
+<Tip>
+
+CogVideoX is available for image-to-video and text-to-video. [THUDM/CogVideoX-5b-I2V](https://huggingface.co/THUDM/CogVideoX-5b-I2V) uses the [`CogVideoXImageToVideoPipeline`] for image-to-video. [THUDM/CogVideoX-5b](https://huggingface.co/THUDM/CogVideoX-5b) and [THUDM/CogVideoX-2b](https://huggingface.co/THUDM/CogVideoX-2b) are available for text-to-video with the [`CogVideoXPipeline`].
+ 
+</Tip>
 
 ```py
 import torch
@@ -31,13 +42,12 @@ from diffusers import CogVideoXImageToVideoPipeline
 from diffusers.utils import export_to_video, load_image
 
 prompt = "A vast, shimmering ocean flows gracefully under a twilight sky, its waves undulating in a mesmerizing dance of blues and greens. The surface glints with the last rays of the setting sun, casting golden highlights that ripple across the water. Seagulls soar above, their cries blending with the gentle roar of the waves. The horizon stretches infinitely, where the ocean meets the sky in a seamless blend of hues. Close-ups reveal the intricate patterns of the waves, capturing the fluidity and dynamic beauty of the sea in motion."
-image = load_image(image="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cogvideox/cogvideox_rocket.png")
+image = load_image(image="cogvideox_rocket.png")
 pipe = CogVideoXImageToVideoPipeline.from_pretrained(
     "THUDM/CogVideoX-5b-I2V",
     torch_dtype=torch.bfloat16
 )
-
-# reduce memory requirements 
+ 
 pipe.vae.enable_tiling()
 pipe.vae.enable_slicing()
 
@@ -50,6 +60,7 @@ video = pipe(
     guidance_scale=6,
     generator=torch.Generator(device="cuda").manual_seed(42),
 ).frames[0]
+
 export_to_video(video, "output.mp4", fps=8)
 ```
 
@@ -64,103 +75,12 @@ export_to_video(video, "output.mp4", fps=8)
   </div>
 </div>
 
-</hfoption>
-<hfoption id="HunyuanVideo">
+ 
+### Stable Video Diffusion
 
-> [!TIP]
-> HunyuanVideo is a 13B parameter model and requires a lot of memory. Refer to the HunyuanVideo [Quantization](../api/pipelines/hunyuan_video#quantization) guide to learn how to quantize the model. CogVideoX and LTX-Video are more lightweight options that can still generate high-quality videos.
+[SVD](../api/pipelines/svd) is based on the Stable Diffusion 2.1 model and it is trained on images, then low-resolution videos, and finally a smaller dataset of high-resolution videos. This model generates a short 2-4 second video from an initial image. You can learn more details about model, like micro-conditioning, in the [Stable Video Diffusion](../using-diffusers/svd) guide.
 
-[HunyuanVideo](https://huggingface.co/tencent/HunyuanVideo) features a dual-stream to single-stream diffusion transformer (DiT) for learning video and text tokens separately, and then subsequently concatenating the video and text tokens to combine their information. A single multimodal large language model (MLLM) serves as the text encoder, and videos are also spatio-temporally compressed with a 3D causal VAE.
-
-```py
-import torch
-from diffusers import HunyuanVideoPipeline, HunyuanVideoTransformer3DModel
-from diffusers.utils import export_to_video
-
-transformer = HunyuanVideoTransformer3DModel.from_pretrained(
-    "hunyuanvideo-community/HunyuanVideo", subfolder="transformer", torch_dtype=torch.bfloat16
-)
-pipe = HunyuanVideoPipeline.from_pretrained(
-  "hunyuanvideo-community/HunyuanVideo", transformer=transformer, torch_dtype=torch.float16
-)
-
-# reduce memory requirements
-pipe.vae.enable_tiling()
-pipe.to("cuda")
-
-video = pipe(
-    prompt="A cat walks on the grass, realistic",
-    height=320,
-    width=512,
-    num_frames=61,
-    num_inference_steps=30,
-).frames[0]
-export_to_video(video, "output.mp4", fps=15)
-```
-
-<div class="flex justify-center">
-  <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/hunyuan-video-output.gif"/>
-</div>
-
-</hfoption>
-<hfoption id="LTX-Video">
-
-[LTX-Video (LTXV)](https://huggingface.co/Lightricks/LTX-Video) is a diffusion transformer (DiT) with a focus on speed. It generates 768x512 resolution videos at 24 frames per second (fps), enabling near real-time generation of high-quality videos. LTXV is relatively lightweight compared to other modern video generation models, making it possible to run on consumer GPUs.
-
-```py
-import torch
-from diffusers import LTXPipeline
-from diffusers.utils import export_to_video
-
-pipe = LTXPipeline.from_pretrained("Lightricks/LTX-Video", torch_dtype=torch.bfloat16).to("cuda")
-
-prompt = "A man walks towards a window, looks out, and then turns around. He has short, dark hair, dark skin, and is wearing a brown coat over a red and gray scarf. He walks from left to right towards a window, his gaze fixed on something outside. The camera follows him from behind at a medium distance. The room is brightly lit, with white walls and a large window covered by a white curtain. As he approaches the window, he turns his head slightly to the left, then back to the right. He then turns his entire body to the right, facing the window. The camera remains stationary as he stands in front of the window. The scene is captured in real-life footage."
-video = pipe(
-    prompt=prompt,
-    width=704,
-    height=480,
-    num_frames=161,
-    num_inference_steps=50,
-).frames[0]
-export_to_video(video, "output.mp4", fps=24)
-```
-
-<div class="flex justify-center">
-  <img src="https://huggingface.co/Lightricks/LTX-Video/resolve/main/media/ltx-video_example_00014.gif"/>
-</div>
-
-</hfoption>
-<hfoption id="Mochi-1">
-
-> [!TIP]
-> Mochi-1 is a 10B parameter model and requires a lot of memory. Refer to the Mochi [Quantization](../api/pipelines/mochi#quantization) guide to learn how to quantize the model. CogVideoX and LTX-Video are more lightweight options that can still generate high-quality videos.
-
-[Mochi-1](https://huggingface.co/genmo/mochi-1-preview) introduces the Asymmetric Diffusion Transformer (AsymmDiT) and Asymmetric Variational Autoencoder (AsymmVAE) to reduces memory requirements. AsymmVAE causally compresses videos 128x to improve memory efficiency, and AsymmDiT jointly attends to the compressed video tokens and user text tokens. This model is noted for generating videos with high-quality motion dynamics and strong prompt adherence.
-
-```py
-import torch
-from diffusers import MochiPipeline
-from diffusers.utils import export_to_video
-
-pipe = MochiPipeline.from_pretrained("genmo/mochi-1-preview", variant="bf16", torch_dtype=torch.bfloat16)
-
-# reduce memory requirements
-pipe.enable_model_cpu_offload()
-pipe.enable_vae_tiling()
-
-prompt = "Close-up of a chameleon's eye, with its scaly skin changing color. Ultra high resolution 4k."
-video = pipe(prompt, num_frames=84).frames[0]
-export_to_video(video, "output.mp4", fps=30)
-```
-
-<div class="flex justify-center">
-  <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/mochi-video-output.gif"/>
-</div>
-
-</hfoption>
-<hfoption id="StableVideoDiffusion">
-
-[StableVideoDiffusion (SVD)](https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt) is based on the Stable Diffusion 2.1 model and it is trained on images, then low-resolution videos, and finally a smaller dataset of high-resolution videos. This model generates a short 2-4 second video from an initial image.
+Begin by loading the [`StableVideoDiffusionPipeline`] and passing an initial image to generate a video from.
 
 ```py
 import torch
@@ -170,8 +90,6 @@ from diffusers.utils import load_image, export_to_video
 pipeline = StableVideoDiffusionPipeline.from_pretrained(
     "stabilityai/stable-video-diffusion-img2vid-xt", torch_dtype=torch.float16, variant="fp16"
 )
-
-# reduce memory requirements
 pipeline.enable_model_cpu_offload()
 
 image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/svd/rocket.png")
@@ -193,12 +111,54 @@ export_to_video(frames, "generated.mp4", fps=7)
   </div>
 </div>
 
-</hfoption>
-<hfoption id="AnimateDiff">
+### I2VGen-XL
 
-[AnimateDiff](https://huggingface.co/guoyww/animatediff) is an adapter model that inserts a motion module into a pretrained diffusion model to animate an image. The adapter is trained on video clips to learn motion which is used to condition the generation process to create a video. It is faster and easier to only train the adapter and it can be loaded into most diffusion models, effectively turning them into “video models”.
+[I2VGen-XL](../api/pipelines/i2vgenxl) is a diffusion model that can generate higher resolution videos than SVD and it is also capable of accepting text prompts in addition to images. The model is trained with two hierarchical encoders (detail and global encoder) to better capture low and high-level details in images. These learned details are used to train a video diffusion model which refines the video resolution and details in the generated video.
 
-Load a `MotionAdapter` and pass it to the [`AnimateDiffPipeline`].
+You can use I2VGen-XL by loading the [`I2VGenXLPipeline`], and passing a text and image prompt to generate a video.
+
+```py
+import torch
+from diffusers import I2VGenXLPipeline
+from diffusers.utils import export_to_gif, load_image
+
+pipeline = I2VGenXLPipeline.from_pretrained("ali-vilab/i2vgen-xl", torch_dtype=torch.float16, variant="fp16")
+pipeline.enable_model_cpu_offload()
+
+image_url = "https://huggingface.co/datasets/diffusers/docs-images/resolve/main/i2vgen_xl_images/img_0009.png"
+image = load_image(image_url).convert("RGB")
+
+prompt = "Papers were floating in the air on a table in the library"
+negative_prompt = "Distorted, discontinuous, Ugly, blurry, low resolution, motionless, static, disfigured, disconnected limbs, Ugly faces, incomplete arms"
+generator = torch.manual_seed(8888)
+
+frames = pipeline(
+    prompt=prompt,
+    image=image,
+    num_inference_steps=50,
+    negative_prompt=negative_prompt,
+    guidance_scale=9.0,
+    generator=generator
+).frames[0]
+export_to_gif(frames, "i2v.gif")
+```
+
+<div class="flex gap-4">
+  <div>
+    <img class="rounded-xl" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/i2vgen_xl_images/img_0009.png"/>
+    <figcaption class="mt-2 text-center text-sm text-gray-500">initial image</figcaption>
+  </div>
+  <div>
+    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/i2vgen-xl-example.gif"/>
+    <figcaption class="mt-2 text-center text-sm text-gray-500">generated video</figcaption>
+  </div>
+</div>
+
+### AnimateDiff
+
+[AnimateDiff](../api/pipelines/animatediff) is an adapter model that inserts a motion module into a pretrained diffusion model to animate an image. The adapter is trained on video clips to learn motion which is used to condition the generation process to create a video. It is faster and easier to only train the adapter and it can be loaded into most diffusion models, effectively turning them into "video models".
+
+Start by loading a [`MotionAdapter`].
 
 ```py
 import torch
@@ -206,6 +166,11 @@ from diffusers import AnimateDiffPipeline, DDIMScheduler, MotionAdapter
 from diffusers.utils import export_to_gif
 
 adapter = MotionAdapter.from_pretrained("guoyww/animatediff-motion-adapter-v1-5-2", torch_dtype=torch.float16)
+```
+
+Then load a finetuned Stable Diffusion model with the [`AnimateDiffPipeline`].
+
+```py
 pipeline = AnimateDiffPipeline.from_pretrained("emilianJR/epiCRealism", motion_adapter=adapter, torch_dtype=torch.float16)
 scheduler = DDIMScheduler.from_pretrained(
     "emilianJR/epiCRealism",
@@ -216,11 +181,13 @@ scheduler = DDIMScheduler.from_pretrained(
     steps_offset=1,
 )
 pipeline.scheduler = scheduler
-
-# reduce memory requirements
 pipeline.enable_vae_slicing()
 pipeline.enable_model_cpu_offload()
+```
 
+Create a prompt and generate the video.
+
+```py
 output = pipeline(
     prompt="A space rocket with trails of smoke behind it launching into space from the desert, 4k, high resolution",
     negative_prompt="bad quality, worse quality, low resolution",
@@ -234,11 +201,38 @@ export_to_gif(frames, "animation.gif")
 ```
 
 <div class="flex justify-center">
-  <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/animatediff.gif"/>
+    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/animatediff.gif"/>
 </div>
 
-</hfoption>
-</hfoptions>
+### ModelscopeT2V
+
+[ModelscopeT2V](../api/pipelines/text_to_video) adds spatial and temporal convolutions and attention to a UNet, and it is trained on image-text and video-text datasets to enhance what it learns during training. The model takes a prompt, encodes it and creates text embeddings which are denoised by the UNet, and then decoded by a VQGAN into a video.
+
+<Tip>
+
+ModelScopeT2V generates watermarked videos due to the datasets it was trained on. To use a watermark-free model, try the [cerspense/zeroscope_v2_76w](https://huggingface.co/cerspense/zeroscope_v2_576w) model with the [`TextToVideoSDPipeline`] first, and then upscale it's output with the [cerspense/zeroscope_v2_XL](https://huggingface.co/cerspense/zeroscope_v2_XL) checkpoint using the [`VideoToVideoSDPipeline`].
+
+</Tip>
+
+Load a ModelScopeT2V checkpoint into the [`DiffusionPipeline`] along with a prompt to generate a video.
+
+```py
+import torch
+from diffusers import DiffusionPipeline
+from diffusers.utils import export_to_video
+
+pipeline = DiffusionPipeline.from_pretrained("damo-vilab/text-to-video-ms-1.7b", torch_dtype=torch.float16, variant="fp16")
+pipeline.enable_model_cpu_offload()
+pipeline.enable_vae_slicing()
+
+prompt = "Confident teddy bear surfer rides the wave in the tropics"
+video_frames = pipeline(prompt).frames[0]
+export_to_video(video_frames, "modelscopet2v.mp4", fps=10)
+```
+
+<div class="flex justify-center">
+    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/modelscopet2v.gif" />
+</div>
 
 ## Configure model parameters
 
@@ -554,9 +548,3 @@ If memory is not an issue and you want to optimize for speed, try wrapping the U
 + pipeline.to("cuda")
 + pipeline.unet = torch.compile(pipeline.unet, mode="reduce-overhead", fullgraph=True)
 ```
-
-## 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) to learn more about supported quantization backends (bitsandbytes, torchao, gguf) and selecting a quantization backend that supports your use case.

examples/advanced_diffusion_training/README.md

@@ -67,17 +67,6 @@ write_basic_config()
 When running `accelerate config`, if we specify torch compile mode to True there can be dramatic speedups.
 Note also that we use PEFT library as backend for LoRA training, make sure to have `peft>=0.6.0` installed in your environment.
 
-Lastly, we recommend logging into your HF account so that your trained LoRA is automatically uploaded to the hub:
-```bash
-huggingface-cli login
-```
-This command will prompt you for a token. Copy-paste yours from your [settings/tokens](https://huggingface.co/settings/tokens),and press Enter.
-
-> [!NOTE]
-> In the examples below we use `wandb` to document the training runs. To do the same, make sure to install `wandb`:
-> `pip install wandb`
-> Alternatively, you can use other tools / train without reporting by modifying the flag  `--report_to="wandb"`.
-
 ### Pivotal Tuning
 **Training with text encoder(s)**
 

examples/advanced_diffusion_training/README_flux.md

@@ -65,17 +65,6 @@ write_basic_config()
 When running `accelerate config`, if we specify torch compile mode to True there can be dramatic speedups.
 Note also that we use PEFT library as backend for LoRA training, make sure to have `peft>=0.6.0` installed in your environment.
 
-Lastly, we recommend logging into your HF account so that your trained LoRA is automatically uploaded to the hub:
-```bash
-huggingface-cli login
-```
-This command will prompt you for a token. Copy-paste yours from your [settings/tokens](https://huggingface.co/settings/tokens),and press Enter.
-
-> [!NOTE]
-> In the examples below we use `wandb` to document the training runs. To do the same, make sure to install `wandb`:
-> `pip install wandb`
-> Alternatively, you can use other tools / train without reporting by modifying the flag  `--report_to="wandb"`.
-
 ### Target Modules
 When LoRA was first adapted from language models to diffusion models, it was applied to the cross-attention layers in the Unet that relate the image representations with the prompts that describe them. 
 More recently, SOTA text-to-image diffusion models replaced the Unet with a diffusion Transformer(DiT). With this change, we may also want to explore 

examples/advanced_diffusion_training/train_dreambooth_lora_flux_advanced.py

@@ -74,7 +74,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.32.0.dev0")
 
 logger = get_logger(__name__)
 

examples/advanced_diffusion_training/train_dreambooth_lora_sd15_advanced.py

@@ -73,7 +73,7 @@ from diffusers.utils.import_utils import is_xformers_available
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.32.0.dev0")
 
 logger = get_logger(__name__)
 
@@ -160,7 +160,7 @@ to trigger concept `{key}` → use `{tokens}` in your prompt \n
 from diffusers import AutoPipelineForText2Image
 import torch
 {diffusers_imports_pivotal}
-pipeline = AutoPipelineForText2Image.from_pretrained('stable-diffusion-v1-5/stable-diffusion-v1-5', torch_dtype=torch.float16).to('cuda')
+pipeline = AutoPipelineForText2Image.from_pretrained('runwayml/stable-diffusion-v1-5', torch_dtype=torch.float16).to('cuda')
 pipeline.load_lora_weights('{repo_id}', weight_name='pytorch_lora_weights.safetensors')
 {diffusers_example_pivotal}
 image = pipeline('{validation_prompt if validation_prompt else instance_prompt}').images[0]

examples/advanced_diffusion_training/train_dreambooth_lora_sdxl_advanced.py

@@ -79,7 +79,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.32.0.dev0")
 
 logger = get_logger(__name__)
 

examples/cogvideo/train_cogvideox_image_to_video_lora.py

@@ -61,7 +61,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.32.0.dev0")
 
 logger = get_logger(__name__)
 

examples/cogvideo/train_cogvideox_lora.py

@@ -52,7 +52,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.32.0.dev0")
 
 logger = get_logger(__name__)
 

examples/community/README.md

@@ -33,12 +33,12 @@ Please also check out our [Community Scripts](https://github.com/huggingface/dif
 | Bit Diffusion                                                                                                                         | Diffusion on discrete data                                                                                                                                                                                                                                                                                                                                                                                                                                                                               | [Bit Diffusion](#bit-diffusion)                                                           | -  |                       [Stuti R.](https://github.com/kingstut) |
 | K-Diffusion Stable Diffusion                                                                                                          | Run Stable Diffusion with any of [K-Diffusion's samplers](https://github.com/crowsonkb/k-diffusion/blob/master/k_diffusion/sampling.py)                                                                                                                                                                                                                                                                                                                                                                  | [Stable Diffusion with K Diffusion](#stable-diffusion-with-k-diffusion)                   | -  |    [Patrick von Platen](https://github.com/patrickvonplaten/) |
 | Checkpoint Merger Pipeline                                                                                                            | Diffusion Pipeline that enables merging of saved model checkpoints                                                                                                                                                                                                                                                                                                                                                                                                                                       | [Checkpoint Merger Pipeline](#checkpoint-merger-pipeline)                                 | -                                                                                                                                                                                                                  | [Naga Sai Abhinay Devarinti](https://github.com/Abhinay1997/) |
-| Stable Diffusion v1.1-1.4 Comparison                                                                                                  | Run all 4 model checkpoints for Stable Diffusion and compare their results together                                                                                                                                                                                                                                                                                                                                                                                                                      | [Stable Diffusion Comparison](#stable-diffusion-comparisons)                              | [Notebook](https://github.com/huggingface/notebooks/blob/main/diffusers/stable_diffusion_comparison.ipynb) |        [Suvaditya Mukherjee](https://github.com/suvadityamuk) |
+| Stable Diffusion v1.1-1.4 Comparison                                                                                                  | Run all 4 model checkpoints for Stable Diffusion and compare their results together                                                                                                                                                                                                                                                                                                                                                                                                                      | [Stable Diffusion Comparison](#stable-diffusion-comparisons)                              | - |        [Suvaditya Mukherjee](https://github.com/suvadityamuk) |
 | MagicMix                                                                                                                              | Diffusion Pipeline for semantic mixing of an image and a text prompt                                                                                                                                                                                                                                                                                                                                                                                                                                     | [MagicMix](#magic-mix)                                                                    | - |                    [Partho Das](https://github.com/daspartho) |
-| Stable UnCLIP                                                                                                                         | Diffusion Pipeline for combining prior model (generate clip image embedding from text, UnCLIPPipeline `"kakaobrain/karlo-v1-alpha"`) and decoder pipeline (decode clip image embedding to image, StableDiffusionImageVariationPipeline `"lambdalabs/sd-image-variations-diffusers"` ).                                                                                                                                                                                                                   | [Stable UnCLIP](#stable-unclip)                                                           | [Notebook](https://github.com/huggingface/notebooks/blob/main/diffusers/stable_unclip.ipynb)  |                                [Ray Wang](https://wrong.wang) |
-| UnCLIP Text Interpolation Pipeline                                                                                                    | Diffusion Pipeline that allows passing two prompts and produces images while interpolating between the text-embeddings of the two prompts                                                                                                                                                                                                                                                                                                                                                                | [UnCLIP Text Interpolation Pipeline](#unclip-text-interpolation-pipeline)                 | [Notebook](https://github.com/huggingface/notebooks/blob/main/diffusers/unclip_text_interpolation.ipynb)| [Naga Sai Abhinay Devarinti](https://github.com/Abhinay1997/) |
+| Stable UnCLIP                                                                                                                         | Diffusion Pipeline for combining prior model (generate clip image embedding from text, UnCLIPPipeline `"kakaobrain/karlo-v1-alpha"`) and decoder pipeline (decode clip image embedding to image, StableDiffusionImageVariationPipeline `"lambdalabs/sd-image-variations-diffusers"` ).                                                                                                                                                                                                                   | [Stable UnCLIP](#stable-unclip)                                                           | -  |                                [Ray Wang](https://wrong.wang) |
+| UnCLIP Text Interpolation Pipeline                                                                                                    | Diffusion Pipeline that allows passing two prompts and produces images while interpolating between the text-embeddings of the two prompts                                                                                                                                                                                                                                                                                                                                                                | [UnCLIP Text Interpolation Pipeline](#unclip-text-interpolation-pipeline)                 | -                                                                                                                                                                                                                  | [Naga Sai Abhinay Devarinti](https://github.com/Abhinay1997/) |
 | UnCLIP Image Interpolation Pipeline                                                                                                   | Diffusion Pipeline that allows passing two images/image_embeddings and produces images while interpolating between their image-embeddings                                                                                                                                                                                                                                                                                                                                                                | [UnCLIP Image Interpolation Pipeline](#unclip-image-interpolation-pipeline)               | -                                                                                                                                                                                                                  | [Naga Sai Abhinay Devarinti](https://github.com/Abhinay1997/) |
-| DDIM Noise Comparative Analysis Pipeline                                                                                              | Investigating how the diffusion models learn visual concepts from each noise level (which is a contribution of [P2 weighting (CVPR 2022)](https://arxiv.org/abs/2204.00227))                                                                                                                                                                                                                                                                                                                             | [DDIM Noise Comparative Analysis Pipeline](#ddim-noise-comparative-analysis-pipeline)     | [Notebook](https://github.com/huggingface/notebooks/blob/main/diffusers/ddim_noise_comparative_analysis.ipynb)|              [Aengus (Duc-Anh)](https://github.com/aengusng8) |
+| DDIM Noise Comparative Analysis Pipeline                                                                                              | Investigating how the diffusion models learn visual concepts from each noise level (which is a contribution of [P2 weighting (CVPR 2022)](https://arxiv.org/abs/2204.00227))                                                                                                                                                                                                                                                                                                                             | [DDIM Noise Comparative Analysis Pipeline](#ddim-noise-comparative-analysis-pipeline)     | - |              [Aengus (Duc-Anh)](https://github.com/aengusng8) |
 | CLIP Guided Img2Img Stable Diffusion Pipeline                                                                                         | Doing CLIP guidance for image to image generation with Stable Diffusion                                                                                                                                                                                                                                                                                                                                                                                                                                  | [CLIP Guided Img2Img Stable Diffusion](#clip-guided-img2img-stable-diffusion)             | - |               [Nipun Jindal](https://github.com/nipunjindal/) |
 | TensorRT Stable Diffusion Text to Image Pipeline                                                                                                    | Accelerates the Stable Diffusion Text2Image Pipeline using TensorRT                                                                                                                                                                                                                                                                                                                                                                                                                                      | [TensorRT Stable Diffusion Text to Image Pipeline](#tensorrt-text2image-stable-diffusion-pipeline)      | - |              [Asfiya Baig](https://github.com/asfiyab-nvidia) |
 | EDICT Image Editing Pipeline                                                                                                          | Diffusion pipeline for text-guided image editing                                                                                                                                                                                                                                                                                                                                                                                                                                                         | [EDICT Image Editing Pipeline](#edict-image-editing-pipeline)                             | [Notebook](https://github.com/huggingface/notebooks/blob/main/diffusers/edict_image_pipeline.ipynb) |                    [Joqsan Azocar](https://github.com/Joqsan) |
@@ -50,7 +50,7 @@ Please also check out our [Community Scripts](https://github.com/huggingface/dif
 |   IADB Pipeline                                                                                                    | Implementation of [Iterative α-(de)Blending: a Minimalist Deterministic Diffusion Model](https://arxiv.org/abs/2305.03486)                                                                                                                                                                                                                                                                                                                                                                                                                                      | [IADB Pipeline](#iadb-pipeline)      | - |              [Thomas Chambon](https://github.com/tchambon)
 |   Zero1to3 Pipeline                                                                                                    | Implementation of [Zero-1-to-3: Zero-shot One Image to 3D Object](https://arxiv.org/abs/2303.11328)                                                                                                                                                                                                                                                                                                                                                                                                                                      | [Zero1to3 Pipeline](#zero1to3-pipeline)      | - |              [Xin Kong](https://github.com/kxhit) |
 | Stable Diffusion XL Long Weighted Prompt Pipeline | A pipeline support unlimited length of prompt and negative prompt, use A1111 style of prompt weighting | [Stable Diffusion XL Long Weighted Prompt Pipeline](#stable-diffusion-xl-long-weighted-prompt-pipeline) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1LsqilswLR40XLLcp6XFOl5nKb_wOe26W?usp=sharing) | [Andrew Zhu](https://xhinker.medium.com/) |
-| FABRIC - Stable Diffusion with feedback Pipeline | pipeline supports feedback from liked and disliked images | [Stable Diffusion Fabric Pipeline](#stable-diffusion-fabric-pipeline) | [Notebook](https://github.com/huggingface/notebooks/blob/main/diffusers/stable_diffusion_fabric.ipynb)| [Shauray Singh](https://shauray8.github.io/about_shauray/) |
+| FABRIC - Stable Diffusion with feedback Pipeline | pipeline supports feedback from liked and disliked images | [Stable Diffusion Fabric Pipeline](#stable-diffusion-fabric-pipeline) | - | [Shauray Singh](https://shauray8.github.io/about_shauray/) |
 | sketch inpaint - Inpainting with non-inpaint Stable Diffusion | sketch inpaint much like in automatic1111 | [Masked Im2Im Stable Diffusion Pipeline](#stable-diffusion-masked-im2im) | - | [Anatoly Belikov](https://github.com/noskill) |
 | sketch inpaint xl - Inpainting with non-inpaint Stable Diffusion | sketch inpaint much like in automatic1111 | [Masked Im2Im Stable Diffusion XL Pipeline](#stable-diffusion-xl-masked-im2im) | - | [Anatoly Belikov](https://github.com/noskill) |
 | prompt-to-prompt | change parts of a prompt and retain image structure (see [paper page](https://prompt-to-prompt.github.io/)) | [Prompt2Prompt Pipeline](#prompt2prompt-pipeline) | - | [Umer H. Adil](https://twitter.com/UmerHAdil) |

examples/community/README_community_scripts.md

@@ -241,15 +241,27 @@ from diffusers import StableDiffusionPipeline
 from diffusers.callbacks import PipelineCallback, MultiPipelineCallbacks
 from diffusers.configuration_utils import register_to_config
 import torch
-from typing import Any, Dict, Tuple, Union
+from typing import Any, Dict, Optional
 
 
-class SDPromptSchedulingCallback(PipelineCallback):
+pipeline: StableDiffusionPipeline = StableDiffusionPipeline.from_pretrained(
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
+    torch_dtype=torch.float16,
+    variant="fp16",
+    use_safetensors=True,
+).to("cuda")
+pipeline.safety_checker = None
+pipeline.requires_safety_checker = False
+
+
+class SDPromptScheduleCallback(PipelineCallback):
     @register_to_config
     def __init__(
         self,
-        encoded_prompt: Union[torch.Tensor, Tuple[torch.Tensor, torch.Tensor]],
-        cutoff_step_ratio=None,
+        prompt: str,
+        negative_prompt: Optional[str] = None,
+        num_images_per_prompt: int = 1,
+        cutoff_step_ratio=1.0,
         cutoff_step_index=None,
     ):
         super().__init__(
@@ -263,10 +275,6 @@ class SDPromptSchedulingCallback(PipelineCallback):
     ) -> Dict[str, Any]:
         cutoff_step_ratio = self.config.cutoff_step_ratio
         cutoff_step_index = self.config.cutoff_step_index
-        if isinstance(self.config.encoded_prompt, tuple):
-            prompt_embeds, negative_prompt_embeds = self.config.encoded_prompt
-        else:
-            prompt_embeds = self.config.encoded_prompt
 
         # Use cutoff_step_index if it's not None, otherwise use cutoff_step_ratio
         cutoff_step = (
@@ -276,164 +284,34 @@ class SDPromptSchedulingCallback(PipelineCallback):
         )
 
         if step_index == cutoff_step:
+            prompt_embeds, negative_prompt_embeds = pipeline.encode_prompt(
+                prompt=self.config.prompt,
+                negative_prompt=self.config.negative_prompt,
+                device=pipeline._execution_device,
+                num_images_per_prompt=self.config.num_images_per_prompt,
+                do_classifier_free_guidance=pipeline.do_classifier_free_guidance,
+            )
             if pipeline.do_classifier_free_guidance:
                 prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds])
             callback_kwargs[self.tensor_inputs[0]] = prompt_embeds
         return callback_kwargs
 
-
-pipeline: StableDiffusionPipeline = StableDiffusionPipeline.from_pretrained(
-    "stable-diffusion-v1-5/stable-diffusion-v1-5",
-    torch_dtype=torch.float16,
-    variant="fp16",
-    use_safetensors=True,
-).to("cuda")
-pipeline.safety_checker = None
-pipeline.requires_safety_checker = False
-
 callback = MultiPipelineCallbacks(
     [
-        SDPromptSchedulingCallback(
-            encoded_prompt=pipeline.encode_prompt(
-                prompt=f"prompt {index}",
-                negative_prompt=f"negative prompt {index}",
-                device=pipeline._execution_device,
-                num_images_per_prompt=1,
-                # pipeline.do_classifier_free_guidance can't be accessed until after pipeline is ran
-                do_classifier_free_guidance=True,
-            ),
-            cutoff_step_index=index,
-        ) for index in range(1, 20)
+        SDPromptScheduleCallback(
+            prompt="Official portrait of a smiling world war ii general, female, cheerful, happy, detailed face, 20th century, highly detailed, cinematic lighting, digital art painting by Greg Rutkowski",
+            negative_prompt="Deformed, ugly, bad anatomy",
+            cutoff_step_ratio=0.25,
+        )
     ]
 )
 
 image = pipeline(
-    prompt="prompt"
-    negative_prompt="negative prompt",
+    prompt="Official portrait of a smiling world war ii general, male, cheerful, happy, detailed face, 20th century, highly detailed, cinematic lighting, digital art painting by Greg Rutkowski",
+    negative_prompt="Deformed, ugly, bad anatomy",
     callback_on_step_end=callback,
     callback_on_step_end_tensor_inputs=["prompt_embeds"],
 ).images[0]
 torch.cuda.empty_cache()
 image.save('image.png')
 ```
-
-```python
-from diffusers import StableDiffusionXLPipeline
-from diffusers.callbacks import PipelineCallback, MultiPipelineCallbacks
-from diffusers.configuration_utils import register_to_config
-import torch
-from typing import Any, Dict, Tuple, Union
-
-
-class SDXLPromptSchedulingCallback(PipelineCallback):
-    @register_to_config
-    def __init__(
-        self,
-        encoded_prompt: Union[torch.Tensor, Tuple[torch.Tensor, torch.Tensor]],
-        add_text_embeds: Union[torch.Tensor, Tuple[torch.Tensor, torch.Tensor]],
-        add_time_ids: Union[torch.Tensor, Tuple[torch.Tensor, torch.Tensor]],
-        cutoff_step_ratio=None,
-        cutoff_step_index=None,
-    ):
-        super().__init__(
-            cutoff_step_ratio=cutoff_step_ratio, cutoff_step_index=cutoff_step_index
-        )
-
-    tensor_inputs = ["prompt_embeds", "add_text_embeds", "add_time_ids"]
-
-    def callback_fn(
-        self, pipeline, step_index, timestep, callback_kwargs
-    ) -> Dict[str, Any]:
-        cutoff_step_ratio = self.config.cutoff_step_ratio
-        cutoff_step_index = self.config.cutoff_step_index
-        if isinstance(self.config.encoded_prompt, tuple):
-            prompt_embeds, negative_prompt_embeds = self.config.encoded_prompt
-        else:
-            prompt_embeds = self.config.encoded_prompt
-        if isinstance(self.config.add_text_embeds, tuple):
-            add_text_embeds, negative_add_text_embeds = self.config.add_text_embeds
-        else:
-            add_text_embeds = self.config.add_text_embeds
-        if isinstance(self.config.add_time_ids, tuple):
-            add_time_ids, negative_add_time_ids = self.config.add_time_ids
-        else:
-            add_time_ids = self.config.add_time_ids
-
-        # Use cutoff_step_index if it's not None, otherwise use cutoff_step_ratio
-        cutoff_step = (
-            cutoff_step_index
-            if cutoff_step_index is not None
-            else int(pipeline.num_timesteps * cutoff_step_ratio)
-        )
-
-        if step_index == cutoff_step:
-            if pipeline.do_classifier_free_guidance:
-                prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds])
-                add_text_embeds = torch.cat([negative_add_text_embeds, add_text_embeds])
-                add_time_ids = torch.cat([negative_add_time_ids, add_time_ids])
-            callback_kwargs[self.tensor_inputs[0]] = prompt_embeds
-            callback_kwargs[self.tensor_inputs[1]] = add_text_embeds
-            callback_kwargs[self.tensor_inputs[2]] = add_time_ids
-        return callback_kwargs
-
-
-pipeline: StableDiffusionXLPipeline = StableDiffusionXLPipeline.from_pretrained(
-    "stabilityai/stable-diffusion-xl-base-1.0",
-    torch_dtype=torch.float16,
-    variant="fp16",
-    use_safetensors=True,
-).to("cuda")
-
-callbacks = []
-for index in range(1, 20):
-    (
-        prompt_embeds,
-        negative_prompt_embeds,
-        pooled_prompt_embeds,
-        negative_pooled_prompt_embeds,
-    ) = pipeline.encode_prompt(
-        prompt=f"prompt {index}",
-        negative_prompt=f"prompt {index}",
-        device=pipeline._execution_device,
-        num_images_per_prompt=1,
-        # pipeline.do_classifier_free_guidance can't be accessed until after pipeline is ran
-        do_classifier_free_guidance=True,
-    )
-    text_encoder_projection_dim = int(pooled_prompt_embeds.shape[-1])
-    add_time_ids = pipeline._get_add_time_ids(
-        (1024, 1024),
-        (0, 0),
-        (1024, 1024),
-        dtype=prompt_embeds.dtype,
-        text_encoder_projection_dim=text_encoder_projection_dim,
-    )
-    negative_add_time_ids = pipeline._get_add_time_ids(
-        (1024, 1024),
-        (0, 0),
-        (1024, 1024),
-        dtype=prompt_embeds.dtype,
-        text_encoder_projection_dim=text_encoder_projection_dim,
-    )
-    callbacks.append(
-        SDXLPromptSchedulingCallback(
-            encoded_prompt=(prompt_embeds, negative_prompt_embeds),
-            add_text_embeds=(pooled_prompt_embeds, negative_pooled_prompt_embeds),
-            add_time_ids=(add_time_ids, negative_add_time_ids),
-            cutoff_step_index=index,
-        )
-    )
-
-
-callback = MultiPipelineCallbacks(callbacks)
-
-image = pipeline(
-    prompt="prompt",
-    negative_prompt="negative prompt",
-    callback_on_step_end=callback,
-    callback_on_step_end_tensor_inputs=[
-        "prompt_embeds",
-        "add_text_embeds",
-        "add_time_ids",
-    ],
-).images[0]
-```

examples/community/adaptive_mask_inpainting.py

@@ -372,7 +372,7 @@ class AdaptiveMaskInpaintPipeline(
         self.register_adaptive_mask_model()
         self.register_adaptive_mask_settings()
 
-        if scheduler is not None and getattr(scheduler.config, "steps_offset", 1) != 1:
+        if hasattr(scheduler.config, "steps_offset") and scheduler.config.steps_offset != 1:
             deprecation_message = (
                 f"The configuration file of this scheduler: {scheduler} is outdated. `steps_offset`"
                 f" should be set to 1 instead of {scheduler.config.steps_offset}. Please make sure "
@@ -386,7 +386,7 @@ class AdaptiveMaskInpaintPipeline(
             new_config["steps_offset"] = 1
             scheduler._internal_dict = FrozenDict(new_config)
 
-        if scheduler is not None and getattr(scheduler.config, "skip_prk_steps", True) is False:
+        if hasattr(scheduler.config, "skip_prk_steps") and scheduler.config.skip_prk_steps is False:
             deprecation_message = (
                 f"The configuration file of this scheduler: {scheduler} has not set the configuration"
                 " `skip_prk_steps`. `skip_prk_steps` should be set to True in the configuration file. Please make"
@@ -416,14 +416,10 @@ class AdaptiveMaskInpaintPipeline(
                 " checker. If you do not want to use the safety checker, you can pass `'safety_checker=None'` instead."
             )
 
-        is_unet_version_less_0_9_0 = (
-            unet is not None
-            and hasattr(unet.config, "_diffusers_version")
-            and version.parse(version.parse(unet.config._diffusers_version).base_version) < version.parse("0.9.0.dev0")
-        )
-        is_unet_sample_size_less_64 = (
-            unet is not None and hasattr(unet.config, "sample_size") and unet.config.sample_size < 64
-        )
+        is_unet_version_less_0_9_0 = hasattr(unet.config, "_diffusers_version") and version.parse(
+            version.parse(unet.config._diffusers_version).base_version
+        ) < version.parse("0.9.0.dev0")
+        is_unet_sample_size_less_64 = hasattr(unet.config, "sample_size") and unet.config.sample_size < 64
         if is_unet_version_less_0_9_0 and is_unet_sample_size_less_64:
             deprecation_message = (
                 "The configuration file of the unet has set the default `sample_size` to smaller than"
@@ -442,7 +438,7 @@ class AdaptiveMaskInpaintPipeline(
             unet._internal_dict = FrozenDict(new_config)
 
         # Check shapes, assume num_channels_latents == 4, num_channels_mask == 1, num_channels_masked == 4
-        if unet is not None and unet.config.in_channels != 9:
+        if unet.config.in_channels != 9:
             logger.info(f"You have loaded a UNet with {unet.config.in_channels} input channels which.")
 
         self.register_modules(
@@ -454,7 +450,7 @@ class AdaptiveMaskInpaintPipeline(
             safety_checker=safety_checker,
             feature_extractor=feature_extractor,
         )
-        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1) if getattr(self, "vae", None) else 8
+        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
         self.image_processor = VaeImageProcessor(vae_scale_factor=self.vae_scale_factor)
         self.register_to_config(requires_safety_checker=requires_safety_checker)
 

examples/community/composable_stable_diffusion.py

@@ -89,7 +89,7 @@ class ComposableStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin)
     ):
         super().__init__()
 
-        if scheduler is not None and getattr(scheduler.config, "steps_offset", 1) != 1:
+        if hasattr(scheduler.config, "steps_offset") and scheduler.config.steps_offset != 1:
             deprecation_message = (
                 f"The configuration file of this scheduler: {scheduler} is outdated. `steps_offset`"
                 f" should be set to 1 instead of {scheduler.config.steps_offset}. Please make sure "
@@ -103,7 +103,7 @@ class ComposableStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin)
             new_config["steps_offset"] = 1
             scheduler._internal_dict = FrozenDict(new_config)
 
-        if scheduler is not None and getattr(scheduler.config, "clip_sample", False) is True:
+        if hasattr(scheduler.config, "clip_sample") and scheduler.config.clip_sample is True:
             deprecation_message = (
                 f"The configuration file of this scheduler: {scheduler} has not set the configuration `clip_sample`."
                 " `clip_sample` should be set to False in the configuration file. Please make sure to update the"
@@ -132,14 +132,10 @@ class ComposableStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin)
                 " checker. If you do not want to use the safety checker, you can pass `'safety_checker=None'` instead."
             )
 
-        is_unet_version_less_0_9_0 = (
-            unet is not None
-            and hasattr(unet.config, "_diffusers_version")
-            and version.parse(version.parse(unet.config._diffusers_version).base_version) < version.parse("0.9.0.dev0")
-        )
-        is_unet_sample_size_less_64 = (
-            unet is not None and hasattr(unet.config, "sample_size") and unet.config.sample_size < 64
-        )
+        is_unet_version_less_0_9_0 = hasattr(unet.config, "_diffusers_version") and version.parse(
+            version.parse(unet.config._diffusers_version).base_version
+        ) < version.parse("0.9.0.dev0")
+        is_unet_sample_size_less_64 = hasattr(unet.config, "sample_size") and unet.config.sample_size < 64
         if is_unet_version_less_0_9_0 and is_unet_sample_size_less_64:
             deprecation_message = (
                 "The configuration file of the unet has set the default `sample_size` to smaller than"
@@ -166,7 +162,7 @@ class ComposableStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin)
             safety_checker=safety_checker,
             feature_extractor=feature_extractor,
         )
-        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1) if getattr(self, "vae", None) else 8
+        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
         self.register_to_config(requires_safety_checker=requires_safety_checker)
 
     def _encode_prompt(self, prompt, device, num_images_per_prompt, do_classifier_free_guidance, negative_prompt):

examples/community/edict_pipeline.py

@@ -35,7 +35,7 @@ class EDICTPipeline(DiffusionPipeline):
             scheduler=scheduler,
         )
 
-        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1) if getattr(self, "vae", None) else 8
+        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
         self.image_processor = VaeImageProcessor(vae_scale_factor=self.vae_scale_factor)
 
     def _encode_prompt(

examples/community/fresco_v2v.py

@@ -1342,7 +1342,7 @@ class FrescoV2VPipeline(StableDiffusionControlNetImg2ImgPipeline):
             feature_extractor=feature_extractor,
             image_encoder=image_encoder,
         )
-        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1) if getattr(self, "vae", None) else 8
+        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
         self.image_processor = VaeImageProcessor(vae_scale_factor=self.vae_scale_factor, do_convert_rgb=True)
         self.control_image_processor = VaeImageProcessor(
             vae_scale_factor=self.vae_scale_factor, do_convert_rgb=True, do_normalize=False

examples/community/gluegen.py

@@ -221,7 +221,7 @@ class GlueGenStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin, St
             language_adapter=language_adapter,
             tensor_norm=tensor_norm,
         )
-        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1) if getattr(self, "vae", None) else 8
+        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
         self.image_processor = VaeImageProcessor(vae_scale_factor=self.vae_scale_factor)
         self.register_to_config(requires_safety_checker=requires_safety_checker)
 

examples/community/img2img_inpainting.py

@@ -95,7 +95,7 @@ class ImageToImageInpaintingPipeline(DiffusionPipeline):
     ):
         super().__init__()
 
-        if scheduler is not None and getattr(scheduler.config, "steps_offset", 1) != 1:
+        if hasattr(scheduler.config, "steps_offset") and scheduler.config.steps_offset != 1:
             deprecation_message = (
                 f"The configuration file of this scheduler: {scheduler} is outdated. `steps_offset`"
                 f" should be set to 1 instead of {scheduler.config.steps_offset}. Please make sure "

examples/community/instaflow_one_step.py

@@ -109,7 +109,7 @@ class InstaFlowPipeline(
     ):
         super().__init__()
 
-        if scheduler is not None and getattr(scheduler.config, "steps_offset", 1) != 1:
+        if hasattr(scheduler.config, "steps_offset") and scheduler.config.steps_offset != 1:
             deprecation_message = (
                 f"The configuration file of this scheduler: {scheduler} is outdated. `steps_offset`"
                 f" should be set to 1 instead of {scheduler.config.steps_offset}. Please make sure "
@@ -123,7 +123,7 @@ class InstaFlowPipeline(
             new_config["steps_offset"] = 1
             scheduler._internal_dict = FrozenDict(new_config)
 
-        if scheduler is not None and getattr(scheduler.config, "clip_sample", False) is True:
+        if hasattr(scheduler.config, "clip_sample") and scheduler.config.clip_sample is True:
             deprecation_message = (
                 f"The configuration file of this scheduler: {scheduler} has not set the configuration `clip_sample`."
                 " `clip_sample` should be set to False in the configuration file. Please make sure to update the"
@@ -152,14 +152,10 @@ class InstaFlowPipeline(
                 " checker. If you do not want to use the safety checker, you can pass `'safety_checker=None'` instead."
             )
 
-        is_unet_version_less_0_9_0 = (
-            unet is not None
-            and hasattr(unet.config, "_diffusers_version")
-            and version.parse(version.parse(unet.config._diffusers_version).base_version) < version.parse("0.9.0.dev0")
-        )
-        is_unet_sample_size_less_64 = (
-            unet is not None and hasattr(unet.config, "sample_size") and unet.config.sample_size < 64
-        )
+        is_unet_version_less_0_9_0 = hasattr(unet.config, "_diffusers_version") and version.parse(
+            version.parse(unet.config._diffusers_version).base_version
+        ) < version.parse("0.9.0.dev0")
+        is_unet_sample_size_less_64 = hasattr(unet.config, "sample_size") and unet.config.sample_size < 64
         if is_unet_version_less_0_9_0 and is_unet_sample_size_less_64:
             deprecation_message = (
                 "The configuration file of the unet has set the default `sample_size` to smaller than"
@@ -186,7 +182,7 @@ class InstaFlowPipeline(
             safety_checker=safety_checker,
             feature_extractor=feature_extractor,
         )
-        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1) if getattr(self, "vae", None) else 8
+        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
         self.image_processor = VaeImageProcessor(vae_scale_factor=self.vae_scale_factor)
         self.register_to_config(requires_safety_checker=requires_safety_checker)
 

examples/community/interpolate_stable_diffusion.py

@@ -86,7 +86,7 @@ class StableDiffusionWalkPipeline(DiffusionPipeline, StableDiffusionMixin):
     ):
         super().__init__()
 
-        if scheduler is not None and getattr(scheduler.config, "steps_offset", 1) != 1:
+        if hasattr(scheduler.config, "steps_offset") and scheduler.config.steps_offset != 1:
             deprecation_message = (
                 f"The configuration file of this scheduler: {scheduler} is outdated. `steps_offset`"
                 f" should be set to 1 instead of {scheduler.config.steps_offset}. Please make sure "

examples/community/ip_adapter_face_id.py

@@ -191,7 +191,7 @@ class IPAdapterFaceIDStableDiffusionPipeline(
     ):
         super().__init__()
 
-        if scheduler is not None and getattr(scheduler.config, "steps_offset", 1) != 1:
+        if hasattr(scheduler.config, "steps_offset") and scheduler.config.steps_offset != 1:
             deprecation_message = (
                 f"The configuration file of this scheduler: {scheduler} is outdated. `steps_offset`"
                 f" should be set to 1 instead of {scheduler.config.steps_offset}. Please make sure "
@@ -205,7 +205,7 @@ class IPAdapterFaceIDStableDiffusionPipeline(
             new_config["steps_offset"] = 1
             scheduler._internal_dict = FrozenDict(new_config)
 
-        if scheduler is not None and getattr(scheduler.config, "clip_sample", False) is True:
+        if hasattr(scheduler.config, "clip_sample") and scheduler.config.clip_sample is True:
             deprecation_message = (
                 f"The configuration file of this scheduler: {scheduler} has not set the configuration `clip_sample`."
                 " `clip_sample` should be set to False in the configuration file. Please make sure to update the"
@@ -234,14 +234,10 @@ class IPAdapterFaceIDStableDiffusionPipeline(
                 " checker. If you do not want to use the safety checker, you can pass `'safety_checker=None'` instead."
             )
 
-        is_unet_version_less_0_9_0 = (
-            unet is not None
-            and hasattr(unet.config, "_diffusers_version")
-            and version.parse(version.parse(unet.config._diffusers_version).base_version) < version.parse("0.9.0.dev0")
-        )
-        is_unet_sample_size_less_64 = (
-            unet is not None and hasattr(unet.config, "sample_size") and unet.config.sample_size < 64
-        )
+        is_unet_version_less_0_9_0 = hasattr(unet.config, "_diffusers_version") and version.parse(
+            version.parse(unet.config._diffusers_version).base_version
+        ) < version.parse("0.9.0.dev0")
+        is_unet_sample_size_less_64 = hasattr(unet.config, "sample_size") and unet.config.sample_size < 64
         if is_unet_version_less_0_9_0 and is_unet_sample_size_less_64:
             deprecation_message = (
                 "The configuration file of the unet has set the default `sample_size` to smaller than"
@@ -269,7 +265,7 @@ class IPAdapterFaceIDStableDiffusionPipeline(
             feature_extractor=feature_extractor,
             image_encoder=image_encoder,
         )
-        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1) if getattr(self, "vae", None) else 8
+        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
         self.image_processor = VaeImageProcessor(vae_scale_factor=self.vae_scale_factor)
         self.register_to_config(requires_safety_checker=requires_safety_checker)
 

examples/community/kohya_hires_fix.py

@@ -463,6 +463,6 @@ class StableDiffusionHighResFixPipeline(StableDiffusionPipeline):
             feature_extractor=feature_extractor,
             image_encoder=image_encoder,
         )
-        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1) if getattr(self, "vae", None) else 8
+        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
         self.image_processor = VaeImageProcessor(vae_scale_factor=self.vae_scale_factor)
         self.register_to_config(requires_safety_checker=requires_safety_checker)

examples/community/latent_consistency_img2img.py

@@ -69,7 +69,7 @@ class LatentConsistencyModelImg2ImgPipeline(DiffusionPipeline):
             safety_checker=safety_checker,
             feature_extractor=feature_extractor,
         )
-        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1) if getattr(self, "vae", None) else 8
+        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
         self.image_processor = VaeImageProcessor(vae_scale_factor=self.vae_scale_factor)
 
     def _encode_prompt(