up

fix Dockerfiles for cuda and xformers. (#13022 )
Improve docstrings and type hints in scheduling_ddim_inverse.py (#13020 )
2026-01-27 14:06:03 +08:00 · 2026-01-23 17:35:26 +05:30 · 2026-01-23 16:45:14 +05:30 · 2026-01-22 15:42:45 -08:00 · 2026-01-22 09:11:14 -08:00 · 2026-01-22 20:21:45 +05:30
33 changed files with 614 additions and 380 deletions
--- a/docker/diffusers-pytorch-cuda/Dockerfile
+++ b/docker/diffusers-pytorch-cuda/Dockerfile
@@ -1,8 +1,8 @@
-FROM nvidia/cuda:12.1.0-runtime-ubuntu20.04
+FROM nvidia/cuda:12.8.0-runtime-ubuntu22.04
 LABEL maintainer="Hugging Face"
 LABEL repository="diffusers"

-ARG PYTHON_VERSION=3.12
+ARG PYTHON_VERSION=3.11
 ENV DEBIAN_FRONTEND=noninteractive

 RUN apt-get -y update \
@@ -32,10 +32,12 @@ RUN uv venv --python ${PYTHON_VERSION} --seed ${VIRTUAL_ENV}
 ENV PATH="$VIRTUAL_ENV/bin:$PATH"

 # pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
+# Install torch, torchvision, and torchaudio together to ensure compatibility
 RUN uv pip install --no-cache-dir \
    torch \
    torchvision \
-    torchaudio
+    torchaudio \
+    --index-url https://download.pytorch.org/whl/cu128

 RUN uv pip install --no-cache-dir "git+https://github.com/huggingface/diffusers.git@main#egg=diffusers[test]"

--- a/docker/diffusers-pytorch-xformers-cuda/Dockerfile
+++ b/docker/diffusers-pytorch-xformers-cuda/Dockerfile
@@ -1,8 +1,8 @@
-FROM nvidia/cuda:12.1.0-runtime-ubuntu20.04
+FROM nvidia/cuda:12.8.0-runtime-ubuntu22.04
 LABEL maintainer="Hugging Face"
 LABEL repository="diffusers"

-ARG PYTHON_VERSION=3.12
+ARG PYTHON_VERSION=3.11
 ENV DEBIAN_FRONTEND=noninteractive

 RUN apt-get -y update \
@@ -32,10 +32,12 @@ RUN uv venv --python ${PYTHON_VERSION} --seed ${VIRTUAL_ENV}
 ENV PATH="$VIRTUAL_ENV/bin:$PATH"

 # pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
+# Install torch, torchvision, and torchaudio together to ensure compatibility
 RUN uv pip install --no-cache-dir \
    torch \
    torchvision \
-    torchaudio
+    torchaudio \
+    --index-url https://download.pytorch.org/whl/cu128

 RUN uv pip install --no-cache-dir "git+https://github.com/huggingface/diffusers.git@main#egg=diffusers[test]"

--- a/docs/source/en/modular_diffusers/overview.md
+++ b/docs/source/en/modular_diffusers/overview.md
@@ -24,7 +24,7 @@ The Modular Diffusers docs are organized as shown below.

 ## Quickstart

- The [quickstart](./quickstart) shows you how to run a modular pipeline, understand its structure, and customize it by modifying the blocks that compose it.
+- A [quickstart](./quickstart) demonstrating how to implement an example workflow with Modular Diffusers.

 ## ModularPipelineBlocks

--- a/docs/source/en/modular_diffusers/quickstart.md
+++ b/docs/source/en/modular_diffusers/quickstart.md
@@ -12,250 +12,333 @@ specific language governing permissions and limitations under the License.

 # Quickstart

-Modular Diffusers is a framework for quickly building flexible and customizable pipelines. At the core of Modular Diffusers are [`ModularPipelineBlocks`] that can be combined with other blocks to adapt to new workflows. The blocks are converted into a [`ModularPipeline`], a friendly user-facing interface for running generation tasks.
+Modular Diffusers is a framework for quickly building flexible and customizable pipelines. At the core of Modular Diffusers are [`ModularPipelineBlocks`] that can be combined with other blocks to adapt to new workflows. The blocks are converted into a [`ModularPipeline`], a friendly user-facing interface developers can use.

-This guide shows you how to run a modular pipeline, understand its structure, and customize it by modifying the blocks that compose it.
+This doc will show you how to implement a [Differential Diffusion](https://differential-diffusion.github.io/) pipeline with the modular framework.

-## Run a pipeline
+## ModularPipelineBlocks

-[`ModularPipeline`] is the main interface for loading, running, and managing modular pipelines.
+[`ModularPipelineBlocks`] are *definitions* that specify the components, inputs, outputs, and computation logic for a single step in a pipeline. There are four types of blocks.
+
+- [`ModularPipelineBlocks`] is the most basic block for a single step.
+- [`SequentialPipelineBlocks`] is a multi-block that composes other blocks linearly. The outputs of one block are the inputs to the next block.
+- [`LoopSequentialPipelineBlocks`] is a multi-block that runs iteratively and is designed for iterative workflows.
+- [`AutoPipelineBlocks`] is a collection of blocks for different workflows and it selects which block to run based on the input. It is designed to conveniently package multiple workflows into a single pipeline.
+
+[Differential Diffusion](https://differential-diffusion.github.io/) is an image-to-image workflow. Start with the `IMAGE2IMAGE_BLOCKS` preset, a collection of `ModularPipelineBlocks` for image-to-image generation.
+
+```py
+from diffusers.modular_pipelines.stable_diffusion_xl import IMAGE2IMAGE_BLOCKS
+IMAGE2IMAGE_BLOCKS = InsertableDict([
+    ("text_encoder", StableDiffusionXLTextEncoderStep),
+    ("image_encoder", StableDiffusionXLVaeEncoderStep),
+    ("input", StableDiffusionXLInputStep),
+    ("set_timesteps", StableDiffusionXLImg2ImgSetTimestepsStep),
+    ("prepare_latents", StableDiffusionXLImg2ImgPrepareLatentsStep),
+    ("prepare_add_cond", StableDiffusionXLImg2ImgPrepareAdditionalConditioningStep),
+    ("denoise", StableDiffusionXLDenoiseStep),
+    ("decode", StableDiffusionXLDecodeStep)
+])
+```
+
+## Pipeline and block states
+
+Modular Diffusers uses *state* to communicate data between blocks. There are two types of states.
+
+- [`PipelineState`] is a global state that can be used to track all inputs and outputs across all blocks.
+- [`BlockState`] is a local view of relevant variables from [`PipelineState`] for an individual block.
+
+## Customizing blocks
+
+[Differential Diffusion](https://differential-diffusion.github.io/) differs from standard image-to-image in its `prepare_latents` and `denoise` blocks. All the other blocks can be reused, but you'll need to modify these two.
+
+Create placeholder `ModularPipelineBlocks` for `prepare_latents` and `denoise` by copying and modifying the existing ones.
+
+Print the `denoise` block to see that it is composed of [`LoopSequentialPipelineBlocks`] with three sub-blocks, `before_denoiser`, `denoiser`, and `after_denoiser`. Only the `before_denoiser` sub-block needs to be modified to prepare the latent input for the denoiser based on the change map.
+
+```py
+denoise_blocks = IMAGE2IMAGE_BLOCKS["denoise"]()
+print(denoise_blocks)
+```
+
+Replace the `StableDiffusionXLLoopBeforeDenoiser` sub-block with the new `SDXLDiffDiffLoopBeforeDenoiser` block.
+
+```py
+# Copy existing blocks as placeholders
+class SDXLDiffDiffPrepareLatentsStep(ModularPipelineBlocks):
+    """Copied from StableDiffusionXLImg2ImgPrepareLatentsStep - will modify later"""
+    # ... same implementation as StableDiffusionXLImg2ImgPrepareLatentsStep
+
+class SDXLDiffDiffDenoiseStep(StableDiffusionXLDenoiseLoopWrapper):
+    block_classes = [SDXLDiffDiffLoopBeforeDenoiser, StableDiffusionXLLoopDenoiser, StableDiffusionXLLoopAfterDenoiser]
+    block_names = ["before_denoiser", "denoiser", "after_denoiser"]
+```
+
+### prepare_latents
+
+The `prepare_latents` block requires the following changes.
+
+- a processor to process the change map
+- a new `inputs` to accept the user-provided change map, `timestep` for precomputing all the latents and `num_inference_steps` to create the mask for updating the image regions
+- update the computation in the `__call__` method for processing the change map and creating the masks, and storing it in the [`BlockState`]
+
+```diff
+class SDXLDiffDiffPrepareLatentsStep(ModularPipelineBlocks):
+    @property
+    def expected_components(self) -> List[ComponentSpec]:
+        return [
+            ComponentSpec("vae", AutoencoderKL),
+            ComponentSpec("scheduler", EulerDiscreteScheduler),
+           ComponentSpec("mask_processor", VaeImageProcessor, config=FrozenDict({"do_normalize": False, "do_convert_grayscale": True}))
+        ]
+    @property
+    def inputs(self) -> List[Tuple[str, Any]]:
+        return [
+            InputParam("generator"),
+           InputParam("diffdiff_map", required=True),
+-           InputParam("latent_timestep", required=True, type_hint=torch.Tensor),
+           InputParam("timesteps", type_hint=torch.Tensor),
+           InputParam("num_inference_steps", type_hint=int),
+        ]
+
+    @property
+    def intermediate_outputs(self) -> List[OutputParam]:
+        return [
+           OutputParam("original_latents", type_hint=torch.Tensor),
+           OutputParam("diffdiff_masks", type_hint=torch.Tensor),
+        ]
+    def __call__(self, components, state: PipelineState):
+        # ... existing logic ...
+       # Process change map and create masks
+       diffdiff_map = components.mask_processor.preprocess(block_state.diffdiff_map, height=latent_height, width=latent_width)
+       thresholds = torch.arange(block_state.num_inference_steps, dtype=diffdiff_map.dtype) / block_state.num_inference_steps
+       block_state.diffdiff_masks = diffdiff_map > (thresholds + (block_state.denoising_start or 0))
+       block_state.original_latents = block_state.latents
+```
+
+### denoise
+
+The `before_denoiser` sub-block requires the following changes.
+
+- a new `inputs` to accept a `denoising_start` parameter,  `original_latents` and `diffdiff_masks` from the `prepare_latents` block
+- update the computation in the `__call__` method for applying Differential Diffusion
+
+```diff
+class SDXLDiffDiffLoopBeforeDenoiser(ModularPipelineBlocks):
+    @property
+    def description(self) -> str:
+        return (
+            "Step within the denoising loop for differential diffusion that prepare the latent input for the denoiser"
+        )
+
+    @property
+    def inputs(self) -> List[str]:
+        return [
+            InputParam("latents", required=True, type_hint=torch.Tensor),
+           InputParam("denoising_start"),
+           InputParam("original_latents", type_hint=torch.Tensor),
+           InputParam("diffdiff_masks", type_hint=torch.Tensor),
+        ]
+
+    def __call__(self, components, block_state, i, t):
+       # Apply differential diffusion logic
+       if i == 0 and block_state.denoising_start is None:
+           block_state.latents = block_state.original_latents[:1]
+       else:
+           block_state.mask = block_state.diffdiff_masks[i].unsqueeze(0).unsqueeze(1)
+           block_state.latents = block_state.original_latents[i] * block_state.mask + block_state.latents * (1 - block_state.mask)
+
+        # ... rest of existing logic ...
+```
+
+## Assembling the blocks
+
+You should have all the blocks you need at this point to create a [`ModularPipeline`].
+
+Copy the existing `IMAGE2IMAGE_BLOCKS` preset and for the `set_timesteps` block, use the `set_timesteps` from the `TEXT2IMAGE_BLOCKS` because Differential Diffusion doesn't require a `strength` parameter.
+
+Set the `prepare_latents` and `denoise` blocks to the `SDXLDiffDiffPrepareLatentsStep` and `SDXLDiffDiffDenoiseStep` blocks you just modified.
+
+Call [`SequentialPipelineBlocks.from_blocks_dict`] on the blocks to create a `SequentialPipelineBlocks`.
+
+```py
+DIFFDIFF_BLOCKS = IMAGE2IMAGE_BLOCKS.copy()
+DIFFDIFF_BLOCKS["set_timesteps"] = TEXT2IMAGE_BLOCKS["set_timesteps"]
+DIFFDIFF_BLOCKS["prepare_latents"] = SDXLDiffDiffPrepareLatentsStep
+DIFFDIFF_BLOCKS["denoise"] = SDXLDiffDiffDenoiseStep
+
+dd_blocks = SequentialPipelineBlocks.from_blocks_dict(DIFFDIFF_BLOCKS)
+print(dd_blocks)
+```
+
+## ModularPipeline
+
+Convert the [`SequentialPipelineBlocks`] into a [`ModularPipeline`] with the [`ModularPipeline.init_pipeline`] method. This initializes the expected components to load from a `modular_model_index.json` file. Explicitly load the components by calling [`ModularPipeline.load_components`].
+
+It is a good idea to initialize the [`ComponentManager`] with the pipeline to help manage the different components. Once you call [`~ModularPipeline.load_components`], the components are registered to the [`ComponentManager`] and can be shared between workflows. The example below uses the `collection` argument to assign the components a `"diffdiff"` label for better organization.
+
+```py
+from diffusers.modular_pipelines import ComponentsManager
+
+components = ComponentManager()
+
+dd_pipeline = dd_blocks.init_pipeline("YiYiXu/modular-demo-auto", components_manager=components, collection="diffdiff")
+dd_pipeline.load_componenets(torch_dtype=torch.float16)
+dd_pipeline.to("cuda")
+```
+
+## Adding workflows
+
+Other workflows can be added to the [`ModularPipeline`] to support additional features without rewriting the entire pipeline from scratch.
+
+This section demonstrates how to add an IP-Adapter or ControlNet.
+
+### IP-Adapter
+
+Stable Diffusion XL already has a preset IP-Adapter block that you can use and doesn't require any changes to the existing Differential Diffusion pipeline.
+
+```py
+from diffusers.modular_pipelines.stable_diffusion_xl.encoders import StableDiffusionXLAutoIPAdapterStep
+
+ip_adapter_block = StableDiffusionXLAutoIPAdapterStep()
+```
+
+Use the [`sub_blocks.insert`] method to insert it into the [`ModularPipeline`]. The example below inserts the `ip_adapter_block` at position `0`. Print the pipeline to see that the `ip_adapter_block` is added and it requires an `ip_adapter_image`. This also added two components to the pipeline, the `image_encoder` and `feature_extractor`.
+
+```py
+dd_blocks.sub_blocks.insert("ip_adapter", ip_adapter_block, 0)
+```
+
+Call [`~ModularPipeline.init_pipeline`] to initialize a [`ModularPipeline`] and use [`~ModularPipeline.load_components`] to load the model components. Load and set the IP-Adapter to run the pipeline.
+
+```py
+dd_pipeline = dd_blocks.init_pipeline("YiYiXu/modular-demo-auto", collection="diffdiff")
+dd_pipeline.load_components(torch_dtype=torch.float16)
+dd_pipeline.loader.load_ip_adapter("h94/IP-Adapter", subfolder="sdxl_models", weight_name="ip-adapter_sdxl.bin")
+dd_pipeline.loader.set_ip_adapter_scale(0.6)
+dd_pipeline = dd_pipeline.to(device)
+
+ip_adapter_image = load_image("https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/diffdiff_orange.jpeg")
+image = load_image("https://huggingface.co/datasets/OzzyGT/testing-resources/resolve/main/differential/20240329211129_4024911930.png?download=true")
+mask = load_image("https://huggingface.co/datasets/OzzyGT/testing-resources/resolve/main/differential/gradient_mask.png?download=true")
+
+prompt = "a green pear"
+negative_prompt = "blurry"
+generator = torch.Generator(device=device).manual_seed(42)
+
+image = dd_pipeline(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    num_inference_steps=25,
+    generator=generator,
+    ip_adapter_image=ip_adapter_image,
+    diffdiff_map=mask,
+    image=image,
+    output="images"
+)[0]
+```
+
+### ControlNet
+
+Stable Diffusion XL already has a preset ControlNet block that can readily be used.
+
+```py
+from diffusers.modular_pipelines.stable_diffusion_xl.modular_blocks import StableDiffusionXLAutoControlNetInputStep
+
+control_input_block = StableDiffusionXLAutoControlNetInputStep()
+```
+
+However, it requires modifying the `denoise` block because that's where the ControlNet injects the control information into the UNet.
+
+Modify the `denoise` block by replacing the `StableDiffusionXLLoopDenoiser` sub-block with the `StableDiffusionXLControlNetLoopDenoiser`.
+
+```py
+class SDXLDiffDiffControlNetDenoiseStep(StableDiffusionXLDenoiseLoopWrapper):
+    block_classes = [SDXLDiffDiffLoopBeforeDenoiser, StableDiffusionXLControlNetLoopDenoiser, StableDiffusionXLDenoiseLoopAfterDenoiser]
+    block_names = ["before_denoiser", "denoiser", "after_denoiser"]
+
+controlnet_denoise_block = SDXLDiffDiffControlNetDenoiseStep()
+```
+
+Insert the `controlnet_input` block and replace the `denoise` block with the new `controlnet_denoise_block`. Initialize a [`ModularPipeline`] and [`~ModularPipeline.load_components`] into it.
+
+```py
+dd_blocks.sub_blocks.insert("controlnet_input", control_input_block, 7)
+dd_blocks.sub_blocks["denoise"] = controlnet_denoise_block
+
+dd_pipeline = dd_blocks.init_pipeline("YiYiXu/modular-demo-auto", collection="diffdiff")
+dd_pipeline.load_components(torch_dtype=torch.float16)
+dd_pipeline = dd_pipeline.to(device)
+
+control_image = load_image("https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/diffdiff_tomato_canny.jpeg")
+image = load_image("https://huggingface.co/datasets/OzzyGT/testing-resources/resolve/main/differential/20240329211129_4024911930.png?download=true")
+mask = load_image("https://huggingface.co/datasets/OzzyGT/testing-resources/resolve/main/differential/gradient_mask.png?download=true")
+
+prompt = "a green pear"
+negative_prompt = "blurry"
+generator = torch.Generator(device=device).manual_seed(42)
+
+image = dd_pipeline(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    num_inference_steps=25,
+    generator=generator,
+    control_image=control_image,
+    controlnet_conditioning_scale=0.5,
+    diffdiff_map=mask,
+    image=image,
+    output="images"
+)[0]
+```
+
+### AutoPipelineBlocks
+
+The Differential Diffusion, IP-Adapter, and ControlNet workflows can be bundled into a single [`ModularPipeline`] by using [`AutoPipelineBlocks`]. This allows automatically selecting which sub-blocks to run based on the inputs like `control_image` or `ip_adapter_image`. If none of these inputs are passed, then it defaults to the Differential Diffusion.
+
+Use `block_trigger_inputs` to only run the `SDXLDiffDiffControlNetDenoiseStep` block if a `control_image` input is provided. Otherwise, the `SDXLDiffDiffDenoiseStep` is used.
+
+```py
+class SDXLDiffDiffAutoDenoiseStep(AutoPipelineBlocks):
+    block_classes = [SDXLDiffDiffControlNetDenoiseStep, SDXLDiffDiffDenoiseStep]
+    block_names = ["controlnet_denoise", "denoise"]
+    block_trigger_inputs = ["controlnet_cond", None]
+```
+
+Add the `ip_adapter` and `controlnet_input` blocks.
+
+```py
+DIFFDIFF_AUTO_BLOCKS = IMAGE2IMAGE_BLOCKS.copy()
+DIFFDIFF_AUTO_BLOCKS["prepare_latents"] = SDXLDiffDiffPrepareLatentsStep
+DIFFDIFF_AUTO_BLOCKS["set_timesteps"] = TEXT2IMAGE_BLOCKS["set_timesteps"]
+DIFFDIFF_AUTO_BLOCKS["denoise"] = SDXLDiffDiffAutoDenoiseStep
+DIFFDIFF_AUTO_BLOCKS.insert("ip_adapter", StableDiffusionXLAutoIPAdapterStep, 0)
+DIFFDIFF_AUTO_BLOCKS.insert("controlnet_input",StableDiffusionXLControlNetAutoInput, 7)
+```
+
+Call [`SequentialPipelineBlocks.from_blocks_dict`] to create a [`SequentialPipelineBlocks`] and create a [`ModularPipeline`] and load in the model components to run.
+
+```py
+dd_auto_blocks = SequentialPipelineBlocks.from_blocks_dict(DIFFDIFF_AUTO_BLOCKS)
+dd_pipeline = dd_auto_blocks.init_pipeline("YiYiXu/modular-demo-auto", collection="diffdiff")
+dd_pipeline.load_components(torch_dtype=torch.float16)
+```
+
+## Share
+
+Add your [`ModularPipeline`] to the Hub with [`~ModularPipeline.save_pretrained`] and set `push_to_hub` argument to `True`.
+
+```py
+dd_pipeline.save_pretrained("YiYiXu/test_modular_doc", push_to_hub=True)
+```
+
+Other users can load the [`ModularPipeline`] with [`~ModularPipeline.from_pretrained`].

 ```py
 import torch
-from diffusers import ModularPipeline
+from diffusers.modular_pipelines import ModularPipeline, ComponentsManager

-pipe = ModularPipeline.from_pretrained("Qwen/Qwen-Image")
-pipe.load_components(torch_dtype=torch.bfloat16)
-pipe.to("cuda")
+components = ComponentsManager()

-image = pipe(
-    prompt="cat wizard with red hat, gandalf, lord of the rings, detailed, fantasy, cute, adorable, Pixar, Disney",
-).images[0]
-image
+diffdiff_pipeline = ModularPipeline.from_pretrained("YiYiXu/modular-diffdiff-0704", trust_remote_code=True, components_manager=components, collection="diffdiff")
+diffdiff_pipeline.load_components(torch_dtype=torch.float16)
 ```
-
-[`~ModularPipeline.from_pretrained`] uses lazy loading - it reads the configuration to learn where to load each component from, but doesn't actually load the model weights until you call [`~ModularPipeline.load_components`]. This gives you control over when and how components are loaded.
-
-Learn more about creating and loading pipelines in the [Creating a pipeline](https://huggingface.co/docs/diffusers/modular_diffusers/modular_pipeline#creating-a-pipeline) and [Loading components](https://huggingface.co/docs/diffusers/modular_diffusers/modular_pipeline#loading-components) guides.
-
-## Understand the structure
-
-A [`ModularPipeline`] has two parts:
- **State**: the loaded components (models, schedulers, processors) and configuration
- **Definition**: the [`ModularPipelineBlocks`] that specify inputs, outputs, expected components and computation logic
-
-The blocks define *what* the pipeline does. Access them through `pipe.blocks`.
-```py
-print(pipe.blocks)
-```
-
-```
-QwenImageAutoBlocks(
-  Class: SequentialPipelineBlocks
-
-  Description: Auto Modular pipeline for text-to-image, image-to-image, inpainting, and controlnet tasks using QwenImage.
-      
-      Supported workflows:
-        - `text2image`: requires `prompt`
-        - `image2image`: requires `prompt`, `image`
-        - `inpainting`: requires `prompt`, `mask_image`, `image`
-        - `controlnet_text2image`: requires `prompt`, `control_image`
-        ...
-
-  Components:
-      text_encoder (`Qwen2_5_VLForConditionalGeneration`)
-      vae (`AutoencoderKLQwenImage`)
-      transformer (`QwenImageTransformer2DModel`)
-      ...
-
-  Sub-Blocks:
-    [0] text_encoder (QwenImageAutoTextEncoderStep)
-    [1] vae_encoder (QwenImageAutoVaeEncoderStep)
-    [2] controlnet_vae_encoder (QwenImageOptionalControlNetVaeEncoderStep)
-    [3] denoise (QwenImageAutoCoreDenoiseStep)
-    [4] decode (QwenImageAutoDecodeStep)
-)
-```
-
-The output returns:
- The supported workflows (text2image, image2image, inpainting, etc.)
- The Sub-Blocks it's composed of (text_encoder, vae_encoder, denoise, decode)
-
-### Workflows
-
-`QwenImageAutoBlocks` is a [`ConditionalPipelineBlocks`], so this pipeline supports multiple workflows and adapts its behavior based on the inputs you provide. For example, if you pass `image` to the pipeline, it runs an image-to-image workflow instead of text-to-image.
-```py
-from diffusers.utils import load_image
-
-input_image = load_image("https://github.com/Trgtuan10/Image_storage/blob/main/cute_cat.png?raw=true")
-
-image = pipe(
-    prompt="cat wizard with red hat, gandalf, lord of the rings, detailed, fantasy, cute, adorable, Pixar, Disney",
-    image=input_image,
-).images[0]
-```
-
-Use `get_workflow()` to extract the blocks for a specific workflow.
-```py
-img2img_blocks = pipe.blocks.get_workflow("image2image")
-```
-
-Conditional blocks are convenient for users, but their conditional logic adds complexity when customizing or debugging. Extracting a workflow gives you the specific blocks relevant to your workflow, making it easier to work with. Learn more in the [AutoPipelineBlocks](https://huggingface.co/docs/diffusers/modular_diffusers/auto_pipeline_blocks) guide.
-
-### Sub-blocks
-
-`QwenImageAutoBlocks` is itself composed of smaller blocks: `text_encoder`, `vae_encoder`, `controlnet_vae_encoder`, `denoise`, and `decode`. Access them through the `sub_blocks` property.
-
-The `doc` property is useful for seeing the full documentation of any block, including its inputs, outputs, and components.
-
-```py
-vae_encoder_block = pipe.blocks.sub_blocks["vae_encoder"]
-print(vae_encoder_block.doc)
-```
-
-This block can be converted to a pipeline and run on its own with [`~ModularPipelineBlocks.init_pipeline`].
-```py
-vae_encoder_pipe = vae_encoder_block.init_pipeline()
-
-# Reuse the VAE we already loaded, we can reuse it with update_components() method
-vae_encoder_pipe.update_components(vae=pipe.vae)
-
-# Run just this block
-image_latents = vae_encoder_pipe(image=input_image).image_latents
-print(image_latents.shape)
-```
-
-It reuses the VAE from our original pipeline instead of reloading it, keeping memory usage efficient. Learn more in the [Loading components](https://huggingface.co/docs/diffusers/modular_diffusers/modular_pipeline#loading-components) guide.
-
-Since blocks are composable, you can modify the pipeline's definition by adding, removing, or swapping blocks to create new workflows. In the next section, we'll add a canny edge detection block to a ControlNet pipeline, so you can pass a regular image instead of a pre-processed canny edge map.
-
-## Compose new workflows
-
-Let's add a canny edge detection block to a ControlNet pipeline. First, load a pre-built canny block from the Hub (see [Building Custom Blocks](https://huggingface.co/docs/diffusers/modular_diffusers/custom_blocks) to create your own).
-
-```py
-from diffusers.modular_pipelines import ModularPipelineBlocks
-
-# Load a canny block from the Hub
-canny_block = ModularPipelineBlocks.from_pretrained(
-    "diffusers-internal-dev/canny-filtering",
-    trust_remote_code=True,
-)
-
-print(canny_block.doc)
-```
-```
-class CannyBlock
-
-  Inputs:
-      image (`Union[Image, ndarray]`):
-          Image to compute canny filter on
-      low_threshold (`int`, *optional*, defaults to 50):
-          Low threshold for the canny filter.
-      high_threshold (`int`, *optional*, defaults to 200):
-          High threshold for the canny filter.
-      ...
-
-  Outputs:
-      control_image (`PIL.Image`):
-          Canny map for input image
-```
-
-Use `get_workflow` to extract the ControlNet workflow from [`QwenImageAutoBlocks`].
-
-```py
-# Get the controlnet workflow that we want to work with
-blocks = pipe.blocks.get_workflow("controlnet_text2image")
-print(blocks.doc)
-```
-```
-class SequentialPipelineBlocks
-
-  Inputs:
-      prompt (`str`):
-          The prompt or prompts to guide image generation.
-      control_image (`Image`):
-          Control image for ControlNet conditioning.
-      ...
-```
-It requires control_image as input. After inserting the canny block, the pipeline will accept a regular image instead.
-
-```py
-# and insert canny at the beginning
-blocks.sub_blocks.insert("canny", canny_block, 0)
-
-# Check the updated structure: CannyBlock is now listed as first sub-block
-print(blocks)
-# Check the updated doc: notice the pipeline now takes "image" as input
-# even though it's a controlnet pipeline, because canny preprocesses it into control_image
-print(blocks.doc)
-```
-```
-class SequentialPipelineBlocks
-
-  Inputs:
-      image (`Union[Image, ndarray]`):
-          Image to compute canny filter on
-      low_threshold (`int`, *optional*, defaults to 50):
-          Low threshold for the canny filter.
-      high_threshold (`int`, *optional*, defaults to 200):
-          High threshold for the canny filter.
-      prompt (`str`):
-          The prompt or prompts to guide image generation.
-      ...
-```
-
-Now the pipeline takes `image` as input - the canny block will preprocess it into `control_image` automatically.
-
-Create a pipeline from the modified blocks and load a ControlNet model. We use [`ComponentsManager`] to enable CPU offloading for reduced memory usage (learn more in the [ComponentsManager](./components_manager) guide).
-```py
-from diffusers import ComponentsManager
-
-manager = ComponentsManager()
-manager.enable_auto_cpu_offload(device="cuda:0")
-
-pipeline = blocks.init_pipeline("Qwen/Qwen-Image", components_manager=manager)
-
-pipeline.load_components(torch_dtype=torch.bfloat16)
-
-# Load the ControlNet model
-controlnet_spec = pipeline.get_component_spec("controlnet")
-controlnet_spec.pretrained_model_name_or_path = "InstantX/Qwen-Image-ControlNet-Union"
-controlnet = controlnet_spec.load(torch_dtype=torch.bfloat16)
-pipeline.update_components(controlnet=controlnet)
-```
-
-Now run the pipeline - the canny block preprocesses the image for ControlNet.
-
-```py
-from diffusers.utils import load_image
-
-prompt = "cat wizard with red hat, gandalf, lord of the rings, detailed, fantasy, cute, adorable, Pixar, Disney"
-image = load_image("https://github.com/Trgtuan10/Image_storage/blob/main/cute_cat.png?raw=true")
-
-output = pipeline(
-    prompt=prompt,
-    image=image,
-).images[0]
-output
-```
-
-## Next steps
-
-<hfoptions id="next">
-<hfoption id="Build custom blocks">
-
-Learn how to create your own blocks with custom logic in the [Building Custom Blocks](./custom_blocks) guide.
-
-</hfoption>
-<hfoption id="Share components">
-
-Use [`ComponentsManager`](./components_manager) to share models across multiple pipelines and manage memory efficiently.
-
-</hfoption>
-<hfoption id="Visual interface">
-
-Connect modular pipelines to [Mellon](https://github.com/cubiq/Mellon), a visual node-based interface for building workflows. Custom blocks built with Modular Diffusers work out of the box with Mellon - no UI code required. Read more in Mellon guide.
-
-</hfoption>
-</hfoptions>
--- a/src/diffusers/loaders/peft.py
+++ b/src/diffusers/loaders/peft.py
@@ -478,7 +478,7 @@ class PeftAdapterMixin:
        Args:
            adapter_names (`List[str]` or `str`):
                The names of the adapters to use.
-            adapter_weights (`Union[List[float], float]`, *optional*):
+            weights (`Union[List[float], float]`, *optional*):
                The adapter(s) weights to use with the UNet. If `None`, the weights are set to `1.0` for all the
                adapters.

@@ -495,7 +495,7 @@ class PeftAdapterMixin:
            "jbilcke-hf/sdxl-cinematic-1", weight_name="pytorch_lora_weights.safetensors", adapter_name="cinematic"
        )
        pipeline.load_lora_weights("nerijs/pixel-art-xl", weight_name="pixel-art-xl.safetensors", adapter_name="pixel")
-        pipeline.unet.set_adapters(["cinematic", "pixel"], adapter_weights=[0.5, 0.5])
+        pipeline.unet.set_adapters(["cinematic", "pixel"], weights=[0.5, 0.5])
        ```
        """
        if not USE_PEFT_BACKEND:
--- a/src/diffusers/models/transformers/transformer_longcat_image.py
+++ b/src/diffusers/models/transformers/transformer_longcat_image.py
@@ -406,6 +406,7 @@ class LongCatImageTransformer2DModel(
    """

    _supports_gradient_checkpointing = True
+    _repeated_blocks = ["LongCatImageTransformerBlock", "LongCatImageSingleTransformerBlock"]

    @register_to_config
    def __init__(
--- a/src/diffusers/schedulers/scheduling_consistency_decoder.py
+++ b/src/diffusers/schedulers/scheduling_consistency_decoder.py
@@ -14,7 +14,7 @@ from .scheduling_utils import SchedulerMixin
 def betas_for_alpha_bar(
    num_diffusion_timesteps: int,
    max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
    """
    Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -28,8 +28,8 @@ def betas_for_alpha_bar(
            The number of betas to produce.
        max_beta (`float`, defaults to `0.999`):
            The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.

    Returns:
        `torch.Tensor`:
--- a/src/diffusers/schedulers/scheduling_ddim.py
+++ b/src/diffusers/schedulers/scheduling_ddim.py
@@ -51,7 +51,7 @@ class DDIMSchedulerOutput(BaseOutput):
 def betas_for_alpha_bar(
    num_diffusion_timesteps: int,
    max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
    """
    Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -65,8 +65,8 @@ def betas_for_alpha_bar(
            The number of betas to produce.
        max_beta (`float`, defaults to `0.999`):
            The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.

    Returns:
        `torch.Tensor`:
--- a/src/diffusers/schedulers/scheduling_ddim_cogvideox.py
+++ b/src/diffusers/schedulers/scheduling_ddim_cogvideox.py
@@ -51,7 +51,7 @@ class DDIMSchedulerOutput(BaseOutput):
 def betas_for_alpha_bar(
    num_diffusion_timesteps: int,
    max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
    """
    Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -65,8 +65,8 @@ def betas_for_alpha_bar(
            The number of betas to produce.
        max_beta (`float`, defaults to `0.999`):
            The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.

    Returns:
        `torch.Tensor`:
@@ -100,14 +100,13 @@ def betas_for_alpha_bar(
    return torch.tensor(betas, dtype=torch.float32)


-def rescale_zero_terminal_snr(alphas_cumprod):
+def rescale_zero_terminal_snr(alphas_cumprod: torch.Tensor) -> torch.Tensor:
    """
-    Rescales betas to have zero terminal SNR Based on https://huggingface.co/papers/2305.08891 (Algorithm 1)
-
+    Rescales betas to have zero terminal SNR Based on (Algorithm 1)[https://huggingface.co/papers/2305.08891]

    Args:
-        betas (`torch.Tensor`):
-            the betas that the scheduler is being initialized with.
+        alphas_cumprod (`torch.Tensor`):
+            The alphas cumulative products that the scheduler is being initialized with.

    Returns:
        `torch.Tensor`: rescaled betas with zero terminal SNR
@@ -142,11 +141,11 @@ class CogVideoXDDIMScheduler(SchedulerMixin, ConfigMixin):
    Args:
        num_train_timesteps (`int`, defaults to 1000):
            The number of diffusion steps to train the model.
-        beta_start (`float`, defaults to 0.0001):
+        beta_start (`float`, defaults to 0.00085):
            The starting `beta` value of inference.
-        beta_end (`float`, defaults to 0.02):
+        beta_end (`float`, defaults to 0.0120):
            The final `beta` value.
-        beta_schedule (`str`, defaults to `"linear"`):
+        beta_schedule (`str`, defaults to `"scaled_linear"`):
            The beta schedule, a mapping from a beta range to a sequence of betas for stepping the model. Choose from
            `linear`, `scaled_linear`, or `squaredcos_cap_v2`.
        trained_betas (`np.ndarray`, *optional*):
@@ -179,6 +178,8 @@ class CogVideoXDDIMScheduler(SchedulerMixin, ConfigMixin):
            Whether to rescale the betas to have zero terminal SNR. This enables the model to generate very bright and
            dark samples instead of limiting it to samples with medium brightness. Loosely related to
            [`--offset_noise`](https://github.com/huggingface/diffusers/blob/74fd735eb073eb1d774b1ab4154a0876eb82f055/examples/dreambooth/train_dreambooth.py#L506).
+        snr_shift_scale (`float`, defaults to 3.0):
+            Shift scale for SNR.
    """

    _compatibles = [e.name for e in KarrasDiffusionSchedulers]
@@ -190,15 +191,15 @@ class CogVideoXDDIMScheduler(SchedulerMixin, ConfigMixin):
        num_train_timesteps: int = 1000,
        beta_start: float = 0.00085,
        beta_end: float = 0.0120,
-        beta_schedule: str = "scaled_linear",
+        beta_schedule: Literal["linear", "scaled_linear", "squaredcos_cap_v2"] = "scaled_linear",
        trained_betas: Optional[Union[np.ndarray, List[float]]] = None,
        clip_sample: bool = True,
        set_alpha_to_one: bool = True,
        steps_offset: int = 0,
-        prediction_type: str = "epsilon",
+        prediction_type: Literal["epsilon", "sample", "v_prediction"] = "epsilon",
        clip_sample_range: float = 1.0,
        sample_max_value: float = 1.0,
-        timestep_spacing: str = "leading",
+        timestep_spacing: Literal["linspace", "leading", "trailing"] = "leading",
        rescale_betas_zero_snr: bool = False,
        snr_shift_scale: float = 3.0,
    ):
@@ -208,7 +209,15 @@ class CogVideoXDDIMScheduler(SchedulerMixin, ConfigMixin):
            self.betas = torch.linspace(beta_start, beta_end, num_train_timesteps, dtype=torch.float32)
        elif beta_schedule == "scaled_linear":
            # this schedule is very specific to the latent diffusion model.
-            self.betas = torch.linspace(beta_start**0.5, beta_end**0.5, num_train_timesteps, dtype=torch.float64) ** 2
+            self.betas = (
+                torch.linspace(
+                    beta_start**0.5,
+                    beta_end**0.5,
+                    num_train_timesteps,
+                    dtype=torch.float64,
+                )
+                ** 2
+            )
        elif beta_schedule == "squaredcos_cap_v2":
            # Glide cosine schedule
            self.betas = betas_for_alpha_bar(num_train_timesteps)
@@ -238,7 +247,7 @@ class CogVideoXDDIMScheduler(SchedulerMixin, ConfigMixin):
        self.num_inference_steps = None
        self.timesteps = torch.from_numpy(np.arange(0, num_train_timesteps)[::-1].copy().astype(np.int64))

-    def _get_variance(self, timestep, prev_timestep):
+    def _get_variance(self, timestep: int, prev_timestep: int) -> torch.Tensor:
        alpha_prod_t = self.alphas_cumprod[timestep]
        alpha_prod_t_prev = self.alphas_cumprod[prev_timestep] if prev_timestep >= 0 else self.final_alpha_cumprod
        beta_prod_t = 1 - alpha_prod_t
@@ -265,7 +274,11 @@ class CogVideoXDDIMScheduler(SchedulerMixin, ConfigMixin):
        """
        return sample

-    def set_timesteps(self, num_inference_steps: int, device: Union[str, torch.device] = None):
+    def set_timesteps(
+        self,
+        num_inference_steps: int,
+        device: Optional[Union[str, torch.device]] = None,
+    ) -> None:
        """
        Sets the discrete timesteps used for the diffusion chain (to be run before inference).

@@ -317,7 +330,7 @@ class CogVideoXDDIMScheduler(SchedulerMixin, ConfigMixin):
        sample: torch.Tensor,
        eta: float = 0.0,
        use_clipped_model_output: bool = False,
-        generator=None,
+        generator: Optional[torch.Generator] = None,
        variance_noise: Optional[torch.Tensor] = None,
        return_dict: bool = True,
    ) -> Union[DDIMSchedulerOutput, Tuple]:
@@ -328,7 +341,7 @@ class CogVideoXDDIMScheduler(SchedulerMixin, ConfigMixin):
        Args:
            model_output (`torch.Tensor`):
                The direct output from learned diffusion model.
-            timestep (`float`):
+            timestep (`int`):
                The current discrete timestep in the diffusion chain.
            sample (`torch.Tensor`):
                A current instance of a sample created by the diffusion process.
@@ -487,5 +500,5 @@ class CogVideoXDDIMScheduler(SchedulerMixin, ConfigMixin):
        velocity = sqrt_alpha_prod * noise - sqrt_one_minus_alpha_prod * sample
        return velocity

-    def __len__(self):
+    def __len__(self) -> int:
        return self.config.num_train_timesteps
--- a/src/diffusers/schedulers/scheduling_ddim_flax.py
+++ b/src/diffusers/schedulers/scheduling_ddim_flax.py
@@ -22,6 +22,7 @@ import flax
 import jax.numpy as jnp

 from ..configuration_utils import ConfigMixin, register_to_config
+from ..utils import logging
 from .scheduling_utils_flax import (
    CommonSchedulerState,
    FlaxKarrasDiffusionSchedulers,
@@ -32,6 +33,9 @@ from .scheduling_utils_flax import (
 )


+logger = logging.get_logger(__name__)
+
+
@flax.struct.dataclass
 class DDIMSchedulerState:
    common: CommonSchedulerState
@@ -125,6 +129,10 @@ class FlaxDDIMScheduler(FlaxSchedulerMixin, ConfigMixin):
        prediction_type: str = "epsilon",
        dtype: jnp.dtype = jnp.float32,
    ):
+        logger.warning(
+            "Flax classes are deprecated and will be removed in Diffusers v1.0.0. We "
+            "recommend migrating to PyTorch classes or pinning your version of Diffusers."
+        )
        self.dtype = dtype

    def create_state(self, common: Optional[CommonSchedulerState] = None) -> DDIMSchedulerState:
@@ -152,7 +160,10 @@ class FlaxDDIMScheduler(FlaxSchedulerMixin, ConfigMixin):
        )

    def scale_model_input(
-        self, state: DDIMSchedulerState, sample: jnp.ndarray, timestep: Optional[int] = None
+        self,
+        state: DDIMSchedulerState,
+        sample: jnp.ndarray,
+        timestep: Optional[int] = None,
    ) -> jnp.ndarray:
        """
        Args:
@@ -190,7 +201,9 @@ class FlaxDDIMScheduler(FlaxSchedulerMixin, ConfigMixin):
    def _get_variance(self, state: DDIMSchedulerState, timestep, prev_timestep):
        alpha_prod_t = state.common.alphas_cumprod[timestep]
        alpha_prod_t_prev = jnp.where(
-            prev_timestep >= 0, state.common.alphas_cumprod[prev_timestep], state.final_alpha_cumprod
+            prev_timestep >= 0,
+            state.common.alphas_cumprod[prev_timestep],
+            state.final_alpha_cumprod,
        )
        beta_prod_t = 1 - alpha_prod_t
        beta_prod_t_prev = 1 - alpha_prod_t_prev
--- a/src/diffusers/schedulers/scheduling_ddim_inverse.py
+++ b/src/diffusers/schedulers/scheduling_ddim_inverse.py
@@ -49,7 +49,7 @@ class DDIMSchedulerOutput(BaseOutput):
 def betas_for_alpha_bar(
    num_diffusion_timesteps: int,
    max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
    """
    Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -63,8 +63,8 @@ def betas_for_alpha_bar(
            The number of betas to produce.
        max_beta (`float`, defaults to `0.999`):
            The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.

    Returns:
        `torch.Tensor`:
@@ -99,7 +99,7 @@ def betas_for_alpha_bar(


 # Copied from diffusers.schedulers.scheduling_ddim.rescale_zero_terminal_snr
-def rescale_zero_terminal_snr(betas):
+def rescale_zero_terminal_snr(betas: torch.Tensor) -> torch.Tensor:
    """
    Rescales betas to have zero terminal SNR Based on https://huggingface.co/papers/2305.08891 (Algorithm 1)

@@ -187,14 +187,14 @@ class DDIMInverseScheduler(SchedulerMixin, ConfigMixin):
        num_train_timesteps: int = 1000,
        beta_start: float = 0.0001,
        beta_end: float = 0.02,
-        beta_schedule: str = "linear",
+        beta_schedule: Literal["linear", "scaled_linear", "squaredcos_cap_v2"] = "linear",
        trained_betas: Optional[Union[np.ndarray, List[float]]] = None,
        clip_sample: bool = True,
        set_alpha_to_one: bool = True,
        steps_offset: int = 0,
-        prediction_type: str = "epsilon",
+        prediction_type: Literal["epsilon", "sample", "v_prediction"] = "epsilon",
        clip_sample_range: float = 1.0,
-        timestep_spacing: str = "leading",
+        timestep_spacing: Literal["leading", "trailing"] = "leading",
        rescale_betas_zero_snr: bool = False,
        **kwargs,
    ):
@@ -210,7 +210,15 @@ class DDIMInverseScheduler(SchedulerMixin, ConfigMixin):
            self.betas = torch.linspace(beta_start, beta_end, num_train_timesteps, dtype=torch.float32)
        elif beta_schedule == "scaled_linear":
            # this schedule is very specific to the latent diffusion model.
-            self.betas = torch.linspace(beta_start**0.5, beta_end**0.5, num_train_timesteps, dtype=torch.float32) ** 2
+            self.betas = (
+                torch.linspace(
+                    beta_start**0.5,
+                    beta_end**0.5,
+                    num_train_timesteps,
+                    dtype=torch.float32,
+                )
+                ** 2
+            )
        elif beta_schedule == "squaredcos_cap_v2":
            # Glide cosine schedule
            self.betas = betas_for_alpha_bar(num_train_timesteps)
@@ -256,7 +264,11 @@ class DDIMInverseScheduler(SchedulerMixin, ConfigMixin):
        """
        return sample

-    def set_timesteps(self, num_inference_steps: int, device: Union[str, torch.device] = None):
+    def set_timesteps(
+        self,
+        num_inference_steps: int,
+        device: Optional[Union[str, torch.device]] = None,
+    ) -> None:
        """
        Sets the discrete timesteps used for the diffusion chain (to be run before inference).

@@ -308,20 +320,10 @@ class DDIMInverseScheduler(SchedulerMixin, ConfigMixin):
        Args:
            model_output (`torch.Tensor`):
                The direct output from learned diffusion model.
-            timestep (`float`):
+            timestep (`int`):
                The current discrete timestep in the diffusion chain.
            sample (`torch.Tensor`):
                A current instance of a sample created by the diffusion process.
-            eta (`float`):
-                The weight of noise for added noise in diffusion step.
-            use_clipped_model_output (`bool`, defaults to `False`):
-                If `True`, computes "corrected" `model_output` from the clipped predicted original sample. Necessary
-                because predicted original sample is clipped to [-1, 1] when `self.config.clip_sample` is `True`. If no
-                clipping has happened, "corrected" `model_output` would coincide with the one provided as input and
-                `use_clipped_model_output` has no effect.
-            variance_noise (`torch.Tensor`):
-                Alternative to generating noise with `generator` by directly providing the noise for the variance
-                itself. Useful for methods such as [`CycleDiffusion`].
            return_dict (`bool`, *optional*, defaults to `True`):
                Whether or not to return a [`~schedulers.scheduling_ddim_inverse.DDIMInverseSchedulerOutput`] or
                `tuple`.
@@ -335,7 +337,8 @@ class DDIMInverseScheduler(SchedulerMixin, ConfigMixin):
        # 1. get previous step value (=t+1)
        prev_timestep = timestep
        timestep = min(
-            timestep - self.config.num_train_timesteps // self.num_inference_steps, self.config.num_train_timesteps - 1
+            timestep - self.config.num_train_timesteps // self.num_inference_steps,
+            self.config.num_train_timesteps - 1,
        )

        # 2. compute alphas, betas
@@ -378,5 +381,5 @@ class DDIMInverseScheduler(SchedulerMixin, ConfigMixin):
            return (prev_sample, pred_original_sample)
        return DDIMSchedulerOutput(prev_sample=prev_sample, pred_original_sample=pred_original_sample)

-    def __len__(self):
+    def __len__(self) -> int:
        return self.config.num_train_timesteps
--- a/src/diffusers/schedulers/scheduling_ddim_parallel.py
+++ b/src/diffusers/schedulers/scheduling_ddim_parallel.py
@@ -51,7 +51,7 @@ class DDIMParallelSchedulerOutput(BaseOutput):
 def betas_for_alpha_bar(
    num_diffusion_timesteps: int,
    max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
    """
    Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -65,8 +65,8 @@ def betas_for_alpha_bar(
            The number of betas to produce.
        max_beta (`float`, defaults to `0.999`):
            The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.

    Returns:
        `torch.Tensor`:
--- a/src/diffusers/schedulers/scheduling_ddpm.py
+++ b/src/diffusers/schedulers/scheduling_ddpm.py
@@ -48,7 +48,7 @@ class DDPMSchedulerOutput(BaseOutput):
 def betas_for_alpha_bar(
    num_diffusion_timesteps: int,
    max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
    """
    Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -62,8 +62,8 @@ def betas_for_alpha_bar(
            The number of betas to produce.
        max_beta (`float`, defaults to `0.999`):
            The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.

    Returns:
        `torch.Tensor`:
@@ -192,7 +192,12 @@ class DDPMScheduler(SchedulerMixin, ConfigMixin):
        beta_schedule: Literal["linear", "scaled_linear", "squaredcos_cap_v2", "sigmoid"] = "linear",
        trained_betas: Optional[Union[np.ndarray, List[float]]] = None,
        variance_type: Literal[
-            "fixed_small", "fixed_small_log", "fixed_large", "fixed_large_log", "learned", "learned_range"
+            "fixed_small",
+            "fixed_small_log",
+            "fixed_large",
+            "fixed_large_log",
+            "learned",
+            "learned_range",
        ] = "fixed_small",
        clip_sample: bool = True,
        prediction_type: Literal["epsilon", "sample", "v_prediction"] = "epsilon",
@@ -210,7 +215,15 @@ class DDPMScheduler(SchedulerMixin, ConfigMixin):
            self.betas = torch.linspace(beta_start, beta_end, num_train_timesteps, dtype=torch.float32)
        elif beta_schedule == "scaled_linear":
            # this schedule is very specific to the latent diffusion model.
-            self.betas = torch.linspace(beta_start**0.5, beta_end**0.5, num_train_timesteps, dtype=torch.float32) ** 2
+            self.betas = (
+                torch.linspace(
+                    beta_start**0.5,
+                    beta_end**0.5,
+                    num_train_timesteps,
+                    dtype=torch.float32,
+                )
+                ** 2
+            )
        elif beta_schedule == "squaredcos_cap_v2":
            # Glide cosine schedule
            self.betas = betas_for_alpha_bar(num_train_timesteps)
@@ -337,7 +350,14 @@ class DDPMScheduler(SchedulerMixin, ConfigMixin):
        t: int,
        predicted_variance: Optional[torch.Tensor] = None,
        variance_type: Optional[
-            Literal["fixed_small", "fixed_small_log", "fixed_large", "fixed_large_log", "learned", "learned_range"]
+            Literal[
+                "fixed_small",
+                "fixed_small_log",
+                "fixed_large",
+                "fixed_large_log",
+                "learned",
+                "learned_range",
+            ]
        ] = None,
    ) -> torch.Tensor:
        """
@@ -472,7 +492,10 @@ class DDPMScheduler(SchedulerMixin, ConfigMixin):

        prev_t = self.previous_timestep(t)

-        if model_output.shape[1] == sample.shape[1] * 2 and self.variance_type in ["learned", "learned_range"]:
+        if model_output.shape[1] == sample.shape[1] * 2 and self.variance_type in [
+            "learned",
+            "learned_range",
+        ]:
            model_output, predicted_variance = torch.split(model_output, sample.shape[1], dim=1)
        else:
            predicted_variance = None
@@ -521,7 +544,10 @@ class DDPMScheduler(SchedulerMixin, ConfigMixin):
        if t > 0:
            device = model_output.device
            variance_noise = randn_tensor(
-                model_output.shape, generator=generator, device=device, dtype=model_output.dtype
+                model_output.shape,
+                generator=generator,
+                device=device,
+                dtype=model_output.dtype,
            )
            if self.variance_type == "fixed_small_log":
                variance = self._get_variance(t, predicted_variance=predicted_variance) * variance_noise
--- a/src/diffusers/schedulers/scheduling_ddpm_parallel.py
+++ b/src/diffusers/schedulers/scheduling_ddpm_parallel.py
@@ -50,7 +50,7 @@ class DDPMParallelSchedulerOutput(BaseOutput):
 def betas_for_alpha_bar(
    num_diffusion_timesteps: int,
    max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
    """
    Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -64,8 +64,8 @@ def betas_for_alpha_bar(
            The number of betas to produce.
        max_beta (`float`, defaults to `0.999`):
            The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.

    Returns:
        `torch.Tensor`:
@@ -202,7 +202,12 @@ class DDPMParallelScheduler(SchedulerMixin, ConfigMixin):
        beta_schedule: Literal["linear", "scaled_linear", "squaredcos_cap_v2", "sigmoid"] = "linear",
        trained_betas: Optional[Union[np.ndarray, List[float]]] = None,
        variance_type: Literal[
-            "fixed_small", "fixed_small_log", "fixed_large", "fixed_large_log", "learned", "learned_range"
+            "fixed_small",
+            "fixed_small_log",
+            "fixed_large",
+            "fixed_large_log",
+            "learned",
+            "learned_range",
        ] = "fixed_small",
        clip_sample: bool = True,
        prediction_type: Literal["epsilon", "sample", "v_prediction"] = "epsilon",
@@ -220,7 +225,15 @@ class DDPMParallelScheduler(SchedulerMixin, ConfigMixin):
            self.betas = torch.linspace(beta_start, beta_end, num_train_timesteps, dtype=torch.float32)
        elif beta_schedule == "scaled_linear":
            # this schedule is very specific to the latent diffusion model.
-            self.betas = torch.linspace(beta_start**0.5, beta_end**0.5, num_train_timesteps, dtype=torch.float32) ** 2
+            self.betas = (
+                torch.linspace(
+                    beta_start**0.5,
+                    beta_end**0.5,
+                    num_train_timesteps,
+                    dtype=torch.float32,
+                )
+                ** 2
+            )
        elif beta_schedule == "squaredcos_cap_v2":
            # Glide cosine schedule
            self.betas = betas_for_alpha_bar(num_train_timesteps)
@@ -350,7 +363,14 @@ class DDPMParallelScheduler(SchedulerMixin, ConfigMixin):
        t: int,
        predicted_variance: Optional[torch.Tensor] = None,
        variance_type: Optional[
-            Literal["fixed_small", "fixed_small_log", "fixed_large", "fixed_large_log", "learned", "learned_range"]
+            Literal[
+                "fixed_small",
+                "fixed_small_log",
+                "fixed_large",
+                "fixed_large_log",
+                "learned",
+                "learned_range",
+            ]
        ] = None,
    ) -> torch.Tensor:
        """
--- a/src/diffusers/schedulers/scheduling_deis_multistep.py
+++ b/src/diffusers/schedulers/scheduling_deis_multistep.py
@@ -34,7 +34,7 @@ if is_scipy_available():
 def betas_for_alpha_bar(
    num_diffusion_timesteps: int,
    max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
    """
    Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -48,8 +48,8 @@ def betas_for_alpha_bar(
            The number of betas to produce.
        max_beta (`float`, defaults to `0.999`):
            The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.

    Returns:
        `torch.Tensor`:
--- a/src/diffusers/schedulers/scheduling_dpm_cogvideox.py
+++ b/src/diffusers/schedulers/scheduling_dpm_cogvideox.py
@@ -52,7 +52,7 @@ class DDIMSchedulerOutput(BaseOutput):
 def betas_for_alpha_bar(
    num_diffusion_timesteps: int,
    max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
    """
    Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -66,8 +66,8 @@ def betas_for_alpha_bar(
            The number of betas to produce.
        max_beta (`float`, defaults to `0.999`):
            The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.

    Returns:
        `torch.Tensor`:
--- a/src/diffusers/schedulers/scheduling_dpmsolver_multistep.py
+++ b/src/diffusers/schedulers/scheduling_dpmsolver_multistep.py
@@ -34,7 +34,7 @@ if is_scipy_available():
 def betas_for_alpha_bar(
    num_diffusion_timesteps: int,
    max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
    """
    Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -48,8 +48,8 @@ def betas_for_alpha_bar(
            The number of betas to produce.
        max_beta (`float`, defaults to `0.999`):
            The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.

    Returns:
        `torch.Tensor`:
--- a/src/diffusers/schedulers/scheduling_dpmsolver_multistep_inverse.py
+++ b/src/diffusers/schedulers/scheduling_dpmsolver_multistep_inverse.py
@@ -34,7 +34,7 @@ if is_scipy_available():
 def betas_for_alpha_bar(
    num_diffusion_timesteps: int,
    max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
    """
    Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -48,8 +48,8 @@ def betas_for_alpha_bar(
            The number of betas to produce.
        max_beta (`float`, defaults to `0.999`):
            The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.

    Returns:
        `torch.Tensor`:
--- a/src/diffusers/schedulers/scheduling_dpmsolver_sde.py
+++ b/src/diffusers/schedulers/scheduling_dpmsolver_sde.py
@@ -117,7 +117,7 @@ class BrownianTreeNoiseSampler:
 def betas_for_alpha_bar(
    num_diffusion_timesteps: int,
    max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
    """
    Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -131,8 +131,8 @@ def betas_for_alpha_bar(
            The number of betas to produce.
        max_beta (`float`, defaults to `0.999`):
            The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.

    Returns:
        `torch.Tensor`:
--- a/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py
+++ b/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py
@@ -36,7 +36,7 @@ logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
 def betas_for_alpha_bar(
    num_diffusion_timesteps: int,
    max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
    """
    Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -50,8 +50,8 @@ def betas_for_alpha_bar(
            The number of betas to produce.
        max_beta (`float`, defaults to `0.999`):
            The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.

    Returns:
        `torch.Tensor`:
--- a/src/diffusers/schedulers/scheduling_euler_ancestral_discrete.py
+++ b/src/diffusers/schedulers/scheduling_euler_ancestral_discrete.py
@@ -51,7 +51,7 @@ class EulerAncestralDiscreteSchedulerOutput(BaseOutput):
 def betas_for_alpha_bar(
    num_diffusion_timesteps: int,
    max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
    """
    Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -65,8 +65,8 @@ def betas_for_alpha_bar(
            The number of betas to produce.
        max_beta (`float`, defaults to `0.999`):
            The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.

    Returns:
        `torch.Tensor`:
--- a/src/diffusers/schedulers/scheduling_euler_discrete.py
+++ b/src/diffusers/schedulers/scheduling_euler_discrete.py
@@ -54,7 +54,7 @@ class EulerDiscreteSchedulerOutput(BaseOutput):
 def betas_for_alpha_bar(
    num_diffusion_timesteps: int,
    max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
    """
    Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -68,8 +68,8 @@ def betas_for_alpha_bar(
            The number of betas to produce.
        max_beta (`float`, defaults to `0.999`):
            The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.

    Returns:
        `torch.Tensor`:
--- a/src/diffusers/schedulers/scheduling_heun_discrete.py
+++ b/src/diffusers/schedulers/scheduling_heun_discrete.py
@@ -51,7 +51,7 @@ class HeunDiscreteSchedulerOutput(BaseOutput):
 def betas_for_alpha_bar(
    num_diffusion_timesteps: int,
    max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
    """
    Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -65,8 +65,8 @@ def betas_for_alpha_bar(
            The number of betas to produce.
        max_beta (`float`, defaults to `0.999`):
            The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.

    Returns:
        `torch.Tensor`:
--- a/src/diffusers/schedulers/scheduling_k_dpm_2_ancestral_discrete.py
+++ b/src/diffusers/schedulers/scheduling_k_dpm_2_ancestral_discrete.py
@@ -52,7 +52,7 @@ class KDPM2AncestralDiscreteSchedulerOutput(BaseOutput):
 def betas_for_alpha_bar(
    num_diffusion_timesteps: int,
    max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
    """
    Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -66,8 +66,8 @@ def betas_for_alpha_bar(
            The number of betas to produce.
        max_beta (`float`, defaults to `0.999`):
            The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.

    Returns:
        `torch.Tensor`:
--- a/src/diffusers/schedulers/scheduling_k_dpm_2_discrete.py
+++ b/src/diffusers/schedulers/scheduling_k_dpm_2_discrete.py
@@ -51,7 +51,7 @@ class KDPM2DiscreteSchedulerOutput(BaseOutput):
 def betas_for_alpha_bar(
    num_diffusion_timesteps: int,
    max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
    """
    Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -65,8 +65,8 @@ def betas_for_alpha_bar(
            The number of betas to produce.
        max_beta (`float`, defaults to `0.999`):
            The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.

    Returns:
        `torch.Tensor`:
--- a/src/diffusers/schedulers/scheduling_lcm.py
+++ b/src/diffusers/schedulers/scheduling_lcm.py
@@ -53,7 +53,7 @@ class LCMSchedulerOutput(BaseOutput):
 def betas_for_alpha_bar(
    num_diffusion_timesteps: int,
    max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
    """
    Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -67,8 +67,8 @@ def betas_for_alpha_bar(
            The number of betas to produce.
        max_beta (`float`, defaults to `0.999`):
            The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.

    Returns:
        `torch.Tensor`:
--- a/src/diffusers/schedulers/scheduling_lms_discrete.py
+++ b/src/diffusers/schedulers/scheduling_lms_discrete.py
@@ -49,7 +49,7 @@ class LMSDiscreteSchedulerOutput(BaseOutput):
 def betas_for_alpha_bar(
    num_diffusion_timesteps: int,
    max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
    """
    Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -63,8 +63,8 @@ def betas_for_alpha_bar(
            The number of betas to produce.
        max_beta (`float`, defaults to `0.999`):
            The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.

    Returns:
        `torch.Tensor`:
--- a/src/diffusers/schedulers/scheduling_pndm.py
+++ b/src/diffusers/schedulers/scheduling_pndm.py
@@ -28,7 +28,7 @@ from .scheduling_utils import KarrasDiffusionSchedulers, SchedulerMixin, Schedul
 def betas_for_alpha_bar(
    num_diffusion_timesteps: int,
    max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
    """
    Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -42,8 +42,8 @@ def betas_for_alpha_bar(
            The number of betas to produce.
        max_beta (`float`, defaults to `0.999`):
            The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.

    Returns:
        `torch.Tensor`:
--- a/src/diffusers/schedulers/scheduling_repaint.py
+++ b/src/diffusers/schedulers/scheduling_repaint.py
@@ -47,7 +47,7 @@ class RePaintSchedulerOutput(BaseOutput):
 def betas_for_alpha_bar(
    num_diffusion_timesteps: int,
    max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
    """
    Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -61,8 +61,8 @@ def betas_for_alpha_bar(
            The number of betas to produce.
        max_beta (`float`, defaults to `0.999`):
            The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.

    Returns:
        `torch.Tensor`:
--- a/src/diffusers/schedulers/scheduling_sasolver.py
+++ b/src/diffusers/schedulers/scheduling_sasolver.py
@@ -35,7 +35,7 @@ if is_scipy_available():
 def betas_for_alpha_bar(
    num_diffusion_timesteps: int,
    max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
    """
    Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -49,8 +49,8 @@ def betas_for_alpha_bar(
            The number of betas to produce.
        max_beta (`float`, defaults to `0.999`):
            The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.

    Returns:
        `torch.Tensor`:
--- a/src/diffusers/schedulers/scheduling_tcd.py
+++ b/src/diffusers/schedulers/scheduling_tcd.py
@@ -52,7 +52,7 @@ class TCDSchedulerOutput(BaseOutput):
 def betas_for_alpha_bar(
    num_diffusion_timesteps: int,
    max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
    """
    Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -66,8 +66,8 @@ def betas_for_alpha_bar(
            The number of betas to produce.
        max_beta (`float`, defaults to `0.999`):
            The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.

    Returns:
        `torch.Tensor`:
--- a/src/diffusers/schedulers/scheduling_unclip.py
+++ b/src/diffusers/schedulers/scheduling_unclip.py
@@ -48,7 +48,7 @@ class UnCLIPSchedulerOutput(BaseOutput):
 def betas_for_alpha_bar(
    num_diffusion_timesteps: int,
    max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
    """
    Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -62,8 +62,8 @@ def betas_for_alpha_bar(
            The number of betas to produce.
        max_beta (`float`, defaults to `0.999`):
            The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.

    Returns:
        `torch.Tensor`:
--- a/src/diffusers/schedulers/scheduling_unipc_multistep.py
+++ b/src/diffusers/schedulers/scheduling_unipc_multistep.py
@@ -34,7 +34,7 @@ if is_scipy_available():
 def betas_for_alpha_bar(
    num_diffusion_timesteps: int,
    max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
    """
    Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -48,8 +48,8 @@ def betas_for_alpha_bar(
            The number of betas to produce.
        max_beta (`float`, defaults to `0.999`):
            The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.

    Returns:
        `torch.Tensor`:
@@ -226,6 +226,7 @@ class UniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
        time_shift_type: Literal["exponential"] = "exponential",
        sigma_min: Optional[float] = None,
        sigma_max: Optional[float] = None,
+        shift_terminal: Optional[float] = None,
    ) -> None:
        if self.config.use_beta_sigmas and not is_scipy_available():
            raise ImportError("Make sure to install scipy if you want to use beta sigmas.")
@@ -245,6 +246,8 @@ class UniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
            self.betas = betas_for_alpha_bar(num_train_timesteps)
        else:
            raise NotImplementedError(f"{beta_schedule} is not implemented for {self.__class__}")
+        if shift_terminal is not None and not use_flow_sigmas:
+            raise ValueError("`shift_terminal` is only supported when `use_flow_sigmas=True`.")

        if rescale_betas_zero_snr:
            self.betas = rescale_zero_terminal_snr(self.betas)
@@ -313,8 +316,12 @@ class UniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
        self._begin_index = begin_index

    def set_timesteps(
-        self, num_inference_steps: int, device: Optional[Union[str, torch.device]] = None, mu: Optional[float] = None
-    ) -> None:
+        self,
+        num_inference_steps: Optional[int] = None,
+        device: Union[str, torch.device] = None,
+        sigmas: Optional[List[float]] = None,
+        mu: Optional[float] = None,
+    ):
        """
        Sets the discrete timesteps used for the diffusion chain (to be run before inference).

@@ -323,13 +330,24 @@ class UniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
                The number of diffusion steps used when generating samples with a pre-trained model.
            device (`str` or `torch.device`, *optional*):
                The device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
+            sigmas (`List[float]`, *optional*):
+                Custom values for sigmas to be used for each diffusion step. If `None`, the sigmas are computed
+                automatically.
            mu (`float`, *optional*):
                Optional mu parameter for dynamic shifting when using exponential time shift type.
        """
+        if self.config.use_dynamic_shifting and mu is None:
+            raise ValueError("`mu` must be passed when `use_dynamic_shifting` is set to be `True`")
+
+        if sigmas is not None:
+            if not self.config.use_flow_sigmas:
+                raise ValueError(
+                    "Passing `sigmas` is only supported when `use_flow_sigmas=True`. "
+                    "Please set `use_flow_sigmas=True` during scheduler initialization."
+                )
+            num_inference_steps = len(sigmas)
+
        # "linspace", "leading", "trailing" corresponds to annotation of Table 2. of https://huggingface.co/papers/2305.08891
-        if mu is not None:
-            assert self.config.use_dynamic_shifting and self.config.time_shift_type == "exponential"
-            self.config.flow_shift = np.exp(mu)
        if self.config.timestep_spacing == "linspace":
            timesteps = (
                np.linspace(0, self.config.num_train_timesteps - 1, num_inference_steps + 1)
@@ -354,8 +372,9 @@ class UniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
                f"{self.config.timestep_spacing} is not supported. Please make sure to choose one of 'linspace', 'leading' or 'trailing'."
            )

-        sigmas = np.array(((1 - self.alphas_cumprod) / self.alphas_cumprod) ** 0.5)
        if self.config.use_karras_sigmas:
+            if sigmas is None:
+                sigmas = np.array(((1 - self.alphas_cumprod) / self.alphas_cumprod) ** 0.5)
            log_sigmas = np.log(sigmas)
            sigmas = np.flip(sigmas).copy()
            sigmas = self._convert_to_karras(in_sigmas=sigmas, num_inference_steps=num_inference_steps)
@@ -375,6 +394,8 @@ class UniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
                )
            sigmas = np.concatenate([sigmas, [sigma_last]]).astype(np.float32)
        elif self.config.use_exponential_sigmas:
+            if sigmas is None:
+                sigmas = np.array(((1 - self.alphas_cumprod) / self.alphas_cumprod) ** 0.5)
            log_sigmas = np.log(sigmas)
            sigmas = np.flip(sigmas).copy()
            sigmas = self._convert_to_exponential(in_sigmas=sigmas, num_inference_steps=num_inference_steps)
@@ -389,6 +410,8 @@ class UniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
                )
            sigmas = np.concatenate([sigmas, [sigma_last]]).astype(np.float32)
        elif self.config.use_beta_sigmas:
+            if sigmas is None:
+                sigmas = np.array(((1 - self.alphas_cumprod) / self.alphas_cumprod) ** 0.5)
            log_sigmas = np.log(sigmas)
            sigmas = np.flip(sigmas).copy()
            sigmas = self._convert_to_beta(in_sigmas=sigmas, num_inference_steps=num_inference_steps)
@@ -403,9 +426,18 @@ class UniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
                )
            sigmas = np.concatenate([sigmas, [sigma_last]]).astype(np.float32)
        elif self.config.use_flow_sigmas:
-            alphas = np.linspace(1, 1 / self.config.num_train_timesteps, num_inference_steps + 1)
-            sigmas = 1.0 - alphas
-            sigmas = np.flip(self.config.flow_shift * sigmas / (1 + (self.config.flow_shift - 1) * sigmas))[:-1].copy()
+            if sigmas is None:
+                sigmas = np.linspace(1, 1 / self.config.num_train_timesteps, num_inference_steps + 1)[:-1]
+            if self.config.use_dynamic_shifting:
+                sigmas = self.time_shift(mu, 1.0, sigmas)
+            else:
+                sigmas = self.config.flow_shift * sigmas / (1 + (self.config.flow_shift - 1) * sigmas)
+            if self.config.shift_terminal:
+                sigmas = self.stretch_shift_to_terminal(sigmas)
+            eps = 1e-6
+            if np.fabs(sigmas[0] - 1) < eps:
+                # to avoid inf torch.log(alpha_si) in multistep_uni_p_bh_update during first/second update
+                sigmas[0] -= eps
            timesteps = (sigmas * self.config.num_train_timesteps).copy()
            if self.config.final_sigmas_type == "sigma_min":
                sigma_last = sigmas[-1]
@@ -417,6 +449,8 @@ class UniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
                )
            sigmas = np.concatenate([sigmas, [sigma_last]]).astype(np.float32)
        else:
+            if sigmas is None:
+                sigmas = np.array(((1 - self.alphas_cumprod) / self.alphas_cumprod) ** 0.5)
            sigmas = np.interp(timesteps, np.arange(0, len(sigmas)), sigmas)
            if self.config.final_sigmas_type == "sigma_min":
                sigma_last = ((1 - self.alphas_cumprod[0]) / self.alphas_cumprod[0]) ** 0.5
@@ -446,6 +480,43 @@ class UniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
        self._begin_index = None
        self.sigmas = self.sigmas.to("cpu")  # to avoid too much CPU/GPU communication

+    # Copied from diffusers.schedulers.scheduling_flow_match_euler_discrete.FlowMatchEulerDiscreteScheduler.time_shift
+    def time_shift(self, mu: float, sigma: float, t: torch.Tensor):
+        if self.config.time_shift_type == "exponential":
+            return self._time_shift_exponential(mu, sigma, t)
+        elif self.config.time_shift_type == "linear":
+            return self._time_shift_linear(mu, sigma, t)
+
+    # Copied from diffusers.schedulers.scheduling_flow_match_euler_discrete.FlowMatchEulerDiscreteScheduler.stretch_shift_to_terminal
+    def stretch_shift_to_terminal(self, t: torch.Tensor) -> torch.Tensor:
+        r"""
+        Stretches and shifts the timestep schedule to ensure it terminates at the configured `shift_terminal` config
+        value.
+
+        Reference:
+        https://github.com/Lightricks/LTX-Video/blob/a01a171f8fe3d99dce2728d60a73fecf4d4238ae/ltx_video/schedulers/rf.py#L51
+
+        Args:
+            t (`torch.Tensor`):
+                A tensor of timesteps to be stretched and shifted.
+
+        Returns:
+            `torch.Tensor`:
+                A tensor of adjusted timesteps such that the final value equals `self.config.shift_terminal`.
+        """
+        one_minus_z = 1 - t
+        scale_factor = one_minus_z[-1] / (1 - self.config.shift_terminal)
+        stretched_t = 1 - (one_minus_z / scale_factor)
+        return stretched_t
+
+    # Copied from diffusers.schedulers.scheduling_flow_match_euler_discrete.FlowMatchEulerDiscreteScheduler._time_shift_exponential
+    def _time_shift_exponential(self, mu, sigma, t):
+        return math.exp(mu) / (math.exp(mu) + (1 / t - 1) ** sigma)
+
+    # Copied from diffusers.schedulers.scheduling_flow_match_euler_discrete.FlowMatchEulerDiscreteScheduler._time_shift_linear
+    def _time_shift_linear(self, mu, sigma, t):
+        return mu / (mu + (1 / t - 1) ** sigma)
+
    # Copied from diffusers.schedulers.scheduling_ddpm.DDPMScheduler._threshold_sample
    def _threshold_sample(self, sample: torch.Tensor) -> torch.Tensor:
        """
Author	SHA1	Message	Date
sayakpaul	6b127364c4	up	2026-01-23 17:35:26 +05:30
Sayak Paul	bff672f47f	fix Dockerfiles for cuda and xformers. (#13022 )	2026-01-23 16:45:14 +05:30
David El Malih	d4f97d1921	Improve docstrings and type hints in scheduling_ddim_inverse.py (#13020 ) docs: improve docstring scheduling_ddim_inverse.py	2026-01-22 15:42:45 -08:00
David El Malih	1d32b19ad4	Improve docstrings and type hints in scheduling_ddim_flax.py (#13010 ) * docs: improve docstring scheduling_ddim_flax.py * docs: improve docstring scheduling_ddim_flax.py * docs: improve docstring scheduling_ddim_flax.py	2026-01-22 09:11:14 -08:00
Garry Ling	699297f647	feat: accelerate longcat-image with regional compile (#13019 )	2026-01-22 20:21:45 +05:30
Aryan V S	7a02fadad3	[scheduler] Support custom sigmas in UniPCMultistepScheduler (#12109 ) * update * fix tests * Apply suggestions from code review * Revert default flow sigmas change so that tests relying on UniPC multistep still pass * Remove custom timesteps for UniPC multistep set_timesteps --------- Co-authored-by: YiYi Xu <yixu310@gmail.com> Co-authored-by: Daniel Gu <dgu8957@gmail.com> Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>	2026-01-21 17:18:59 -08:00
David El Malih	ec37629371	Improve docstrings and type hints in scheduling_ddim_cogvideox.py (#12992 ) docs: improve docstring scheduling_ddim_cogvideox.py	2026-01-20 12:33:50 -08:00
Guillaume Besson	4b843c8430	Fix variable name in docstring for PeftAdapterMixin.set_adapters (#13003 ) Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>	2026-01-20 15:43:59 +05:30