fix

docs/source/en/modular_diffusers/overview.md

@@ -24,7 +24,7 @@ The Modular Diffusers docs are organized as shown below.
 
 ## Quickstart
 
-- A [quickstart](./quickstart) demonstrating how to implement an example workflow with Modular Diffusers.
+- A [quickstart](./quickstart) shows you how to run a modular pipeline, understand its structure, and customize it by modifying the blocks that compose it.
 
 ## ModularPipelineBlocks
 

docs/source/en/modular_diffusers/quickstart.md

@@ -12,333 +12,243 @@ 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 developers can use.
+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.
 
-This doc will show you how to implement a [Differential Diffusion](https://differential-diffusion.github.io/) pipeline with the modular framework.
+This guide shows you how to run a modular pipeline, understand its structure, and customize it by modifying the blocks that compose it.
 
-## ModularPipelineBlocks
+## Run a pipeline
 
-[`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`].
+[`ModularPipeline`] is the main interface for loading, running, and managing modular pipelines.
 
 ```py
 import torch
-from diffusers.modular_pipelines import ModularPipeline, ComponentsManager
+from diffusers import ModularPipeline
 
-components = ComponentsManager()
+pipe = ModularPipeline.from_pretrained("Qwen/Qwen-Image")
+pipe.load_components(torch_dtype=torch.bfloat16)
+pipe.to("cuda")
 
-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)
+image = pipe(
+    prompt="cat wizard with red hat, gandalf, lord of the rings, detailed, fantasy, cute, adorable, Pixar, Disney",
+).images[0]
+image
 ```
+
+[`~ModularPipeline.from_pretrained`] uses lazy loading - it reads the configuration and knows 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
+
+The pipeline you loaded from `"Qwen/Qwen-Image"` is built from a [`ModularPipelineBlocks`] called `QwenImageAutoBlocks`. Print it to see its structure.
+
+```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)
+)
+```
+
+From this output you can see two things:
+- It supports multiple **workflows** (text2image, image2image, inpainting, etc.)
+- It's composed of **sub_blocks** (text_encoder, vae_encoder, denoise, decode)
+
+### Workflows
+
+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]
+```
+
+Learn more about conditional blocks in the [AutoPipelineBlocks](https://huggingface.co/docs/diffusers/modular_diffusers/auto_pipeline_blocks) guide.
+
+Use `get_workflow()` to extract the blocks for a specific workflow.
+
+```py
+img2img_blocks = pipe.blocks.get_workflow("image2image")
+```
+
+### Sub-blocks
+
+Blocks are the building blocks of the modular system. They are *definitions* that specify the inputs, outputs, and computation logic for a step - and they can be composed together in different ways.
+
+`QwenImageAutoBlocks` is itself composed of smaller blocks: `text_encoder`, `vae_encoder`, `controlnet_vae_encoder`, `denoise`, and `decode`. Access them through the `sub_blocks` property.
+
+Let's take a look at the `vae_encoder` block as an example. Use the `doc` property to see the full documentation for any block, including its inputs, outputs, and components.
+
+```py
+vae_encoder_block = pipe.blocks.sub_blocks["vae_encoder"]
+print(vae_encoder_block.doc)
+```
+
+Just like `QwenImageAutoBlocks`, this block can be converted to a pipeline and run on its own.
+```py
+vae_encoder_pipe = vae_encoder_block.init_pipeline()
+
+# Reuse the VAE we already loaded, we can reuse it with update_componenets() 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)
+```
+
+This reuses the VAE from our original pipeline instead of loading it again, keeping memory usage efficient. Learn more in the [Loading components](https://huggingface.co/docs/diffusers/modular_diffusers/modular_pipeline#loading-components) guide.
+
+You can also add new blocks to compose new workflows. Let's add a canny edge detection block to create a ControlNet pipeline.
+
+First, load the canny block from the Hub and insert it into the controlnet workflow. If you want to learn how to create your own custom blocks and share them on the Hub, check out the [Building Custom Blocks](https://huggingface.co/docs/diffusers/modular_diffusers/custom_blocks) guide.
+
+```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
+```
+
+The canny block takes an `image` as input and outputs a `control_image` - exactly what we need for ControlNet. Now get the controlnet workflow and check its inputs.
+
+```py
+# Get the controlnet workflow 
+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.
+      ...
+```
+Notice 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 - 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.
+
+```py
+pipeline = blocks.init_pipeline("Qwen/Qwen-Image")
+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)
+pipeline.to("cuda")
+```
+
+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>

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.
-            weights (`Union[List[float], float]`, *optional*):
+            adapter_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"], weights=[0.5, 0.5])
+        pipeline.unet.set_adapters(["cinematic", "pixel"], adapter_weights=[0.5, 0.5])
         ```
         """
         if not USE_PEFT_BACKEND:

src/diffusers/models/modeling_utils.py

@@ -675,7 +675,6 @@ class ModelMixin(torch.nn.Module, PushToHubMixin):
         variant: Optional[str] = None,
         max_shard_size: Union[int, str] = "10GB",
         push_to_hub: bool = False,
-        use_flashpack: bool = False,
         **kwargs,
     ):
         """
@@ -708,9 +707,6 @@ class ModelMixin(torch.nn.Module, PushToHubMixin):
                 Whether or not to push your model to the Hugging Face Hub after saving it. You can specify the
                 repository you want to push to with `repo_id` (will default to the name of `save_directory` in your
                 namespace).
-            use_flashpack (`bool`, *optional*, defaults to `False`):
-                Whether to save the model in [FlashPack](https://github.com/fal-ai/flashpack) format. FlashPack is a
-                binary format that allows for faster loading. Requires the `flashpack` library to be installed.
             kwargs (`Dict[str, Any]`, *optional*):
                 Additional keyword arguments passed along to the [`~utils.PushToHubMixin.push_to_hub`] method.
         """
@@ -731,6 +727,12 @@ class ModelMixin(torch.nn.Module, PushToHubMixin):
                     " the logger on the traceback to understand the reason why the quantized model is not serializable."
                 )
 
+        weights_name = SAFETENSORS_WEIGHTS_NAME if safe_serialization else WEIGHTS_NAME
+        weights_name = _add_variant(weights_name, variant)
+        weights_name_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(
+            ".safetensors", "{suffix}.safetensors"
+        )
+
         os.makedirs(save_directory, exist_ok=True)
 
         if push_to_hub:
@@ -744,80 +746,67 @@ class ModelMixin(torch.nn.Module, PushToHubMixin):
         # Only save the model itself if we are using distributed training
         model_to_save = self
 
+        # Attach architecture to the config
         # Save the config
         if is_main_process:
             model_to_save.save_config(save_directory)
 
-        if use_flashpack:
-            if not is_main_process:
-                return
+        # Save the model
+        state_dict = model_to_save.state_dict()
 
-            from ..utils.flashpack_utils import save_flashpack
+        # Save the model
+        state_dict_split = split_torch_state_dict_into_shards(
+            state_dict, max_shard_size=max_shard_size, filename_pattern=weights_name_pattern
+        )
 
-            save_flashpack(model_to_save, save_directory, variant=variant)
-        else:
-            weights_name = SAFETENSORS_WEIGHTS_NAME if safe_serialization else WEIGHTS_NAME
-            weights_name = _add_variant(weights_name, variant)
-            weights_name_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(
-                ".safetensors", "{suffix}.safetensors"
-            )
+        # Clean the folder from a previous save
+        if is_main_process:
+            for filename in os.listdir(save_directory):
+                if filename in state_dict_split.filename_to_tensors.keys():
+                    continue
+                full_filename = os.path.join(save_directory, filename)
+                if not os.path.isfile(full_filename):
+                    continue
+                weights_without_ext = weights_name_pattern.replace(".bin", "").replace(".safetensors", "")
+                weights_without_ext = weights_without_ext.replace("{suffix}", "")
+                filename_without_ext = filename.replace(".bin", "").replace(".safetensors", "")
+                # make sure that file to be deleted matches format of sharded file, e.g. pytorch_model-00001-of-00005
+                if (
+                    filename.startswith(weights_without_ext)
+                    and _REGEX_SHARD.fullmatch(filename_without_ext) is not None
+                ):
+                    os.remove(full_filename)
 
-            state_dict = model_to_save.state_dict()
-            state_dict_split = split_torch_state_dict_into_shards(
-                state_dict, max_shard_size=max_shard_size, filename_pattern=weights_name_pattern
-            )
-
-            # Clean the folder from a previous save
-            if is_main_process:
-                for filename in os.listdir(save_directory):
-                    if filename in state_dict_split.filename_to_tensors.keys():
-                        continue
-                    full_filename = os.path.join(save_directory, filename)
-                    if not os.path.isfile(full_filename):
-                        continue
-                    weights_without_ext = weights_name_pattern.replace(".bin", "").replace(".safetensors", "")
-                    weights_without_ext = weights_without_ext.replace("{suffix}", "")
-                    filename_without_ext = filename.replace(".bin", "").replace(".safetensors", "")
-                    # make sure that file to be deleted matches format of sharded file, e.g. pytorch_model-00001-of-00005
-                    if (
-                        filename.startswith(weights_without_ext)
-                        and _REGEX_SHARD.fullmatch(filename_without_ext) is not None
-                    ):
-                        os.remove(full_filename)
-
-            # Save each shard
-            for filename, tensors in state_dict_split.filename_to_tensors.items():
-                shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors}
-                filepath = os.path.join(save_directory, filename)
-                if safe_serialization:
-                    # At some point we will need to deal better with save_function (used for TPU and other distributed
-                    # joyfulness), but for now this enough.
-                    safetensors.torch.save_file(shard, filepath, metadata={"format": "pt"})
-                else:
-                    torch.save(shard, filepath)
-
-            # Save index file if sharded
-            if state_dict_split.is_sharded:
-                index = {
-                    "metadata": state_dict_split.metadata,
-                    "weight_map": state_dict_split.tensor_to_filename,
-                }
-                save_index_file = SAFE_WEIGHTS_INDEX_NAME if safe_serialization else WEIGHTS_INDEX_NAME
-                save_index_file = os.path.join(save_directory, _add_variant(save_index_file, variant))
-                # Save the index as well
-                with open(save_index_file, "w", encoding="utf-8") as f:
-                    content = json.dumps(index, indent=2, sort_keys=True) + "\n"
-                    f.write(content)
-                logger.info(
-                    f"The model is bigger than the maximum size per checkpoint ({max_shard_size}) and is going to be "
-                    f"split in {len(state_dict_split.filename_to_tensors)} checkpoint shards. You can find where each parameters has been saved in the "
-                    f"index located at {save_index_file}."
-                )
+        for filename, tensors in state_dict_split.filename_to_tensors.items():
+            shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors}
+            filepath = os.path.join(save_directory, filename)
+            if safe_serialization:
+                # At some point we will need to deal better with save_function (used for TPU and other distributed
+                # joyfulness), but for now this enough.
+                safetensors.torch.save_file(shard, filepath, metadata={"format": "pt"})
             else:
-                path_to_weights = os.path.join(save_directory, weights_name)
-                logger.info(f"Model weights saved in {path_to_weights}")
+                torch.save(shard, filepath)
+
+        if state_dict_split.is_sharded:
+            index = {
+                "metadata": state_dict_split.metadata,
+                "weight_map": state_dict_split.tensor_to_filename,
+            }
+            save_index_file = SAFE_WEIGHTS_INDEX_NAME if safe_serialization else WEIGHTS_INDEX_NAME
+            save_index_file = os.path.join(save_directory, _add_variant(save_index_file, variant))
+            # Save the index as well
+            with open(save_index_file, "w", encoding="utf-8") as f:
+                content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+                f.write(content)
+            logger.info(
+                f"The model is bigger than the maximum size per checkpoint ({max_shard_size}) and is going to be "
+                f"split in {len(state_dict_split.filename_to_tensors)} checkpoint shards. You can find where each parameters has been saved in the "
+                f"index located at {save_index_file}."
+            )
+        else:
+            path_to_weights = os.path.join(save_directory, weights_name)
+            logger.info(f"Model weights saved in {path_to_weights}")
 
-        # Push to hub if requested (common to both paths)
         if push_to_hub:
             # Create a new empty model card and eventually tag it
             model_card = load_or_create_model_card(repo_id, token=token)
@@ -950,10 +939,6 @@ class ModelMixin(torch.nn.Module, PushToHubMixin):
                 If set to `None`, the `safetensors` weights are downloaded if they're available **and** if the
                 `safetensors` library is installed. If set to `True`, the model is forcibly loaded from `safetensors`
                 weights. If set to `False`, `safetensors` weights are not loaded.
-            use_flashpack (`bool`, *optional*, defaults to `False`):
-                If set to `True`, the model is first loaded from `flashpack` (https://github.com/fal-ai/flashpack)
-                weights if a compatible `.flashpack` file is found. If flashpack is unavailable or the `.flashpack`
-                file cannot be used, automatic fallback to the standard loading path (for example, `safetensors`).
             disable_mmap ('bool', *optional*, defaults to 'False'):
                 Whether to disable mmap when loading a Safetensors model. This option can perform better when the model
                 is on a network mount or hard drive, which may not handle the seeky-ness of mmap very well.
@@ -997,7 +982,6 @@ class ModelMixin(torch.nn.Module, PushToHubMixin):
         low_cpu_mem_usage = kwargs.pop("low_cpu_mem_usage", _LOW_CPU_MEM_USAGE_DEFAULT)
         variant = kwargs.pop("variant", None)
         use_safetensors = kwargs.pop("use_safetensors", None)
-        use_flashpack = kwargs.pop("use_flashpack", False)
         quantization_config = kwargs.pop("quantization_config", None)
         dduf_entries: Optional[Dict[str, DDUFEntry]] = kwargs.pop("dduf_entries", None)
         disable_mmap = kwargs.pop("disable_mmap", False)
@@ -1215,31 +1199,7 @@ class ModelMixin(torch.nn.Module, PushToHubMixin):
             from .modeling_pytorch_flax_utils import load_flax_checkpoint_in_pytorch_model
 
             model = load_flax_checkpoint_in_pytorch_model(model, resolved_model_file)
-
-        flashpack_file = None
-        if use_flashpack:
-            try:
-                flashpack_file = _get_model_file(
-                    pretrained_model_name_or_path,
-                    weights_name=_add_variant("model.flashpack", variant),
-                    cache_dir=cache_dir,
-                    force_download=force_download,
-                    proxies=proxies,
-                    local_files_only=local_files_only,
-                    token=token,
-                    revision=revision,
-                    subfolder=subfolder,
-                    user_agent=user_agent,
-                    commit_hash=commit_hash,
-                    dduf_entries=dduf_entries,
-                )
-            except EnvironmentError:
-                flashpack_file = None
-                logger.warning(
-                    "`use_flashpack` was specified to be True but not flashpack file was found. Resorting to non-flashpack alternatives."
-                )
-
-        if flashpack_file is None:
+        else:
             # in the case it is sharded, we have already the index
             if is_sharded:
                 resolved_model_file, sharded_metadata = _get_checkpoint_shard_files(
@@ -1255,7 +1215,6 @@ class ModelMixin(torch.nn.Module, PushToHubMixin):
                     dduf_entries=dduf_entries,
                 )
             elif use_safetensors:
-                logger.warning("Trying to load model weights with safetensors format.")
                 try:
                     resolved_model_file = _get_model_file(
                         pretrained_model_name_or_path,
@@ -1321,29 +1280,6 @@ class ModelMixin(torch.nn.Module, PushToHubMixin):
         if dtype_orig is not None:
             torch.set_default_dtype(dtype_orig)
 
-        if flashpack_file is not None:
-            from ..utils.flashpack_utils import load_flashpack
-
-            # Even when using FlashPack, we preserve `low_cpu_mem_usage` behavior by initializing
-            # the model with meta tensors. Since FlashPack cannot write into meta tensors, we
-            # explicitly materialize parameters before loading to ensure correctness and parity
-            # with the standard loading path.
-            if any(p.device.type == "meta" for p in model.parameters()):
-                model.to_empty(device="cpu")
-            load_flashpack(model, flashpack_file)
-            model.register_to_config(_name_or_path=pretrained_model_name_or_path)
-            model.eval()
-
-            if output_loading_info:
-                return model, {
-                    "missing_keys": [],
-                    "unexpected_keys": [],
-                    "mismatched_keys": [],
-                    "error_msgs": [],
-                }
-
-            return model
-
         state_dict = None
         if not is_sharded:
             # Time to load the checkpoint
@@ -1391,6 +1327,7 @@ class ModelMixin(torch.nn.Module, PushToHubMixin):
             keep_in_fp32_modules=keep_in_fp32_modules,
             dduf_entries=dduf_entries,
             is_parallel_loading_enabled=is_parallel_loading_enabled,
+            disable_mmap=disable_mmap,
         )
         loading_info = {
             "missing_keys": missing_keys,
@@ -1436,8 +1373,6 @@ class ModelMixin(torch.nn.Module, PushToHubMixin):
         if output_loading_info:
             return model, loading_info
 
-        logger.warning(f"Model till end {pretrained_model_name_or_path} loaded successfully")
-
         return model
 
     # Adapted from `transformers`.

src/diffusers/pipelines/pipeline_loading_utils.py

@@ -756,7 +756,6 @@ def load_sub_model(
     low_cpu_mem_usage: bool,
     cached_folder: Union[str, os.PathLike],
     use_safetensors: bool,
-    use_flashpack: bool,
     dduf_entries: Optional[Dict[str, DDUFEntry]],
     provider_options: Any,
     disable_mmap: bool,
@@ -839,9 +838,6 @@ def load_sub_model(
         loading_kwargs["variant"] = model_variants.pop(name, None)
         loading_kwargs["use_safetensors"] = use_safetensors
 
-        if is_diffusers_model:
-            loading_kwargs["use_flashpack"] = use_flashpack
-
         if from_flax:
             loading_kwargs["from_flax"] = True
 

src/diffusers/pipelines/pipeline_utils.py

@@ -243,7 +243,6 @@ class DiffusionPipeline(ConfigMixin, PushToHubMixin):
         variant: Optional[str] = None,
         max_shard_size: Optional[Union[int, str]] = None,
         push_to_hub: bool = False,
-        use_flashpack: bool = False,
         **kwargs,
     ):
         """
@@ -269,9 +268,7 @@ class DiffusionPipeline(ConfigMixin, PushToHubMixin):
                 Whether or not to push your model to the Hugging Face model hub after saving it. You can specify the
                 repository you want to push to with `repo_id` (will default to the name of `save_directory` in your
                 namespace).
-            use_flashpack (`bool`, *optional*, defaults to `False`):
-                Whether or not to use `flashpack` to save the model weights. Requires the `flashpack` library: `pip
-                install flashpack`.
+
             kwargs (`Dict[str, Any]`, *optional*):
                 Additional keyword arguments passed along to the [`~utils.PushToHubMixin.push_to_hub`] method.
         """
@@ -343,7 +340,6 @@ class DiffusionPipeline(ConfigMixin, PushToHubMixin):
             save_method_accept_safe = "safe_serialization" in save_method_signature.parameters
             save_method_accept_variant = "variant" in save_method_signature.parameters
             save_method_accept_max_shard_size = "max_shard_size" in save_method_signature.parameters
-            save_method_accept_flashpack = "use_flashpack" in save_method_signature.parameters
 
             save_kwargs = {}
             if save_method_accept_safe:
@@ -353,8 +349,6 @@ class DiffusionPipeline(ConfigMixin, PushToHubMixin):
             if save_method_accept_max_shard_size and max_shard_size is not None:
                 # max_shard_size is expected to not be None in ModelMixin
                 save_kwargs["max_shard_size"] = max_shard_size
-            if save_method_accept_flashpack:
-                save_kwargs["use_flashpack"] = use_flashpack
 
             save_method(os.path.join(save_directory, pipeline_component_name), **save_kwargs)
 
@@ -713,11 +707,6 @@ class DiffusionPipeline(ConfigMixin, PushToHubMixin):
                 If set to `None`, the safetensors weights are downloaded if they're available **and** if the
                 safetensors library is installed. If set to `True`, the model is forcibly loaded from safetensors
                 weights. If set to `False`, safetensors weights are not loaded.
-            use_flashpack (`bool`, *optional*, defaults to `False`):
-                If set to `True`, the model is first loaded from `flashpack` weights if a compatible `.flashpack` file
-                is found. If flashpack is unavailable or the `.flashpack` file cannot be used, automatic fallback to
-                the standard loading path (for example, `safetensors`). Requires the `flashpack` library: `pip install
-                flashpack`.
             use_onnx (`bool`, *optional*, defaults to `None`):
                 If set to `True`, ONNX weights will always be downloaded if present. If set to `False`, ONNX weights
                 will never be downloaded. By default `use_onnx` defaults to the `_is_onnx` class attribute which is
@@ -783,7 +772,6 @@ class DiffusionPipeline(ConfigMixin, PushToHubMixin):
         variant = kwargs.pop("variant", None)
         dduf_file = kwargs.pop("dduf_file", None)
         use_safetensors = kwargs.pop("use_safetensors", None)
-        use_flashpack = kwargs.pop("use_flashpack", False)
         use_onnx = kwargs.pop("use_onnx", None)
         load_connected_pipeline = kwargs.pop("load_connected_pipeline", False)
         quantization_config = kwargs.pop("quantization_config", None)
@@ -1073,7 +1061,6 @@ class DiffusionPipeline(ConfigMixin, PushToHubMixin):
                     low_cpu_mem_usage=low_cpu_mem_usage,
                     cached_folder=cached_folder,
                     use_safetensors=use_safetensors,
-                    use_flashpack=use_flashpack,
                     dduf_entries=dduf_entries,
                     provider_options=provider_options,
                     disable_mmap=disable_mmap,

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", "laplace"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp"] = "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 (`str`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
+        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
 
     Returns:
         `torch.Tensor`:

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", "laplace"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp"] = "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 (`str`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
+        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
 
     Returns:
         `torch.Tensor`:

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", "laplace"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp"] = "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 (`str`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
+        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
 
     Returns:
         `torch.Tensor`:
@@ -100,13 +100,14 @@ def betas_for_alpha_bar(
     return torch.tensor(betas, dtype=torch.float32)
 
 
-def rescale_zero_terminal_snr(alphas_cumprod: torch.Tensor) -> torch.Tensor:
+def rescale_zero_terminal_snr(alphas_cumprod):
     """
-    Rescales betas to have zero terminal SNR Based on (Algorithm 1)[https://huggingface.co/papers/2305.08891]
+    Rescales betas to have zero terminal SNR Based on https://huggingface.co/papers/2305.08891 (Algorithm 1)
+
 
     Args:
-        alphas_cumprod (`torch.Tensor`):
-            The alphas cumulative products that the scheduler is being initialized with.
+        betas (`torch.Tensor`):
+            the betas that the scheduler is being initialized with.
 
     Returns:
         `torch.Tensor`: rescaled betas with zero terminal SNR
@@ -141,11 +142,11 @@ 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 0.00085):
+        beta_start (`float`, defaults to 0.0001):
             The starting `beta` value of inference.
-        beta_end (`float`, defaults to 0.0120):
+        beta_end (`float`, defaults to 0.02):
             The final `beta` value.
-        beta_schedule (`str`, defaults to `"scaled_linear"`):
+        beta_schedule (`str`, defaults to `"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*):
@@ -178,8 +179,6 @@ 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]
@@ -191,15 +190,15 @@ class CogVideoXDDIMScheduler(SchedulerMixin, ConfigMixin):
         num_train_timesteps: int = 1000,
         beta_start: float = 0.00085,
         beta_end: float = 0.0120,
-        beta_schedule: Literal["linear", "scaled_linear", "squaredcos_cap_v2"] = "scaled_linear",
+        beta_schedule: str = "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: Literal["epsilon", "sample", "v_prediction"] = "epsilon",
+        prediction_type: str = "epsilon",
         clip_sample_range: float = 1.0,
         sample_max_value: float = 1.0,
-        timestep_spacing: Literal["linspace", "leading", "trailing"] = "leading",
+        timestep_spacing: str = "leading",
         rescale_betas_zero_snr: bool = False,
         snr_shift_scale: float = 3.0,
     ):
@@ -209,15 +208,7 @@ 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)
@@ -247,7 +238,7 @@ 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: int, prev_timestep: int) -> torch.Tensor:
+    def _get_variance(self, timestep, prev_timestep):
         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
@@ -274,11 +265,7 @@ class CogVideoXDDIMScheduler(SchedulerMixin, ConfigMixin):
         """
         return sample
 
-    def set_timesteps(
-        self,
-        num_inference_steps: int,
-        device: Optional[Union[str, torch.device]] = None,
-    ) -> None:
+    def set_timesteps(self, num_inference_steps: int, device: Union[str, torch.device] = None):
         """
         Sets the discrete timesteps used for the diffusion chain (to be run before inference).
 
@@ -330,7 +317,7 @@ class CogVideoXDDIMScheduler(SchedulerMixin, ConfigMixin):
         sample: torch.Tensor,
         eta: float = 0.0,
         use_clipped_model_output: bool = False,
-        generator: Optional[torch.Generator] = None,
+        generator=None,
         variance_noise: Optional[torch.Tensor] = None,
         return_dict: bool = True,
     ) -> Union[DDIMSchedulerOutput, Tuple]:
@@ -341,7 +328,7 @@ class CogVideoXDDIMScheduler(SchedulerMixin, ConfigMixin):
         Args:
             model_output (`torch.Tensor`):
                 The direct output from learned diffusion model.
-            timestep (`int`):
+            timestep (`float`):
                 The current discrete timestep in the diffusion chain.
             sample (`torch.Tensor`):
                 A current instance of a sample created by the diffusion process.
@@ -500,5 +487,5 @@ class CogVideoXDDIMScheduler(SchedulerMixin, ConfigMixin):
         velocity = sqrt_alpha_prod * noise - sqrt_one_minus_alpha_prod * sample
         return velocity
 
-    def __len__(self) -> int:
+    def __len__(self):
         return self.config.num_train_timesteps

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", "laplace"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp"] = "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 (`str`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
+        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
 
     Returns:
         `torch.Tensor`:

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", "laplace"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp"] = "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 (`str`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
+        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
 
     Returns:
         `torch.Tensor`:

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", "laplace"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp"] = "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 (`str`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
+        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
 
     Returns:
         `torch.Tensor`:
@@ -192,12 +192,7 @@ 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",
@@ -215,15 +210,7 @@ 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)
@@ -350,14 +337,7 @@ 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:
         """
@@ -492,10 +472,7 @@ 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
@@ -544,10 +521,7 @@ 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

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", "laplace"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp"] = "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 (`str`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
+        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
 
     Returns:
         `torch.Tensor`:
@@ -202,12 +202,7 @@ 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",
@@ -225,15 +220,7 @@ 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)
@@ -363,14 +350,7 @@ 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:
         """

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", "laplace"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp"] = "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 (`str`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
+        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
 
     Returns:
         `torch.Tensor`:

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", "laplace"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp"] = "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 (`str`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
+        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
 
     Returns:
         `torch.Tensor`:

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", "laplace"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp"] = "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 (`str`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
+        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
 
     Returns:
         `torch.Tensor`:

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", "laplace"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp"] = "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 (`str`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
+        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
 
     Returns:
         `torch.Tensor`:

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", "laplace"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp"] = "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 (`str`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
+        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
 
     Returns:
         `torch.Tensor`:

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", "laplace"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp"] = "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 (`str`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
+        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
 
     Returns:
         `torch.Tensor`:

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", "laplace"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp"] = "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 (`str`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
+        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
 
     Returns:
         `torch.Tensor`:

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", "laplace"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp"] = "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 (`str`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
+        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
 
     Returns:
         `torch.Tensor`:

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", "laplace"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp"] = "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 (`str`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
+        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
 
     Returns:
         `torch.Tensor`:

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", "laplace"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp"] = "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 (`str`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
+        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
 
     Returns:
         `torch.Tensor`:

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", "laplace"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp"] = "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 (`str`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
+        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
 
     Returns:
         `torch.Tensor`:

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", "laplace"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp"] = "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 (`str`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
+        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
 
     Returns:
         `torch.Tensor`:

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", "laplace"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp"] = "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 (`str`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
+        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
 
     Returns:
         `torch.Tensor`:

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", "laplace"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp"] = "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 (`str`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
+        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
 
     Returns:
         `torch.Tensor`:

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", "laplace"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp"] = "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 (`str`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
+        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
 
     Returns:
         `torch.Tensor`:

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", "laplace"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp"] = "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 (`str`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
+        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
 
     Returns:
         `torch.Tensor`:

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", "laplace"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp"] = "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 (`str`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
+        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
 
     Returns:
         `torch.Tensor`:

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", "laplace"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp"] = "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 (`str`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
+        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
 
     Returns:
         `torch.Tensor`:

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", "laplace"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp"] = "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 (`str`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
+        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
 
     Returns:
         `torch.Tensor`:
@@ -226,7 +226,6 @@ 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.")
@@ -246,8 +245,6 @@ 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)
@@ -316,12 +313,8 @@ class UniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
         self._begin_index = begin_index
 
     def set_timesteps(
-        self,
-        num_inference_steps: Optional[int] = None,
-        device: Union[str, torch.device] = None,
-        sigmas: Optional[List[float]] = None,
-        mu: Optional[float] = None,
-    ):
+        self, num_inference_steps: int, device: Optional[Union[str, torch.device]] = None, mu: Optional[float] = None
+    ) -> None:
         """
         Sets the discrete timesteps used for the diffusion chain (to be run before inference).
 
@@ -330,24 +323,13 @@ 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)
@@ -372,9 +354,8 @@ 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)
@@ -394,8 +375,6 @@ 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)
@@ -410,8 +389,6 @@ 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)
@@ -426,18 +403,9 @@ class UniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
                 )
             sigmas = np.concatenate([sigmas, [sigma_last]]).astype(np.float32)
         elif self.config.use_flow_sigmas:
-            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
+            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()
             timesteps = (sigmas * self.config.num_train_timesteps).copy()
             if self.config.final_sigmas_type == "sigma_min":
                 sigma_last = sigmas[-1]
@@ -449,8 +417,6 @@ 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
@@ -480,43 +446,6 @@ 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:
         """

src/diffusers/utils/flashpack_utils.py

@@ -1,81 +0,0 @@
-import json
-import os
-from typing import Optional
-
-from ..utils import _add_variant
-from .import_utils import is_flashpack_available
-from .logging import get_logger
-
-
-logger = get_logger(__name__)
-
-
-def save_flashpack(
-    model,
-    save_directory: str,
-    variant: Optional[str] = None,
-    is_main_process: bool = True,
-):
-    """
-    Save model weights in FlashPack format along with a metadata config.
-
-    Args:
-        model: Diffusers model instance
-        save_directory (`str`): Directory to save weights
-        variant (`str`, *optional*): Model variant
-    """
-    if not is_flashpack_available():
-        raise ImportError(
-            "The `use_flashpack=True` argument requires the `flashpack` package. "
-            "Install it with `pip install flashpack`."
-        )
-
-    from flashpack import pack_to_file
-
-    os.makedirs(save_directory, exist_ok=True)
-
-    weights_name = _add_variant("model.flashpack", variant)
-    weights_path = os.path.join(save_directory, weights_name)
-    config_path = os.path.join(save_directory, "flashpack_config.json")
-
-    try:
-        target_dtype = getattr(model, "dtype", None)
-        logger.warning(f"Dtype used for FlashPack save: {target_dtype}")
-
-        # 1. Save binary weights
-        pack_to_file(model, weights_path, target_dtype=target_dtype)
-
-        # 2. Save config metadata (best-effort)
-        if hasattr(model, "config"):
-            try:
-                if hasattr(model.config, "to_dict"):
-                    config_data = model.config.to_dict()
-                else:
-                    config_data = dict(model.config)
-
-                with open(config_path, "w") as f:
-                    json.dump(config_data, f, indent=4)
-
-            except Exception as config_err:
-                logger.warning(f"FlashPack weights saved, but config serialization failed: {config_err}")
-
-    except Exception as e:
-        logger.error(f"Failed to save weights in FlashPack format: {e}")
-        raise
-
-
-def load_flashpack(model, flashpack_file: str):
-    """
-    Assign FlashPack weights from a file into an initialized PyTorch model.
-    """
-    if not is_flashpack_available():
-        raise ImportError("FlashPack weights require the `flashpack` package. Install with `pip install flashpack`.")
-
-    from flashpack import assign_from_file
-
-    logger.warning(f"Loading FlashPack weights from {flashpack_file}")
-
-    try:
-        assign_from_file(model, flashpack_file)
-    except Exception as e:
-        raise RuntimeError(f"Failed to load FlashPack weights from {flashpack_file}") from e

src/diffusers/utils/import_utils.py

@@ -231,7 +231,6 @@ _aiter_available, _aiter_version = _is_package_available("aiter")
 _kornia_available, _kornia_version = _is_package_available("kornia")
 _nvidia_modelopt_available, _nvidia_modelopt_version = _is_package_available("modelopt", get_dist_name=True)
 _av_available, _av_version = _is_package_available("av")
-_flashpack_available, _flashpack_version = _is_package_available("flashpack")
 
 
 def is_torch_available():
@@ -426,10 +425,6 @@ def is_av_available():
     return _av_available
 
 
-def is_flashpack_available():
-    return _flashpack_available
-
-
 # docstyle-ignore
 FLAX_IMPORT_ERROR = """
 {0} requires the FLAX library but it was not found in your environment. Checkout the instructions on the
@@ -947,16 +942,6 @@ def is_aiter_version(operation: str, version: str):
     return compare_versions(parse(_aiter_version), operation, version)
 
 
-@cache
-def is_flashpack_version(operation: str, version: str):
-    """
-    Compares the current flashpack version to a given reference with an operation.
-    """
-    if not _flashpack_available:
-        return False
-    return compare_versions(parse(_flashpack_version), operation, version)
-
-
 def get_objects_from_module(module):
     """
     Returns a dict of object names and values in a module, while skipping private/internal objects