Introducing Modular Diffusers – Composable Building Blocks for Diffusion Pipelines

Modular Diffusers introduces a new way to build diffusion pipelines by composing reusable blocks. Instead of writing entire pipelines from scratch, you can mix and match blocks to create workflows tailored to your needs! This complements the existing DiffusionPipeline class with a more flexible, composable alternative.

In this post, we’ll walk through how Modular Diffusers works — from the familiar API to run a modular pipeline, to building fully custom blocks and composing them into your own workflow. We’ll also show how it integrates with Mellon, a node-based visual workflow interface that you can use to wire Modular Diffusers blocks together.

Table of contents

Quickstart

Here is a simple example of how to run inference with FLUX.2 Klein 4B using pre-built blocks:

import torch
from diffusers import ModularPipeline


pipe = ModularPipeline.from_pretrained(
    "black-forest-labs/FLUX.2-klein-4B"
)

pipe.load_components(torch_dtype=torch.bfloat16)
pipe.to("cuda")


image = pipe(
    prompt="a serene landscape at sunset",
    num_inference_steps=4,
).images[0]

image.save("output.png")

You get the same results as with a standard DiffusionPipeline, but the pipeline is very different under the hood: it’s composed of flexible blocks — text encoding, image encoding, denoising, and decoding — that you can inspect directly:

print(pipe.blocks)

Flux2KleinAutoBlocks(
  ...
  Sub-Blocks:
    [0] text_encoder (Flux2KleinTextEncoderStep)
    [1] vae_encoder (Flux2KleinAutoVaeEncoderStep)
    [2] denoise (Flux2KleinCoreDenoiseStep)
    [3] decode (Flux2DecodeStep)
)

Each block is self-contained with its own inputs and outputs. You can run any block independently as its own pipeline, or add, remove, and swap blocks freely — they dynamically recompose to work with whatever blocks remain. Use .init_pipeline() to convert blocks into a runnable pipeline, and .load_components() to load the model weights.

blocks = pipe.blocks


text_blocks = blocks.sub_blocks.pop("text_encoder")


text_pipe = text_blocks.init_pipeline("black-forest-labs/FLUX.2-klein-4B")


text_pipe.load_components(torch_dtype=torch.bfloat16)
text_pipe.to("cuda")
prompt_embeds = text_pipe(prompt="a serene landscape at sunset").prompt_embeds



remaining_pipe = blocks.init_pipeline("black-forest-labs/FLUX.2-klein-4B")
remaining_pipe.load_components(torch_dtype=torch.bfloat16)
remaining_pipe.to("cuda")
image = remaining_pipe(prompt_embeds=prompt_embeds, num_inference_steps=4).images[0]

For more on block types, composition patterns, lazy loading, and memory management with ComponentsManager, check out the Modular Diffusers documentation.

Custom Blocks

Modular Diffusers really shines when creating your own blocks. A custom block is a Python class that defines its components, inputs, outputs, and computation logic — and once defined, you can plug it into any workflow.

Writing a Custom Block

Here’s an example block that extracts depth maps from images using Depth Anything V2.

class DepthProcessorBlock(ModularPipelineBlocks):
    @property
    def expected_components(self):
        return [
            ComponentSpec("depth_processor", DepthPreprocessor,
                          pretrained_model_name_or_path="depth-anything/Depth-Anything-V2-Large-hf")
        ]

    @property
    def inputs(self):
        return [
            InputParam("image", required=True,
                       description="Image(s) to extract depth maps from"),
        ]

    @property
    def intermediate_outputs(self):
        return [
            OutputParam("control_image", type_hint=torch.Tensor,
                        description="Depth map(s) of input image(s)"),
        ]

    @torch.no_grad()
    def __call__(self, components, state):
        block_state = self.get_block_state(state)
        depth_map = components.depth_processor(block_state.image)
        block_state.control_image = depth_map.to(block_state.device)
        self.set_block_state(state, block_state)
        return components, state

• expected_components defines what models the block needs — in this case, a depth estimation model. The pretrained_model_name_or_path parameter sets a default Hub repo to load from, so load_components automatically fetches the depth model unless you override it in modular_model_index.json.
• inputs and intermediate_outputs define what goes in and comes out.
• __call__ is where the computation logic lives.

Composing Blocks into Workflows

Let’s use this block with Qwen’s ControlNet workflow. Extract the ControlNet workflow and insert the depth block at the beginning:

pipe = ModularPipeline.from_pretrained("Qwen/Qwen-Image")

print(pipe.blocks.available_workflows)








blocks = pipe.blocks.get_workflow("controlnet_text2image")

print(blocks)



blocks.sub_blocks.insert("depth", DepthProcessorBlock(), 0)


blocks.sub_blocks['depth'].doc

Blocks in a sequence share data automatically: the depth block’s control_image output flows to downstream blocks that need it, and its image input becomes a pipeline input since no earlier block provides it.

from diffusers import ComponentsManager, AutoModel
from diffusers.utils import load_image



manager = ComponentsManager()

pipeline = blocks.init_pipeline("Qwen/Qwen-Image", components_manager=manager)
pipeline.load_components(torch_dtype=torch.bfloat16)




controlnet = AutoModel.from_pretrained("InstantX/Qwen-Image-ControlNet-Union", torch_dtype=torch.bfloat16)
pipeline.update_components(controlnet=controlnet)


image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg")
output = pipeline(
    prompt="an astronaut hatching from an egg, detailed, fantasy, Pixar, Disney",
    image=image,
).images[0]

Sharing Custom Blocks on the Hub

You can publish your custom block to the Hub so anyone can load it with trust_remote_code=True. We’ve created a template to get you started — check out the Building Custom Blocks guide for the full walkthrough.

pipeline.save_pretrained(local_dir, repo_id="your-username/your-block-name", push_to_hub=True)

The DepthProcessorBlock from this post is published at diffusers/depth-processor-custom-block — you can load and use it directly:

from diffusers import ModularPipelineBlocks

depth_block = ModularPipelineBlocks.from_pretrained(
    "diffusers/depth-processor-custom-block", trust_remote_code=True
)

We’ve published a collection of ready-to-use custom blocks here.

Modular Repositories

ModularPipeline.from_pretrained works with any existing Diffusers repo out of the box, but Modular Diffusers also introduces a new kind of repo: the Modular Repository.

A modular repository is able to reference components from their original model repos. For example, diffusers/flux2-bnb-4bit-modular contains a quantized transformer and loads the remaining components from the original repo.

{
    "transformer": [
        "diffusers", 
        "Flux2Transformer2DModel", 
        {
            "pretrained_model_name_or_path": "diffusers/flux2-bnb-4bit-modular",
            "subfolder": "transformer",
            "type_hint": ["diffusers", "Flux2Transformer2DModel"]
        }
    ],
    "vae": [
        "diffusers", 
        "AutoencoderKLFlux2", 
        {
            "pretrained_model_name_or_path": "black-forest-labs/FLUX.2-dev",
            "subfolder": "vae",
            "type_hint": ["diffusers", "AutoencoderKLFlux2"]
        }
    ],
    ...
}

Modular repositories can also host custom pipeline blocks as Python code and visual UI configurations for tools like Mellon — all in one place.

Community Pipelines

The community has already started building complete pipelines with Modular Diffusers and publishing them on the Hub, with model weights and ready-to-run code.

• Krea Realtime Video — A 14B parameter real-time video generation model distilled from Wan 2.1, achieving 11fps on a single B200 GPU. It supports text-to-video, video-to-video, and streaming video-to-video — all built as modular blocks. Users can modify prompts mid-generation, restyle videos on-the-fly, and see first frames within 1 second.

import torch
from diffusers import ModularPipeline

pipe = ModularPipeline.from_pretrained("krea/krea-realtime-video", trust_remote_code=True)
pipe.load_components(
    trust_remote_code=True, 
    device_map="cuda",
    torch_dtype={"default": torch.bfloat16, "vae": torch.float16}
)

• Waypoint-1 — A 2.3B parameter real-time diffusion world model from Overworld. It autoregressively generates interactive worlds from control inputs and text prompts — you can explore and interact with generated environments in real time on consumer hardware.

Teams can build novel architectures, package them as blocks, and publish the entire pipeline on the Hub for anyone to use with ModularPipeline.from_pretrained.

Check out the full collection of community pipelines for more.

Integration with Mellon

💡 Mellon is in early development and not ready for production use yet. Consider this a sneak peek of how the integration works!

Mellon is a node graph interface integrated with Modular Diffusers. If you’re familiar with node-based tools like ComfyUI, you’ll feel right at home — but there are some key differences:

• Dynamic nodes — Instead of dozens of model-specific nodes, we have a small set of nodes that automatically adapt their interface based on the model you select. Learn them once, use them with any model.
• Single-node workflows — Thanks to Modular Diffusers’ composable block system, you can collapse an entire pipeline into a single node. Run multiple workflows on the same canvas without the clutter.
• Hub integration out of the box — Custom blocks published to the Hugging Face Hub work instantly in Mellon. We provide a utility function to automatically generate the node interface from your block definition — no UI code required.

This integration is possible because every block exposes the same properties (inputs, intermediate_outputs, expected_components). This consistent API means Mellon can automatically generate a node’s UI from any block definition and compose blocks into higher-level nodes.

For example, diffusers/FLUX.2-klein-4B-modular contains a pipeline definition, component references, and a mellon_pipeline_config.json — all in one repo. Load it in Python with ModularPipeline.from_pretrained("diffusers/FLUX.2-klein-4B-modular") or in Mellon to create either a single-node or multi-node workflow.

Here’s a quick example. We add a Gemini prompt expansion node — hosted as a modular repo at diffusers/gemini-prompt-expander-mellon — to an existing text-to-image workflow:

1. Drag in a Dynamic Block node and enter the repo_id (i.e. diffusers/gemini-prompt-expander-mellon)
2. Click LOAD CUSTOM BLOCK — the node automatically grows a textbox for your prompt input and an output socket named “prompt”, all configured from the repo
3. Type a short prompt, connect the output to the Encode Prompt node, and run

Gemini expands your short prompt into a detailed description before generating the image. No code, no configuration — just a Hub repo id.

This is just one example. For a detailed walkthrough, check out the Mellon x Modular Diffusers guide. You can also check out this video!

Conclusion

Modular Diffusers brings the composability and flexibility the community has been asking for, without compromising the features that make Diffusers powerful. It’s still early — we want your input to shape what comes next. Give it a try and tell us what works, what doesn’t, and what’s missing.

Resources

Thanks to Chun Te Lee for the thumbnail, and to Poli, Pedro, Lysandre, Linoy, Aritra, and Steven for their thoughtful reviews.