huggingface / huggingface/diffusers

Modular Diffusers 🧨

Open
#13,295 20 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
34.5k
Forks
7.3k
Avg merge
3d 3h
Merged PRs (30d)
91

Description

Hey folks 👋

We recently released Modular Diffusers, which gives developers the flexibility to reuse existing pipeline blocks in different workflows and also easily implement custom "modular" blocks.

While the DiffusionPipeline class has helped establish a standard abstraction layer, it has also been a bit rigid when it comes to extensions. With Modular Diffusers, we want to give our users the utmost flexibility while also complementing our standard pipeline interfaces.

To improve modular, we are soliciting contributions from the community. Contributions for modular can be manifold:

  • Implement a modular version of an existing pipeline
  • Implement a cool custom modular pipeline and share it with us
  • Identify a feature that could be improved in modular and improve it

We're looking forward to hearing from you!

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the Modular Diffusers announcement linked in the issue to understand the modular pipeline concept. The issue does not name files or tests; done would mean implementing an existing pipeline, sharing a custom modular pipeline, or improving a specific modular feature and presenting the contribution to the project.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Active
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.