Repository navigation
[Model integration] Add Hy-Nomas support to Diffusers #15113
Description
Model/Pipeline/Scheduler description
Hi Diffusers maintainers,
I'm a member of the Hy-Nomas team. We would like to contribute Hy-Nomas inference support to Diffusers.
The implementation includes:
- A modular pipeline, Hy-Nomas transformer, and PixelUMM decoder.
- Plain and structured prompts, camera conditioning, and multi-turn continuation.
- Checkpoint conversion, tests, and usage documentation.
Implementation branch:
https://github.com/jiaxiangc/diffusers/tree/hy-nomas
The work was AI-assisted and reviewed using the repository's self-review skill. Local validation includes focused CPU tests and a pixel-identical 10-second comparison with the original implementation under matched inference settings.
I am also submitting a companion PR so that the proposed scope and implementation can be reviewed together. I will add the PR link here once it is created.
We welcome your feedback on the integration scope and design and are happy to adjust the implementation.
PR link: #15114
Open source status
- The model implementation is available.
- The model weights are available (Only relevant if addition is not a scheduler).
Provide useful links for the implementation
No response
Activity
github-actions commentedon Oct 23, 2026
Thanks for the request!
How new model support works in Diffusers
We're a small team, and our review queue shouldn't be what decides whether a model is usable in Diffusers. With Modular Diffusers, a pipeline can live as remote code in any Hub repo and load straight from there with
from_pretrained.🛠️ Want to bring this model to Diffusers?
Please start with a Hub repo — you don't need anything from us to do that, and people can use it immediately. From there we decide how to support it: we might work with the authors, upstream an existing community version, or just point people at the one on the Hub. The pipelines we integrate are usually the ones people are already running.
Tag
@asomozawhen you have something to share — we'll give feedback on the implementation, help get it in front of people, and add the ones we like to our hand-picked Modular Pipelines collection. Tell us where you hit friction along the way, too: confusing APIs, missing docs, bugs. That feedback is worth as much to us as the pipeline.👋 Are you an author of the model? We'd love to hear from you — comment here and we'll help you pick the path that fits.
📚 Quickstart · Building custom blocks — template repo, and how to publish to the Hub · Modular Pipelines and Custom Blocks — examples to crib from
This is an automated message.