Add support to Meissonic

[viiika]

Meissonic is a non-autoregressive mask image modeling text-to-image synthesis model that can generate high-resolution images. It is designed to run on consumer graphics cards.

The model checkpoint can be found in https://huggingface.co/MeissonFlow/Meissonic
The inference code can be found in https://github.com/viiika/Meissonic
The paper can be found in https://arxiv.org/abs/2410.08261

Anyone interested in implementing this?

[protimroy]

What kind of support are you looking for?

[viiika]

What kind of support are you looking for?

Just to integrate the related pipeline, schedule, transformer backbone to diffusers, so that if one wants to inference with Meissonic, simply by importing diffusers instead of cloning the source code.

[protimroy]

I can attempt (:

[viiika]

I can attempt (:

Wow, thx a lot! Feel free to add your name on the first line of the copyright if you’d like. If you need further assistance or clarification, please let me know.

[viiika]

I can attempt (:

I submitted the relevant codes in #9875.

[protimroy]

ok

[github-actions]

This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread.

Please note that issues that do not follow the contributing guidelines are likely to be ignored.