[Feature] VisualCloze: A universal image generation framework that can support a wide range of in-domain tasks and generalize to unseen ones.

[nitinmukesh]

Checklist

• 1. If the issue you raised is not a feature but a question, please raise a discussion at https://github.com/mit-han-lab/nunchaku/discussions/new/choose. Otherwise, it will be closed.
• 2. I will do my best to describe the issue in English.

Motivation

Please add support in Nunchaku
https://github.com/lzyhha/VisualCloze

Models
https://huggingface.co/VisualCloze/VisualClozePipeline-384
https://huggingface.co/VisualCloze/VisualClozePipeline-512

I tried the demo and it's very good.

Related resources

Support in diffusers is added
huggingface/diffusers#11377

It is based on Flux so may be easy to implement

[github-actions]

This issue has been automatically closed due to 30-day inactivity. Please feel free to reopen it if needed.