modelscope / modelscope/DiffSynth-Studio
[Question] Controlnet for Qwen-image/Wan2.2 planned?
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
Hi, I think Qwen image is better than flux dev for photo realism (I think flux dev maybe have trained both for realism and animation or 3D, so some times it fails to generate realistic image, little unnatural).
there are Multi modal Controlnets for Flux-dev but not for Qwen Image yet.
I wonder Diffsynth studio would have any plan for it
I have trained my own canny/depth/seg controlnets for flux-dev using diffusers library but the generated result images by the 3 merged multi controlnets were slightly not satisfactory.
I think Contrlnet for Qwen Image would show much better results!
Plus, Controlnet for Wan 2.2 also must be great!
Thank you!
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
This is a planning request for ControlNet support for Qwen Image and Wan2.2, but it names no files, tests, entry points, or acceptance criteria. Start by determining whether either model is supported in the project and where model integrations are implemented; completion would require an agreed scope and maintainers' direction.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100