modelscope / modelscope/DiffSynth-Studio
Inpainting or swapping using Wan VACE
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 tried to perform video inpainting/swapping with Wan VACE, but unfortunately the results were poor. For example, if I provide a video with a gray mask as a 'vace_video' argument, and a 'vace_reference_image', the output is still gray in the mask area. I tried other variants like providing a white mask, but it's even worse.
Hence, how should be the input vace_video prepared?
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
Start by reproducing the reported case with Wan VACE using a gray or white mask in vace_video and a vace_reference_image. Determine the required vace_video preparation and verify that the generated output no longer leaves the masked area gray.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100