modelscope / modelscope/DiffSynth-Studio

Inpainting or swapping using Wan VACE

Open
#622 3 comments 0 reactions 0 assignees View on GitHub

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

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. 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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.