modelscope / modelscope/DiffSynth-Studio

Does WAN2.1-VACE-1.3B support the vace_video and vace_mask_video parameters? Can the height=480, width=832 be adjusted to a vertical screen size?

Open
#718 1 comment 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

1.Does WAN2.1-VACE-1.3B support the vace_video and vace_mask_video parameters? The official documentation states that they are supported. However, if the vace_mask_video parameter is entered with height=480 and width=832, an error message will be displayed, indicating that the dimension mismatch in the concat operation.
2.Why does a dimension mismatch error occur when I adjust the screen to vertical screen size, that is, when the height is larger than the width? The only successful run was height=416, width=240, but it still ran in landscape mode and was full of noise.

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

No files or tests are named. Reproduce the WAN2.1-VACE-1.3B case with vace_video and vace_mask_video at height=480, width=832 and with vertical dimensions, then locate the concat path that reports the mismatch. Done means determining whether both parameters and vertical video sizes are supported and explaining the dimension constraints.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.