modelscope / modelscope/DiffSynth-Studio

Using WAN 2.1 image2video, we found that when the original-sized image is used as the first frame input, the output video appears enlarged and cropped around the edges.

Open
#625 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

The input key frame JPG has a native resolution of 832 pixels wide and 480 pixels high, but in the output video, the frame appears slightly enlarged, with cropping around the edges (the top and bottom cropping is particularly noticeable). What could be causing this?

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 WAN 2.1 image2video case with the 832×480 JPG, then trace the image preprocessing and video frame-size handling to identify where scaling or cropping occurs. Done means the cause is confirmed and the unintended enlargement and edge cropping are corrected or clearly documented.

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
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.