modelscope / modelscope/DiffSynth-Studio
How to choose the resolution of training data in Wan2.1
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
When training a 720P Wan model, should only 720P resolution video data be used, or should 480P and 720P video data be mixed during the training process? What is the rationale behind this approach?
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
Review the Wan2.1 training guidance and the issue's 480P and 720P data scenarios first. Document whether resolutions should be mixed for 720P training, explain the rationale, and make the recommendation clear enough for someone preparing a training dataset.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- machine-learning
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100