modelscope / modelscope/DiffSynth-Studio

How to choose the resolution of training data in Wan2.1

Open
#531 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

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

  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

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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.