modelscope / modelscope/DiffSynth-Studio
train_scale_cfg
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
set train_scale_cfg=4.0 processed 3000 video, after train, the result still bad; similar to uncfg train;
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
Start by reproducing the reported training setup with train_scale_cfg=4.0 and the stated 3,000 videos. Compare the result with an uncfg training run and document the configuration, observed output, and whether the setting changes behavior; the issue needs a clearer reproduction and expected result before implementation can be scoped.
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
- Active
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100