modelscope / modelscope/DiffSynth-Studio
wan2.2 training 的时候，无法支持batch_size > 1 吗
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
同时，unified_dataset的返回中是PIL.Image的list。
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 at the WAN2.2 training entry point described in the issue and inspect unified_dataset, whose output is a list of PIL.Image objects. Reproduce the behavior with batch_size greater than 1 and trace where only the first item is selected. Done means the training path processes every image in the batch without dropping items.
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
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100