modelscope / modelscope/DiffSynth-Studio
Wan2.2-5B-TI2V LoRA训练只支持固定的宽高比吗？
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
如题，看训练的脚本以及VideoDataset似乎会将训练视频缩放到指定宽高，推理的时候视频宽高比差异过大怎么办？
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 reading the training script and VideoDataset referenced in the issue to confirm how training dimensions and aspect ratios are handled. Then inspect the inference entry point for its behavior with substantially different video dimensions; done should clarify the supported ratio behavior and identify any required documentation or implementation change.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100