modelscope / modelscope/DiffSynth-Studio
微调后的模型不支持多卡推理吗？
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
全量微调后pipe.dit.load_state_dict(state_dict)，开启use_usp=True，8卡推理后生成的视频全是花屏。
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 issue with full fine-tuning, pipe.dit.load_state_dict(state_dict), use_usp=True, and 8-card inference. Trace the model-loading and multi-card inference path to determine why the generated video becomes corrupted. Done means the same setup produces a correctly rendered video.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- distributed-systems, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100