modelscope / modelscope/DiffSynth-Studio
8卡4090*48g, lora微调wan2.1 14B I2V模型OOM，怎么解决？
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
This issue has no description.
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
The issue has no body, files, tests, or entry points, and reports an out-of-memory failure during LoRA fine-tuning of the Wan2.1 14B I2V model on 8×4090 48 GB GPUs. Start by locating the Wan2.1 I2V fine-tuning entry point and collecting the missing configuration and traceback; done means a reproducible memory-safe configuration or a documented explanation of the required changes.
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
- 25/100