modelscope / modelscope/DiffSynth-Studio
wan2.2-vace模型decoder部分会oom
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
运行其他wan2.2相关模型都可以在H20上顺利推理，但vace模型会在运行完50步diffusion后oom，调小resolution和frame number并没有帮助
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
No file, test, or entry point is named. Reproduce wan2.2-vace inference on an H20 and inspect the decoder after 50 diffusion steps, comparing it with the other wan2.2 models. Done means the same inference completes without an out-of-memory failure, with the relevant resolution and frame settings recorded.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning, performance
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100