modelscope / modelscope/DiffSynth-Studio
How to load 3 wan2.2 dit and avoid the OOM error?
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
I have trained my own wan2.2 dits which separate the timesteps into 3 stage, resulting in 3 different dits.
However, when i load them in the original inference script, it will cause OOM error when load these dits.
How to avoid it ?
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 reviewing the original inference script and reproducing the out-of-memory error while loading the three trained Wan 2.2 DITs. Determine how loading the three stages affects memory, and consider the issue complete when the three DITs can be used without an OOM error.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100