modelscope / modelscope/DiffSynth-Studio
显存占用明显大于diffusers框架
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
当使用Wan2.1-VACE-1.3B模型推理相同的视频时（81帧，480*832）时，diffsynth的显存占用（34G）显著高于diffusers框架推理（23G），请问可能是哪些原因导致的呢？感谢
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
Reproduce inference with Wan2.1-VACE-1.3B using 81 frames at 480×832, and compare DiffSynth-Studio's 34G usage with diffusers' 23G usage. The issue names no files, tests, or entry points, so first identify the corresponding inference paths and measure where memory differs. Done means explaining the discrepancy and identifying a concrete correction or limitation.
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
- 30/100