thu-ml / thu-ml/TurboDiffusion
提示词控制有点欠缺
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 3.7k
- Forks
- 277
- Avg merge
- 2h 57m
- Merged PRs (30d)
- 2
Description
我测了下，速度提升了非常多，然后画面质量也挺好的，但是好像提示词控制不是很好，不知道是量化、步数蒸馏还是SLA的问题，如果是步数蒸馏导致提示词控制差了，能否用减少步数少点的cache机制来代替步数蒸馏？
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 files, tests, or entry points are identified in the issue. First investigate whether quantization, step distillation, or SLA is responsible for the reported prompt-control problem, then define a reproducible quality measure and compare it with the speed improvement; the issue is done only when prompt control improves without losing the stated acceleration.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100