modelscope / modelscope/DiffSynth-Studio
为什么max_timestep_boundary和switch_DiT_boundary不同？
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
您好，我想请问一下，在训练时high noise和low noise模型使用不同的采样时间边界，为什么推理时switch_DiT_boundary不沿用0.358这个边界而是新值0.875呢？
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 mentions the training boundary max_timestep_boundary and the inference boundary switch_DiT_boundary, including values 0.358 and 0.875. Start by locating where these settings are defined or used; done would be a clear explanation of why training and inference use different boundaries.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100