modelscope / modelscope/DiffSynth-Studio
Wan 2.2 TI2V lora训练速度
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
你好，TI2V 5B lora的训练速度很慢是正常吗？平均下来bz 16 12s/step。是哪里需要再修改什么吗？
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 with the Wan 2.2 TI2V 5B LoRA training setup described in the issue and reproduce the reported batch size 16, 12 seconds per step result. Compare the observed speed with the project's expected training behavior and inspect the available training configuration for relevant settings. Done means determining whether the performance is expected and identifying the configuration or implementation area responsible if it is not.
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
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100