modelscope / modelscope/DiffSynth-Studio
lora_base_model疑问
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，感谢您们的开源工作。
我是一个初学者，有一个疑问，我发现 lora_base_model 好像只支持单个模块的lora微调，比如说 vace 或 dit。即我的训练脚本参数传入 --lora_base_model "vace" 或 --lora_base_model "dit" 都可以，但是传入 --lora_base_model "vace,dit" 就报错。
我想微调一个视频 inpainting 的任务，想尝试同时微调 dit 和 vace，当前框架貌似不支持，是出于什么考虑呢？还是说我仅仅微调 dit 或 vace 就够了呢？
期待您们的回答
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 locating the training script's handling of the --lora_base_model argument and reproduce the reported behavior with "vace", "dit", and "vace,dit". Determine whether multi-module LoRA training is intended to be supported; done would be a clear maintainer decision and corresponding behavior or documentation.
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
- 20/100