modelscope / modelscope/DiffSynth-Studio
编辑模型能使用lora差分训练吗？
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
感谢这次重大的更新！更新中提到了lora的差分训练，我想知道编辑模型适合这种训练方式吗？如果适合的话，在下面的公式中，生成图 1 和 生成图2应该是什么呢？分别是编辑前后的图像吗？训练LoRA 1和LoRA 2的时候，编辑指令应该设置成什么呢？
LoRA 1 = 生成图 1
LoRA 1 + LoRA 2 = 生成图 2
另外，文档中提到“多个图像对训练增加稳定性”，数量多少合适呢？训练完之后是将这些图像对的 LoRA 2 中的权重加起来平均吗？
期待您的解答！
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 reviewing the documentation sections describing LoRA differential training and editing models. Determine whether the proposed training setup applies, define the two generated images and editing instructions, explain how many image pairs are appropriate, and clarify whether LoRA 2 weights should be averaged. Done means these questions have clear, documented answers.
Written by the indexing model from the issue text.
Assessment
- Domain
- documentation, machine-learning
- Issue type
- Documentation
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100