kohya-ss / kohya-ss/sd-scripts
Support Lumina 2.0
- Dominant language
- Python
- Stars
- 7.2k
- Forks
- 1.2k
- Avg merge
- 11m
- Merged PRs (30d)
- 2
Description
code:https://github.com/Alpha-VLLM/Lumina-Image-2.0
Currently, they have a very strong power, and the license using Apache 2.0 is also very friendly.
Compared to SANA, the re norm CFG method they adopt to a great extent offsets the high saturation and smoothness issues brought by synthetic data.
Gemma2B is also very new LLM, captions for multilingual training.
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by reviewing the Lumina 2.0 project linked in the issue and the repository's existing support for comparable models such as SANA. Define the integration points and validation needed so Lumina 2.0 can be supported, including its re-norm CFG method and multilingual Gemma2B captions.
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