lucasjinreal/LLaVA-Magvit2
LLaVA combines with Magvit Image tokenizer, training MLLM without an Vision Encoder. Unifying image understanding and generation.
Python
Pinned issues
Issues
- 12
Progress Status
#2 opened by lucasjinreal - 3
Have a tech report or paper?
#1 opened by daixiangzi