Emu2
modelSecond-generation multimodal model from BAAI, advancing vision-language generation with improved architecture and training. Supports any-to-any generation across text and images.
Model Details
Variants
| Name | Parameters | Notes |
|---|---|---|
| Emu2 | — | — |
| Name | Parameters | Notes |
|---|---|---|
| Emu2 | — | — |