Hugging Face's logo

VIPL-GENUN
/
Jodi

Diffusion
Text-to-Image
Controllable-Generation
Image-Perception
Model card Files
xet
Community
1
Jodi / README.md
xyfJASON's picture
xyfJASON
Update README.md
6850d60 verified
preview code
|
raw
history blame
443 Bytes
metadata
base_model:
  - Efficient-Large-Model/Sana_1600M_1024px_BF16
  - VIPL-GENUN/Jodi
tags:
  - Diffusion
  - Text-to-Image
  - Controllable-Generation
  - Image-Perception

Jodi

We introduce Jodi, a diffusion framework that unifies visual generation and understanding by jointly modeling the image domain and multiple label domains.