Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
base_model:
|
| 5 |
+
- Efficient-Large-Model/Sana_1600M_1024px_BF16
|
| 6 |
+
- VIPL-GENUN/Jodi
|
| 7 |
+
tags:
|
| 8 |
+
- diffusion
|
| 9 |
+
- unified-visual-generation-understanding
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Jodi
|
| 13 |
+
|
| 14 |
+
We introduce Jodi, a diffusion framework that unifies visual generation and understanding by jointly modeling the image domain and multiple label domains.
|
| 15 |
+
|
| 16 |
+
- **Project page**: <https://VIPL-GENUN.github.io/Project-Jodi>
|
| 17 |
+
- **GitHub**: <https://github.com/VIPL-GENUN/Jodi>
|