sberbank-ai
commited on
Commit
•
807e2b2
1
Parent(s):
cabdd47
Update README.md
Browse files
README.md
CHANGED
|
@@ -19,7 +19,7 @@ Kandinsky 2.0 — the first multilingual latent diffusion text2image model.
|
|
| 19 |
|
| 20 |
It is a latent diffusion model with two multi-lingual text encoders:
|
| 21 |
* mCLIP-XLMR (560M parameters)
|
| 22 |
-
* mT5-small (
|
| 23 |
|
| 24 |
|
| 25 |
These encoders and multilingual training datasets unveil the real multilingual text2image generation experience!
|
|
|
|
| 19 |
|
| 20 |
It is a latent diffusion model with two multi-lingual text encoders:
|
| 21 |
* mCLIP-XLMR (560M parameters)
|
| 22 |
+
* mT5-small (146M parameters)
|
| 23 |
|
| 24 |
|
| 25 |
These encoders and multilingual training datasets unveil the real multilingual text2image generation experience!
|