Commit
•
331c1d6
1
Parent(s):
a5fb64b
Update README.md
Browse files
README.md
CHANGED
|
@@ -10,6 +10,8 @@ inference: false
|
|
| 10 |
|
| 11 |
# Kandinsky 2.2
|
| 12 |
|
|
|
|
|
|
|
| 13 |
Kandinsky inherits best practices from Dall-E 2 and Latent diffusion while introducing some new ideas.
|
| 14 |
|
| 15 |
It uses the CLIP model as a text and image encoder, and diffusion image prior (mapping) between latent spaces of CLIP modalities. This approach increases the visual performance of the model and unveils new horizons in blending images and text-guided image manipulation.
|
|
|
|
| 10 |
|
| 11 |
# Kandinsky 2.2
|
| 12 |
|
| 13 |
+
Finetuned on Midjourney V6! 🔥🖼️
|
| 14 |
+
|
| 15 |
Kandinsky inherits best practices from Dall-E 2 and Latent diffusion while introducing some new ideas.
|
| 16 |
|
| 17 |
It uses the CLIP model as a text and image encoder, and diffusion image prior (mapping) between latent spaces of CLIP modalities. This approach increases the visual performance of the model and unveils new horizons in blending images and text-guided image manipulation.
|