ai-forever commited on
Commit
ea9077d
β€’
1 Parent(s): 4a02f7d

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +1 -1
app.py CHANGED
@@ -164,7 +164,7 @@ with block as demo:
164
  [Offical site](https://fusionbrain.ai/diffusion)
165
 
166
  ## Model architecture:
167
- Kandinsky 2.1 inherits best practicies from Dall-E 2 and Latent diffucion, while introducing some new ideas.
168
 
169
  As text and image encoder it uses CLIP model 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.
170
 
 
164
  [Offical site](https://fusionbrain.ai/diffusion)
165
 
166
  ## Model architecture:
167
+ Kandinsky 2.1 inherits best practicies from Dall-E 2 and Latent diffusion, while introducing some new ideas.
168
 
169
  As text and image encoder it uses CLIP model 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.
170