firdavsus commited on
Commit
cf6006e
·
verified ·
1 Parent(s): 921787a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -1
README.md CHANGED
@@ -4,4 +4,7 @@ license: mit
4
 
5
  # Text 2 Image
6
  this is text 2 timage model based on ViT trained on 1M timage text pairs. backbone is T5 Encoder and Sana audio tokenizer
7
- for more information: https://github.com/firdavsus/Text2Image
 
 
 
 
4
 
5
  # Text 2 Image
6
  this is text 2 timage model based on ViT trained on 1M timage text pairs. backbone is T5 Encoder and Sana audio tokenizer
7
+ for more information: https://github.com/firdavsus/Text2Image
8
+
9
+ # VAE-VQ
10
+ this model takes 128x128 image and compressed it to 16x16 codebook with decent quality reconstrcution loss 0.07 (22 epoch 1M images)!