Hugging Face's logo

BlinkDL
/
clip-guided-binary-autoencoder

Model card Files Community
1
BlinkDL commited on
Commit
f573f2d
·
1 Parent(s): dd4d734

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -2,7 +2,7 @@
2
  license: apache-2.0
3
  ---
4
 
5
- This model can encode 224x224 RGB image into 28x28x13bit (1274 bytes) latent. The compression rate is 28x28x13/(224x224x24)=1/118, or 0.203 bpp.
6
 
7
  12M params for Encoder + Decoder. Trained on LAION-Aesthetics V2 5+ for 60M images.
8
 
 
2
  license: apache-2.0
3
  ---
4
 
5
+ This model can encode 224x224 RGB image into 28x28x13bit (1274 bytes) latent. The compression rate is 28x28x13/(224x224x24)=1/118, or 0.203 bpp (same as VQGAN_f8_8192).
6
 
7
  12M params for Encoder + Decoder. Trained on LAION-Aesthetics V2 5+ for 60M images.
8