Update README.md
Browse files
README.md
CHANGED
@@ -4,10 +4,8 @@ license: apache-2.0
|
|
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
|
8 |
|
9 |
-
Guided by https://huggingface.co/laion/CLIP-ViT-B-32-laion2B-s34B-b79K (it's great. better than OpenAI CLIP B/32) and https://github.com/dingkeyan93/DISTS.
|
10 |
-
|
11 |
-
No GAN loss. So probably the image is slightly blurred in some cases?
|
12 |
|
13 |
(still training. final checkpt will be better)
|
|
|
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 130M images.
|
8 |
|
9 |
+
Guided by https://huggingface.co/laion/CLIP-ViT-B-32-laion2B-s34B-b79K (it's great. better than OpenAI CLIP B/32) and https://github.com/dingkeyan93/DISTS. No GAN loss.
|
|
|
|
|
10 |
|
11 |
(still training. final checkpt will be better)
|