Image-to-Image
Diffusers
Safetensors
drhead commited on
Commit
fcbce1c
1 Parent(s): 1919635

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -0
README.md CHANGED
@@ -7,6 +7,13 @@ This is a VAE decoder finetune, resumed from stabilityai/sd-vae-ft-mse using ima
7
 
8
  Our testing has shown that the VAE is good at eliminating unwanted high-frequency noise when used on models trained on similar data. It may have some generalizability to a broader range of art styles due to the variety of different styles in the dataset.
9
 
 
 
 
 
 
 
 
10
  #### Licensing:
11
 
12
  You are free to use this model for personal, non-commercial use.
 
7
 
8
  Our testing has shown that the VAE is good at eliminating unwanted high-frequency noise when used on models trained on similar data. It may have some generalizability to a broader range of art styles due to the variety of different styles in the dataset.
9
 
10
+ Default VAE (kl-f8):
11
+ ![Default VAE](crop3[1].png)
12
+ Furception 1.0:
13
+ ![Our VAE](crop4[1].png)
14
+
15
+
16
+
17
  #### Licensing:
18
 
19
  You are free to use this model for personal, non-commercial use.