Text-to-Image
Not-For-All-Audiences
drhead commited on
Commit
8d3ef97
1 Parent(s): e66a55f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -1
README.md CHANGED
@@ -1,3 +1,16 @@
1
  ---
2
- license: wtfpl
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: mit
3
  ---
4
+
5
+ A finetune of lodestones/fluffyrock-1088-minsnr-zsnr-vpred-ema-pytorch with the following changes:
6
+
7
+ - Caption dropout of 10% to improve classifier-free guidance
8
+ - Timesteps weighted by 1/(snr+1) to improve output quality
9
+ - A higher virtual batch size of 64
10
+ - Includes RedRocket/furception_vae for convenience (licensed separately, please refer to its repository for more information)
11
+
12
+ A refiner model is also planned. Stay tuned for more information.
13
+
14
+ The VAE decoder is licensed under Furception's license (as of writing CC-BY-NC-SA 4.0 though due to change). All other model components are licensed under the MIT license.
15
+
16
+ Special thanks to @RedHotTensors for providing compute power.