Severian-Void commited on
Commit
2d6b215
1 Parent(s): cc4db00

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -3
README.md CHANGED
@@ -8,8 +8,6 @@ tags:
8
  license: creativeml-openrail-m
9
 
10
  ---
11
- **!!** model files uploaded hopefully soon **!!**
12
-
13
  # Starsector Portraits
14
 
15
  This is a fine-tuned Stable Diffusion model trained on images from the videogame Starsector
@@ -31,4 +29,9 @@ Even with the training I found it was still useful to include some other phrases
31
 
32
  # Sample images from the model:
33
  ![output Samples](https://huggingface.co/Severian-Void/Starsector-Portraits/resolve/main/patherflightschool.png)
34
- ![output Samples](https://huggingface.co/Severian-Void/Starsector-Portraits/resolve/main/RandomPortraits.png)
 
 
 
 
 
 
8
  license: creativeml-openrail-m
9
 
10
  ---
 
 
11
  # Starsector Portraits
12
 
13
  This is a fine-tuned Stable Diffusion model trained on images from the videogame Starsector
 
29
 
30
  # Sample images from the model:
31
  ![output Samples](https://huggingface.co/Severian-Void/Starsector-Portraits/resolve/main/patherflightschool.png)
32
+ ![output Samples](https://huggingface.co/Severian-Void/Starsector-Portraits/resolve/main/RandomPortraits.png)
33
+
34
+ # File Version
35
+ All version were trained using a hand labeled image set of 556 images with black/white backgrounds as well as flipped version of the same images
36
+
37
+ Any checkpoint version with pploss in the name were trained with prior preservation loss enabled and a regularization set of 8000 portrait images comprised of photos/paintings/digitalart of humans in modern day attire.