nightknocker commited on
Commit
581bf24
·
verified ·
1 Parent(s): b015fe9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -1
README.md CHANGED
@@ -13,7 +13,6 @@ The decoder model redraws the masked area based on the booru tags.
13
  The input and the training target are based on:
14
  - LAB color space
15
  - FFT
16
- - FDL
17
 
18
  As in another [encoder](https://huggingface.co/nightknocker/sdxs-1b-image-to-longclip-encoder) model, the image was split to 4 equal-sized squares, and then one of the squares was masked by less than 30%.
19
 
 
13
  The input and the training target are based on:
14
  - LAB color space
15
  - FFT
 
16
 
17
  As in another [encoder](https://huggingface.co/nightknocker/sdxs-1b-image-to-longclip-encoder) model, the image was split to 4 equal-sized squares, and then one of the squares was masked by less than 30%.
18