bertbobson commited on
Commit
ed67a8d
·
verified ·
1 Parent(s): 5eb09c1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -1
README.md CHANGED
@@ -2,4 +2,8 @@ This is an unavoidable double quantization due to the release state of Ideogram4
2
 
3
  The FP8 weights were cast to FP32 with the FP8 scales, then downcast to BF16 before being converted to INT8.
4
 
5
- For use with https://github.com/BobJohnson24/ComfyUI-INT8-Fast
 
 
 
 
 
2
 
3
  The FP8 weights were cast to FP32 with the FP8 scales, then downcast to BF16 before being converted to INT8.
4
 
5
+ For use with https://github.com/BobJohnson24/ComfyUI-INT8-Fast
6
+
7
+ Quick comparison:
8
+
9
+ <img src="Comparison.jpg" width="1000" height="500">