bertbobson's picture
Update README.md
7ca7fca verified
|
Raw
History Blame
255 Bytes
Flux Klein 9B in INT8 for 2x inference gains on 30-Series GPUs.
To be used with https://github.com/BobJohnson24/ComfyUI-Flux2-INT8
Comparison against FP8:
FP8 | INT8
|---------|---------|
| ![FP8 Example](FP8Grid.jpg) | ![INT8 Example](INT8Grid.jpg) |