Update README.md
Browse files
README.md
CHANGED
|
@@ -5,6 +5,10 @@ This is the conversion of SmoothMix WAN 2.2 V2.0 - https://civitai.com/models/19
|
|
| 5 |
|
| 6 |
I'm experimentei running the script https://github.com/Kickbub/Dequant-FP8-ComfyUI/blob/main/dequantize_fp8v2.py to turn it to FP16 to check if there is an imporvement on quality and size
|
| 7 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
Videos made with UMT GGUF Q8 and VAE FP32
|
| 9 |
|
| 10 |
| . | F8 | F16 |
|
|
|
|
| 5 |
|
| 6 |
I'm experimentei running the script https://github.com/Kickbub/Dequant-FP8-ComfyUI/blob/main/dequantize_fp8v2.py to turn it to FP16 to check if there is an imporvement on quality and size
|
| 7 |
|
| 8 |
+
There is the full FP16 conversion, around 40Gb, and some GGUF.
|
| 9 |
+
|
| 10 |
+
Please provide feedback so I know if I should run this script always before GGUF other models.
|
| 11 |
+
|
| 12 |
Videos made with UMT GGUF Q8 and VAE FP32
|
| 13 |
|
| 14 |
| . | F8 | F16 |
|