Hugging Face's logo

Kijai
/
WanVideo_comfy_fp8_scaled

Diffusion Single File
comfyui
Model card Files
xet
Community
12
WanVideo_comfy_fp8_scaled / README.md
Kijai's picture
Kijai
Update README.md
0d3d8b1 verified
preview code
|
raw
history blame contribute delete
1.09 kB
metadata
tags:
  - diffusion-single-file
  - comfyui
license: apache-2.0
base_model:
  - Wan-AI/Wan2.1-VACE-14B
  - Wan-AI/Wan2.1-VACE-1.3B

Better fp8 scaled models (when measured against fp16) based on quantization code from https://github.com/Tencent-Hunyuan/HunyuanVideo/blob/main/hyvideo/modules/fp8_optimization.py

Can be used with: https://github.com/kijai/ComfyUI-WanVideoWrapper (latest version) and ComfyUI native WanVideo nodes.

14B-T2V comparison test without LoRAs, 25 steps, 832x480x81

2.2 A14B-T2V test

The e5m2 marked as v2 is the one uploaded here and these are all scaled even if I forgot to label properly.