working in ComfyUI with sdxl models:

Just need the two safetensors model1 and model2. clip_g and clip_l for the common name from sdxl

Needs my custom loader here to work: https://github.com/Apache0ne/ComfyUI-SDXLNVFP4

Workflow in images, also I am using taesd vae for both.


With NVFP4 CLIP


with normal CLIP

S
Description
No description provided
Readme
3.5 MiB
Languages
Python 100%