CoolFace
Modelpublic

calcuis/sd3.5-lite-gguf

sourceHugging Faceotherupdated 1y agoView on Hugging Face
7likes555downloads
Model Card

sd3.5-lite-gguf

  • —use 8-step which is faster around 70% than the original 24-step; quality remains (it depends)
  • —run it with gguf-connector; simply execute the command below in console/terminal
ggc s3
GGUF file(s) available. Select which one to use: 1. sd3.5-2b-lite-iq4nl.gguf 2. sd3.5-2b-lite-iq4xs.gguf 3. sd3.5-2b-lite-mxfp4moe.gguf Enter your choice (1 to 3):
  • —select gguf in your currently working directory to interact with; then start your first prompt
  • —you will get the image output in few seconds (2b) even with the beginner level gpu or cpu

<Gallery />

run it with gguf-node via comfyui

  • —drag sd3.5-lite to > ./ComfyUI/models/diffusion_models
  • —t5xxl [2.75GB], clip-g [1.39GB], clip-l-v2 [248MB] to > ./ComfyUI/models/text_encoders
  • —drag pig [168MB] to > ./ComfyUI/models/vae

screenshot

reference