gguf quantized models for Flux-Krea for usage in ComfyUI

how to use

  1. put the gguf model in comfyui/models/diffusion_models
  2. git clone city96 custom node into your custom_nodes folder in comfyui
  3. cd into ComfyUI-GGUF inside custom_nodes and run pip install -r requirements.txt
  4. load the model with the unet loader node in any flux workflow

warning: q4, and especially q2 versions may have noticeable quality loss.

Downloads last month
149
GGUF
Model size
12B params
Architecture
flux
Hardware compatibility
Log In to view the estimation

2-bit

4-bit

6-bit

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support