Shuttle 3.1 Aesthetic NF4

This is a conversion of the Shuttle 3.1 Aesthetic model to NF4 Unet only 6.5GB (needs the T5_encoder, clip, an VAE)

model get good quality images very quickly with just 4 steps (ideal for fixing details on the InvokeAI canvas)

It takes 18 seconds per image with RTX 3060 12GB

Thanks to the original author