Ultimate Diffusion

My personal custom trained model.

Recommended settings

VAE: None (it's included)

Clip skip: 1

Sampling method: DPM++ SDE Karras

Sampling steps: 25

CFG scale: 7~10

Negative prompt: extra fingers, fewer fingers, bad-hands-5, by bad-artist, (bad eyes:1.2), (misfigured pupils:1.2), (bad clothing:1.3), (undetailed clothing:1.3), ng_deepnegative_v1_75t, verybadimagenegative_v1.3, (nonsensical backrounds:1.2), (bad backrounds:1.2), (bad shadows:1.2), (bad ???????:1.1)