Re:Stable Diffusion with Core ML on Apple Silicon
by pmarreck on Monday December 05, 2022 @12:24PM
(#33868578)
Some stable diffusion interfaces let you specify a "negative input" which will bias results away from it. It wouldn't be terribly hard to do some semantic interpretation prior to submission to the model that would turn "not a <thing>" into "negate-input <thing>"
e.g. SD2 prompted with "not a cat" produces a cat, and "1 + 1" doesn't produce "2".