You might be thinking of a LoRA. LoRA are adapters you use with larger models to help it generate whatever concept you want.
Comment on How to Create Art for a Book?
nicgentile@lemmy.world 3 weeks agoEyevballing here. I’m a learner and have hardly used this.
Would a checkpoint model (right term?) achieve consistency, built from a specific set of pictures?
Even_Adder@lemmy.dbzer0.com 3 weeks ago
nicgentile@lemmy.world 3 weeks ago
Right. That. Thanks.
tal@lemmy.today 3 weeks ago
Yes, if you have or can create a LoRA trained on images of the character you’re presenting.