Trained on about 48 images. 29 base suit, 15 future suit, and 4 bl3 suit.
Tested this out with my image grabber angular / python app to automate getting images from google/yahoo/yandex, so the I wanted this to be a proof of concept for that. Definitely wanna fine tune with more distribution.
Base outfit: default outfit, red tie, vest
Future outfit: alternate outfit
BL3 outfit (turns him into a chromed out cyberpunk character): bl3 outfit, mustache
Starter Prompt:
<lora:RhysV1.0:0.8> rhystftbl, (1boy), (brown hair), default suit, vest, red tie, single mechanical arm, temple port, (heterochromia:1.2)