유형
LORA
게시 날짜
2025-02-17
기본 모델
Flux.1 D
트리거 단어
J0hnnyD
복사


This is my first attempt at a lora (at least one that turned out alright). I was testing a workflow to make headshots, and I wanted to create a lora using only a handful of images to see how it would come out.
This seems to work at a .8-1 strength and does decently well when doing a close-up image (like a headshot), for images with more going on, I'd recommend using a face detailer with this lora.
Every image has a grainy look to it, which I'm not sure why as my training images didn't have that look. But it makes the images look like they're from the 80s, so that can look cool.
1. 재게시된 모델의 권리는 원 제작자에게 있습니다.
2. 모델 원작자가 모델을 인증받으려면 공식 채널을 통해 SeaArt.AI 직원에게 문의하세요. 저희는 모든 창작자의 권리를 보호하기 위해 노력합니다. 인증하러 이동
