This version is a LoCon.
It is good but not necessarily better than the previous version for all uses.










Lacks a bit on detail accuracy but should be flexible. Detail quality goes up when using AI upscales (hi-res fix).
Suggested weight: 1
This will work well at 1 with most models and while stacking most loras. You can safely try raising 0.1 at a time if issues appear that you struggle to fix with prompting. The max is quite high. You may also want to go under 1.0 but I've personally never needed to even while stacking 5+ loras.
prompt suggestions:
ajitani hifumi, school uniform halo black pantyhose
ajitani hifumi, frilled halo sunglasses
ajitani hifumi, one-piece halo
less reliable
ajitani hifumi, playboy halo [high heels:4]
ajitani hifumi, track uniform halo shorts
pray to RNG:
backpack, doll hug, stuffed toy, sneakers
included in training but expect garbage:
bullpup, grenade, holding strap
This version is a LoCon.
It is good but not necessarily better than the previous version for all uses.
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
