유형
LORA
게시 날짜
2024-08-02
기본 모델
Pony
트리거 단어
score_9, score_8_up, score_7_up,
beautiful aesthetic, very intricate, high quality details,
복사
Model Parameters
clip_skip：2
트레이닝 매개변수
Epochs：18
Steps：0
버전 소개
This one is tricky. Around 0.8 weight the AI loses its mind so the hands start to get messed up. So I suggest using the LoRA around 0.7~0.8 weight for good results. Negatives and combinations with other styles might mitigate that problem.
Enjoy! :)
I use these prompts on every image with great results:
POSITIVE:
score_9, score_8_up, score_7_up,
beautiful aesthetic, very intricate, high quality details,
You can get really good results with no Negatives. Try it out.
