모델 XL

Infested Pony

#성숙한 여성

#몬스터

#사이보그

#언데드

#크리처

#소녀

Infested Pony - AI Model cover image
업로드 날짜
2025. 1. 25. PM 12:09
이용수
192
리뷰
훌륭함  (1)
샘플링 단계

30

샘플링 방식

Euler a

CFG 스케일

5

제외 조건

score_6, score_5, score_4, source_pony, (worst quality:1.2), (low quality:1.2), (normal quality:1.2), lowres, bad anatomy, bad hands, signature, watermarks, ugly, imperfect eyes, skewed eyes, unnatural face, unnatural body, error, extra limb, missing limbs, painting by bad-artist, (((long_neck:1.5))), disfigured,ugly, poorly drawn face,

권한
  • 이미지 생성 및 공유 허용
  • 다른 사용자가 내 모델을 다운로드하도록 허용합니다
  • 생성된 이미지의 상업적 이용 허용

설명

Unstable and creative merge of Troubled Confusion LX Overburnt and AutismMix Confetti.Recommended parameters:Undead V2 - Euler A or DDPM samplers with 30..40 steps OR DPM++ SDE sampler with 8..10 stepsUndead - Euler A or DDPM samplers with 30..40 stepsPlague - Euler A or DDPM samplers with 30..40 stepsFlu - Euler A or DDPM samplers with 30..40 steps OR DPM++ SDE sampler with CFG 2..3 and 8..10 stepstensor_pwm merge method is (Python code):def tensor_pwm(a: Tensor, b: Tensor, alpha: float, beta: float, **kwargs) -> Tensor: # pylint: disable=unused-argument """ Takes a slice of Secondary Model and repeatedly pastes it into Primary Model Alpha sets the width of the slice Beta sets the start point of the slice ie Alpha = 0.125 Beta = 0.25 is (AABABABA) """ tt = a.clone() i = beta
while i < 1: start = int(a.shape[0] * i) i = min(i + alpha, 1) end = int(a.shape[0] * i) i = min(i + alpha, 1) k = a[start:end].nanmedian() - b[start:end].nanmedian() tt[start:end] = k + b[start:end].clone()
return tt

댓글