PixAI 멤버십
PixAI
PixAI
Generate
Sign in
홈
생성
모델
Studio
NEW
콘테스트
Mio.2 창작
AI 도구
NEW
가이드

사용자 LoRA

XL

[PonyXL] Elongation/Stretching/Elastic body

#스트레칭
AI 도구
  • AI 애니메 생성기
  • 애니메 피규어 생성기
  • 캐릭터 시트 생성기
  • 잡지 표지 생성기
  • 봉제인형 생성기
  • 대형 동상 생성기

찾아보기

  • 인기 태그
  • 랭킹
  • 모델 마켓
  • 콘테스트
  • 뉴스

소개

  • 가이드
  • PixAI 블로그
  • Tsubaki.2
  • Mio 소개
  • 콘텐츠 규칙

요금 및 도움말

  • 멤버십
  • 크레딧 팩
  • 연락처

모바일 앱

  • PixAI 앱 다운로드
  • 앱 스토어
  • 구글 플레이
© 2026 PixAI
  • 개인정보
  • 개인정보 처리방침
  • 저작권 정책
  • 저작자 표시
  • 특정상업거래법
[PonyXL] Elongation/Stretching/Elastic body - AI Model 커버 이미지
업로드 날짜
2024. 6. 9. 오전 8:58
이용수
6.6k
리뷰
리뷰 없음
트리거 단어

elongated, long torso, long arms, long legs, long neck, noodling, tangled, wrapped around

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

추천 LoRA

Misaki Suzuhara (Angelic Layer) - AI Model 커버 이미지

사용자 LoRA

Misaki Suzuhara (Angelic Layer)
3
Kitsune (Furry) - AI Model 커버 이미지

사용자 LoRA

Kitsune (Furry)
17
Hanabi Yasuraoka (安楽岡花火) - Scum's Wish (クズの本懐) (3 Outfits) - AI Model 커버 이미지

사용자 LoRA

Hanabi Yasuraoka (安楽岡花火) - Scum's Wish (クズの本懐) (3 Outfits)
19
Samurai girl {kirin} - AI Model 커버 이미지

사용자 LoRA

Samurai girl {kirin}
1

설명

A loRA made by NSFW on CivitAI: https://civitai.com/models/468746?modelVersionId=521625

"Turns people all noodley! I've taken a few cracks at this one and I don't think I'm going to get it to work the way I want (until technology or I improve), so maybe you all can have some fun with this for now. Be prepared to hunt / cherry pick if you want good results.v1 does more intense noodling | v0 is milder but affects styles moreNotes:To use, start with a LoRA weight of 1 and a trigger word weight of 1. Next increase the LoRA weight .1 at a time up to 1.5 (I've found 1.3 is usually good when mixed with character LoRAs), then increase the trigger word weight .1 at a time up to 1.5. I've found the LoRA weight increases stretchiness (and starts splitting limbs) but keeps coherence, and the trigger word weight increases noodling but tends to go wild.Once you've got it generating as well as possible, do some seed hunting / cherry picking.Upscaling can be done at the same rates.Seems to work more intensely in wide pictures (rather than tall)Additional fun prompt terms that may help:laying down on PLACE, falling on floor - seems to improve the "just fell all over the place" looklong neck - works as advertisedbarefoot, holding THING, COLOR hair - can keep people coherent when the weight is highnoodle arms, noodle legs - seems to have an effect. Too high a weight and you get actual noodles, though.tangled - trained in but I didn't find it useful myselfstretched - seems to have a bit of an effectstrewn about - seems to increase noodlagetransforming - seems to increase coherence"

댓글