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

SDXL

Hex Anime [Illustrious]

제작

  • AI 이미지 생성기
  • AI 애니메이션 생성기
  • AI 도구
  • 테마 생성기
  • LoRA 학습
  • Mio.2 에이전트
  • Studio

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
Hex Anime [Illustrious] - AI Model cover image
업로드 날짜
2025. 12. 1. 오후 8:52
이용수
541
리뷰
훌륭함  (1)
샘플링 단계

25

샘플링 방식

Euler a

CFG 스케일

5

제외 조건

worst quality, low quality, bad, artistic error, worst aesthetic, jpeg artifacts, bad hands, mutated hands, extra digits, ugly, signature, watermark, nose, extra ears, helmet, mask, yellow hair, orange hair

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

설명

                       Hex AnimeHex Anime has a 2.5D, Semirealistic, or 2D Anime look to it depending on the prompt. Plus, it has a similar style to Hexbloom as that's the whole point.Originally, V0.5 is Ionsyx V5.9 but renamed and posted here on the new account. V1.0 of this will be the final version unless someone wants this to be updated past V1.0I don’t recommend starting with this if you’re new to Illustrious or Danbooru in general—unless you enjoy a challenge—since poor prompting will result in poor images.Feel free to leave suggestions on what I can add here to help fix issues you may encounter. You’re also welcome to leave critiques, whether positive or negative, as long as they’re specific to this checkpoint model. I like having feedback so I can improve.You are also free to publish images made from this model. It helps people find both the model and your images. I also enjoy checking my model pages, so it’s usually a free like from me if I enjoy what you’ve posted. Feel free to bid on the model if you like it.You can tip, like, or follow the model to show support—only if you want to. I do this purely as a hobby, so tips go toward future LoRAs I create, LoRAs used behind the scenes in models, and bidding in model auctions if I have enough buzz. The original version on the Ionsyx page (V1.0) was made on a GTX 1060 3GB GPU—surprisingly. I’m also the same person (Arctenox) as this is my New Account, I can guarantee that.Recommended "V0.5" Settings:Steps: 20+ / Depends on the Sampler and Scheduler used.CFG: 3.0+Sampler:  Euler / (Mostly a personal preference and starting point.)Scheduler: Normal / Simple (Mostly a personal preference and starting point.)Base generation for characters can be bad, so I recommend using: ADetailers / Upscalers / HiResNote: You may need to generate a few times, if you don't get what you want exactly, as always. Recommended Negatives - Don't have to use it if you have something better but this is a starting point:masterpiece, best qualityRecommended Negatives - Don't have to use it if you have something better but this is a starting point:worst quality, watermark, artist sign, artist name, username, signature, logo, four fingers, six fingersNote: Due to how far along this is now four fingers, six fingers might not have been retained and usable anymore instead use the danbooru equivalent: fewer digits, extra digits

댓글