PixAI 멤버십

SDXL

Yesmix XL (NAI-VPRED)

Yesmix XL (NAI-VPRED) - AI Model 커버 이미지
업로드 날짜
2025. 5. 9. 오후 2:05
이용수
510
리뷰
리뷰 없음
샘플링 단계

25

샘플링 방식

Euler a

CFG 스케일

7

제외 조건

⊘, lowres,bad,error,fewer,extra,missing,worst quality,jpeg artifacts,bad quality,watermark,signature,extra digits,artistic error,username,abstract,artist logo,artist name,signature,bad fingers,bad hand,patreon username, patreon logo, web address,simple background,

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

추천 LoRA

ancient abandoned spaceship - AI Model 커버 이미지

사용자 LoRA

ancient abandoned spaceship
1
Samurai Painting - AI Model 커버 이미지

사용자 LoRA

Samurai Painting
2
Detailed Furry - AI Model 커버 이미지

사용자 LoRA

Detailed Furry
90
Julia1.0 - AI Model 커버 이미지

사용자 LoRA

Julia1.0
10

설명

IntroductionThis is a V-PRED version of the YesmixXL model. It was trained on the same dataset as YesmixXL but uses v_prediction sampling instead of the standard SDXL epsilon method. The model was fine-tuned on NoobAI-V-PRED using v_prediction method and further DPO-optimized with a personal anime preference dataset for enhanced output quality. Keys for v_prediction and zero_terminal_snr are integrated, allowing direct image generation in ComfyUI. A known minor issue is a rare blue artifact in some image regions, resolvable by regenerating; otherwise, the model demonstrates stable generation across diverse prompts.UsageSampler: Euler A (Recommended)CFG Scale: 6~7.5 (Recommended)Steps: 25 (Recommended)Single Prompt Weight: <1.3, 1 is recommended

댓글

Yesmix XL (NAI-VPRED)으로 만든 작품

홈모델Mio.2프로필
홈모델Mio.2프로필