사용자 LoRA

XL
캐릭터

Chronoa [Time Power Unleashed With Brainwashed Version • Dragon Ball]

#성숙한 여성

#드래곤볼

#소녀

#드래곤볼 제노버스

Chronoa [Time Power Unleashed With Brainwashed Version • Dragon Ball] - AI Model cover image
업로드 날짜
2024. 12. 27. AM 3:19
이용수
235
리뷰
리뷰 없음
권한
  • 이미지 생성 및 공유 허용
  • 다른 사용자가 내 모델을 다운로드하도록 허용합니다
  • 생성된 이미지의 상업적 이용 허용

설명

https://civitai.com/models/959590/chronoa-time-power-unleashed-with-brainwashed-version-dragon-ball

A model of Chronoa Time Power Unleashed, trained over 91 images for 1024 using AAA as a training modelNormal:Trigger word: chtropnuoaWeight: 1 to 0.5 (0.7 is recommended)Looks tags: colored skin, pink skin, long hair, pink hair, circlet, gold circlet, yellow eyes, pointy ears, yellow earrings, potara earrings, halo, yellow haloClothes tags: tunic, long sleeves tunic, white tunic, bare shoulders, gold trim, gold button, shirt under tunic, yellow undershirt, sleeveless undershirt, high collar, yellow sash, pants, loose pants, yellow pantsBrainwashed: Trigger word: chtropnuoaevil (tbh you don't need it, just use the one above)Weight: 1 to 0.5 (0.7 is recommended)Looks tags: colored skin, pink skin, long hair, white hair, circlet, red circlet, black sclera, colored sclera, red eyes, yellow earrings, potara earringsClothes tags: tunic, single sleeve, black sleeve, red tunic, bare shoulders, white trim, white button, black sash, pants, loose pants, black pants, bandages, purple bandagesAdditional information:Webui I useAAA Anime VAE SDXL v1_4 as VAESampling method: Euler aSchedule type I set it to automaticSampling steps I go 20-304x-Ultrasharp as an UpscalerHires steps I go 8-15 (I don't always use hires fix)Denoising strength I go 0.4Upscale by 1.2 to 1.5 depending on the starting image dimensionsDetail Daemon at default settingsImagine dimensions vary depending on what I'm trying to doI use 5 CFG Scale and CFG Scale Fix set at 9uddetailer for faces, I use mediapipe_face_mesh set Dilation to 50 and Y offset to 30 to get the full faceI do all of my lora training here, if you can spare any buzz I would appreciate it

댓글