상세 정보
추천
v1.0
FluxDetailer

FluxDetailer

1.4K
7
0
#사실적인
#FLUX
#사진
#풍경

All credits go to @bissonfrederic69429 from civitai:


I created this lora to tryout a theorie. Theorie that is the same as my skin detailer lora and I think that worked pretty well. There is alot of place for improvement but this version work good already. Stay tune for any new version.

It look to work good for those setting, but you can experiment around that:

Lora weight: 0.2-1.0
Sampler: Deis

Scheduler: Beta

Guidance: 3

Steps: 40


My prefered weight setting that provide balance with minimum deformation is 1.0 when used with no other lora.

If you try to use it with a person lora, lucky for you, it won't deform much the person and will keep image coherent. Then i use lower weight value, it depend of the strength that have your other lora but weight can be from 0.2-0.6.

If you are using Comfyui, you can also mix with sharpening node, a laying sigma sampler and a color correct. (i used them for the generation of pictures of the lora).


Have fun with it and share your creation.

번역문 보기

평점 및 리뷰

-- /5
0 개의 평점

충분한 평가나 댓글을 받지 못했습니다.

no-data
데이터 없음
avatar
모델과 대화하기
공고
2024-11-13
모델 게시
2024-11-13
모델 정보 업데이트
모델 상세정보
유형
LORA
게시 날짜
2024-11-13
기본 모델
Flux.1 D
Model Parameters
clip_skip:1
트레이닝 매개변수
Epochs:1
Steps:6000
버전 소개

All credits go to @bissonfrederic69429 from civitai:


I created this lora to tryout a theorie. Theorie that is the same as my skin detailer lora and I think that worked pretty well. There is alot of place for improvement but this version work good already. Stay tune for any new version.

It look to work good for those setting, but you can experiment around that:

Lora weight: 0.2-1.0
Sampler: Deis

Scheduler: Beta

Guidance: 3

Steps: 40


My prefered weight setting that provide balance with minimum deformation is 1.0 when used with no other lora.

If you try to use it with a person lora, lucky for you, it won't deform much the person and will keep image coherent. Then i use lower weight value, it depend of the strength that have your other lora but weight can be from 0.2-0.6.

If you are using Comfyui, you can also mix with sharpening node, a laying sigma sampler and a color correct. (i used them for the generation of pictures of the lora).


Have fun with it and share your creation.

허가 범위
모델 출처: civitai

1. 재게시된 모델의 권리는 원 제작자에게 있습니다.

2. 모델 원작자가 모델을 인증받으려면 공식 채널을 통해 SeaArt.AI 직원에게 문의하세요. 저희는 모든 창작자의 권리를 보호하기 위해 노력합니다. 인증하러 이동

창작 허가 범위
온라인 생방송
혼합 진행
다운로드 허용
상업적 허가 범위
생성된 이미지를 판매하거나 상업적 목적으로 사용 가능
모델의 재판매 또는 융합 후 판매 허용
QR Code
SeaArt 앱 다운로드
모바일에서 AI 창작 여정을 계속하세요