상세 정보
추천
v1.0
backlighting(光照)

backlighting(光照)

801
130
385
#애니메이션
#3D
#조명
#스타일
#illumination
#girls
#light
#raincoat
#소년들
#2.5d style

一款逆光(背光)光照Lora效果,在光照方面表现不错,还有雨衣兜帽风格,希望可以给我多一些反馈,我会继续进步,谢谢!

推荐分辨率:512*768
推荐二次元采样方法:Euler a ,DPM++ 2M SDE Karras,DPM++ 2M Karras ,DPM++ 2S a Karras,
推荐写实采样方法:DPM++ 2M SDE Karras

和别的LORA搭配使用也不错~

如果开启高清修复,出图效果会更好~

高清修复推荐设置:
二次元推荐放大算法:R-ESRGAN 4x+ Anime6B 放大倍数1.5-2倍

写实推荐放大算法:R-ESRGAN 4x+
重绘幅度:0.4-0.7

推荐二次元大模型:meinamix_meinaV11.previewkidsmix_v10.previewmanmaruMix_v20.preview,CounterfeitV30_v30.previewmeinamix_meinaV10.preview,darkSushiMixMix_225D.preview ,二次元模型基本都可以。
推荐写实大模型: revAnimated_v122.preview,ghostmix_v20Bakedvae.preview,dreamshaper_7.preview

Lora触发词:sparkle

Lora推荐权重:0.6-0.8

负面提示词:(EasyNegative:1.2),badhandv4,ng_deepnegative_v1_75t,worst quality,low quality,monochrome,

正向提示词: (best quality, masterpiece:1.2),


我的B站:https://space.bilibili.com/505531014

A backlit (backlit) lighting Lora effect, good in terms of lighting and a mackintosh hood style, I hope I can ???????? more feedback, I will continue to improve, thanks!

Recommended resolution: 512*768

Recommended secondary sampling methods: Euler a , DPM + + 2M SDE Karras, DPM + + 2M Karras, DPM + + 2S a Karras.

Recommended Realistic Sampling Method: DPM++ 2M SDE Karras

It's also good to use with other LORA.

If you turn on HD Repair, the result will be better.

Recommended settings for HD restoration:

Recommended amplification algorithm for secondary: R-ESRGAN 4x+ Anime6B 1.5-2x amplification

Realistic Recommended Zoom Algorithm: R-ESRGAN 4x+

Redraw amplitude: 0.4-0.7

Recommended secondary large models: meinamix_meinaV11.preview, kidsmix_v10.preview, manmaruMix_v20.preview, CounterfeitV30_v30.preview, meinamix_meinaV10. preview, darkSushiMixMix_225D.preview , secondary models are basically OK.

Recommended realistic large models: revAnimated_v122.preview, ghostmix_v20Bakedvae.preview, dreamshaper_7.preview

Lora trigger word: sparkle

Lora referral weight: 0.6-0.8

Negative Cue Words: (EasyNegative:1.2),badhandv4,ng_deepnegative_v1_75t,worst quality,low quality,monochrome,

Positive cue words: (best quality, masterpiece:1.2),

번역문 보기

평점 및 리뷰

-- /5
0 개의 평점

충분한 평가나 댓글을 받지 못했습니다.

no-data
데이터 없음
B
모델과 대화하기
공고
2024-04-02
모델 게시
2023-08-17
모델 정보 업데이트
모델 상세정보
유형
LORA
게시 날짜
2023-08-17
기본 모델
SD 1.5
트리거 단어
sparkle
복사
버전 소개

A backlit (backlit) lighting Lora effect, good in terms of lighting and a mackintosh hood style, I hope I can ???????? more feedback, I will continue to improve, thanks!

Recommended resolution: 512*768

Recommended secondary sampling methods: Euler a , DPM + + 2M SDE Karras, DPM + + 2M Karras, DPM + + 2S a Karras.

Recommended Realistic Sampling Method: DPM++ 2M SDE Karras

It's also good to use with other LORA.

If you turn on HD Repair, the result will be better.

Recommended settings for HD restoration:

Recommended amplification algorithm for secondary: R-ESRGAN 4x+ Anime6B 1.5-2x amplification

Realistic Recommended Zoom Algorithm: R-ESRGAN 4x+

Redraw amplitude: 0.4-0.7

Recommended secondary large models: meinamix_meinaV11.preview, kidsmix_v10.preview, manmaruMix_v20.preview, CounterfeitV30_v30.preview, meinamix_meinaV10. preview, darkSushiMixMix_225D.preview , secondary models are basically OK.

Recommended realistic large models: revAnimated_v122.preview, ghostmix_v20Bakedvae.preview, dreamshaper_7.preview

Lora trigger word: sparkle

Lora referral weight: 0.6-0.8

Negative Cue Words: (EasyNegative:1.2),badhandv4,ng_deepnegative_v1_75t,worst quality,low quality,monochrome,

Positive cue words: (best quality, masterpiece:1.2),

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