用戶LoRA

XL

Remi Izumi (Hentai: Inbaku Gakuen / School of Bondage) PonyXL / SD 1.5 animefull

#熟女

#老師

#女孩

Remi Izumi (Hentai: Inbaku Gakuen / School of Bondage) PonyXL / SD 1.5 animefull - AI Model cover image
上傳時間
2024年10月10日 下午6:05
使用數
977
評論
非常好  (1)
觸發詞

Remi Izumi, mature female,1girl, , brown hair, short hair, hair up, green eyes, glasses, earrings,, brown hair, long hair, green eyes,, blazer, pencil skirt, black thighhighs, lace trim,, black bra, high heels, black footwear,

許可權
  • 允許圖片生成與分享
  • 允許使用者下載此模型
  • 允許生成圖片用於商業用途

描述

Remi Uzumi from hentai and manga Inbaku Gakuen (School of Bondage) is on PonyXL and SD1.5 anime now!

(Hentai without shitty censorship from 2000s :3)

PonyXL tags:

Main:

Remi Izumi, mature female,1girl, brown hair, short hair, hair up, green eyes, glasses, earrings,

alternative style:

brown hair, long hair, green eyes,

Teacher outfit:

blazer, pencil skirt, black thighhighs, lace trim, high heels, black footwear, black bra

SD 1.5 tags: Izumiremi, mature female, teacher, 1girl, solo, brown hair, short hair, hair up, single hair intake, green eyes, makeup, glasses, jewelry, earrings, skirt suit, black thighhighs, lingerie, high heels large breasts, cleavage, thighs,

optional:

long hair (put "short hair, hair up" and "single hair intake" in negative then)

PonyDiffusion v6 (XL) quality settings:

Style settings for PonyXL before prompt (important):

score_9, score_8_up, score_7_up, score_6_up, uncensored,

For more influence of "baked-in" LoRA style or Style LoRA you need only "score_9" without any other scores.

Negative prompt for PonyXL (recommended):

dutch angle, censored, watermark, jpeg artifacts, muscular female

SD1.5 quality settings:

masterpiece, high quality

in negative: worst quality, low quality

Upscaler / adetailer settings:

Hires.fix: Upscaler foolhardy_remacri (download and put in "ESRGAN" folder in "models" if you are using automatic1111 or forge).

Hires steps: 16-18

Denoising strength: 0.2-0.3

Adetailer: denoising strength 0.3. Detection model confident threshhold: 0.7-0.8.

Best sampling method is euler a, 25-40 sampling steps. cfg 7-9, You don't need any DPM++.

I will be glad to receive feedback from you and a demonstration of your art with my LoRA!

https://tensor.art/u/604375505701151021

評論