modèles/Prefectious XL NSFW - v1.0

Prefectious XL NSFW - v1.0

8/22/2025

4:10:35 AM

Mots-clés et tags associés

anime,modèle de base,base models,checkpoint,clip skip,girls,goofy_ai,highres.fix,illustrious,illustrious xl,image generation,prefectious-v1,prefectious xl nsfw,stable diffusion,styles,v1.0,femme

Close-up portrait of Yor Briar with black hair and grey hairband, eyes closed, wearing a white tank top with arms raised.

Anime style blonde-haired girl with red eyes wearing a black crop top and black pants, white jacket draped over shoulders, covering mouth with hand.

Mature woman with black braided ponytail and blue eyes smiling in black kimono with white sash, standing outdoors under blue sky.

Anime character Evelyn from Zenless Zone Zero with blonde hair, purple eyes, wearing a white sleeveless shirt, black bodysuit, yellow necktie, and jewelry

Anime-style blonde woman with purple eyes and black gloves eating ramen with chopsticks indoors at night, sitting at a table with a city view outside the window.

Prompts recommandés

masterpiece,best quality,absurdres,amazing quality

masterpiece, best quality, amazing quality, 1girl

Prompts négatifs recommandés

bad quality,worst quality,worst detail,sketch,censored,watermark,signature,artist name

bad quality, worst quality, worst detail, sketch, censor, artist name, signature, watermark, patreon username

Paramètres recommandés

samplers

Euler A, DPM++ 2M, Euler a

steps

20 - 30

cfg

5 - 7

resolution

832x1216

vae

sdxl_vae_fixed.safetensors

Paramètres haute résolution recommandés

upscaler

4x-Ultrasharp

denoising strength

0.24 - 0.34

Conseils

Use afterdetailer for enhancing face details.

Use tiled diffusion for img2img upscaling.

Do not use restore faces.

Consider using Noise Inversion for extra details.

Use ENSD setting 31337.

Points forts de la version

I had CLIP skip 1 on every image
Samplers : Eular A, DPM++ 2M
CFG : 5-6
I had ENSD: 31337 all of them
All of them had highres.fix or img2img at higher resolution.
I don't use restore faces
I use afterdetailer for face details
Tiled diffusion for img2img upscaling and sometimes Noise Inversion for some more extra details.
4x-Ultrasharp upscaler
positive: masterpiece,best quality,absurdres, amazing quality
negative: bad quality,worst quality,worst detail,sketch,censored,watermark, signature, artist name

Sponsors du créateur

Free GPU use on Tensor

Mage provides Unlimited Generations

Patreon account. do check it out

If you want commission dm me on Discord.

Get early access to my upcoming NSFW Lora in my Patreon

Join my Discord Server

If you like my work, drop a 5 review and hit the heart icon. it's free and keeps me motivated

this is a new illustrious merge. still trying to know this base model more. It might have bugs and is definitely not perfect.

Free GPU use on Tensor

Mage provides Unlimited Generations

Patreon account. do check it out

I post my upcoming concepts and nsfw lora early on my patreon

If you want commission dm me on Discord.

Get early access to my upcoming NSFW Lora in my Patreon .

Support my work by joining any one of them and get early access to all my upcoming loras and other perks such as fan requests and Discord role.

Suggested settings:

I had CLIP skip 1 on every image
Samplers : Eular A, DPM++ 2M
CFG : 5-6
I had ENSD: 31337 all of them
All of them had highres.fix or img2img at higher resolution.
I don't use restore faces
I use afterdetailer for face details
Tiled diffusion for img2img upscaling and sometimes Noise Inversion for some more extra details.
4x-Ultrasharp upscaler
positive: masterpiece,best quality,absurdres, amazing quality
negative: bad quality,worst quality,worst detail,sketch,censored,watermark, signature, artist name