Iscrizione PixAI
PixAI
PixAI
Generate
Sign in
Home
Generazione
Modelli
Studio
NEW
Contest
Crea con Mio.2
AI Tools
NEW
Guide

SDXL

IllusionBreed v5.0

#Plastic model

Crea

  • Generatore di immagini IA
  • Generatore di animazioni IA
  • AI Tools
  • Generatori tematici
  • Allena LoRA
  • Agente Mio.2
  • Studio

Scopri

  • Trending Tags
  • Classifica
  • Market dei modelli
  • Contest
  • Notizia

Informazioni

  • Guide
  • Come utilizzare PixAI
  • Tsubaki.2
  • Scopri Mio
  • Regole sui contenuti

Prezzi e assistenza

  • Appartenenza
  • Pacchetti di crediti
  • Contatto

App mobile

  • Scarica l'app PixAI
  • App Store
  • Google Play
© 2026 PixAI
  • Termini di servizio
  • Informativa sulla privacy
  • Politica sul copyright
  • Attributions
  • Legge sulle transazioni commerciali specificate
IllusionBreed v5.0 - AI Model cover image
Caricato su
22 apr 2025, 10:56
Utilizzi
12.4k
Reviews
Excellent  (6)
Passaggi di campionamento

25

Metodo di campionamento

Euler a

Scala CFG

4

Negativo

lowres, bad quality, worst quality, bad anatomy, sketch, jpeg artifacts, ugly, poorly drawn, blurry, watermark, bad eyes, bright pupils, white pupils, bad hands, bad face,

Permessi
  • Allow image generation & sharing
  • Permettete agli utenti di scaricare il vostro modello
  • Usi commerciali

Recommended LoRAs

Misaoka Style | Zilient - AI Model cover image

User LoRA

Misaoka Style | Zilient
15
アニメ風/anime style(強さ1.3推奨) - AI Model cover image

User LoRA

アニメ風/anime style(強さ1.3推奨)
32
Syuro V2 - AI Model cover image

User LoRA

Syuro V2
25
cure arcana shadow (meitantei precure!) / キュアアルカナ・シャドウ (名探偵プリキュア!) - AI Model cover image

User LoRA

cure arcana shadow (meitantei precure!) / キュアアルカナ・シャドウ (名探偵プリキュア!)
289

Descrizione

https://civitai.com/models/935880

Recommended output settings

CFG Scale : 4-5

Sampler : Eular A

Sampling steps : 20 - 40

Resolution : mainly tested on 768x768, 768x1152, 832x1216, 800x1200 and 1024x768

Using A-Detailer (for face etc.) is highly recommended. (inpaint denoising strength : 0.3 for face, 0.5 for breasts, etc.)

HiRes Fix : use SwinIR_4x, R-ESRGAN 4x+ or 4x-UltraSharp with denoise strength 0.3-0.7.

Quality prompt / Negative prompt : See below.

VAE : embedded.

Quality prompts sample This and base checkpoints are derived from Illustrious, so use quality prompts for Illustrious models.

masterpiece, best quality, amazing quality, very aesthetic, absurdres, 
cute face, slender, detailed eyes, detailed hair,
(PUT YOUR PROMPTS HERE)

Negative prompts sample

lowres, bad quality, worst quality, bad anatomy, sketch, jpeg artifacts, ugly, poorly drawn, blurry, watermark, 
bad eyes, bright pupils, white pupils, bad hands, bad face,
(PUT YOUR NEGATIVE PROMPTS HERE)

推奨される出力設定や品質指定プロンプト・ネガティブプロンプトなどは上記を参照してください。

サンプラーに「Eular A」系統以外を使うと画質が劣化しやすいので注意してください。

ネガティブプロンプトは空にせず、低品質系のワードを入れて調整したほうが良い画質が出やすいようです。(高速出力などのため使えない場合は無くても大丈夫です)

A-Detailerの使用を推奨します。顔のリファインのInpaint denoising strengthは0.3、裸体の胸には0.5程度がよいでしょう。

Illustriousベースのため、PonyベースのBreedシリーズモデルに比べ、当方公開の各種LoRAの効きが弱くなりますのでご了承ください。

その他、Illustrious系特有の癖などがありますので、Illustriousモデルの使い方解説記事などを参照してください。

VAEは焼き込み済みですので、別途用意する必要はありません。

Commenti