PixAI Membership
PixAI
PixAI
Generate
Sign in
Home
Generation
Models
Studio
NEW
Contest
Create with Mio.2
AI Tools
NEW
Guide

SDXL

SelphMix

#Plastic model

Create

  • AI Image Generator
  • AI Animation Generator
  • AI Tools
  • Thematic generators
  • Train LoRA
  • Mio.2 Agent
  • Studio

Discover

  • Trending Tags
  • Ranking
  • Model Market
  • Contest
  • News

About

  • Guide
  • PixAI Blog
  • Tsubaki.2
  • Meet Mio, Our Mascot
  • Content Rules

Pricing & Help

  • Membership
  • Buy Credits
  • Contact

Mobile App

  • Get the PixAI app
  • App Store
  • Google Play
© 2026 PixAI
  • Terms of Service
  • Privacy Policy
  • Copyright Policy
  • Attributions
  • Specified Commercial Transactions Law
SelphMix - AI Model cover image
Uploaded at
Apr 2, 2025, 12:43 AM
Uses
2.2k
Reviews
Excellent  (2)
Sampling Steps

25

Sampling Method

Euler a

CFG Scale

5

Negative

worst quality, low quality, lowres, signature, artist_name, watermark, old

Permissions
  • Allow image generation & sharing
  • Allow users to download this model
  • Allow commercial use of generated images

Recommended LoRAs

Hyper Quality V2 SDXL - AI Model cover image

User LoRA

Hyper Quality V2 SDXL
217
LCM&TurboMix LoRA (eular a.fix) XL - AI Model cover image

User LoRA

LCM&TurboMix LoRA (eular a.fix) XL
10.62k
Gunvolt - Azure Striker Gunvolt 蒼き雷霆 - AI Model cover image

User LoRA

Gunvolt - Azure Striker Gunvolt 蒼き雷霆
3
彼女、お借りします 水原千鶴 - AI Model cover image

User LoRA

彼女、お借りします 水原千鶴
10

Description

By popular demand from a fair lot of people, this is my mix for Illustrious.UsageThe model can do a wide variety of stuffs just like everything else in Illu. I haven't found something I've wanted to make that it isn't capable of.SettingsThe settings I use for this mix are the same I use for everything Illu. They are subjective and there might be better. Obviously, add what fits your subject.Euler Sampler, Normal Scheduler, CFG 5Positives: masterpiece, best_quality, newest, absurdres, highresNegatives: worst quality, low quality, lowres, signature, artist_name, watermark, oldRecommendationsThe model is very 3D without artist tags, as you can see by the example pics. From closed testing with other genners, it also struggles with some 2D styles

Comments