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

User LoRA

DiT.2DiT.1XL
Style

Detailed Painted Semi-Realistic Style

#Mature Female#Girl
AI Tools
  • AI Anime Generator
  • Anime Figure Generator
  • Character Sheet Generator
  • Magazine Cover Generator
  • Plushie Generator
  • Giant Statue Generator

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
Detailed Painted Semi-Realistic Style - AI Model cover image
Trained by
Avatar image of ドフィー / Doffy

ドフィー / Doffy

Train Your Own LoRA
Uploaded at
Mar 20, 2026, 9:03 AM
Uses
1.54m
Earned
2,747,981
Reviews
Excellent  (76)
Trigger Words

painted art style, paint style, acrylic piainting, oil painting, layered painting, semi-realistic art style, attractive features, detailed features, pseudo-realistic style, semi-realism, detailed colouring, detiled painting, detailed style

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

Recommended LoRAs

Margo Gru (Despicable me) - AI Model cover image

User LoRA

Margo Gru (Despicable me)
1
Style semi-realistic manhwa - AI Model cover image

User LoRA

Style semi-realistic manhwa
42
Yoneyama Mai Dit.2 (✯◡✯) - AI Model cover image

User LoRA

Yoneyama Mai Dit.2 (✯◡✯)
219
pepper0 style - AI Model cover image

User LoRA

pepper0 style
49

Description

My other semi-realistic models don't make the prettiest women.

So I made this model instead! Heads up, it REALLY loves close up, like super close up.

But this model makes attractive semi-realistic women in Niji Journey v6 Style!

To optimise best results: Use models from the preset, such as Hakura to ensure that you get most out of this LoRA.

However, this does not mean EVERY market model doesn't have affect or EVERY SDXL preset model has affect. Ensure the model you are taking practice with can easily be influenced by styled LoRAs with obvious results to see the LoRA takw effect.

Better results range 25-30 sampling steps, I typically use 25 since I'm cheap and constantly run out of points.

(I am aware now about the misspelling but I made this LoRA through Pix.ai and it won’t allow me to change the prompt regardless. The LoRA best functions on Hakura because it a Pix.ai trained LoRA. I made it for fun with images I found off of Mid journey.)

Comments9