PixAI Membership
PixAI
PixAI
Generate
Sign in
Home
Generate
Models
Studio
Contest
Mio.2

Conversational creation

AI Tools
Guide

User LoRA

XL
Style

Semi-Realistic Chinese Fantasy Style [Haruka Ver.]

#Hanfu#China#Fantasy

AI Tools

  • OC Maker
  • AI Anime Generator
  • VTuber Maker
  • Sonic OC Maker
  • Hazbin Hotel OC Maker
  • Anime Character Creator
  • AI Figure Generator
  • Genshin OC Maker
  • All AI Tools

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
Semi-Realistic Chinese Fantasy Style [Haruka Ver.] - AI Model cover image
Trained by
Avatar image of Soda

Soda

Train Your Own LoRA
Uploaded at
Jul 24, 2025, 10:27 AM
Uses
216
Earned
25,669
Reviews
Excellent  (2)
Trigger Words

masterpiece, best quality, amazing quality, chinese fantasy, fantasy

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

Recommended LoRAs

Riay.H artstyle (Pony) - AI Model cover image

User LoRA

Riay.H artstyle (Pony)
1
ariela raven - AI Model cover image

User LoRA

ariela raven
5
nono - AI Model cover image

User LoRA

nono
0
KMS Peter Strasser (彼得·史特拉塞) (ペーター・シュトラサッサー) - Azur Lane - AI Model cover image

User LoRA

KMS Peter Strasser (彼得·史特拉塞) (ペーター・シュトラサッサー) - Azur Lane
8

Description

!! This is a version made with Haruka !!

This is a semi-realistic style of Chinese fantasy, especially the one that can be found on loading screens of Chinese mobile games and their sprites. This LoRA can also imitate the style close to the one used in Romance of the Three Kingdoms games. This LoRA always tends to create semi-realistic style, even with anime models. Portraits and face-centered images without too complex backgrounds can be created on all models, even low cost ones, whereas more complex images, with a vast view, complex architecture and multiple characters are better to be generated on more powerful models (like Haruka, for example). This LoRA is also trained to generate multiple characters if you want to generate more than one.

Example images are made without using any additional LoRA except this one to show the raw capability of the LoRA. For better and even more detailed results with more complex images, use enhancer LoRA. Portrait images don't strictly require the use of additional LoRA if you don't want to.

Comments