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

User LoRA

DiT.1DiT.2
Character

Chikage Hizaki / 緋崎 千影 | Triage X / トリアージX | DiT V1/V2

#purple hair#Purple eyes#Triage X#Chikage

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

  • App Store
  • Google Play
© 2026 PixAI
  • Terms of Service
  • Privacy Policy
  • Copyright Policy
  • Specified Commercial Transactions Law
Chikage Hizaki / 緋崎 千影 | Triage X / トリアージX | DiT V1/V2 - AI Model cover image
Trained by
Avatar image of Hans

Hans

Train Your Own LoRA
Uploaded at
Apr 24, 2026, 9:14 PM
Uses
180
Earned
1,560
Reviews
Excellent  (1)
Trigger Words

Chikage Hizaki, from anime Triage X, purple hair, long hair, purple hair, school uniform, big breasts,

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

Recommended LoRAs

René Cardiff Shishioh ヴァージョン2 - AI Model cover image

User LoRA

René Cardiff Shishioh ヴァージョン2
12
[hikari]赤木澪 / Akagi Mio 《ボクと彼女(ナース)の研修日誌》 Character Pony LoRA - AI Model cover image

User LoRA

[hikari]赤木澪 / Akagi Mio 《ボクと彼女(ナース)の研修日誌》 Character Pony LoRA
14
Amane Lily | 天音 リリ - AI Model cover image

User LoRA

Amane Lily | 天音 リリ
5
Deborah Gorini (My Hero Academia) | [Illustrious] - AI Model cover image

User LoRA

Deborah Gorini (My Hero Academia) | [Illustrious]
2

Description

Trained on Tsubaki, 12 images.

I forgot to include her eye colour ( violet/purple). Her hairstyle sometimes doesn't generate accurately. If you know prompts for it, please share. The same goes for her hair colour, she has a light shade of purple, maybe even pink going on in her hair, so if you figure out a prompt for that, be kind to share. Hope you enjoy.

I use Euler A. 28 steps. Because the results are pretty good, I think you can generate 3 images in parallel, and you will still be fine. Unlike SDXL, DiT is pretty consistent from my initial experience. Of course, if you demand a lot of detail, then maybe go cheap first.

I use 3, 4.5 and 6CFG. 0.7 Rescale CFG, same as every DiT V1 LoRAs I use.

Thumbnail model: Tsubaki

Comments