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

Conversational creation

AI Tools
Guide

User LoRA

SD
Character

Chacha Akaza - 藜チャチャ / Maken-ki! - マケン姫っ!

#Chacha Akaza

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
Chacha Akaza - 藜チャチャ / Maken-ki! - マケン姫っ! - AI Model cover image
Trained by
Avatar image of Hans

Hans

Train Your Own LoRA
Uploaded at
Sep 5, 2023, 2:53 PM
Uses
909
Earned
35,659
Reviews
Excellent  (1)
Trigger Words

ChachaAkaza, dark skin, green eyes, white hair, ponytail, massive breasts,

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

Description

Trained on Hassaku, 20 images. I will test ze model and add description later, trained on majority "SFW" images. I used anime screenshots as well as fanarts, I got some good data. I recommend using settings like Euler A: 23 seeds, 0 credits cost before you spend any. This model can be tricky to handle

Eyes, according to Wiki, Chacha has green eyes, but I only found a few images from season 1. Her eyes will likely generate grey or blue, I think you can brute force it with brackets.

GrahamAingPikas generates face without problem, DarkSushi too. MeinPastel and Hassaku mostly too it seems. It's definitely harder to generate a good face, I now know to not include art from artists who use a different style compared to anime, it can confuse ze program responsible for creating LoRa.

For me, LoRa strength 0.7 works best. You may experiment, I haven't got positive results with stronger LoRa, that might be a problem on my side though.

I use "6" or a bit unusual CFG, 6.8 instead of 7 or 8.

There's already one model, I haven't tried it, but you may also give it a go: https://pixai.art/model/1651579275644507526

Comments