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

User LoRA

XL
Character

Haruka Hoshinogawa - Hirake! Cocotama

AI Tools
  • AI Anime Generator
  • AI Image Generator
  • AI Animation 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
Haruka Hoshinogawa - Hirake! Cocotama - AI Model cover image
Uploaded at
Mar 22, 2025, 6:32 AM
Uses
899
Reviews
No reviews
Trigger Words

harukah, hair bow,, white shirt, pink hoodie, necklace, blue skirt, white socks, pink footwear,

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

Recommended LoRAs

Vivi Hachioji (Himitsu no Aipri) - AI Model cover image

User LoRA

Vivi Hachioji (Himitsu no Aipri)
1
Erer - AI Model cover image

User LoRA

Erer
0
my_favorite_2 - AI Model cover image

User LoRA

my_favorite_2
1
Kan'u Unchou [Ikkitousen] - AI Model cover image

User LoRA

Kan'u Unchou [Ikkitousen]
4

Description

Doing a few requests for a change of pace, i havent seen this anime personally. Working on Hikari Chono, Kokoro Yotsuba, and Nozomi Sakurai. Those will be staggered releases throughout the day most likely unless i decide to train them all while i am sleeping instead but in any case expect those to be the next models i release.Recommend a weight of about 0.8-0.9, it may have over trained a little which surprised me since i ran at low repeats. The other characters have a smaller dataset so if they actually turn out better i may re-evaluate how i look at datasets.

Comments