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

User LoRA

XL
Style

Little Girl

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
Little Girl - AI Model cover image
Trained by
Avatar image of Yumiko

Yumiko

Train Your Own LoRA
Uploaded at
May 12, 2025, 3:03 AM
Uses
303k
Earned
879,942
Reviews
Excellent  (18)
Trigger Words

(little girl:2)

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

Recommended LoRAs

Sigewinne (Genshin Impact) - AI Model cover image

User LoRA

Sigewinne (Genshin Impact)
4
Rikose Style - AI Model cover image

User LoRA

Rikose Style
113
[Illustrious] Star Platinum (Jojo's Bizarre Adventure) + 3 Versions - AI Model cover image

User LoRA

[Illustrious] Star Platinum (Jojo's Bizarre Adventure) + 3 Versions
9
Baby Ruby Hoshino - AI Model cover image

User LoRA

Baby Ruby Hoshino
17

Description

There is a new version: https://pixai.art/model/2013972513369049388

Writing a bit of a guide how to use this LoRA here, but nobody seems to read LoRA descriptions before using them these days... If you happened to see this, please read the description before using...

This LoRA makes body even smaller, like that of kindergarteners or preschoolers (or close to that range), aged around 4-8.

Recommended LoRA weight is around 1 and it is not advised to set it above 1 , otherwise you will probably get visible distorion and saturation issues.

Consider adjusting keyword weight to control effect more closely (don't confuse this with LoRA weight, which is adjusted by the slider);

The keyword weight is expressed in following format (keyword:weight), the default being 1 if only keyword is set and weight is omitted.The keyword weight controls how important the keyword is in the prompt and how closely AI must try to follow this specific keyword in generation.If keyword weight not strong enough, AI can converge on something that "it thinks makes more sense" and somewhat ignore the word.Also, other LoRA's and character tags might interfere with the effect,most often when it's a character tag of someone generally depicted as adult.In these cases you should add "aged down" to the prompt and adjust it's weight accordingly.

It is generally not advised to set keyword weight above 4 to avoid artifacts or completely unexpected results.

The desired effect is best achieved this keyword weight being 2 on most models, but this might not be true for all of them.Decrease the weight value if you see distortion and artifacts and increase it if you don't see desired effect when using on your model.

Example prompt: "1girl,solo,(little girl:2),full body,simple background, white background,aged down,bag,child,kindergarten bag,kindergarten uniform,school hat,yellow hat,kindergartener,blue dress,white socks,kneehighs,long sleeves,smock,hat,shoulder bag,yellow bag,contrast collar,name tag,shirakami fubuki, (ears through headwear:1.2), aqua eyes, fox ears, single braid, animal ears, virtual youtuber, fox girl, white hair,hair between eyes, side braid, braid, animal ear fluff, ahoge, sidelocks"

Comments