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

Conversational creation

AI Tools
Guide

User LoRA

XL
Style

JSのポーズLORA (Haruka v2 & Illustrious向)

#Small Breasts

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
JSのポーズLORA (Haruka v2 & Illustrious向) - AI Model cover image
Trained by
Avatar image of kawa86tarou

kawa86tarou

Train Your Own LoRA
Uploaded at
Jan 29, 2026, 1:16 AM
Uses
153k
Earned
783,894
Reviews
Excellent  (6)
Trigger Words

Elementary school student, Loli, panties,small breasts,

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

Recommended LoRAs

深園 希衣佳(ゴア・スクリーミング・ショウ) - AI Model cover image

User LoRA

深園 希衣佳(ゴア・スクリーミング・ショウ)
3
Surrounded by penises (kneeling) - AI Model cover image

User LoRA

Surrounded by penises (kneeling)
24
Margie  - AI Model cover image

User LoRA

Margie
1
[PONY] Cheerleader Outfit | Blue Archive - AI Model cover image

User LoRA

[PONY] Cheerleader Outfit | Blue Archive
128

Description

実写JS(多分china系?可愛い娘)が自由に楽しくポーズをとっている画像を100枚フル学習させてLOLAにしました 水着、下着以外着用ナシの画像が元なので生成時に変な物体や文字は出ないと思います 成人キャラクターをLOLI化する時やJSのポーズ画像を生成するときに足しになるかも…

前に作成した「こどもぱんつLOLA」との違いは、前はぱんつのクローズアップに特化した学習構成でしたが今回は全身と頭から膝上を中心に学習してポーズ全体の破綻を回避する目的で作成してます

推奨される比重は0.4-0.5、 0.6-0.7だとリアル寄りになる傾向があります リアル寄りの画像生成ではそのまま使えますがアニメキャラだと違和感が出る可能性があるので低めに設定して下さい。自分で何枚か生成しましたが時に問題はありませんでした。問題がある様なら非公開にします お気に召しましたら,いいねブックマーク宜しくお願いします  (26.01.29 Illustrious向きのバージョンを追加しました)

I created LOLA by training it with 100 images of a live-action JS character (probably a cute girl of Chinese descent?) posing freely and happily. Since the images were based on images of the character wearing nothing but a swimsuit or underwear, I don't think any strange objects or text will appear during generation. This may be useful when creating LOLIs for adult characters or generating JS pose images.

The difference from my previous "Kids' Panties LOLA" is that while the previous image composition focused on close-ups of panties, this one focuses on the whole body and above the knees to avoid pose issues.

The recommended weighting is 0.4-0.5, while 0.6-0.7 tends to be more realistic. It can be used as is for generating realistic images, but it may look unnatural with anime characters, so set it lower. I generated several images myself and didn't have any problems. If there are any issues, I will make them private. If you like them, please like and bookmark them.

Comments