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

フェアリーちゃん

AI Tools
  • AI Anime 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
フェアリーちゃん - AI Model cover image
Trained by
Avatar image of yamanoda

yamanoda

Train Your Own LoRA
Uploaded at
Aug 23, 2026, 2:35 AM
Uses
56
Earned
0
Reviews
No reviews
Trigger Words

fairy, chibi_character

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

Description

[日本語] ちびキャラ: フェアリーちゃんのLoraです(⁠•⁠‿⁠•⁠) シリーズで生成しているフェアリーちゃんの画像を選別して学習しました♪ [注意] 素材がDIT.2産なのでモデルによっては不安定だったり崩れや意図しない結果等になる可能性があります。 コレクション ボックスにsample画像がありますので、確認してから使用有無の判断をお願いします。 sample画像に使用したモデルは「Haruka V2」「Animagine XL V3」「VXP_illustrious (low cost version)」「NoobAI-XL (NAI-XL)」の4種類です。 Sampling STEP、CFGスケール、ネガティブプロンプトは全てデフォルト設定。 リスケールCFG、シフトは一切設定しないで生成した画像になります。 DIT.3が正式に実装されたら、DIT.3 Ver.を作成する予定です(⁠•⁠‿⁠•⁠)

[English] Chibi Character: Fairy-chan LoRA (⁠•⁠‿⁠•⁠) I trained this model by selecting and learning from a series of generated Fairy-chan images♪

[Notice] Since the training data is from DIT.2, results might be unstable, distorted, or unexpected depending on the model you use. Sample images are available in the collection box, so please check them before deciding to use this LoRA. The four models used for the sample images are "Haruka V2", "Animagine XL V3", "VXP_illustrious (low cost version)", and "NoobAI-XL (NAI-XL)". Sampling steps, CFG scale, and negative prompts are all set to default settings. The images were generated without setting any rescale CFG or shift. Once DIT.3 is officially implemented, I plan to create a DIT.3 version! (⁠•⁠‿⁠•⁠)

Comments