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

User LoRA

DiT.3DiT.2XL
Style

Yuu_Cel shading style

Create

  • AI Image Generator
  • AI Animation Generator
  • AI Tools
  • Thematic generators
  • Train LoRA
  • Mio.2 Agent
  • Studio

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
Yuu_Cel shading style - AI Model cover image
Trained by
Avatar image of ゆう(late reply)

ゆう(late reply)

Train Your Own LoRA
Uploaded at
Aug 12, 2026, 4:00 AM
Uses
30.6k
Earned
1,251,967
Reviews
Excellent  (3)
Trigger Words

cel shading style, hard shadow, flat colors, clean lineart, sharp lines, vector art, crisp lines, flat colors, vibrant color palette, rim lighting, soft glowing light, smooth shading, flawless, intricate, very aesthetic, intricate details, high resolution, newest, flawless, beautiful face, (beautiful detailed eyes:1.2),

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

Description

アニメや漫画のような手描き風に見せる描画スタイルです。光と影のグラデーションをあえて省き、境界線をはっきりさせた平坦な影をつけることで、平面的なセル画(アニメ絵)のように表現します。Divineモデルでトリガーワードで生成したイラスト100枚、Step数13、CFG Scale4.5、DDIMで作成したものを学習させました。Lcm&Turbo MixやDMD系のLORAと一緒に併用したらより効果が得られると思います。

This drawing style mimics the hand-drawn look of anime and manga. It achieves a flat, "cel-shaded" aesthetic by intentionally omitting light-and-shadow gradients in favor of distinct, hard-edged shadows. The model was trained on 100 illustrations generated using the Divine model with specific trigger words, utilizing 13 steps, a CFG scale of 4.5, and the DDIM sampler. You may achieve even better results by combining this with LCM & Turbo Mix or DMD-based LoRAs.

Comments