Ahli PixAI
PixAI
PixAI
Generate
Sign in
Laman Utama
Jana
Model
Studio
NEW
Kontes
Cipta dengan Mio.2
Kotak Alat
NEW
Guide

User LoRA

DiT.3DiT.2XL
Gaya

Yuu_Cel shading style

Cipta

  • Penjana Imej AI
  • Penjana Animasi AI
  • Kotak Alat
  • Penjana Tematik
  • Latih LoRA
  • Ejen Mio.2
  • Studio

Temui

  • Tag Popular
  • Ranking
  • Pasaran Model
  • Kontes
  • Berita

Tentang

  • Guide
  • Cara Menggunakan PixAI
  • Tsubaki.2
  • Kenali Mio
  • Peraturan Kandungan

Harga & Bantuan

  • Keanggotaan
  • Pek Kredit
  • Kontak

Aplikasi Mudah Alih

  • Dapatkan aplikasi PixAI
  • App Store
  • Google Play
© 2026 PixAI
  • Syarat Perkhidmatan
  • Dasar Privasi
  • Dasar Hak Cipta
  • Attributions
  • Undang-undang Transaksi Komersial Tertentu
Yuu_Cel shading style - AI Model cover image
Dilatih oleh
Avatar image of ゆう

ゆう

Latih LoRA Anda Sendiri
Dimuat naik pada
12 Ogo 2026, 4:00 PG
Kegunaan
30.6k
Diperoleh
1,251,967
Ulasan
Cemerlang  (3)
Kata Pencetus

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),

Kebenaran
  • Allow image generation & sharing
  • Benarkan pengguna memuat turun model anda
  • Kegunaan komersial

Keterangan

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.

Komen