Iscrizione PixAI
PixAI
PixAI
Generate
Sign in
Home
Generazione
Modelli
Studio
NEW
Contest
Crea con Mio.2
AI Tools
NEW
Guide

PixAI DiT.1

Tsubaki

Crea

  • Generatore di immagini IA
  • Generatore di animazioni IA
  • AI Tools
  • Generatori tematici
  • Allena LoRA
  • Agente Mio.2
  • Studio

Scopri

  • Trending Tags
  • Classifica
  • Market dei modelli
  • Contest
  • Notizia

Informazioni

  • Guide
  • Come utilizzare PixAI
  • Tsubaki.2
  • Scopri Mio
  • Regole sui contenuti

Prezzi e assistenza

  • Appartenenza
  • Pacchetti di crediti
  • Contatto

App mobile

  • Scarica l'app PixAI
  • App Store
  • Google Play
© 2026 PixAI
  • Termini di servizio
  • Informativa sulla privacy
  • Politica sul copyright
  • Attributions
  • Legge sulle transazioni commerciali specificate
Tsubaki - AI Model cover image
Caricato su
24 giu 2025, 03:39
Utilizzi
28.8m
Reviews
Excellent  (454)
Passaggi di campionamento

25

Metodo di campionamento

Euler

Scala CFG

4.5

Negativo

bad quality, low quality, worst quality, lowres, nsfw, jpeg artifacts, scan artifacts, mosaic, cropped, error, fewer digits, bad reflection, bad composition, bad anatomy, bad hands, bad fingers, missing fingers, extra hands, extra legs, excess fingers, light particles, artist name, text, watermark, username, copyright name

Permessi
  • Allow image generation & sharing
  • Permettete agli utenti di scaricare il vostro modello
  • Usi commerciali

Recommended LoRAs

Sabotenman Style DiT.1 - AI Model cover image

User LoRA

Sabotenman Style DiT.1
42
Background Enhancer [SDXL] - AI Model cover image

User LoRA

Background Enhancer [SDXL]
6.70k
Semi-realistic_women - AI Model cover image

User LoRA

Semi-realistic_women
770
Detailed Cute Style v2.0 - AI Model cover image

User LoRA

Detailed Cute Style v2.0
753

Descrizione

✨ Tsubaki

A next-generation PixAI model built entirely from scratch, powered by cutting-edge Diffusion Transformers (DiT). DiT combines the creative breadth of diffusion models with the efficiency of transformer attention—delivering sharper details, richer compositions, and smarter prompt handling.


🚀 Key Strengths

  • Natural-language prompts supported (tags optional)
  • Fine-grained prompt following, even with per-character instructions in a single image
  • Long, detailed, and complex prompts fully supported
  • Higher-quality multi-character generation (spacing, interaction, balance)
  • Improved character interactions (eye-lines, gestures, overlaps)

🔧 Smarter Prompt Helper (ON by default)

Our improved Prompt Helper auto-rewrites your input on the fly—injecting style tags, balancing weights, and optimizing structure for DiT.

  • Short prompts? No problem—Prompt Helper fills in the gaps.
  • Prefer full control? Toggle it OFF and supply a long, descriptive prompt for best results.

Tip: To inspect the rewritten prompt, open Profile → Generation Tasks → your task.


✨ Tsubaki

PixAI がゼロから開発した次世代モデル。最先端の Diffusion Transformers(DiT) を採用しています。
DiT は拡散モデルの表現力とトランスフォーマーアテンションの効率性を融合し、より鮮明なディテール、豊かな構図、そして賢いプロンプト解釈を実現します。


🚀 主な強み

  • 自然言語プロンプト に対応 (タグでもOK!)
  • 1枚の画像内でキャラクターごとの指示も忠実に反映
  • 長文・詳細・複雑なプロンプトにも対応
  • 複数キャラクター生成の品質向上(配置・相互作用・バランス)
  • キャラクター間のインタラクション表現がさらに自然(視線・ジェスチャー・重なり)

🔧 改良版 Prompt Helper(デフォルト ON)

改良版 Prompt Helper が入力をリアルタイムで自動リライトし、スタイルタグの挿入や重み付けを調整して DiT に最適化します。

  • 短いプロンプトでも問題なし — Prompt Helper が不足を補います。
  • 完全に手動で制御したい場合はPrompt Helperを OFF にしてください。その場合、高品質な画像を得るためには長くて詳細なプロンプトをオススメします。

ヒント: 拡張されたプロンプトを確認するには Profile → Generation Tasks → 該当するタスク を開いてください。


Commenti275