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

Conversational creation

AI Tools
Guide

User LoRA

DiT.3
Style

DiT3 SDカードダス風style

#card
HomeModelsMio.2Profile

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

  • About PixAI
  • 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
DiT3 SDカードダス風style - AI Model cover image
Trained by
Avatar image of 七夢
avatar-frame

七夢

Train Your Own LoRA
Uploaded at
Sep 18, 2026, 11:44 PM
Uses
46
Earned
0
Reviews
No reviews
Trigger Words

carddass_holographic_chibi_character_card_with_top_white_banner_and_top_left_navigation_marker_style.

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

Description

DiT2 SDカードダス風styleからの焼き直しです。DiT3になったことで、DiT2の制約がほぼすべてなくなりました。簡単に遊べるようになっています。

プロンプト構成としては、冒頭にトリガーワードを入れて、そのあとに、キャラクター・シーン・セリフを追加して頂くだけで普通に遊べます。

セリフは、こんな感じのプロンプトで入れらば大丈夫です。 ※あくまでも1例です。 --------------------------- 上の白いコマには、以下の日本語を描写します。ルビはふりません。

ごきげんよう。 ---------------------------

(LoRAの強さについて)

LoRAの強さも、0.7で遊べます。キャラLoRA併用でも0.7同士の掛け合わせでいけますが、崩れる場合には、本LoRAを1.2の強さまで引き上げてみて頂ければと思います。

(その他)

DiT3になり、性能が引きあがり、プロンプトへの解釈が豊かになった結果、カードの形状が少し変化しています。気にならないレベルではあるので、現状はそのままとしています。

DiT3: SD Carddass Style

This is a revamped version of the "DiT2 SD Carddass Style." With the transition to DiT3, almost all the limitations found in DiT2 have been eliminated, making it easier to use.

To use it, simply place the trigger word at the beginning of your prompt, followed by the character, scene, and dialogue.

You can include dialogue using a prompt structure like this: This is just an example. ------------------------------ Depict the following Japanese text in the white panel at the top. Do not include furigana (reading aids).

Greetings. -------------------------------

(Regarding LoRA Strength)

A LoRA strength of 0.7 works well. You can combine it with a character LoRA at 0.7, but if the image quality degrades, try increasing this LoRA's strength to 1.2.

(Other Notes)

The upgrade to DiT3 has improved performance and enriched prompt interpretation, resulting in a slight change to the card's shape. As the difference is negligible, I have left it as-is for now.

Comments