PixAI会員
PixAI
PixAI
Generate
Sign in
ホーム
生成
モデル
Studio
NEW
コンテスト
Mio.2 で作成
ツールボックス
NEW
ガイド

ユーザーLoRA

XL
キャラ

Tokisaki Kurumi | Date a Bullet

創作

  • AI画像生成
  • AI動画生成
  • ツールボックス
  • テーマジェネレーター
  • LoRA学習
  • Mio.2 エージェント
  • Studio

探索

  • 人気タグ
  • ランキング
  • モデルマーケット
  • コンテスト
  • お知らせ

PixAIについて

  • ガイド
  • PixAI ブログ
  • Tsubaki.2
  • マスコットのミオに会う
  • コンテンツ規則

料金とヘルプ

  • 会員
  • クレジットパック
  • お問い合わせ

アプリ

  • App Store
  • Google Play
© 2026 PixAI
  • 利用規約
  • プライバシーポリシー
  • 著作権ポリシー
  • 特定商取引法
Tokisaki Kurumi | Date a Bullet - AI Model cover image
アップロード日時
2025/12/04 23:13
採用数
94
レビュー
不評
トリガーワード

kurumi_cnr, 1girl, tokisaki kurumi, black hair, twintails, red eyes, long hair, clock eyes, yellow eyes, heterochromia, symbol-shaped pupils, medium breasts,, hairband, red hair ribbon,detached sleeves, red dress, frills, detached collar, choker,boots, frills,

権限
  • 画像生成と共有を許可する
  • ユーザーによるモデルのダウンロードを許可する
  • 生成画像の商用利用を許可する

おすすめLoRA

Fkey style - AI Model cover image

ユーザーLoRA

Fkey style
16
Pegasus Tenma from Saint Seiya: Legend of Sanctuary - AI Model cover image

ユーザーLoRA

Pegasus Tenma from Saint Seiya: Legend of Sanctuary
4
Yu Zhong/ MLBB - AI Model cover image

ユーザーLoRA

Yu Zhong/ MLBB
1
firecracker suit (the boys) - AI Model cover image

ユーザーLoRA

firecracker suit (the boys)
13

詳細説明

https://civitai.com/models/2194538/tokisaki-kurumi-or-date-a-bullet

✨ Hey everyone, welcome to another one of my LoRAs. I'm implementing some changes for my new and existing LoRAs. These won't apply to all of them, but they will apply to the majority of my models.

  1. Added support for representing the original anime style. You can now use the following tags to guide the artistic style,

2010s (style) 2000s (style) 2020s (style) You can also look up the anime's original release year and write it in the same format. Since the art style is inherently tied to its era, you'll get better results by representing it with the decade the anime was released.

I've tested this feature with the "WAI-illustrious-SDXL v15" and "Hoseki - LustrousMix" checkpoints. I'm unsure if other IL checkpoints are compatible. It would be great if someone could test it out and share their findings!

  1. My models now have a unique quality tag. For cases where the model consistently generates images with the same pose or expression, you can activate a special tag:

enh_cnr Important

This tag is exclusive to my LoRAs and will not work with any others.

You can enhance its effect like this: (enh_cnr:1.5).

I do not recommend using a weight above 2.0, as the character's essential features will begin to be lost.

💬 SUGGEST A CHARACTER

━━━━━━━━━━━━━━━

You can submit your favorite characters here 👇

(I can’t promise to make them all, but I do check every suggestion and many end up on my list!) 📩https://docs.google.com/forms/d/e/1FAIpQLScszoBsFOPGky4Fcx_BVEOCp_nftd0Fj5_cSDZXsYQccB6AOg/viewform

🎯 COMMISSION A CHARACTER (Priority / Exclusive)

━━━━━━━━━━━━━━━

If you want a character made just for you, or wish to skip the suggestion queue, I offer priority commissions through Civitai and Ko-Fi.

This includes:

  • Guaranteed character creation

  • Option to request extra outfits or custom styles

  • Exclusive or early access

🔹 Civitai Commissions: Just send me DM

🔹 Ko-Fi: Cinabrio

📝 INSTRUCTIONS ━━━━━━━━━━━━━━━

Each model I release is made with two main goals in mind:

✔ Stay true to the character’s essence (face, body, unique traits)

✔ Give you freedom to mix outfits and styles however you like

Below I explain how the prompts are organized so you can get the best results quickly and easily.

You can find the full prompts in the “About this version” section.

🧬 Physical Core (Base Prompt)

This is what I call the visual DNA of the character. It includes the face, body, eyes, and any defining physical traits.

Use this as the foundation to generate the character in different outfits or scenes. You are free to combine these traits with any clothing tags you prefer.

👗 Signature Outfit Prompt

This section includes the default iconic outfit(s) of the character.

To keep the LoRA efficient and lightweight, I usually include 1–2 recognizable outfits. More may be added in future updates if needed.

🎨 Recommended Settings

These are the settings I personally use for stable results (feel free to experiment!):

  • Sampler: Euler or DPM++2M (25–35 steps)

  • LoRA Weight: 0.8 (up to 1.0 for stronger accuracy)

  • ADetailer: On (for sharp facial features)

  • CFG Scale: 5–6

⚡ Thank you for supporting my work!

Every interaction, downloads, comments, or a little Buzz⚡. helps me continue creating more characters and improving future models.

Enjoy exploring this LoRA and have fun generating!

Discussion

コメント