Thành viên PixAI
PixAI
PixAI
Generate
Sign in
Trang chủ
Tạo
Mô hình
Studio
NEW
Cuộc thi
Tạo bằng Mio.2
Hộp công cụ
NEW
Guide

User LoRA

XL
Nhân vật

Tokisaki Kurumi | Date a Bullet

Tạo

  • Trình tạo ảnh AI
  • Trình tạo hoạt hình AI
  • Hộp công cụ
  • Trình tạo chủ đề
  • Huấn luyện LoRA
  • Trợ lý Mio.2
  • Studio

Khám phá

  • Thẻ Đang Thịnh Hành
  • Xếp hạng
  • Thị trường Mô hình
  • Cuộc thi
  • Tin tức

Giới thiệu

  • Guide
  • Cách sử dụng PixAI
  • Tsubaki.2
  • Gặp gỡ Mio
  • Quy tắc nội dung

Giá & Trợ giúp

  • Thành viên
  • Gói tín dụng
  • Liên hệ

Ứng dụng di động

  • App Store
  • Google Play
© 2026 PixAI
  • Điều khoản dịch vụ
  • Chính sách quyền riêng tư
  • Chính sách bản quyền
  • Luật Giao dịch Thương mại Đặc định
Tokisaki Kurumi | Date a Bullet - AI Model cover image
Đã tải lên vào
23:13 4 thg 12, 2025
Lượt sử dụng
94
Đánh giá
Không hài lòng
Từ khóa

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,

Quyền
  • Allow image generation & sharing
  • Cho phép người dùng tải xuống mô hình của bạn
  • Sử dụng thương mại

Recommended LoRAs

Fkey style - AI Model cover image

User LoRA

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

User LoRA

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

User LoRA

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

User LoRA

firecracker suit (the boys)
13

Mô tả

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

Bình luận