Back to Details

character-reference-sheet

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Character Reference Sheet

角色参考图

Capability

功能特性

Analyzes an attached character image to perform deep feature extraction (facial physiognomy, physical attributes, costume details) and generates a split-screen image containing two full-body views (Front and Back) on a simple color background, maintaining the exact visual style of the source.
分析上传的角色图片，进行深度特征提取（面部特征、体态属性、服装细节），生成包含两个全身视图（正面和背面）的分屏图片，背景为纯色，完全保留源图的视觉风格。

Triggers

触发指令

  • "Create a character reference sheet."
  • "Generate a front and back view of this character."
  • "Make a split-screen character sheet."
  • "Analyze this character and create a reference image."
  • "创建角色参考图。"
  • "生成该角色的正面和背面视图。"
  • "制作分屏角色参考图。"
  • "分析该角色并创建参考图。"

Instructions

操作步骤

  1. Research Character (Visual & Web Search):
    • Visual Analysis: detailed feature extraction (physiognomy, attributes, costume).
    • Web Search: If the character appears to be from a franchise or has a name, use 
      search_web
      to find setting/lore details to inform dynamic poses.
  2. Construct the Image Generation Prompt:
    • Layout & Views:
      • Default (Split Screen): "Split-screen, Left: Front view, Right: Back view."
      • 2x2 Layout: "Four-panel grid. Top-Left: Front view. Top-Right: Back view. Bottom-Left & Bottom-Right: Dynamic action poses [based on character setting]."
      • 3x3 Layout: "Nine-panel grid. Center: Front view. Top-Center: Back view. Remaining panels: Varied dynamic poses and close-ups [based on character setting]."
      • Mandatory: Front and Back views are always required.
    • Background: "...on a simple color background."
    • Details: "Exact mirror of facial features, physical attributes, and costume details from the source."
    • Visual Constraints: "Style Fidelity: Retain the exact visual style, rendering technique, and lighting quality of the source image."
  3. Generate the Image:
    • Use the image generation tool with the constructed prompt and the user's reference image.
  1. 角色调研（视觉分析与网络搜索）:
    • 视觉分析: 提取详细特征（面部特征、体态属性、服装细节）。
    • 网络搜索: 如果识别出角色来自某个IP或有明确名称，使用
      search_web
      工具查找背景设定/世界观细节，用于设计动态姿势。
  2. 构建图像生成提示词:
    • 布局与视图:
      • 默认（分屏）: "分屏布局，左侧：正面视图，右侧：背面视图。"
      • 2x2布局: "四格网格布局。左上：正面视图。右上：背面视图。左下与右下：基于角色设定的动态动作姿势。"
      • 3x3布局: "九格网格布局。中心：正面视图。顶部中心：背面视图。其余格子：基于角色设定的多种动态姿势及特写。"
      • 强制要求: 必须包含正面和背面视图。
    • 背景: "……背景为纯色。"
    • 细节: "完全镜像还原源图中的面部特征、体态属性及服装细节。"
    • 视觉约束: "风格保真：完全保留源图的视觉风格、渲染技法及光影效果。"
  3. 生成图像:
    • 使用图像生成工具，结合构建好的提示词和用户上传的参考图片。

Tools / Commands

工具/命令

  • search_web
    : To research character background/setting.
  • Image generation tool: To generate the reference sheet.
  • search_web
    : 用于调研角色背景/设定。
  • 图像生成工具: 用于生成参考图。

Examples

示例

User: "Create a reference sheet for this character." (User attaches 
[image]
) Action:
  1. Research: Analyze 
    [image]
    . (Optional) Web search if character is recognized.
  2. Prompt: "A split-screen character reference sheet... Left: Front, Right: Back..."
  3. Generate: Call tool.
User: "Make a 3x3 reference sheet for 'Cloud Strife'." (User attaches 
[image]
) Action:
  1. Research: Recognize "Cloud Strife". Search web -> "FF7, Buster Sword, Soldier pose".
  2. Prompt: "Nine-panel grid character sheet for Cloud Strife. Center: Front static. Top-Center: Back static. Surrounding panels: Dynamic sword swings, limit break poses. High fidelity to source."
  3. Generate: Call tool.
用户: "为这个角色创建参考图。"（用户上传
[图片]
） 操作:
  1. 调研: 分析
    [图片]
    。（可选）若识别出角色，进行网络搜索。
  2. 提示词: "1:1分屏角色参考图……左侧：正面，右侧：背面……"
  3. 生成: 调用工具。
用户: "为'Cloud Strife'制作3x3参考图。"（用户上传
[图片]
） 操作:
  1. 调研: 识别出"Cloud Strife"。网络搜索→"FF7，破坏剑，战士姿势"。
  2. 提示词: "Cloud Strife的九格网格角色参考图。中心：静态正面。顶部中心：静态背面。其余格子：挥剑动态姿势、极限爆发姿势。高度还原源图风格。"
  3. 生成: 调用工具。