怎麼填變量：[唐代襦裙] 是唯一必填項，可以換成"宋代褙子""明代馬面裙""漢代曲裾"這類服飾，也可以換成器物和工藝，如"越窯青瓷""景泰藍""榫卯木椅"，模型會自動改成器物拆解版式；背景色可以按主題換成"淺灰綠""暖米黃"。示例圖是原作者的出圖：頂部大標題"唐代襦裙"，中間是一位梳高髻、披淺青披帛、穿橙紅長裙的女子全身像；左側依次拆解襦、裙、披帛、腰帶和履，右側是絲綢、錦緞、紗羅的面料小樣和主色板、紋樣，底部是從穿內衣到繫腰帶的穿着順序流程圖和核心特徵總結。

常見問題與調整：

• 中文小字出錯：減少說明文字量，"每個說明不超過 20 個字"。
• 版式跑偏成古風寫真：強調"這是展板資訊圖，人物只佔中間三分之一寬度"。
• 想出英文版給外國朋友：把"所有文字必須是簡體中文"改成"中英雙語，中文在上"。
• 結構不準：在主題後補充關鍵部件，例如"[明代馬面裙：馬面、褶襉、裙腰]"。

適合：傳統服飾 / 文物科普長圖、課堂展板、文創介紹頁；圖中歷史細節需要對照文博資料核實，不適合直接當學術依據。

英文原版

Please automatically generate a "museum catalog-style Chinese disassembly infographic" based on the [Subject].

The entire image is required to combine a realistic main visual, structural disassembly, Chinese annotations, material descriptions, pattern meanings, color meanings, and core feature summaries. You need to automatically determine the most appropriate main subject, clothing system, artifact structure, era style, key components, material craftsmanship, color scheme, and layout structure based on the [Subject], and the user does not need to provide any other information.

The overall style should be: national museum exhibition boards, historical clothing catalogs, and cultural/museum thematic infographics, rather than ordinary posters, ancient-style portraits, e-commerce detail pages, or anime illustrations. The background uses paper textures such as off-white, silk white, and light tea color, making the overall look premium, restrained, professional, and collectible.

The layout is fixed as:
- Top: Chinese main title + subtitle + introduction
- Left: Structural disassembly area, with Chinese lead lines annotating key components, accompanied by close-up details
- Upper right: Material / craftsmanship / texture area, displaying real texture samples with descriptions
- Middle right: Pattern / color / meaning area, displaying the main color palette, pattern samples, and cultural explanations
- Bottom: Dressing order / composition flowchart + core feature summary

If the subject is suitable for character display, use a full-body standing posture of a real person as the central subject; if it is more suitable for artifacts or single structures, change it to a central subject disassembly diagram, but the overall form remains a complete Chinese infographic. All text must be in Simplified Chinese, clear, neat, and readable, without garbled characters, typos, English, or pinyin.

Avoid: poster feel, studio portrait feel, e-commerce feel, anime feel, cosplay feel, random annotations, incorrect structures, blurry text, fake materials, excessive decoration.

改編自 @MrLarus 發佈、wuyoscar/GPT-Image2-Skill 收錄的提示詞，倉庫許可證 MIT（Copyright (c) 2026 Wuyoscar）。