由一張參考圖生成的雙人自拍亭 2×2 拼圖

無縫 2×2 自拍亭拼圖：戴眼鏡的金髮女生和穿條紋 T 恤的男生在藍色拍照間裡擺搞怪姿勢，包括揹著對方

{
  "task": "Create an iPhone-realistic photobooth collage (4 photos in a 2x2 grid)",
  "subjects": [
    {
      "id": "Subject 1",
      "description": "EXACTLY from the Reference Image (same face, hairstyle, skin tone, body proportions, overall look).",
      "outfit": "EXACTLY the same as in the Reference Image. Do not change clothing, glasses, or accessories."
    },
    {
      "id": "Subject 2",
      "description": "EXACTLY from the Reference Image (same face, hairstyle, skin tone, body proportions, overall look).",
      "outfit": "EXACTLY the same as in the Reference Image. Do not change clothing, glasses, or accessories."
    }
  ],
  "scene": {
    "location": "Inside a small BOX photo booth",
    "background": "Matte blue walls and blue floor, tight enclosed corner, clean minimal environment",
    "camera_look": "Ultra wide / slight fisheye lens look with subtle perspective distortion typical of photobox cameras. iPhone 17 Pro, photobooth wide-angle.",
    "lighting": "Bright neutral-white flash lighting, evenly illuminating faces, soft shadow falloff on blue walls, crisp detail, realistic skin texture. Direct neutral white flash (no yellow / no warm tone).",
    "aesthetic": "4K, amateur photobooth aesthetic, high contrast but still natural, no cinematic grading, no heavy beauty filter, no blur, no text, no watermark."
  },
  "layout": {
    "type": "2x2 grid collage",
    "aspect_ratio": "9:16 (vertical collage)",
    "style": "Clean, with NO white borders, NO frame lines, NO gaps, and NO outlines between photos (seamless collage). Each frame fills its quadrant edge-to-edge."
  },
  "frames": [
    {
      "position": "top-left",
      "content": "Subject 1 leans diagonally toward the camera from the front-left, one arm stretched down, playful serious face; Subject 2 stands behind in the center, arms raised and flexing like “strongman”, smiling."
    },
    {
      "position": "top-right",
      "content": "Subject 2 leans forward toward the camera, hands on knees, curious expression; Subject 1 enters from the right side very close to camera, tilting her head, one arm arched above her head like a half-heart pose, soft smile."
    },
    {
      "position": "bottom-left",
      "content": "Piggyback pose — Subject 1 on Subject 2’s back, arms wrapped around shoulders; both laughing big, faces close to camera, dynamic motion vibe."
    },
    {
      "position": "bottom-right",
      "content": "Subject 2 bends sideways/leans forward with a goofy face; Subject 1 stands behind making playful “claw/horns” hand gestures above Subject 2’s head, slightly pouting for fun."
    }
  ]
}

{
  "task": "Create an smartphone-realistic photobooth collage (4 photos in a 2x2 grid)",
  "subjects": [
    {
      "id": "Subject 1",
      "description": "EXACTLY from the Reference Image (same face, hairstyle, skin tone, body proportions, overall look).",
      "outfit": "EXACTLY the same as in the Reference Image. Do not change clothing, glasses, or accessories."
    },
    {
      "id": "Subject 2",
      "description": "EXACTLY from the Reference Image (same face, hairstyle, skin tone, body proportions, overall look).",
      "outfit": "EXACTLY the same as in the Reference Image. Do not change clothing, glasses, or accessories."
    }
  ],
  "scene": {
    "location": "Inside a small BOX photo booth",
    "background": "Matte blue walls and blue floor, tight enclosed corner, clean minimal environment",
    "camera_look": "Ultra wide / slight fisheye lens look with subtle perspective distortion typical of photobox cameras. flagship smartphone, photobooth wide-angle.",
    "lighting": "Bright neutral-white flash lighting, evenly illuminating faces, soft shadow falloff on blue walls, crisp detail, realistic skin texture. Direct neutral white flash (no yellow / no warm tone).",
    "aesthetic": "4K, amateur photobooth aesthetic, high contrast but still natural, no cinematic grading, no heavy beauty filter, no blur, no text, no watermark."
  },
  "layout": {
    "type": "2x2 grid collage",
    "aspect_ratio": "9:16 (vertical collage)",
    "style": "Clean, with NO white borders, NO frame lines, NO gaps, and NO outlines between photos (seamless collage). Each frame fills its quadrant edge-to-edge."
  },
  "frames": [
    {
      "position": "top-left",
      "content": "Subject 1 leans diagonally toward the camera from the front-left, one arm stretched down, playful serious face; Subject 2 stands behind in the center, arms raised and flexing like “strongman”, smiling."
    },
    {
      "position": "top-right",
      "content": "Subject 2 leans forward toward the camera, hands on knees, curious expression; Subject 1 enters from the right side very close to camera, tilting her head, one arm arched above her head like a half-heart pose, soft smile."
    },
    {
      "position": "bottom-left",
      "content": "Piggyback pose — Subject 1 on Subject 2’s back, arms wrapped around shoulders; both laughing big, faces close to camera, dynamic motion vibe."
    },
    {
      "position": "bottom-right",
      "content": "Subject 2 bends sideways/leans forward with a goofy face; Subject 1 stands behind making playful “claw/horns” hand gestures above Subject 2’s head, slightly pouting for fun."
    }
  ]
}

\biPhone 1\d(?: Pro(?: Max)?)?\b -> 'flagship smartphone' x1
\biPhone[- ]realistic\b -> 'smartphone-realistic' x1

cinel 為生成示例圖做了以上替換。

模型

1K 約 9 積分。比例 9:16。需要你自己上傳參考圖。

電影感極簡時尚宮格ratio 9x16needs reference

引數

分類	人像寫真
畫面比例	9:16
輸入	需要參考圖
示例圖模型	GPT Image 2.5
推薦模型	Nano Banana Pro, Nano Banana 2, Seedream 5 Pro
原作者	@NameIsSudee · X 原帖
原帖模型	nanobanana

這條提示詞為什麼有效

重現自助拍照亭的樂趣：狹小的藍色拍照間、略帶魚眼的廣角鏡頭、明亮的中性閃光，以及四個寫好的搞怪姿勢（大力士秀肌肉、半個比心、揹著跑、在朋友頭上比“角”）。它還要求格與格之間沒有邊框和縫隙，讓九比十六的整張影象一張無縫的大頭貼。原文為了這種觀感指定了某款手機型號，我們改成了旗艦智慧手機。用一張兩位成年朋友的虛構參考圖（戴眼鏡的金髮女生和穿條紋 T 恤的男生），成品四格中兩人的臉和服裝都保持一致。適合活動拍照亭、友情節帖子或情侶內容。

如何改寫

變數	作用	示例
Subject 1 / Subject 2	參考圖中的兩個人	兩位朋友, 情侶, 兄弟姐妹
哑光蓝墙和蓝地板	拍照間顏色	粉色拍照間, 白色拍照間
frames（4 个姿势）	姿勢指令碼	揹著、秀肌肉、半個比心、比角