Nano Banana Pro 提示詞

一張用低質素即棄相機拍攝的日常照片。一張由日本高中生拍得不太好的相片。

分析輸入圖像的整體構圖。識別所有出現的主要主體（無論是單人、群組／情侶、車輛或特定物件），以及它們之間的空間關係與互動。 …

Completely reproduce the attached image as a single slide in a pptx file. Make the text fully editable, and crop and use the diagrams and graphs from the original image as they are.

生成一個由 9 張圖片組成的「photo dump」網格，記錄這個人物的週末生活：一張對鏡自拍、一張咖啡廳照片、一張與朋友聚餐的合照、一張模糊的派對照、一張散步時拍下的照片、一張筆記本電腦配咖啡的工作照、一張與寵物互動的照片、一張日落風景，以及一張自然開懷大笑的抓拍。

{ "technical_specs": { "aspect_ratio": "2:3", "camera_angle": "Overhead / High-angle (bird's-eye view)", "lighting_style": "Soft, natural indoor light" }, "subject": { "demographics": { "type": "Woman", "age": 19 }, "p…

Input this instruction, allowing the AI to complete the entire process step-by-step: extracting selling points, determining style, determining layout, and finally generating a complete, system-wide prompt. Finally, give the AI-generated prompt to the Nano Ban…

{ "technical_specs": { "aspect_ratio": "2:3", "camera_angle": "Overhead / High-angle (bird's-eye view)", "lighting_style": "Soft, natural indoor light" }, "subject": { "demographics": { "type": "Woman", "age": 19 }, "p…

{ "prompt_type": "photorealistic gym mirror selfie", "main_composition": "mirror selfie of two athletic young women standing side by side with backs to the camera in a dimly lit modern gym, confidently posing with hands on hips and slight arch to emphasize…

"image_generation":( "quality": "hyper-realistic", "face": ("preserve_original": true, "reference_match'": true), "subject":{ "description": "A stylish person with the same face.", “clothing":{ "Top": ("type": "knitted sweater", "color": "{argument name="sw…

{   "prompt_data": {     "subject": {       "description": "Young woman with long, wavy blonde hair and a light fair skin",       "features": "Natural skin texture with visible tan lines on the chest, slight flush on cheeks, soft smile, navel piercing, light f…