Videos Images
Sign in
JSON selfie-in-car mirror prompt for Nano Banana Pro

JSON selfie-in-car mirror prompt for Nano Banana Pro

views1,100
likes50
comments36
shares27
bookmarks5
quotes1
{
  "image_generation_prompt": {
    "subject": {
      "description": "Young woman with long brown hair",
      "pose": "Leaning gently on car window, resting head on one hand, relaxed and confident",
      "action": "Taking a selfie in the side mirror reflection"
    },
    "clothing": {
      "top": "Simple red turtleneck long-sleeve top",
      "accessories": "Minimalist stud earrings"
    },
    "props": {
      "item": "iPhone 17 Pro Max",
      "details": "Realistic proportions, accurate lens design, held in hand"
    },
    "environment": {
      "location": "Outdoors, reflected in the side mirror of a black Toyota Land Cruiser",
      "background": "Trees and orange-blue evening sky",
      "depth_of_field": "Subtly blurred background for depth (bokeh)"
    },
    "lighting": {
      "type": "Golden hour",
      "characteristics": "Warm sunlight, soft natural glow, evening light, realistic shadows"
    },
    "style": {
      "aesthetic": "Natural, ultra-realistic, minimalist, Instagram style",
      "quality": "8k resolution, highly detailed, sharp focus, cinematic photography"
    },
    "technical_constraints": {
      "perspective": "Accurate mirror reflection, correct optical orientation",
      "distortion_control": "No exaggeration or distortion of features or phone"
    }
  },
  "negative_prompt": "cartoon, illustration, painting, drawing, bad anatomy, disfigured, deformed, blurry face, low quality, pixelated, unnatural lighting, distorted phone, wrong reflection angle, extra fingers, messy hair, heavy makeup, text, watermark"
}

✨ Generate Original post Open in Hitboard

How to use this prompt

Copy the prompt and paste it into Nano Banana Pro. Keep the composition, lighting and style terms as written — they are what produced this result. Swap the subject or scene details to make it yours, keep the aspect ratio, and attach the reference images the prompt mentions if any. Regenerate two or three times; the strongest version is usually not the first.