Ultra-Realistic Cinematic Night Street Selfie During a High-Speed Escape

An extremely detailed, structured prompt for an ultra-realistic cinematic selfie. It specifies complex elements like pose, detailed facial features (preserving identity), outfit, environment (rainy night city with a police chase), high-contrast lighting, and camera style, demonstrating GPT Image 1.5's precision in handling structured visual data.

Prompt by @KView the original post β†—Published 2025-12-20CC BY 4.0

The prompt

Fill in the blanks β€” 2 placeholders

Edit any of these and the prompt below updates. Copy gives you the filled-in version.

"Ultra-realistic cinematic night street selfie with a confident, stylish person in the reference photo leaning out of a car window in a rainy city during a high-speed escape.",

"pose": {

"arm": "extended toward the camera holding the phone",

"head": "slightly tilted back",

"attitude": "fearless, playful"

},

"face\_and\_skin": {

"identity": "100% preserved, no changes to facial structure, proportions, or unique features",

"skin": "smooth, luminous with glossy streetlight highlights",

"cheekbones": "softly sculpted",

"lips": "glossy,",

"eyes": "expressive, partially hidden behind narrow black rectangular sunglasses",

"texture": "realistic, natural skin texture, visible pores, reflections"

},

"hair": {

"style": "long, flowing, wind-blown by speed and night air",

"volume": "natural"

},

"outfit\_and\_details": {

"coat": "bold leopard-print faux-fur draped luxuriously over the shoulders",

"manicure": "glossy red",

"jewelry": "minimal silver rings",

"glass": "elegant martini glass with a clear cocktail and green olives, catching sharp reflections"

},

"environment": {

"setting": "wet asphalt night city street",

"motion": "intense, high-speed, with a police car chasing behind",

"lights": {

"headlights": "blurred, aggressive light streaks",

"street\_lights": "golden sodium street lamps creating large dramatic bokeh circles",

"police\_lights": "blue and red siren flashes creating reflections"

},

"mood": "rebellious, playful, glamorous chaos; adrenaline-fueled nightlife energy",

"aesthetic": "fashion-editorial crime style"

},

"lighting": {

"contrast": "high, dynamic mix of warm sodium streetlights, cold blue police lights, and red siren flashes",

"reflections": "glossy on skin, glass, car body, and rain-soaked street"

},

"camera\_and\_style": {

"perspective": "wide-angle smartphone selfie",

"depth\_of\_field": "shallow",

"background": "strong motion blur with light streaks",

"detail": "ultra-high, realistic film grain",

"color\_grading": "cinematic",

"vibe": "modern luxury runaway"

},

"body": {

": {

"size": "slightly larger and elongated"

}

},

"ratio": "9:16"

Generate asks for your photo, then opens the editor with the prompt already loaded.

Model
GPT Image 1.5
Media
Image
Language
English
Words
268
Retro / VintageCinematic / Film StillPhotographyFood / DrinkFashion ItemVehicle

How to use this prompt

  1. 1Copy the prompt β€” fill in any placeholders first and the copy takes your version.
  2. 2Paste it into your image model, or press Generate to open it here with your own photo.
  3. 3Run it twice. Generation is not deterministic and the second pass is often the keeper.
  4. 4Finish it with the free tools: upscale, crop to the platform you need, compress before sharing.

Go beyond generating the image

Everything after the generation, on the same site.

Upscale to 4K β†’Remove the background β†’Crop for a platform β†’Compress before sharing β†’All AI apps β†’

More from GPT Image 1.5

Same model, same dataset β€” GPT Image 1.5 prompts people have shared.

View all GPT Image 1.5 prompts β†’

All image categories

Use cases
Styles
Subjects