Hyper-Realistic Cinematic Portrait

A highly detailed, structured prompt comparing GPT Image 1.5 and Gemini Nano Banana Pro. The prompt aims to generate a hyper-realistic, cinematic portrait of a rugged man in a worn leather jacket, set in a moody outdoor mountain landscape with specific camera settings (85mm, f/1.8, shallow depth of field) and desaturated color palette.

Prompt by @JohnnView the original post β†—Published 2025-12-19CC BY 4.0

The prompt

{
  "render_goal": "Create a hyper-realistic, cinematic portrait with a rugged outdoor adventure aesthetic",
  "subject": {
    "gender": "male",
    "age_range": "mid-to-late 20s",
    "appearance": {
      "hair": "textured, windswept",
      "beard": "short, well-groomed",
      "facial_features": "sharp, chiseled",
      "expression": "intense, serious"
    },
    "skin_detail": "ultra-detailed, natural texture with realistic tones"
  },
  "wardrobe": {
    "outerwear": "worn dark leather jacket",
    "details": "visible stitching, rugged texture"
  },
  "environment": {
    "location": "outdoor mountain landscape",
    "background": {
      "mountains": "misty, fog-covered",
      "trees": "dark evergreen forest fading into distance",
      "atmosphere": "dense atmospheric fog"
    }
  },
  "lighting_and_color": {
    "lighting_style": "moody, cinematic",
    "light_source": "soft overcast daylight",
    "shadows": "dramatic but natural",
    "color_palette": "cool, desaturated tones"
  },
  "camera_settings": {
    "lens": "85mm",
    "aperture": "f/1.8",
    "depth_of_field": "shallow",
    "focus": "razor-sharp on subject, blurred background"
  },
  "photography_style": {
    "quality": "professional photography",
    "realism_level": "hyper-realistic",
    "details": "high micro-detail, crisp textures, cinematic contrast"
  }
}

Generate opens this prompt in the editor, ready to run.

Model
GPT Image 1.5
Media
Image
Language
English
Words
129
Cinematic / Film StillPhotographyLandscape / NaturePortrait / SelfieAbstract / Background

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