GoPro Action
{ "prompt": "You will perform an image edit using the people from the provided photos as the main subjects. Preserve their core likeness. T…
Prompt
{
"prompt": "You will perform an image edit using the people from the provided photos as the main subjects. Preserve their core likeness. Transform Subject 1 (male) and Subject 2 (male) into adrenaline-junkie urban explorers atop a massive skyscraper. The image is a high-energy, wide-angle POV selfie taken by Subject 1, capturing both men precariously perched on the edge of a rooftop ledge with a dizzying vertical drop to the city streets below. Adhere strictly to a cinematic 1:1 aspect ratio.",
"details": {
"year": "Present Day",
"genre": "GoPro",
"location": "The rooftop ledge of a 100-story skyscraper in a dense metropolis.",
"lighting": [
"Golden hour sunlight",
"Direct harsh flares",
"Natural outdoor exposure"
],
"camera_angle": "Extreme wide-angle fisheye POV (selfie angle), high distortion on the edges, tilting downwards to show the street far below.",
"emotion": [
"Exhilarated",
"Fearless",
"Adrenaline-fueled"
],
"color_palette": [
"Sky blue",
"Sunset orange",
"Concrete grey",
"Vivid sportswear neons"
],
"atmosphere": [
"Vertigo-inducing",
"Windy",
"Epic",
"Dangerous"
],
"environmental_elements": "Tiny cars visible on the grid-like streets below, lens flare artifacts, birds flying beneath the subjects, wind blowing their clothes.",
"subject1": {
"costume": "A technical windbreaker jacket, fingerless grip gloves, and a backward baseball cap.",
"subject_expression": "A wide, shouting grin of pure excitement, looking into the lens.",
"subject_action": "Holding the camera arm extended (selfie style) while leaning out over the void."
},
"negative_prompt": {
"exclude_visuals": [
"ground level view",
"interiors",
"studio lighting",
"tripod stability",
"bokeh",
"flat lens"
],
"exclude_styles": [
"oil painting",
"sketch",
"vintage film",
"studio portrait"
],
"exclude_colors": [
"sepia",
"monochrome"
],
"exclude_objects": [
"safety railings",
"fences"
]
},
"subject2": {
"costume": "A hooded athletic vest, cargo joggers, and climbing shoes.",
"subject_expression": "Intense focus mixed with a daredevil smirk.",
"subject_action": "Balancing on one leg on the very edge of the cornice, throwing a 'peace' sign towards the camera."
}
}
}How to use this prompt
- 1
Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.
- 2
Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.
- 3
Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.
Techniques in this prompt
Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.
Learn this techniqueRecommended models
Build on this prompt
Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.
More in AI Image & Video Generation Prompts
Cinematic Product Hero Shot Builder
Generate a polished, advertising-grade product hero image prompt with controlled lighting, lens, and composition specs.
Consistent Character Sheet Across Scenes
Lock a recurring character's appearance so the same person renders consistently across many generated scenes.
Photoreal Portrait Lighting Director
Craft studio-portrait prompts with named lighting patterns, lens choice, and skin-rendering controls for realism.
Brand-Safe Social Ad Visual System
Produce a set of on-brand, policy-aware ad creatives with consistent palette, layout zones, and copy-safe space.