System JSON prompt template for ultra-realistic iPhone-style AI influencers

A long-form system-style prompt that defines a role, cognitive principles, visual aesthetic, and JSON schema for generating ultra-realistic mobile-photo influencer images with Nano Banana Pro.

Prompt

3,139 charactersOpen Astorie studio ↗
<role>
You are specialized in computational photography, specifically the optical characteristics of the {argument name="phone model" default="iPhone 16/17 Pro Max"} sensor system. You translate human concepts into mathematically precise image generation prompts.
</role>

<cognitive_framework>
<principle name="Context Hunger">
If the user provides a vague concept (for example, "{argument name="example vague concept" default="girl at a cafe"}"), you must explicitly invent the missing environmental, lighting, and styling details to ensure a complete image.
</principle>
<principle name="The iPhone Aesthetic">
All outputs must strictly simulate high-end mobile photography.
- Focal Lengths: {argument name="main focal length" default="24mm"} (Main), {argument name="ultra wide focal length" default="13mm"} (Ultra Wide), or {argument name="telephoto focal length" default="77mm"} (Telephoto).
- Characteristics: "Apple ProRAW" color science, sharp details (Deep Fusion), computational bokeh (Portrait Mode), and Smart HDR dynamic range.
- Avoid: anamorphic lens flares, exaggerated "cinema" bokeh, or vintage film grain (unless specified as a filter).
</principle>
<principle name="Imperfection is Realism">
To achieve "ultra-realism," you must inject terms describing unpolished reality: digital noise (not film grain), skin texture, slightly blown-out highlights (common in mobile), and natural "snapshot" framing.
</principle>
<principle name="JSON Precision">
Your output is a strict JSON object designed for programmatic use.
</principle>
</cognitive_framework>

<visual_analysis_reference>
The "Influencer Aesthetic" is defined by:
- Vibe: "Plandid" (planned candid), effortlessness, aspirational lifestyle.
- Lighting: natural window light, golden hour, or "flash photography" (hard flash) for night shots.
- Framing: vertical (9:16) native mobile aspect ratio, often selfies or point-of-view (POV).
</visual_analysis_reference>

<instructions>
1. Analyze the user's request for subject and mood.
2. Enrich the request using "iPhone Photography" constraints.
3. Format the output strictly as a JSON object with the following schema.
</instructions>

<json_schema>
{
  "meta_data": {
    "style": "iPhone Pro Max Photography",
    "aspect_ratio": "9:16"
  },
  "prompt_components": {
    "subject": "Detailed description of person, styling, pose (mirror selfie, 0.5x angle, etc.)",
    "environment": "Detailed background, location, social setting",
    "lighting": "Smart HDR lighting, natural source, or direct flash",
    "camera_gear": "iPhone 16 Pro Max, Main Camera 24mm f/1.78, or Ultra Wide 13mm",
    "processing": "Apple ProRAW, Deep Fusion, Shot on iPhone",
    "imperfections": "Digital noise, motion blur, authentic skin texture, screen reflection (if mirror)"
  },
  "full_prompt_string": "The combined, comma-separated string optimized for realistic mobile generation",
  "negative_prompt": "Standard negatives + 'professional camera, DSLR, bokeh balls, anamorphic, cinema lighting, studio lighting'"
}
</json_schema>

<task>
Await the user's description of the scene. Generate the JSON output immediately.
</task>
From sourceView source ↗

More to explore

Low-angle stylized portrait of a young woman in a dim room — output
High-contrast rim-lit black and white conceptual side-profile portrait — output

High-contrast rim-lit black and white conceptual side-profile portrait

AlejoGemini 3, Nano Banana Pro
A powerful, high-contrast black-and-white side-profile portrait of a person (attached photo), with distinctly human yet timeless features — emerging from complete darkness. The composition is minimalist and sculptural, where form, light, and shadow define the subject rather than color or texture.
The subject’s profile is clean and strong, contemplative expression, as if caught between thought and transcendence. They wear a dark, form-fitting turtleneck sweater that merges seamlessly into the black void, erasing all detail except for the glowing edge of their silhouette.

A single, narrow rim light, bright, sharp, and directional, carves out the shape of the head, neck, and shoulder, tracing the contours with precision. The light originates from directly behind and slightly above the subject, creating a thin, luminous halo along the jawline and the curve of the skull, while the rest dissolves into pure black.

The background is absolute darkness, a void without texture or depth, emphasizing the luminous boundary between shadow and light. There are no midtones, only the purest black and a deliberate contrast with the brightest whites that heightens drama and abstraction.

Mood & Aesthetic: Minimalist, conceptual, and deeply introspective. The image evokes solitude, contemplation, and timeless elegance. It feels cinematic yet intimate, an exploration of identity through light.

Technical details:

Shot with a telephoto lens for compressed perspective.

Aperture wide open (f/1.8-2.8) to create a glowing contour with shallow depth of field.

Optical realism: rendered with ultra-realistic 8K cinematic quality, incorporating true lens physics, depth of field, and subtle film grain, front face good lighting. (Use my picture for reference)

Inspired by @ShreyaYadav___
JSON selfie-in-car mirror prompt for Nano Banana Pro — output

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

Mahnoor FatimaGemini 3, Nano Banana Pro
{
  "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": "{argument name=\"phone model\" default=\"iPhone 17 Pro Max\"}",
      "details": "Realistic proportions, accurate lens design, held in hand"
    },
    "environment": {
      "location": "Outdoors, reflected in the side mirror of a {argument name=\"car model\" default=\"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"
}
JSON selfie-on-bed prompt for Nano Banana Pro — output

JSON selfie-on-bed prompt for Nano Banana Pro

LexGemini 3, Nano Banana Pro
{
  "subject": {
    "type": "young woman",
    "pose": "lying on her back, taking a selfie with her right arm extended upward",
    "expression": "soft smile, relaxed and natural",
    "gaze": "looking toward the camera",
    "skin_details": {
      "complexion": "smooth, warm, sunlit glow",
      "freckles": "visible on nose and cheeks"
    },
    "hair": {
      "color": "{argument name=\"hair color\" default=\"medium brown\"}",
      "length": "long",
      "style": "loose, spread out on the pillow around her head"
    },
    "eyes": {
      "color": "{argument name=\"eye color\" default=\"light blue or green\"}",
      "makeup": "subtle eyeliner"
    }
  },
  "clothing": {
    "top": {
      "type": "ribbed tank top",
      "color": "white",
      "fit": "form-fitting",
      "neckline": "scoop neck"
    },
    "bottoms": {
      "type": "jeans",
      "color": "light blue",
      "visibility": "partially visible"
    },
    "accessories": {
      "earrings": "small studs",
      "necklace": "thin, minimal chain"
    }
  },
  "environment": {
    "location": "bed or soft resting surface",
    "bedding": {
      "pillow": "white",
      "sheets": "white"
    },
    "background": "neutral wall and edge of headboard or furniture barely visible"
  },
  "lighting": {
    "type": "natural sunlight",
    "direction": "coming from upper left of frame",
    "effect": "creates warm highlights and soft shadows on face and torso"
  },
  "composition": {
    "camera_angle": "top-down selfie angle",
    "framing": "close-up of face, upper torso, and part of jeans",
    "focus": "sharp on face and upper body",
    "colors": "warm skin tones, white bedding, brown hair, neutral background"
  },
  "mood": "warm, relaxed, comfortable, natural"
}
City tallest buildings 3D cartoon showcase prompt — output

City tallest buildings 3D cartoon showcase prompt

Michal MalewiczGemini 3, Nano Banana Pro
Present a clear, side miniature 3D cartoon view of the tallest buildings in {argument name="city in English" default="YOUR CITY"}. Use minimal textures with realistic materials and soft, lifelike lighting and shadows. Use a clean, minimalistic composition showing exactly the three tallest buildings in {argument name="reference city in English" default="Sopot"}, arranged from left to right in strict descending height order. The tallest must appear visibly tallest, the second must be clearly shorter than the first, and the third must be clearly shorter than the second.
All buildings must follow accurate relative proportions: if a building is taller in real life, it must be taller in the image by the same approximate ratio. No building may be visually stretched or compressed.
Each building should stand separately on a thin, simple ceramic base. Below each base, centered text should display:
Height in meters — semibold sans-serif, medium size
Year built — lighter-weight sans-serif, smaller size, directly beneath the height text
Provide consistent padding, spacing, leading, and kerning. Write “{argument name="city name title" default="YOUR CITY NAME"}” centered above the buildings, using a medium-sized sans-serif font.
No building top should overlap or touch the text above. Use accurate architectural proportions based on real-world references. Maintain a consistent camera angle and identical scale for each building model.
No forced perspective. Use straight-on orthographic-style rendering. Do not exaggerate or stylize size differences beyond proportional accuracy.

Use a square 1080×1080 composition. Use a clean, neutral background. Ensure no extra objects are present.

Find your next direction

ASTORIE CANVAS

Take the idea further.

Bring your prompts, references and results together in one creative space.

Open your canvas ↗