
Gemini Image Prompt for json, photograph: task: Generate a photobooth strip visual, mimicking an iP...
Professional AI image generation prompt for JSON, Photograph.
{ "task": "Generate a photobooth strip visual, mimicking an iPhone's realism, arranged as a 2x2 grid of four images.", "subjects": [ { "id": "Subject Alpha", "description": "Identical to the individual in the provided Reference Image (exact facial features, coiffure, complexion, physique proportions, overall likeness).", "attire": "Precisely matching the garments, eyewear, and adornments shown in the Reference Image. No alterations to clothing, spectacles, or accoutrements." }, { "id": "Subject Beta", "description": "Identical to the individual in the provided Reference Image (exact facial features, coiffure, complexion, physique proportions, overall likeness).", "attire": "Precisely matching the garments, eyewear, and adornments shown in the Reference Image. No alterations to clothing, spectacles, or accoutrements." } ], "scene": { "environment": "Confined space of a compact PHOTO BOOTH enclosure", "backdrop": "Uniform matte blue walls and floor, tight corner setting, unadorned and uncluttered atmosphere.", "perspective": "Ultra-wide angle or mild fisheye lens perspective, exhibiting minor distortion characteristic of photobooth optics. Emulate an iPhone 17 Pro's photobooth wide-angle capture.", "illumination": "Intense, neutral-white flash lighting that uniformly brightens faces. Subtle shadow gradation on the blue walls, sharp detail rendition, and authentic skin texture. Direct, neutral white flash emission (avoiding yellow or warm tones).", "style_guide": "4K resolution, raw photobooth aesthetic, pronounced contrast yet natural appearance, devoid of cinematic color grading, heavy retouching filters, motion blur, superimposed text, or digital watermarks." }, "composition": { "arrangement": "A 2x2 grid mosaic", "orientation": "9:16 (portrait orientation for the overall collage)", "presentation": "Seamless integration without any white borders, division lines, inter-image spacing, or framing elements. Each individual photo segment occupies its quadrant edge-to-edge." }, "image_segments": [ { "quadrant": "upper-left", "action": "Subject Alpha angles towards the viewer from the front-left, one arm extended downwards, displaying a playfully serious expression; Subject Beta stands centrally behind, arms raised and flexed in a 'strongman' pose with a smile." }, { "quadrant": "upper-right", "action": "Subject Beta leans forward towards the lens, hands resting on knees, exhibiting a curious look; Subject Alpha enters the frame from the right edge, very close to the viewer, tilting their head, one arm arched overhead forming a partial heart shape, a gentle smile." }, { "quadrant": "lower-left", "action": "Piggyback configuration – Subject Alpha mounted on Subject Beta's back, arms encircling shoulders; both individuals are captured in mid-laugh, faces close to the camera, conveying a sense of vibrant movement." }, { "quadrant": "lower-right", "action": "Subject Beta adopts a sideways, forward-leaning posture with a humorous facial expression; Subject Alpha stands behind, making playful 'claw' or 'horn' hand gestures above Subject Beta's head, feigning a pout for amusement." } ] }
Try it Live for FREE
Test this prompt directly in our chat interface below.
How to Use This Prompt
Copy and paste this prompt into your preferred AI image generator like Google Nano Banana Image Generator or Midjourney or Stable Diffusion or any AI Image generator
