GPT Image Prompt
How to useCopy this prompt and paste it into ChatGPT, Gemini, Nano Banana, or your favorite AI image tool. Adjust details if needed.
Build the image around a playful Y2K phone-booth fashion moment: a single fashion subject stands inside a glass city booth, holding a bright green receiver to her ear while pushing a ring-covered open hand into the fisheye foreground. The mood is cheeky and camera-aware, with one eye winking, puckered lips, and the viewer feeling almost inside the booth.
Keep the pose mostly frontal with a slight torso angle and compact standing balance. One hand grips the receiver naturally at the cheek and ear, the cord running back to the green payphone body on the left. The opposite arm reaches toward the lens, palm facing camera, enlarged by the ultra-wide perspective with colorful plastic rings readable across the fingers.
Style her in a fitted navy cropped spaghetti-strap tank with pale trim and a bold white number graphic, low-rise frayed denim shorts, a black belt, layered bead necklaces, bracelets, small belly jewelry, long dark side-swept hair, colorful butterfly clips, and partly visible white furry boots.
Use a vertical close fisheye composition with curved booth frames, reflective glass, instruction panels, overhead light, and a dark circular edge vignette. Outside, keep dense daylight signage, traffic, pedestrians, sidewalk, and blue sky as saturated urban color blocks rather than exact text.
Keep the palette source-faithful: glossy green phone plastic, deep navy fabric, blue denim, warm natural skin, dark glossy hair, clean white graphics and fur, and candy-colored accessories. Let daylight through the glass create controlled highlights, mild booth shadows, readable hand contact, natural proportions, and clear separation between plastic, glass, skin, fabric, denim, fur, and jewelry.