Image prompt
A cinematic prompt creating a dual-identity effect by showing a person standing in front of their own idealized digital advertisement in a Seoul subway.
Copy directly into the target model and adjust for your input assets.
Inside a photorealistic Seoul subway platform, the {argument name="subject" default="uploaded person"} stands in front of a glowing LED wall advertisement, smiling with pride and slightly pointing at their own image.
The billboard displays a highly refined fan-art campaign featuring the same individual, designed in a {argument name="theme color" default="[THEME COLOR & MOOD]"} theme with elegant typography reading “{argument name="main slogan" default="[MAIN SLOGAN]"}” and a secondary line “[SUB SLOGAN / DATE]”.
There is a strong visual contrast between the real person—casually styled, grounded, human—and the polished, idealized digital version on the screen, creating a cinematic dual-identity effect.
The environment features realistic Korean subway architecture, tiled surfaces, overhead signage, and soft motion blur of passing commuters. Lighting mixes cool station fluorescents with warm LED glow reflections.
Captured on 35mm lens, shallow depth of field, ultra-realistic skin rendering, cinematic commercial photography tone.
A beautiful female lead with soft expressive eyes, flawless but natural skin texture, elegant silk gown, subtle jewelry.
Include full-body turnaround, expressive head studies, cinematic portrait, fabric flow breakdown, makeup detail studies, annotation notes, height scale.
Mood: soft studio lighting, golden Hollywood glamour aesthetic.
Original source details are kept for attribution and review.
GitHub source：YouMind-OpenLab/gpt-image-2-prompts-search
This page is adapted from YouMind OpenLab GitHub prompt libraries. License: MIT。