A highly detailed Japanese prompt for gpt-image-2 designed to generate realistic or illustrative selfies of a character from a high-rise rooftop overlooking the Shibuya Scramble Crossing, emphasizing composition and lighting.
Prompt
Describe the person in the reference image at the rooftop observation deck of a high-rise commercial building overlooking the Shibuya Scramble Crossing directly below and in front, capturing the moment they are taking a selfie with a smartphone. This is a selfie-style composition captured by a close-range third-person camera, not the actual phone screen view.
Maintain the facial features, eyes, hairstyle, hair color, age, and the color, shape, material, and decoration of the outfit from the reference image to ensure consistency. Do not inherit the original background, lighting, composition, or pose.
Make the person the sole focus in a stable 3/4 body shot from the face to around the thighs. Prioritize the reproduction of the face, upper body, outfit, smartphone, and background over showing the full body.
The person stands on a safe rooftop deck, extending one arm forward holding the smartphone and looking naturally at the screen. The smartphone should appear somewhat large in the foreground without obscuring the face or outfit. Place the other arm naturally near the body.
Show a small portion of the rooftop floor and a transparent glass fence at the bottom or sides of the frame to clarify the location. The rooftop should occupy less than 10% of the screen. Avoid themes of floating, falling, or standing on dangerous edges.
The camera is slightly ahead and above the person, providing a diagonal high-angle view of Shibuya. Do not use a top-down view. Place the Scramble Crossing prominently below and behind the center of the person, showing wide crosswalks in multiple directions, the center of the intersection, and numerous pedestrians. Do not leave the center empty or sparse.
Surround the scene with high-density commercial buildings, curved glass, storefront facades, and large digital billboards, showing at least three screens. The screens should display vibrant abstract visuals in blue, cyan, red, magenta, and pink without readable text or real brand logos.
The time is a soft natural light afternoon. Roads are neutral gray, and crosswalks are clear white. Do not desaturate or whiten the background; maintain the colorful glamor of Shibuya through the crowds and digital reflections. Avoid overexposure, excessive HDR, sunsets, night views, fog, or blue tints. The person's face and outfit should be slightly clearer than the background.
Maintain the quality of realistic reference images, or the art style, lines, coloring, and texture of anime/illustration references. Do not convert between realism and anime. Avoid anatomical errors, distorted smartphones, or readable advertising text.
How to use this prompt
1
Copy the full prompt above.
2
Open a platform that supports GPT Image 2, such as YouMind, and paste the prompt in.
3
Swap the subject, style, or details to fit your idea, then generate.
This is a free AI prompt from YouMind's prompt library. Explore thousands more image prompts, all free to copy and adapt.
Let AI search through tens of thousands of prompts. Filter by model, time range, keywords, and sort by engagement — views, bookmarks, reposts and more.
Turn any photo into a detailed AI image prompt. The free image to prompt converter analyzes composition, style, and lighting so you can recreate any look in seconds.
