A unique cinematic prompt that transitions from a rainy Tokyo street into a miniature city hidden within the reflection of a drink can.
Prompt
Create a 30-second ultra-realistic cinematic miniature-world video, 9:16 vertical, 4K HDR, photorealistic macro cinematography.
0–4s:
Rainy Tokyo-inspired street at night. A futuristic vending machine glows under neon lights. Wet pavement reflects cyan and magenta colors. A young man approaches, presses a button, and a cold drink can drops naturally.
4–8s:
He picks up the can. Extreme macro shot of water droplets and neon reflections on the aluminum surface. The camera slowly moves into the reflection. Tiny moving lights appear inside it.
8–13s:
The camera seamlessly enters the reflection and reveals a miniature futuristic Tokyo inside the can: tiny skyscrapers, streets, pedestrians, cars, vending machines and an elevated train. Everything has realistic scale and movement.
13–19s:
The camera flies through the miniature city at street level. Tiny cars pass through wet intersections, pedestrians walk naturally, a train crosses overhead, and neon lights reflect on miniature roads. Realistic atmospheric steam and rain.
19–24s:
The camera rises above the city, revealing the entire miniature metropolis contained inside the cylindrical drink can. Flying delivery drones move between skyscrapers. The metallic walls of the can surround the city.
24–27s:
The camera smoothly pulls backward through the reflection. The miniature city becomes smaller and disappears into the can.
27–30s:
Return to the real Tokyo street. The man holds the can and looks at it with genuine surprise. The camera pushes toward the can one final time, briefly revealing the glowing miniature city inside its reflection.
STYLE:
Photorealistic miniature world, realistic human movement, detailed architecture, physically accurate rain and reflections, realistic aluminum surface, cinematic depth of field, natural focus breathing, subtle handheld movement, premium Japanese sci-fi commercial, 4K HDR.
CONTINUITY:
One character, one can, one vending machine, one miniature city. Keep identical scale, lighting, architecture and objects throughout. No teleportation or sudden scene changes.
NEGATIVE:
cartoon, toy-like, CGI look, plastic textures, inconsistent scale, distorted buildings, duplicate people, duplicate vehicles, flickering, unrealistic physics, blurry details, excessive bloom, text, subtitles, logos, watermark.
How to use this prompt
1
Copy the full prompt above.
2
Open a platform that supports Seedance 2.5, 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 video 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.
