Service Tunnel Sprint
An eight-second tunnel sprint: a trolley camera retreats at knee height as a train headlight floods in.
Fills the prompt and every setting below into the Seedance 2.5 form. Nothing is submitted until you press generate.
The prompt
Deep in a service tunnel, a runner in a hi-vis vest sprints along the narrow walkway beside the rails, arms pumping, breath fogging. The camera rides a trolley ahead of them, retreating backwards at knee height so the tunnel walls streak away on both sides. Almost everything is black until a train headlight floods in from behind, rimming the runner and throwing a long shadow down the wall. Gritty 35mm, crushed blacks, handheld micro-shake. Audio: gravel footsteps, a swelling roar, tunnel echo.
Settings this prompt was written for
| Field | Value |
|---|---|
| Mode | Text to video |
| Duration | 8 seconds |
| Resolution | 720p |
| Aspect ratio | 16:9 |
| Audio | Audio on |
| Credits | 311 |
They are the real price of that exact configuration — computed with the same pricing engine the API charges with, at the resolution, duration and audio setting shown on the card. Change any of those in the generator and the price updates with it.
Why it works
A chase beat needs legible geography at eight seconds, so the tunnel, the walkway and the retreating trolley are named as one system. The train headlight does the work of forty extras: it hides the set, rims the runner and gives the shadow a direction. Crushed blacks let the model get away with a nearly empty background.
Mode
Most cases are text-to-video and need nothing but the prompt. The ones marked "needs one reference image" are image-to-video: you supply a photo and the prompt keeps that subject or product locked while the camera moves.
More prompts like this
Prompts stay in English on every language of this site: that is the language the model was trained on, and translating a prompt changes what it renders. The page around it is translated.