One-Take Corridor Walk
One unbroken gimbal take: two colleagues walk a hotel corridor while the camera leads them backward.
Fills the prompt and every setting below into the Seedance 2.5 form. Nothing is submitted until you press generate.
The prompt
Two colleagues in charcoal suits walk toward the lens down a long hotel corridor, the taller one talking with quick open hands while the other listens and nods. A gimbal rig retreats ahead of them at chest height, holding both in the lower third as brass wall sconces slide past the frame edges. Warm sconce pools alternate with cold blue exit signs, late evening. Anamorphic 40mm, fine 35mm grain, shallow focus. Audio: soft footsteps on carpet, one low voice, a door latch clicking.
Settings this prompt was written for
| Field | Value |
|---|---|
| Mode | Text to video |
| Duration | 10 seconds |
| Resolution | 720p |
| Aspect ratio | 21:9 |
| Audio | Audio on |
| Credits | 389 |
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 ten second take only holds if the people have continuous business, so the prompt gives them a conversation with hand movement and lets the camera do one predictable thing: lead them backwards. Naming the sconces and exit signs as the light sources stops the model flooding the corridor, and the anamorphic look is described loosely on purpose so the renderer picks its own flare.
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.