Interview Gone Wrong
A candidate hears her own answer land wrong and the interviewer's pen stops.
Fills the prompt and every setting below into the Seedance 2.5 form. Nothing is submitted until you press generate.
The prompt
A candidate in a slightly too-tight jacket answers a question, then realises mid-sentence that it was the wrong one; her hand closes on the folder in her lap, she straightens, and the interviewer's pen stops moving. The camera sits at the far end of the table on a slow push-in that never reaches her face. Cool overhead office light, one window behind, plants out of focus. Laminated desk, thin carpet, loose paper. Air conditioning hum and a pen clicking once.
Settings this prompt was written for
| Field | Value |
|---|---|
| Mode | Text to video |
| Duration | 10 seconds |
| Resolution | 720p |
| Aspect ratio | 16:9 |
| 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
The emotion is embarrassment, which plays as a physical sequence: a hand tightening on a folder, a spine straightening, a pen going still in someone else's hand. Ten seconds is requested because the beat needs a slow build before the freeze. Holding the camera short of her face makes the scene more uncomfortable than a close-up would, and the flat office lighting keeps the focus on the two performances rather than the look.
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.