Argument at the Kitchen Table
One stops chewing: a kitchen-table argument where the tell is a fork set down, not the words.
Fills the prompt and every setting below into the Seedance 2.5 form. Nothing is submitted until you press generate.
The prompt
Two people in their forties sit across a kitchen table with breakfast half eaten; the one on the left keeps talking with both hands flat on the wood while the other stops chewing, sets down a fork, and looks at the window instead. The camera stays low and close at table height, drifting a few centimetres left, no cut. Flat grey morning light through net curtains. Chipped enamel mugs, formica, cooling toast. Room tone, a ticking clock, one chair creak.
Settings this prompt was written for
| Field | Value |
|---|---|
| Mode | Text to video |
| Duration | 8 seconds |
| Resolution | 720p |
| Aspect ratio | 4:3 |
| 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
No line of dialogue is written, because a model cannot lip-sync a script but can absolutely read a fork being set down. The beat is a single reaction — one person keeps going, the other disengages — and the mirrored hand positions give the animator two clear states to move between. The 4:3 frame and table-height camera keep both faces close without a cut, and eight seconds leaves room for the pause after the fork lands.
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.