Cat Knocks a Mug Off the Table
A photo of a cat beside a mug, extended into the slow paw push, the topple and the drop.
Fills the prompt and every setting below into the Seedance 2.5 form. Nothing is submitted until you press generate.
The prompt
Same cat, same markings, same mug on the table; only the paw moves. It stares at the mug, then reaches out one paw and pushes it twice, watching it slide, topple over the edge and drop out of frame while the head tilts down to follow the fall. A fast push-in paired with a slight zoom-out lands as the mug goes over. Warm late-afternoon window light, shallow depth of field, plain wall. Audio: claw on ceramic, a clatter, a small chirp.
Settings this prompt was written for
| Field | Value |
|---|---|
| Mode | Image to video |
| Duration | 5 seconds |
| Resolution | 720p |
| Aspect ratio | adaptive |
| Audio | Audio on |
| Credits | 195 |
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
Comedy timing is the hard part, so the action is split into beats the model can order: stare, tap, slide, topple, drop. Naming one object and one paw keeps the anatomy simple, and the small push-in matched by a slight zoom-out lands on the moment of the fall without the camera racing the subject.
What to put in the reference image
Upload a photo of your cat on a table with a single object beside it — a mug, a glass, a small pot — at least a head-width away. Shoot from roughly table level so the paw, the object and the table edge all share one frame.
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.