Chocolate Unwrap and Snap
Eight seconds of foil, snap and crumb: a warm low-key unwrap that keeps the wrapper facing the lens.
Fills the prompt and every setting below into the Seedance 2.5 form. Nothing is submitted until you press generate.
The prompt
Foil peels back from the chocolate bar in your reference photo, the printed sleeve staying face-up and unchanged, until two squares break away with a clean snap. The camera tilts down from the rumpled foil to the fractured edge, holding as cocoa crumbs scatter. A warm tungsten practical sits low on the right, low-key, falling off into deep brown shadow. Tempered chocolate shows a matte snap face and a faint gloss on the moulded side. Audio: dry foil crinkle, then one crisp snap.
Settings this prompt was written for
| Field | Value |
|---|---|
| Mode | Image to video |
| Duration | 8 seconds |
| Resolution | 720p |
| Aspect ratio | adaptive |
| 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
Eight seconds is used here because the beat is really two actions in sequence: the peel and then the snap, and squeezing both into five usually rushes the second one into a blur. The camera only tilts, never cuts, because the interesting event is a fracture and a cut would hide it. Low-key tungsten is chosen over bright daylight so the foil keeps a warm specular edge instead of flaring white, and the two-part audio cue is written as crinkle then snap so the sound edit has an obvious sync point.
What to put in the reference image
A photo of the wrapped bar with the printed sleeve facing the camera, plus a clean surface underneath. Avoid photos where the wrapper is already torn open or creased beyond recognition — the model animates the tear you show it, so start from an intact wrapper.
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.