Skip to main content

Ice Block Fracture

One tap, one hairline crack, one punch-in at the exact moment a clear block of ice splits in two.

Macro & ASMRText to video195 credits

Fills the prompt and every setting below into the Seedance 2.5 form. Nothing is submitted until you press generate.

The prompt

A steel pick taps a clear block of ice once and a hairline crack races across the interior, splitting the block into two clean halves. The camera holds on the crack line and punches in fast at the exact moment of fracture, then settles. A hard cold beam from directly above drills through the ice so the fracture flashes white while the outer faces stay frosted. Late winter, the air visibly cold, no background detail. Audio: a low creak, a sharp crack, then ice chips tinkling onto metal.

Settings this prompt was written for

Settings this prompt was written for
FieldValue
ModeText to video
Duration5 seconds
Resolution720p
Aspect ratio1:1
AudioAudio on
Credits195

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

Fracture is a single-frame event, so the prompt anchors the camera to it: hold, then punch in exactly at the split. Without that instruction the model tends to spread the break over the whole clip and the impact disappears. Top-down hard light is specified because transmitted light is what makes the crack flash white against the frosted faces, and the three-part audio cue — creak, crack, tinkle — gives the moment a clear pre-roll and tail that an editor can sync to.

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.

ice cracking videoasmr ice promptmacro fractureslow motion ice

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.