Glossy Slime Stretch and Snap
A translucent slab stretches to a bubble window and snaps, lit from underneath by a gel light.
Fills the prompt and every setting below into the Seedance 2.5 form. Nothing is submitted until you press generate.
The prompt
Two hands pull a glossy translucent slab of slime slowly apart, the sheet thinning into a window of bubbles before it tears. The camera follows the stretch upward and stops dead the instant it snaps, letting the recoil finish in frame. A coloured gel light from underneath pushes through the material so the stretched middle glows turquoise while the surface keeps hard wet highlights. Tabletops are matte grey, nothing else in shot, an unhurried evening studio. Audio: a long wet squeak, then one clean snap.
Settings this prompt was written for
| Field | Value |
|---|---|
| Mode | Text to video |
| Duration | 8 seconds |
| Resolution | 720p |
| Aspect ratio | 1:1 |
| 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
The satisfying part of this material is the last two seconds, so the prompt builds towards it: thinning into a bubble window, tearing, then a recoil that the camera refuses to chase. Freezing the move at the snap is what stops the model from drifting across the frame at exactly the moment the eye wants stillness. Underlighting is the reason the stretch reads as translucent depth instead of as a glowing blob, and the wet highlights on the surface give it the tacky skin the material needs to look real.
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.