Rain Street Magic Casting
Magic over a rain puddle: water beads lift, gather into a ring of ice, then fall back as rain.
Fills the prompt and every setting below into the Seedance 2.5 form. Nothing is submitted until you press generate.
The prompt
Both hands open over a rain puddle and the water answers: beads lift off the surface, gather into a spinning ring and harden into thin ice that holds for a single breath, then drops back as rain. The camera is handheld and close on the hands, racking focus from the puddle up to the ring and back down. Overcast drizzle, flat grey daylight, wet asphalt throwing pale reflections. Fantasy realism, fine skin and water detail. Audio: faint crackle, rain on stone.
Settings this prompt was written for
| Field | Value |
|---|---|
| Mode | Text to video |
| Duration | 5 seconds |
| Resolution | 720p |
| Aspect ratio | 9:16 |
| 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
Magic needs a physical anchor or it turns into abstract noise, so the effect is written as something water can be seen to do: beads lifting, a ring forming, ice holding for a breath, then rain again. Racking focus between the puddle and the ring keeps the viewer's eye on the hands, which is where a model renders most stably. Flat overcast daylight lets the ice read as a material with thickness rather than as a glow effect.
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.