Cel-Shaded Sword Draw
One draw, one three-frame smear: a masked duelist clears her blade as the background erupts into speed lines.
Fills the prompt and every setting below into the Seedance 2.5 form. Nothing is submitted until you press generate.
The prompt
A masked duelist in a red haori plants both feet on wet stone and draws in one motion; the blade leaves the sheath in a three-frame smear while background lines radiate outward. The camera snaps from a low profile to a fast lateral whip and settles tight on her eyes. Flat overcast dawn light. Hand-drawn cel-shaded 2D animation, hard shadow shapes, bold line work, limited palette. Audio: a short steel ring and one gust of wind.
Settings this prompt was written for
| Field | Value |
|---|---|
| Mode | Text to video |
| Duration | 5 seconds |
| Resolution | 720p |
| Aspect ratio | 16:9 |
| 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
The three-frame smear and the radiating background lines are the parts a video model can actually draw, and together they give the cut a physical beat and a style marker at once. Naming the sheath, the blade and the eyeline keeps a five-second action readable, while flat dawn light stops the model inventing glossy 3D highlights over cel shading. One short audio event means the steel ring lands on the smear instead of drifting across the shot.
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.