The Candlelit Library
A scholar turns a paper volume toward a candle, dust drifting through the beam.
Fills the prompt and every setting below into the Seedance 2.5 form. Nothing is submitted until you press generate.
The prompt
Keep the figure, robe and lighting exactly as in the reference image. A scholar lifts a paper volume from a low shelf and turns it toward a candle; dust drifts through the beam and the pages settle. The camera glides sideways along the aisle past carved wooden shelving, then rests on the open book. Warm candle pools against deep shadow, late night, still air. Bamboo slips, linen thread binding, wax, aged paper.
Settings this prompt was written for
| Field | Value |
|---|---|
| Mode | Image to video |
| Duration | 5 seconds |
| Resolution | 720p |
| Aspect ratio | adaptive |
| Audio | Silent |
| 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
Candlelight is the whole scene, so the prompt names it as part of the locked reference rather than letting the model relight the shot. The action is small and slow — lift, turn, settle — which is exactly the range image-to-video handles convincingly. Dust in the beam supplies the movement, and listing the book's construction keeps the prop from drifting into something generic.
What to put in the reference image
Upload a portrait or full-body reference of the figure in period dress, ideally lit by a single warm source. Avoid flash-lit or hard-lit photos and anything with modern props in frame — the model copies the reference lighting and objects more literally than the prompt.
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.