Candlelit tavern keeper leans across the bar with a half-smile
- Model
- Seedance 2.0
- Task
- Image to video
- Resolution
- 480p
- Duration
- 5 s
- Aspect ratio
- 3:4
Output
This preview is blurred
This preview is marked sensitive. Confirm your age to see it.
Input
image_url
Swap in your own when you run it.
PromptEN324 characters
She drops the ice into the horn cup, then leans her forearms on the counter, slowly tilts toward the camera and runs one fingertip along the laced edge of her bodice, holding the camera's eye with a slow half-smile as the candle flames jump. Close across the bar, shallow depth of field, heavy film grain, tallow gold light.Written in English, exactly as we sent it.
Run this example
Checking the price…
Opens the playground with every setting filled in and shows the exact price before you run.
Same model, starting from this prompt. Other settings use their defaults.
Why this prompt works
`image_url` is the opening frame: a red-haired tavern keeper in a low-cut linen blouse and a laced dark-red leather bodice holds an ice cube over a horn cup, with candle chandeliers, walls of barrels and a crowded hall behind her. The clip follows the prompt beat by beat: the ice drops into the cup, she folds her forearms on the counter, leans toward the camera and runs one fingertip along the laced edge of her bodice, holding the camera's eye with a slow half-smile. `aspect_ratio` `3:4` keeps the portrait frame, and `generate_audio` is `false`, so the clip is silent.
Settings used
| Setting | Value | What it does |
|---|---|---|
| resolution | 480p | Output resolution, 720p by default and reaching 4k; no upscaled tier is offered here. It sets a rate tier, and higher tiers mean bigger files and longer renders. It governs the delivered format only and adds no detail the source frame does not have. |
| aspect_ratio | 3:4 | Output framing, `adaptive` by default: the clip follows the ratio of the image you supplied, which removes the pre-crop step and keeps the subject away from the edges. Choose a fixed ratio only when the placement format is already set; the still is then centre-cropped to it. No effect on billing. |
| generate_audio | false | Whether a native soundtrack is rendered in sync with the picture. On by default; switch it off for silent loops or when sound is added in post. |
| duration_seconds | 5 | Length in whole seconds, 4 to 15, defaulting to 5, and the billed quantity. Pass -1 and the model picks the length itself: the estimate assumes the 15-second maximum and the final charge follows the delivered length. A shot driven by one frame drifts further the longer it runs, so confirm the motion at 4 or 5 seconds, and build longer pieces from several takes cut together. |
