Skip to main content

Rooftop slow dance from first frame to a closing dip

Model
Wan 3.0
Task
Image to video
Resolution
720p
Duration
5.1 s

Output

Input

  • Input image
    image_url
  • Input image
    last_image_url

Swap in your own when you run it.

PromptEN316 characters

He draws her in by the hand and lowers her into a slow dance dip, holding her there on the final frame. Her green dress swings and catches the string lights as she leans back; the skyline stays soft behind them. Locked camera, one continuous take, blue-hour light, soft jazz from a small speaker and distant traffic.

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` and `last_image_url` are two stills of the same couple on the same rooftop from the same camera position: an open dance hold to start, the bottom of a dip to end. With both ends fixed the prompt only has to describe the move in between, and the clip opens on the first still and lands on the second with the dress, the shirt and the string lights unchanged. `duration_seconds` `5` at `720p` with `generate_audio` on.

Settings used

SettingValueWhat it does
resolution720p480p, 720p or 1080p. Defaults to 720p. Resolution changes both the price and how long the task takes to come back.
generate_audiotrueOn by default. The clip comes back with sound already locked to the picture. Set false when you are scoring the shot yourself.
duration_seconds5Any whole number from 2 to 30, or -1 for smart duration, where the model picks the length: the 30-second maximum is held up front and the charge settles on the length actually delivered. Defaults to 5. Longer clips drift more, so settle the look at 5 seconds before extending.