Two portraits cast into a rooftop slow dance, with sound

Model: Wan 2.6 Flash
Task: Reference to video
Resolution: 720p
Duration: 5 s
Aspect ratio: 16:9

Output

A woman in a green silk dress and a man in a white linen shirt slow-dance on a city rooftop at night under swaying string lights.

This preview is blurred

This preview is marked sensitive. Confirm your age to see it.

Input

reference_image_urls
reference_image_urls

Swap in your own when you run it.

PromptEN553 characters

character1, an adult woman in a dark green silk slip dress, and character2, an adult man in an open-collar white linen shirt, slow-dance on a city rooftop at night, foreheads almost touching. Her hand slides up the back of his neck as he pulls her closer by the waist; she laughs quietly against his cheek. String lights sway in the wind, the city glows behind them. Slow handheld orbit around the pair, warm practical light, shallow depth of field, film grain. Sound: soft wind, distant traffic, her low laugh, a saxophone drifting up from a bar below.

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.

Edit the prompt and run

Same model, starting from this prompt. Other settings use their defaults.

Why this prompt works

Two stills and nothing else: a portrait of each person in `reference_image_urls`, named character1 and character2 in the prompt, cast into a scene neither was photographed in. `generate_audio` is on, so the wind, the traffic and the laugh written into the prompt come back as sound, at twice the per-second rate. Stills are not billed, so the 5 seconds of output are the whole bill.

Settings used

Setting	Value	What it does
resolution	720p	720p or 1080p, default 720p. It sets the per-second rate and how long the task takes, and both resolutions accept all five aspect ratios.
aspect_ratio	16:9	16:9, 9:16, 1:1, 4:3 or 3:4, default 16:9, available at both resolutions. It is chosen per request rather than inherited from a reference, so one set of references can be delivered in several shapes.
generate_audio	true	Off by default, so the clip comes back as picture only. On, the clip comes back with a generated soundtrack of voices, effects and ambience, and the per-second rate doubles at either resolution.
duration_seconds	5	Any whole number from 2 to 10, default 5. It is the main driver of the price, and also where likeness drifts: check the last second of a long clip before committing to that length.