Seedance 2.0 Fast reference-to-video from ByteDance builds one shot from your own material: up to 9 images, 3 video clips and 3 audio tracks, with no first frame. Output is 4 to 15 seconds at 480p or 720p, with sound in the same pass.
Workbench
These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.
- Output5s
three-angles-moonlit-terrace `reference_image_urls` holds three photos of the same woman in the same red backless gown on the same moonlit terrace — front, side and back — and the prompt assigns each a turn of the orbit: "@Image1, @Image2 and @Image3 as three angles of one woman." The camera circles from photo one's front view through photo two's profile to photo three's back, where she glances over her shoulder and draws her fingertips down the open back of the gown; her face, hair and the gown hold throughout. `duration_seconds` is `5`.
- 720p
- 1:1
- audio
- Output5s
product-in-three-angles `reference_image_urls` holds three photos of the same sneaker — side, front three-quarter and top-down — and the prompt assigns each a turn: "@Image1, @Image2 and @Image3 as three angles of one sneaker." The output opens on photo one's side view, turns through photo two's front three-quarter and tilts up to photo three's top-down view, with the leather, gum sole and laces unchanged throughout. `duration_seconds` is `5`.
- 720p
- 1:1
- audio
- Output4s
skate-crew-own-footage Three kinds of reference at once: `reference_image_urls` takes up to nine stills, `reference_video_urls` up to three clips and `reference_audio_urls` up to three tracks, and the brief is written as an edit instruction over that material rather than as a description of a scene. When you already own the footage and the sound, this is the call that casts from it — the prompt names the cut and the light, not the people.
- 480p
- 3:4
- 4s
- Output12s
borrowed-camera-move Three reference kinds split the job: `reference_video_urls` carries the move — a slow, uncut crane rise — `reference_audio_urls` the timing, `reference_image_urls` the set. Naming the move in words too backs up the footage. The output opens low on gravel and rises to the clip's dusk skyline, timed to the track's swell. `aspect_ratio` is `21:9`, wider than the reference footage.
- 720p
- 21:9
- audio
This example starts at $0.045 per output second. The Playground updates the estimate when you change the settings.