Seedance 2.0 Mini 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
gatsby-champagne-toast Two references, each named in the prompt with its job. `@Image1` is the woman: a black finger-waved bob, a gold feather headband, pearls and a gold beaded flapper dress with a deep V neckline. `@Image2` is the setting without her: a white mansion, a lit turquoise pool, a champagne coupe tower and a band in white jackets under strings of lights. The clip puts her into that scene: she walks along the pool edge with a coupe in hand, passes the glowing tower, turns to the camera and lifts her glass with a slow smile as confetti drifts down. `duration_seconds` is `5`, and `generate_audio` is `true`, so the clip comes with its own sound.
- 720p
- 16:9
- audio
- Output6s
reusable-cast Four references, each with a job: "References 1-3 are the same man from front, three-quarter and profile; reference 4 is his apron." That's the pattern for a reusable character: lock identity across angles, hand off wardrobe separately. The output carries the headshots' likeness into a bakery scene, apron worn as shown, glancing up as the door chimes. `duration_seconds` is `6`.
- 720p
- 16:9
- audio
- Output4s
same-couple-three-angles A third angle on a scene that already exists elsewhere. The references carry the two performers and the bench, so the prompt only has to describe the new camera position and the backlight; continuity is not something it is being asked to hold in words. Up to nine stills, three clips and three audio tracks travel in one request, which lets a shot be cast from the same material each time instead of re-described.
- 480p
- 3:4
- 4s
- Output8s
pace-from-a-clip The brief borrows rhythm, not look: `reference_video_urls` gives a clip's pacing, `reference_audio_urls` the beat, `reference_image_urls` the set — a warehouse aisle, not the clip's own hallway. The output keeps a hand trailing the shelving in lower frame through open and midpoint, matching one continuous push, no cut. `aspect_ratio` is `9:16`, `duration_seconds` `8`.
- 720p
- 9:16
- audio
This example starts at $0.025 per output second. The Playground updates the estimate when you change the settings.