Seedance 2.0 Fast image-to-video from ByteDance starts the clip on a still you supply and animates it, with sound in the same pass. Clips run 4 to 15 seconds at 480p or 720p, and an optional closing still makes the shot arrive on a set frame.
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
sunflower-field-drone-reveal `image_url` is the opening frame: a woman in a lemon-yellow backless sundress, thin straps crossed low on her back, stands among sunflowers at golden hour with the sun flaring above the horizon. The clip plays the prompt in order: she turns and looks back over her shoulder at the camera with a slow smile, then the drone pulls back and rises in one continuous move until the field fills the frame to the horizon and she is a small yellow figure at its center. `aspect_ratio` `21:9` matches the ultra-wide opening frame, and `generate_audio` is `true`, so the clip comes with its own sound.
- 720p
- 21:9
- audio
- Output5s
dominoes-two-hands The whole prompt is one mechanical event and a stopping point: dominoes falling inward from both ends and coming to rest short of contact. Because `image_url` already fixes the macro composition and the depth of field, the sentence spends nothing on the look and everything on timing and where the motion ends. `duration_seconds` is `4`, the floor here — long enough for the fall, short enough that nothing invents a second beat.
- 480p
- 3:4
- 5s
- Output6s
cafe-sign-flip A shopfront still turned into six seconds of motion, with 16:9 named explicitly for a fixed landscape placement instead of leaving the default adaptive to follow the still.
- 720p
- 16:9
- audio
- Output10s
before-and-after Both `image_url` and `last_image_url` are supplied, so the model interpolates toward a known ending. The prompt just orders the beats — rug, sofa, lamps, light — while the closing still pins the final look. In the output the rolled rug unrolls flat to match the second photo almost exactly. `duration_seconds` is `10`, room for four beats to read as distinct.
- 720p
- 16:9
- 10s
This example starts at $0.045 per output second. The Playground updates the estimate when you change the settings.