ByteDance's Seedance 2.5 Flash reference-to-video builds a new 4–30 second scene from up to 10 images, 5 clips and 5 audio files that you name in the prompt as @Image 1, @Video 1 and @Audio 1, at 480p or 720p with generated sound.
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
vintage-elevator-two-portraits Two 864×1152 waist-up portraits and no clip, 16:9 at 720p for 5 seconds: the woman from @Image 1 and the man from @Image 2 share one brass elevator with their faces, hair and clothes kept, the floor display ticks from 3 to 4, he says "Top floor." close to her ear and she straightens his collar. The output was 1280×720 and 5.056 seconds; with no clip attached, the plain per-second rate applies.
- 720p
- 16:9
- audio
- Output4s
gas-station-greeting-mixed-refs One portrait, one 1280×720 gas-station clip of about five seconds and one voice file, four seconds at 480p: the man from @Image 1 walks past the vintage car of @Video 1 and smiles into the lens, in 854×480. Billing adds the clip's seconds to the four requested ones at the with-clips rate.
- 480p
- 16:9
- audio
- Output4s
bar-dropper-bottle-two-images Two images and no clip, 9:16 at 480p: the man from @Image 1 picks up the bottle from @Image 2 and turns it toward the camera. The output was 480×854 and used both references; with no clip attached, the plain per-second rate applies.
- 480p
- 9:16
- audio
This example starts at $0.115 per output second. The Playground updates the estimate when you change the settings.
