Seedance 2.0 Spicy is ByteDance's uncensored image-to-video model, animating a still you supply as the first frame, with sound in the same pass. Clips run 4 to 15 seconds at 480p, 720p, 1080p or 4K; only the image is required.
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.
- Output4s
velvet-spiral-turn - 720p
- 3:4
- 4s
- Output5s
fogged-mirror-lean The clip on this page, request and all: the opening still supplies the wardrobe, the steam and the mirror, and the prompt does nothing but move her. Five seconds at 720p with audio on.
- 720p
- audio
- 5s
- Output5s
darkroom-safelight A single-colour light source and almost nothing else: red safelight, a print lifted dripping out of the tray, chemical ripples throwing reflections onto the ceiling. Monochromatic scenes strip away the colour cues a model normally leans on, so this one is about whether shape and wet surfaces still read.
- 720p
- 5s
- Output6s
library-ladder-dust Adaptive framing, so a landscape still comes back in its own shape rather than cropped. The payload is the dust she blows off the top edge of the book: a cloud that has to turn and glitter in a shaft of low sun, which is a far harder ask than moving a person.
- 720p
- adaptive
- audio
This example starts at $0.114 per output second. The Playground updates the estimate when you change the settings.