Seedance 2.0 Pro

ByteDance · Video Generation
POST /v1/videos/generationsMultimodal video model for cinematic output from text, image, audio, or video inputs, with stable motion and consistent characters.
At a glance
Pricing
Example request
Parameters
Notes
Multimodal video from text, images, audio, and video inputs. Native audio-video sync, strong motion stability, consistent character handling. Outputs up to 4K (3840x2160).
Tip
- Pair with Seedream 5.0 Lite for the reference image first when targeting lifelike-face cohesion across multiple inputs.
4K output
- 4K outputs are native 10-bit H.265 (HEVC) for maximum quality, delivered in full on download and through the API. Browsers cannot decode 4K HEVC inline, so the playground plays a 1080p preview while Download gives the full 4K. Open 4K files in any HEVC-capable player or editor.
Uploaded media preprocessing
- Video inputs are capped to 15 seconds for reference, edit, and extend workflows.
- Uploaded video inputs are normalized to provider-compatible MP4 when needed.
Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/seedance-2-0-pro.
