You're looking at a specific version of this model. Jump to the model overview.
bytedance /seedance-2.0:affbecc3
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| prompt |
string
|
Text prompt for video generation
|
|
| image |
string
|
Input image for image-to-video generation (start frame).
|
|
| last_frame_image |
string
|
Input image for last frame generation. Only works if an image start frame is also provided.
|
|
| reference_images |
array
|
[]
|
Reference images (up to 9) for character consistency, style guidance, and scene composition. Cannot be used together with first frame or last frame images.
|
| reference_videos |
array
|
[]
|
Reference videos (up to 3, max 15s each) for motion transfer, camera movement guidance, and style reference.
|
| reference_audios |
array
|
[]
|
Reference audio files (up to 3, max 15s each) for audio-visual synchronization, lip-sync, and beat matching.
|
| duration |
integer
|
5
Min: -1 Max: 15 |
Video duration in seconds. Set to -1 for intelligent duration (model picks the best length).
|
| resolution |
None
|
720p
|
Video resolution.
|
| aspect_ratio |
None
|
16:9
|
Video aspect ratio. Set to 'adaptive' to let the model choose the best ratio based on inputs.
|
| generate_audio |
boolean
|
True
|
Generate audio synchronized with the video. When enabled, the model outputs a video with native audio including dialogue, sound effects, and ambient sounds.
|
| seed |
integer
|
Random seed. Set for reproducible generation
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'format': 'uri', 'title': 'Output', 'type': 'string'}