bytedance/seedance-1.5-pro

A joint audio-video model that accurately follows complex instructions.

Capabilities

Reference ImagesSeed

Community model (estimated from hardware time)

Name	Type	Description	Default	Constraints
`prompt`*	string	Text prompt for video generation	`—`	—
`aspect_ratio`	string	Video aspect ratio. Ignored if an image is used.	`"16:9"`	16:94:31:13:49:1621:99:21
`camera_fixed`	boolean	Whether to fix camera position	`false`	—
`duration`	integer	Video duration in seconds	`5`	min: 2, max: 12
`fps`	integer	Frame rate (frames per second)	`24`	24
`generate_audio`	boolean	Generate audio synchronized with the video. When enabled, the model outputs a video with audio that matches the visuals.	`false`	—
`image`	string(uri)	Input image for image-to-video generation	`—`	—
`last_frame_image`	string(uri)	Input image for last frame generation. This only works if an image start frame is given too.	`—`	—
`seed`	integer	Random seed. Set for reproducible generation	`—`	—

promptrequiredstring

Text prompt for video generation

aspect_ratiostring

Video aspect ratio. Ignored if an image is used.

Default: "16:9"

16:94:31:13:49:1621:99:21

camera_fixedboolean

Whether to fix camera position

Default: false

durationinteger

Video duration in seconds

Default: 5min: 2, max: 12

fpsinteger

Frame rate (frames per second)

Default: 24

generate_audioboolean

Generate audio synchronized with the video. When enabled, the model outputs a video with audio that matches the visuals.

Default: false

imagestring

Input image for image-to-video generation

last_frame_imagestring

Input image for last frame generation. This only works if an image start frame is given too.

seedinteger

Random seed. Set for reproducible generation

Version: 78c1986fecf4Updated: 8/1/20264.0M runs