bytedance/seedance-2.5

OfficialView on Replicate →

ByteDance's flagship multimodal video model with native audio, native 30-second generation, and large multimodal reference sets.

Capabilities

Reference ImagesSeed

Cost

Community model (estimated from hardware time)

Input Parameters

Name	Type	Description	Default	Constraints
`aspect_ratio`	string	Video aspect ratio. Set to 'adaptive' to let the model choose the best ratio based on inputs. First/last-frame, editing, and extension modes require 'adaptive'.	`"16:9"`	16:94:31:13:49:1621:9adaptive
`duration`	integer	Video duration in seconds. Set to -1 for intelligent duration (the model picks the best length). Editing mode requires -1.	`5`	min: -1, max: 30
`generate_audio`	boolean	Generate synchronized audio with the video, including dialogue (use double quotes in prompt), sound effects, and background music.	`true`	—
`image`	string(uri)	First-frame image for image-to-video or first/last-frame generation. Cannot be combined with reference images, videos, or audios.	`—`	—
`last_frame_image`	string(uri)	Last-frame image. Requires a first-frame image. Cannot be combined with reference images, videos, or audios.	`—`	—
`output_format`	string	Output video container format.	`"mp4"`	mp4mov
`prompt`	string	Text prompt for video generation. Optional when a media input (image, reference images/videos/audios) is supplied. Seedance 2.5 works best with detailed, structured 'production brief' style prompts.	`""`	—
`reference_audios`	array	Reference audio files (up to 10, combined duration max 30s) for audio-driven generation and lip-sync. Requires at least one reference image or video. Reference them in your prompt as [Audio1], [Audio2], etc.		—
`reference_images`	array	Reference images (up to 30) for character consistency, style guidance, and scene composition. Cannot be combined with first/last frame images. Reference them in your prompt as [Image1], [Image2], etc.		—
`reference_videos`	array	Reference videos (up to 10, combined duration max 30s) for motion transfer, style reference, editing, and extension. Reference them in your prompt as [Video1], [Video2], etc.		—
`resolution`	string	Video resolution.	`"720p"`	480p720p
`seed`	integer	Random seed. Set for reproducible generation. Reproducibility is not guaranteed.	`—`	—
`watermark`	boolean	Add a watermark to the generated video.	`false`	—

aspect_ratiostring

Video aspect ratio. Set to 'adaptive' to let the model choose the best ratio based on inputs. First/last-frame, editing, and extension modes require 'adaptive'.

Default: "16:9"

16:94:31:13:49:1621:9adaptive

durationinteger

Video duration in seconds. Set to -1 for intelligent duration (the model picks the best length). Editing mode requires -1.

Default: 5min: -1, max: 30

generate_audioboolean

Generate synchronized audio with the video, including dialogue (use double quotes in prompt), sound effects, and background music.

Default: true

imagestring

First-frame image for image-to-video or first/last-frame generation. Cannot be combined with reference images, videos, or audios.

last_frame_imagestring

Last-frame image. Requires a first-frame image. Cannot be combined with reference images, videos, or audios.

output_formatstring

Output video container format.

Default: "mp4"

mp4mov

promptstring

Text prompt for video generation. Optional when a media input (image, reference images/videos/audios) is supplied. Seedance 2.5 works best with detailed, structured 'production brief' style prompts.

Default: ""

reference_audiosarray

Reference audio files (up to 10, combined duration max 30s) for audio-driven generation and lip-sync. Requires at least one reference image or video. Reference them in your prompt as [Audio1], [Audio2], etc.

Default:

reference_imagesarray

Reference images (up to 30) for character consistency, style guidance, and scene composition. Cannot be combined with first/last frame images. Reference them in your prompt as [Image1], [Image2], etc.

Default:

reference_videosarray

Reference videos (up to 10, combined duration max 30s) for motion transfer, style reference, editing, and extension. Reference them in your prompt as [Video1], [Video2], etc.

Default:

resolutionstring

Video resolution.

Default: "720p"

480p720p

seedinteger

Random seed. Set for reproducible generation. Reproducibility is not guaranteed.

watermarkboolean

Add a watermark to the generated video.

Default: false

Version: ca38262bae09Updated: 9/20/202671.3K runs