GlobalAiOpc

Seedance2.0 - Create Task

Create video generation tasks using Seedance2.0 models with support for standard, fast, and Pro variants

POST/kyyReactApiServer/v1/kyyvideo2/videos

Seedance2.0 Create Video Task

Create high-quality video generation tasks using Seedance2.0's advanced AI models with support for multiple model options and multimodal reference inputs.

Authentication

Get Key

All requests require a Bearer token in the request header:

cURL

Authorization: Bearer {{key}}

Base URL

https://zcbservice.aizfw.cn/kyyReactApiServer

baseUrl is the shared prefix for all public APIs. The api field in the current page frontmatter shows the full endpoint. Use this baseUrl as the common prefix when reading or composing request paths.

Request Parameters

modelstringrequired

Model name, available options:

seedance_2_0 - Standard model (only supports generation with reference videos)
seedance_2_0_fast - Fast model (only supports generation with reference videos)
seedance_2_0_pro - Pro model (optional reference videos)
seedance_2_0_fast_pro - Fast Pro model (optional reference videos)

promptstringrequired

Video generation prompt describing the desired video content

Example: "A cat dancing in the rain, cinematic style"

durationinteger

Video duration in seconds, default 5 seconds, range 4-15 seconds

first_imagestring

First frame image URL for image-to-video scenarios

Use Cases:

Standalone: Image-to-video with first frame
Combined with last_image: First and last frame scenario

Format Requirements:

Format: jpeg, png, webp, bmp, tiff, gif
Aspect ratio (width/height): 0.4 ~ 2.5
Size: 300-6000 px
Value type: Public URL or asset ID (asset://assetID)

Mutually exclusive with referenceImages/referenceVideos/referenceAudios

last_imagestring

Last frame image URL for first and last frame scenario

Format Requirements:

Format: jpeg, png, webp, bmp, tiff, gif
Aspect ratio (width/height): 0.4 ~ 2.5
Size: 300-6000 px
Value type: Public URL or asset ID (asset://assetID)

Must be used together with first_image

aspect_ratiostring

Output video aspect ratio, default 16:9

Available options:

16:9 - Landscape
4:3 - Standard
1:1 - Square
3:4 - Portrait
9:16 - Portrait
21:9 - Ultra-wide
adaptive - Adaptive

generateAudioboolean

Whether to generate synchronized audio, default true

true: Output video includes synchronized audio
false: Output video is silent

referenceAudiosarray

Multimodal reference audio list

Format Requirements:

Format: wav, mp3
Duration: Single audio 2-15 seconds, max 3 segments, total duration ≤ 15 seconds
Size: Single ≤ 15 MB
Value type: Public URL or asset ID (asset://assetID)

Mutually exclusive with first_image/last_image

referenceImagesarray

Multimodal reference image list

Format Requirements:

Quantity: 1-9 images
Format: jpeg, png, webp, bmp, tiff, gif
Aspect ratio (width/height): 0.4 ~ 2.5
Size: 300-6000 px
Value type: Public URL or asset ID (asset://assetID)

Images involving faces or virtual avatars must be uploaded to the asset library for review first

Mutually exclusive with first_image/last_image

referenceVideosarray

Multimodal reference video list

Format Requirements:

Resolution: 480p, 720p
Duration: Single video 2-15 seconds, max 3 videos, total duration ≤ 15 seconds
Aspect ratio (width/height): 0.4 ~ 2.5
Size: 300-6000 px
Value type: Public URL or asset ID (asset://assetID)

System automatically selects the optimal backend model

Mutually exclusive with first_image/last_image

Response Parameters

idstring

Unique identifier for the video generation task, used for subsequent status queries

objectstring

Object type, always video

createdinteger

Task creation timestamp

modelstring

Model name used

statusstring

Task status:

queued - Queued
processing - Processing
completed - Completed
failed - Failed

errorstring

Error message, returned when status is failed

Model Features

seedance_2_0

Standard model, only supports generation with reference videos

seedance_2_0_fast

Fast model, only supports generation with reference videos, faster generation speed

seedance_2_0_pro

Pro model, optional reference videos, higher quality

seedance_2_0_fast_pro

Fast Pro model, optional reference videos, balances speed and quality

Parameter Selection Rules

Mutually Exclusive Parameters:

First/Last Frame Scenario: When using first_image and last_image, cannot use referenceImages, referenceVideos, referenceAudios
Multimodal Reference: When using referenceImages, referenceVideos, referenceAudios, cannot use first_image, last_image

Model Feature Comparison

Model	Reference Video Support	Generation Speed	Video Quality
seedance_2_0	✅ Only with reference videos	Standard	Standard
seedance_2_0_fast	✅ Only with reference videos	Fast	Standard
seedance_2_0_pro	⭕ Optional reference videos	Standard	High Quality
seedance_2_0_fast_pro	⭕ Optional reference videos	Fast	High Quality

Best Practices:

Video generation is asynchronous, use the returned id to query task status and results
Clearly describe desired visual effects and style in the prompt
Choose the appropriate model based on needs: select standard or fast models when reference videos are needed, choose Pro models for quality
Reference images involving faces must be uploaded to the asset library for review first
Set reasonable video duration (4-15 seconds), shorter duration generates faster

Prompt Suggestions:

Include specific scene descriptions
Add style keywords (e.g., "cinematic style", "artistic style", "realistic style")
Describe actions and movement patterns
Specify lighting and color preferences