Vidu/Video Extension

Video Extension Extend Interface Description

Asynchronous Task Submission

Interface

https://api.umodelverse.ai/v1/tasks/submit

Input

Parameter	Type	Required	Description
model	string	Yes	Model name, options: `viduq2-turbo`, `viduq2-pro`
input.video_url	string	No	Video URL. Video duration should not be less than 4 seconds or exceed 1 minute
input.last_frame_url	string	No	Reference image for extending to the last frame, supports image URL or Base64 encoding
input.prompt	string	No	Prompt for extension, used to control the content of the extended video
parameters.vidu_type	string	Yes	Vidu interface type, should be `extend` for video extension
parameters.duration	int	No	Extension duration (seconds), options 1-7, default 5
parameters.resolution	string	No	Video resolution, options: `540p`, `720p`, `1080p`, default `720p`

Notes:

video_url
- The video link to be extended must be provided and accessible publicly.
last_frame_url parameter
- Supports Base64 encoding or image URL (ensured accessible);
- Reference image supports png, jpeg, jpg, webp formats
- Image ratio must be less than 1:4 or 4:1
- Image size should not exceed 50 MB
- Note: The byte length after base64 decode must be less than 10M, and the encoding must contain the appropriate content type string, such as data:image/png;base64,{base64_encode}

Request Example (using video_url)

⚠️ If using Windows, it is recommended to use Postman or other API calling tools.


curl --location --globoff 'https://api.umodelverse.ai/v1/tasks/submit' \
--header 'Authorization: <YOUR_API_KEY>' \
--header 'Content-Type: application/json' \
--data '{
    "model": "viduq2-turbo",
    "input": {
      "video_url": "https://umodelverse-inference.cn-wlcb.ufileos.com/maxcot-dance.mp4",
      "last_frame_url": "https://umodelverse-inference.cn-wlcb.ufileos.com/ucloud-maxcot.jpg",
      "prompt": "Continue the video with smooth camera movement"
    },
    "parameters": {
      "vidu_type": "extend",
      "duration": 5,
      "resolution": "720p"
    }
  }'

Output

Parameter	Type	Description
output.task_id	string	Unique identifier for the asynchronous task
request_id	string	Unique identifier for the request

Response Example


{
  "output": {
    "task_id": "task_id"
  },
  "request_id": "request_id"
}

Check Task Status

Interface

https://api.umodelverse.ai/v1/tasks/status?task_id=<task_id>

Request Example


curl --location 'https://api.umodelverse.ai/v1/tasks/status?task_id=<task_id>' \
--header 'Authorization: <YOUR_API_KEY>'

Output

Parameter	Type	Description
output.task_id	string	Unique identifier for the asynchronous task
output.task_status	string	Task status: `Pending`,`Running`,`Success`,`Failure`
output.urls	array	List of URLs for video results
output.submit_time	integer	Task submission timestamp
output.finish_time	integer	Task completion timestamp
output.error_message	string	Error message returned upon failure
usage.duration	integer	Duration of the extended video (seconds)
request_id	string	Unique identifier for the request

Response Example


{
  "output": {
    "task_id": "task_id",
    "task_status": "Success",
    "urls": ["https://xxxxx/xxxx-extended.mp4"],
    "submit_time": 1756959000,
    "finish_time": 1756959050
  },
  "usage": {
    "duration": 5
  },
  "request_id": ""
}