Skip to main content
POST
The model name for Vidu Q4 in AIReiter is vidu_q4. This model requires at least one image to be passed in, does not support pure text-to-video generation, and does not support start and end frames.

Authorizations

string
required
All endpoints require Bearer Token authentication.Get an API Key:Visit the API Key management page to get your API Key.Add to the request header when using:

Body

string
required
Model name, fixed value:
  • vidu_q4
object
required
Model parameters object.
string
required
Caller task ID.User-defined task identifier, required. Supports only letters, numbers, underscores, and hyphens, with a length of 1-64 characters. This ID can be used later to query task status and results.

Response

string
Initiator task ID, can be used to query results.
string
Initial status, typically "pending".
string
Creation time, in ISO format.

Query Task

Vidu Q4 is an asynchronous video generation model. After submitting a task, please use out_task_id to query the task status; querying every 10-15 seconds is recommended.
string
required
The initiator task ID passed when submitting the task.
After the query succeeds and completes, the output array in the response will contain the generated video, with elements containing the video field.

Mode Notes

frame uses 1 image as the first frame to generate a video, the prompt is optional, and the aspect ratio follows the image; reference combines 1-15 reference images and up to 3 reference audio clips to generate new visuals, the prompt is required, and the aspect ratio can be specified.
When type is frame, image_url must contain exactly 1 image, and do not pass audio_url. When type is reference, prompt cannot be empty, with a maximum of 15 reference images and up to 3 reference audio clips.