Model name
Accepted values: viduq1

• viduq1: Clear image, smooth transition, stable camera operation

The model will use the subjects in the provided images as references to generate a video with subject consistency. Different model versions accept different numbers of reference images
Note 1: The viduq1 series models accept 1 to 7 images
Note 2: Assets can be provided via Base64 encode or image URLs (make sure they are accessible)
Note 3: Supported formats: png, jpeg, jpg, webp
Note 4: The dimensions of the images must be at least 128x128 pixels, and the aspect ratio of the images must be less than 1:4 or 4:1
Note 5: The post body of the HTTP request should not exceed 20MB, and it must include an appropriate content type string. For instance:
data:image/png;base64,{base64_encode}

Text prompt
A textual description for video generation
Note: The maximum length is 5000 characters

Whether to add background music to the generated video. Default: false. Accepted values: true, false

• When true, the system will automatically select a suitable BGM from the preset library and add it. When it is not passed or set to false, no BGM will be added
• BGM has no time limit and the system automatically adapts to the video duration
• BGM does not take effect when the duration of the q2 series models is 9 or 10 seconds

Video duration parameter, with default values depending on the model:

• viduq1: Default is 5 seconds, available option: 5

Random seed
When it is not passed or set to 0, a random number will be used instead
Manually set values will be used as the seed

The aspect ratio of the output video
Defaults to 16:9, accepted values: 1:1, 9:16, 16:9, 3:4, 4:3
auto: Automatically recommended based on the input image or video

The movement amplitude of objects in the frame
Defaults to auto, accepted values: auto, small, medium, large

Resolution parameter, with default values depending on the model and video duration:

• viduq1 (5s): Default is 1080p, available option: 1080p

Transparent transmission parameters
No processing, only data transmission
Note: Maximum of 1048576 characters

Off-peak mode. Default: false. Accepted values:

• true: Generate videos in off-peak mode
• false: Generate videos immediately
  Note 1: Off-peak mode consumes fewer credits. For details, see Pricing
  Note 2: Tasks submitted in off-peak mode will be generated within 48 hours. Tasks that are not completed will be automatically cancelled and their credits will be refunded
  Note 3: You can also manually cancel off-peak tasks
  Note 4: The q1 series models support off-peak tasks when the audio parameter is false

Whether to add a watermark

• true: Add watermark
• false: Do not add watermark
  Note 1: The current watermark content is fixed and generated by AI. By default, no watermark is added
  Note 2: You can obtain the watermarked video content via the watermarked_url parameter. For details, see the Get Creation API

Watermark position, indicating where the watermark appears on the image. Default: 3. Accepted values:
1: Top left
2: Top right
3: Bottom right
4: Bottom left

Watermark content, which is an image URL
If not provided, the default watermark will be used: Content generated by AI

Metadata identifier, a JSON-formatted string and a transparent transmission field. You can customize the format or use the sample format below:
{
"Label": "your_label","ContentProducer": "your_content_producer","ContentPropagator": "your_content_propagator","ProduceID": "your_product_id", "PropagateID": "your_propagate_id","ReservedCode1": "your_reserved_code1", "ReservedCode2": "your_reserved_code2"
}
When this parameter is empty, the metadata identifier generated by Vidu is used by default

Callback protocol
You need to actively set the callback_url when creating a task. The request method is POST. When the video generation task changes its status, Vidu will send a callback request containing the latest status of the task to this URL. The structure of the callback request content is the same as the return body of the Get Creation API
The "status" returned in the callback includes the following states:

• processing: Task is being processed
• success: Task is completed (if sending fails, it will retry the callback three times)
• failed: Task failed (if sending fails, it will retry the callback three times)
  Vidu uses a callback signature algorithm for verification. Check out the details here: Callback Signature

Task ID generated by Vidu

It will be returned to a specific processing state:

• created: created task successfully
• queueing: task in queue
• processing: processing
• success: generation successful
• failed: task failed

The model used for this call

Replace {your api key} with your API key

Model name
Accepted values: viduq1

• viduq1: Clear image, smooth transition, stable camera operation

Whether to use the intelligent subject library capability. Default: false. Accepted values: true, false

• true: Use the intelligent subject library capability
• false: Do not use the intelligent subject library capability

Replace {your api key} with your API key

Task id. The id is returned upon the successful creation of a task by the Start Generating API