⌘K

Vidu Q2 Pro - Reference to Video

viduq2_pro_reference

Vidu Q2 Pro - Reference to Video supports both image and video references to generate high-quality videos with subject consistency

Authentication

authorization string required

All APIs require authentication via Bearer Token.

Get API Key:

Visit API Key Management Page to get your API Key.

Usage:

Add to request header:

Authorization: Bearer YOUR_API_KEY

Parameters

model string required

Model ID used for the request

Value: viduq2_pro_reference

images array<string> required

Image references. Supports uploading 1 to 7 images. The model uses subjects from these images to generate videos with subject consistency.

Note 1: For this model, if no video is uploaded, 1 to 7 images are supported. If video is uploaded, 1 to 4 images are supported.
Note 2: Supports image Base64 input or image URL input (must be accessible).
Note 3: Supported image formats: png, jpeg, jpg, webp.
Note 4: Image resolution must be at least 128x128, aspect ratio must be less than 1:4 or 4:1, and file size must not exceed 50MB.
Note 5: HTTP request post body must not exceed 20MB, and encoding must include a proper content-type prefix, for example: data:image/png;base64,{base64_encode}.

videos array<string> required

Video references. Supports uploading 1 to 2 videos. The model uses these videos as references to generate videos with subject consistency.

Note 1: With video reference enabled, at most 1 video of 8 seconds or 2 videos of 5 seconds are supported.
Note 2: Supported video formats: mp4, avi, mov.
Note 3: Video resolution must be at least 128x128, aspect ratio must be less than 1:4 or 4:1, and file size must not exceed 100MB.
Note 4: Base64 decoded byte length must be less than 20MB, and encoding must include a proper content-type prefix, for example: data:video/mp4;base64,{base64_encode}.

prompt string required

Text prompt describing the video to generate.

Limit: Maximum 5000 characters.

bgm boolean

Whether to add background music to the generated video.

If set to true, the system automatically selects and adds suitable music from the preset BGM library. If omitted or set to false, no BGM is added.
BGM has no duration limit and is automatically adapted to video duration.
Note: In this model, when duration is 9 or 10, bgm does not take effect.

Options: true, false

Default: false

duration integer

Video duration parameter.

Options: 0 to 10 (0 means auto duration selection)

Default: 5

seed integer

Random seed. If omitted or set to 0, a random value is used. If set manually, the provided seed is used.

aspect_ratio string

Aspect ratio.

Options: 16:9, 9:16, 4:3, 3:4, 1:1

Default: 16:9

resolution string

Resolution parameter.

Options: 540p, 720p, 1080p

Default: 720p

payload string

Pass-through parameter. No processing is performed, only data transfer.

Limit: Maximum 1048576 characters.

off_peak boolean

Note: Temporarily unavailable

Off-peak mode.

true: Generate video in off-peak mode.
false: Generate video immediately.

Note 1: Off-peak mode consumes fewer credits.
Note 2: Tasks submitted in off-peak mode are generated within 48 hours. Unfinished tasks are automatically canceled and credits are refunded.
Note 3: You can also manually cancel off-peak tasks.
Note 4: Audio-video direct output does not support off-peak mode.

Options: true, false

Default: false

watermark boolean

Whether to add watermark.

true: Add watermark.
false: Do not add watermark.

Note 1: Current watermark content is fixed and AI-generated, and is disabled by default.
Note 2: You can obtain watermarked video content through the watermarked_url field.

Options: true, false

Default: false

wm_position integer

Watermark position.

1: Top-left
2: Top-right
3: Bottom-right
4: Bottom-left

Default: 3

wm_url string

Watermark image URL. If omitted, the default watermark is used (AI-generated).

meta_data string

Metadata identifier.

callback_url string

Callback URL.

Polling

Since result generation takes time, you need to poll the task status after creating the task.

The initial response only returns information such as the task ID and initial status. The final result must be obtained by polling the task status endpoint using the task ID.

See the examples on the right for polling requests and responses.

Response Format

error object

Error information. Only appears when status is failed.

code integer

Error code

error_message string

Detailed error message

output array

Generation result. Only appears when status is completed.

content array

Generated content list

type string

Resource type

Value: video

url string

URL of generated content

usage object

Usage statistics. Only appears when status is completed.

cost string

Total cost (USD)

discount number

Discount amount

metadata object

Metadata information.