⌘K

Vidu Create Subjects

vidu_create_subjects

Vidu Create Subjects allows creating reusable subjects with image and video references and voice configuration.

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 to use for the request

Value: vidu_create_subjects

name string required

Subject name (recommended to be unique)

images array[string]

Subject images, at least 1 image must be uploaded

Note 1: Supports image Base64 encoding or image URL (ensure accessible)
Note 2: Maximum 3 images supported
Note 3: Supported image formats: png, jpeg, jpg, webp
Note 4: Image aspect ratio must be less than 1:4 or 4:1
Note 5: Image size must not exceed 50 MB
Note 6: Please note that the byte length after base64 decode must be less than 20M, and the encoding must include an appropriate content type string, for example:

data:image/png;base64,{base64_encode}

videos array[string]

Video reference, supports uploading 1 subject video

Note 1: Only the viduq2-pro reference generation model supports video subjects
Note 2: Maximum 1 video of 5 seconds supported
Note 3: Supported video formats: mp4, avi, mov
Note 4: Video resolution must not be less than 128*128, aspect ratio must be less than 1:4 or 4:1, and size must not exceed 100M
Note 5: Please note that the byte length after base64 decode must be less than 20M, and the encoding must include an appropriate content type string, for example:

data:video/mp4;base64,{base64_encode}

voice_id string

Subject voice ID, used only when creating audio-video direct output tasks

Note 1: If no voice ID is provided when creating audio-video direct output tasks, the system will automatically recommend a voice
Note 2: q2-pro does not support using a voice ID

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

output array

Generation result. Only present when status is completed.

content array

List of generated content

text string

Subject info JSON string, containing the following fields:
id: Generated subject ID (server_id)
name: Custom subject name for this generation
images: Image parameters of the generated subject
videos: Video parameters of the generated subject
voice_id: Voice ID bound to the generated subject
style: Style information of the generated subject
description: Description of the generated subject
credits: Credits consumed by this call

type string

Resource type, this endpoint returns text