Vidu Q1 Reference-to-Video
Video
Vidu Q1 Reference-to-Video
POST
Vidu Q1 Reference-to-Video
Vidu Q1 Reference-to-Video generates videos using reference images and text descriptions. It supports various subjects, such as characters and objects. By uploading multiple views of a subject, you can create videos that maintain visual consistency.
Request Headers
Enum value:
application/jsonBearer authentication format: Bearer {{API Key}}.
Request Body
The model will use the provided images as references to generate a video with a consistent subject.Image field requirements:
- Accepts 1 to 7 images
- Image resources can be provided via URL or Base64 encoding
- Must use one of the following formats: PNG, JPEG, JPG, WebP
- Image dimensions must be at least 128x128 pixels
- The image aspect ratio must be less than 1:4 or 4:1
- All images are limited to 50MB
- The decoded base64 length must be less than 10MB and must include the appropriate content-type string. For example:
The text prompt for video generation, with a maximum length of 1500 characters.
Video duration in seconds. Defaults to 5 seconds. Currently, only the
5-second option is supported.The random seed for video generation.
- Defaults to a random seed value
- A manually set value will override the default random seed
The aspect ratio of the output video. Default value:
Available values:
16:9Available values:
16:9, 9:16, 1:1The output video resolution. Defaults to 1080p. Currently, only the
1080p option is supported.The movement amplitude of objects in the frame. Default value:
Available values:
autoAvailable values:
auto, small, medium, largeWhether to add background music to the generated video. Default value:
Available values:
falseAvailable values:
true, falseWhen set to true, the system will automatically add suitable BGM. There is no duration limit for the BGM; the system will adapt it automatically.Response
The task_id of the async task. You should use this task_id to request the Get Task Result API to obtain the generation result.