I2V-01-live

The algorithm model ID to be called. Optional values: MiniMax-Hailuo-02

Description for generating a video. (Note: Must be less than 200 words)

The default value is True. The model will automatically optimize the provided prompt to improve generation quality. If more precise control is required, you can set this parameter to False, and the model will follow the instructions more strictly. In this case, it is recommended to provide a more detailed prompt to achieve the best results.

512P: Default 6, optional values: 6, 10
768P: Default 6, optional values: 6, 10
1080P: Default 6, optional values: 6

6s duration: Default value is 768P, optional values: 512P, 768P, 1080P;
10s duration: Default value is 768P, optional values: 512P, 768P.

When the resolution is 512P, a first frame image must be provided; for resolutions of 768P or 1080P, the first frame image is optional.

The model will use the provided image in the input parameters as the first frame of the generated video. Images can be provided via image URL or base64 encoding. When an image is provided, the prompt can be set as an empty string or omitted, and the model will automatically determine how the scene evolves.

The uploaded image must meet the following requirements: the file format must be JPG, JPEG, or PNG; the aspect ratio must be between 2:5 and 5:2; the shorter side must be at least 300px; and the image size must not exceed 20MB.

The model will use the image provided in this parameter as the final frame to generate the video. It supports passing the image as a URL or in base64 encoding. When this parameter is provided, you can set the prompt to an empty string or omit the prompt, and the model will autonomously determine how the scene evolves.

Callback address, send data to this address via POST