Algorithm model ID for invocation. Options: I2V-01, I2V-01-live, I2V-01-Director
prompt
string
optional
Video generation description. (Note: Must be under 200 characters)
prompt_optimizer
boolean
optional
Default value is True, where the model automatically optimizes the input prompt to improve generation quality. For more precise control, set this parameter to False, and the model will strictly follow the instructions. In this case, providing a more detailed prompt is recommended for optimal results.
first_frame_image
string
required
The model uses the image provided in this parameter as the first frame to generate the video. Supports image URL or base64 encoding. When this parameter is provided, the prompt can be set to an empty string or omitted, and the model will autonomously determine how the scene evolves. Input images must meet the following conditions: JPG/JPEG/PNG format; aspect ratio between 2:5 and 5:2; short side greater than 300px; file size not exceeding 20MB.
Example
{"model":"I2V-01-live","prompt":"a man is smile","first_frame_image":"https://file.302ai.cn/gpt/imgs/20241012/813d3e2cecf146b1b5a3d1e742ee3e5d.png"}
Request samples
Shell
JavaScript
Java
Swift
Go
PHP
Python
HTTP
C
C#
Objective-C
Ruby
OCaml
Dart
R
Request Request Example
Shell
JavaScript
Java
Swift
curl--location--request POST 'https://api.302.ai/minimaxi/v1/video_generation' \
--header'Authorization: Bearer sk-jls4AaVBGoe1GwZD64qZA1qyKTN1MPHa4NmvH1cT68z7K1Zz' \
--header'Content-Type: application/json' \
--data-raw'{
"model": "I2V-01-live",
"prompt": "a man is smile",
"first_frame_image": "https://file.302ai.cn/gpt/imgs/20241012/813d3e2cecf146b1b5a3d1e742ee3e5d.png"
}'