Skip to main content
POST
Hunyuan Text-to-Video
HunyuanVideo is an industry-leading text-to-video generation model that can generate high-quality videos with realistic motion based on text descriptions.
This is an asynchronous API that only returns the task_id of the async task. You should use this task_id to call the Query Task Result API to retrieve the generated results.

Request Headers

string
required
Enum value: application/json
string
required
Bearer authentication format: Bearer {{API Key}}.

Request Body

string
required
Model name.Supported: hunyuan-video-fast.
integer
required
Width of the output video.Supported: 720, 1280.
integer
required
Height of the output video.Supported:
  • When width is 1280, height is 720
  • When width is 720, height is 1280
integer
required
Random seed used for noise generation, making the output reproducible. The same seed and parameters will produce the same content.Range: -1 <= x <= 9999999999.
integer
required
Number of denoising steps. More steps generally produce better results but take longer.Range: 2 <= x <= 30.
string
required
Prompt to guide the generation.Range: 1 <= x <= 2000.

Response

string
required
The task_id of the async task. Use the task_id to call the Get Async Task Result API to retrieve the generated result.