Skip to main content
POST
/
v3
/
async
/
hunyuan-video-fast
Hunyuan Video Fast
curl --request POST \
  --url https://api.novita.ai/v3/async/hunyuan-video-fast \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '{
  "model_name": "<string>",
  "width": 123,
  "height": 123,
  "seed": 123,
  "steps": 123,
  "prompt": "<string>"
}'
{
  "task_id": "<string>"
}
Accelerated inference for HunyuanVideo with high resolution, a state-of-the-art text-to-video generation model capable of creating high-quality videos with realistic motion from text descriptions.
This is an asynchronous API; only the task_id will be returned. You should use the task_id to request the Task Result API to retrieve the video generation results.

​
Request Headers

​
Content-Type
string
required
Supports: application/json
​
Authorization
string
required
Bearer authentication format, for example: Bearer {{API Key}}.

​
Request Body

​
model_name
string
required
Name of the model checkpoint.Supports: hunyuan-video-fast.
​
width
integer
required
Width of the output video.Supports: 720, 1280.
​
height
integer
required
Height of the output video.Supports:
  • 720 for width of 1280
  • 1280 for width of 720
​
seed
integer
required
A seed is a number generates noise, which, makes generation deterministic. Using the same seed and set of parameters will produce identical content each time.Range: -1 <= x <= 9999999999.
​
steps
integer
required
The number of denoising steps. More steps usually produce higher quality content but take more time to generate.Range: 2 <= x <= 30.
​
prompt
string
required
Prompt text required to guide the generation.Range: 1 <= x <= 2000.

​
Response

​
task_id
string
required
Use the task_id to request the Task Result API to retrieve the generated outputs.

​
Example

Here is an example of how to use the Hunyuan Video Fast API.
  1. Generate a task_id by sending a POST request to the Hunyuan Video Fast API.
Request: 
curl --location 'https://api.novita.ai/v3/async/hunyuan-video-fast' \
--header 'Authorization: Bearer {{API Key}}' \
--header 'Content-Type: application/json' \
--data '{
    "model_name": "hunyuan-video-fast",
    "height": 720,
    "width": 1280,
    "seed": -1,
    "steps": 30,
    "prompt": "A close up view of a glass sphere that has a zen garden within it. There is a small dwarf in the sphere who is raking the zen garden and creating patterns in the sand.",
    "frames": 85
}'
Response: 
{
    "task_id": "{Returned Task ID}"
}
  1. Use task_id to get output videos.
HTTP status codes in the 2xx range indicate that the request has been successfully accepted, while status codes in the 5xx range indicate internal server errors. You can get videos url in videos of response. Request: 
curl --location --request GET 'https://api.novita.ai/v3/async/task-result?task_id={Returned Task ID}' \
--header 'Authorization: Bearer {{API Key}}'
Response: 
{
    "task": {
        "task_id": "{Returned Task ID}",
        "task_type": "HUNYUAN_VIDEO_FAST",
        "status": "TASK_STATUS_SUCCEED",
        "reason": "",
        "eta": 0,
        "progress_percent": 100
    },
    "images": [],
    "videos": [
        {
            "video_url": "{The URL of the generated video}",
            "video_url_ttl": "3600",
            "video_type": "mp4"
        }
    ]
}
Video files: