Skip to main content
POST
/
v3
/
async
/
minimax-hailuo-2.3-i2v
Minimax Hailuo 2.3 Image to Video
curl --request POST \
  --url https://api.novita.ai/v3/async/minimax-hailuo-2.3-i2v \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "prompt": "<string>",
  "image": "<string>",
  "duration": 123,
  "resolution": "<string>",
  "enable_prompt_expansion": true,
  "fast_pretreatment": true
}
'
{
  "task_id": "<string>"
}

Documentation Index

Fetch the complete documentation index at: https://novita.ai/docs/llms.txt

Use this file to discover all available pages before exploring further.

Minimax Hailuo 2.3 is a new video generation model, breakthroughs in body movement, facial expressions, physical realism, and prompt adherence.
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

​
prompt
string
required
Prompt text required to guide the generation.Range: 1 <= x <= 2000.Supported 15 camera commands:
  • Truck: [Truck left], [Truck right]
  • Pan: [Pan left], [Pan right]
  • Push: [Push in], [Pull out]
  • Pedestal: [Pedestal up], [Pedestal down]
  • Tilt: [Tilt up], [Tilt down]
  • Zoom: [Zoom in], [Zoom out]
  • Shake: [Shake]
  • Follow: [Tracking shot]
  • Static: [Static shot]
Usage rules:
  • Combined movements: Multiple commands inside one [] take effect simultaneously (e.g., [Pan left,Pedestal up]). Recommended max: 3.
  • Sequential movements: Commands appear in order, e.g., ”…[Push in], then…[Push out]”.
  • Natural language: Free-form descriptions also work, but explicit commands yield more accurate results.
​
image
string
required
The image to be used for video generation. Supports public URL or Base64 encoding(data:image/jpeg;base64,...).
​
duration
integer
The length of the generated video in seconds. Default: 6
Optional values: 6, 10
​
resolution
string
The resolution of the generated video. Default: 768P
  • For 6-second videos: supports 768P, 1080P
  • For 10-second videos: supports 768P only
​
enable_prompt_expansion
boolean
Whether to enable prompt optimization.Default: true.
​
fast_pretreatment
boolean
default:false
Whether to shorten the prompt optimization time.Default: false.

​
Response

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