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.highwayapi.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>"
}
Minimax Hailuo 2.3 is a newly upgraded video generation model with stronger performance in body movements, physical effects, and the ability to understand and execute instructions.
This is an asynchronous API and only returns the async task’s task_id. You should use this task_id to request the Get Task Result API to retrieve the video generation result.

​
Request Headers

​
Content-Type
string
required
Enum value: application/json
​
Authorization
string
required
Bearer authentication format: Bearer {{API Key}}.

​
Request Body

​
prompt
string
required
The prompt text used to guide generation.Range: 1 <= x <= 2000.Supports 15 camera movement instructions:
  • Dolly left/right: [左移], [右移]
  • Pan left/right: [左摇], [右摇]
  • Push/pull: [推进], [拉远]
  • Rise/fall: [上升], [下降]
  • Tilt up/down: [上摇], [下摇]
  • Zoom: [变焦推近], [变焦拉远]
  • Others: [晃动], [跟随], [固定]
Usage rules:
  • Combined camera movements: Multiple instructions within the same [] take effect simultaneously, such as [左摇,上升]. It is recommended to combine no more than 3 instructions.
  • Sequential camera movements: Instructions that appear before and after each other in the prompt take effect in sequence, such as ”…[推进], then…[拉远]”.
  • Natural language: Camera movements can also be described in natural language, but using standard instructions produces more accurate responses.
​
image
string
required
The image used for video generation. Supports a public URL or Base64 encoding, such as data:image/jpeg;base64,....
​
duration
integer
The duration of the generated video in seconds. Default value: 6
Available values: 6, 10
​
resolution
string
The resolution of the generated video. Default value: 768P
  • 6-second videos support: 768P, 1080P
  • 10-second videos only support: 768P
​
enable_prompt_expansion
boolean
Whether to enable prompt optimization.Default value: true.
​
fast_pretreatment
boolean
default:false
Whether to reduce the time required for prompt optimization.Default value: false.

​
Response

​
task_id
string
required
The task_id of the asynchronous task. You should use this task_id to request the Get Task Result API to obtain the generation result.