MiniMax-Hailuo-2.3
MiniMax-Hailuo-2.3 Video Generation
Generate videos using MiniMax Hailuo 2.3 series models, supporting text-to-video and image-to-video with optional Fast mode
POST
- Async task API, returns task ID upon submission
- Supported models:
MiniMax-Hailuo-2.3,MiniMax-Hailuo-2.3-Fast MiniMax-Hailuo-2.3: Supports text-to-video and image-to-video, best qualityMiniMax-Hailuo-2.3-Fast: Image-to-video only (first frame image required), faster generation
Authentication
All endpoints require Bearer Token authentication.
Request Parameters
Model name.Options:
MiniMax-Hailuo-2.3- Supports text-to-video and image-to-videoMiniMax-Hailuo-2.3-Fast- Image-to-video only (image_urlsrequired)
Video content description, max 2000 characters.Supports 15 camera directives (e.g.,
[Push in], [Pull out], [Pan left, Pedestal up]), see the Camera Directives table below.Example: "A cat running in a garden [Push in], then stops and looks at the camera [Static shot]"Video duration in seconds.Options:
6 or 10Video resolution.Options:
768P- HD (default)1080P- Full HD (6-second duration only)
First frame image URL array.
- Not provided: text-to-video (
MiniMax-Hailuo-2.3-Fastdoes not support this, must provide) - 1 image: image-to-video, image used as video starting frame
- Format: JPG, JPEG, PNG, WebP
- Size: under 20MB
- Dimensions: short side > 300px, aspect ratio between 2:5 and 5:2
["https://example.com/first-frame.jpg"]Extended parameters.
Model Comparison
| Model | Text-to-Video | Image-to-Video | Resolution | Duration |
|---|---|---|---|---|
MiniMax-Hailuo-2.3 | ✅ | ✅ | 768P / 1080P | 6s / 10s |
MiniMax-Hailuo-2.3-Fast | ❌ | ✅ (first frame required) | 768P / 1080P | 6s / 10s |
Resolution and Duration Combinations
| Resolution | Supported Durations | Note |
|---|---|---|
| 768P | 6s, 10s | Default resolution |
| 1080P | 6s | 10s not supported |
Camera Directives
Use[directive] syntax in prompt to control camera movement:
| Category | Directives |
|---|---|
| Pan | [Pan left] [Pan right] |
| Tilt | [Tilt up] [Tilt down] |
| Push/Pull | [Push in] [Pull out] |
| Pedestal | [Pedestal up] [Pedestal down] |
| Truck | [Truck left] [Truck right] |
| Zoom | [Zoom in] [Zoom out] |
| Other | [Shake] [Tracking shot] [Static shot] |
- Combine up to 3 directives in one bracket for simultaneous movement, e.g.,
[Pan left, Pedestal up] - Sequence directives in the prompt for ordered camera moves, e.g.,
"...[Push in], then...[Pull out]"
Response
Task ID for querying task status.
Object type, always
generation.task.Model name used for this request.
Task status:
queued, in_progress, completed, or failed.Task creation timestamp.
Examples
Text-to-Video
Image-to-Video
Image-to-Video (Fast Mode)
Camera Control
10-Second Long Video
Video generation is an async task. Use Get Video Task Status to query progress and results.