> ## Documentation Index
> Fetch the complete documentation index at: https://docs.toapis.com/llms.txt
> Use this file to discover all available pages before exploring further.

# MiniMax-Hailuo-02 動画生成

> Generate videos using MiniMax Hailuo 02 model, supporting text-to-video, image-to-video, and first-last-frame generation

* Async task API, returns task ID upon submission
* Supported model: `MiniMax-Hailuo-02`
* Three generation modes: text-to-video, image-to-video, first-last-frame generation
* Supports 512P / 768P / 1080P resolution, 6-second and 10-second duration

<Warning>
  Please provide publicly accessible image URLs. Do not pass base64 image data directly in `image_urls` or `metadata`; upload local images first using the [Upload 画像API](../../uploads/images) to get URLs.
</Warning>

## 認証

<ParamField header="Authorization" type="string" required>
  All endpoints require Bearer Token authentication.

  ```
  Authorization: Bearer YOUR_API_KEY
  ```
</ParamField>

## リクエストパラメータ

<ParamField body="model" type="string" required>
  モデル name, fixed as `MiniMax-Hailuo-02`.
</ParamField>

<ParamField body="prompt" type="string">
  Video content description, max **2000 characters**.

  * **必須** for text-to-video mode
  * 任意 for image-to-video and first-last-frame modes (can describe desired motion)

  Supports 15 camera directives (e.g., `[Push in]`, `[Pull out]`, `[Pan left, Pedestal up]`), see the Camera Directives table below.

  Example: `"A mouse runs toward the camera, smiling and blinking"`
</ParamField>

<ParamField body="duration" type="integer" default="6">
  Video duration in seconds.

  Options: `6` or `10`

  <Warning>
    When using `1080P` resolution, only `6` seconds is supported.
  </Warning>
</ParamField>

<ParamField body="resolution" type="string" default="768P">
  Video resolution.

  Options:

  * `512P` - Standard definition (available for image-to-video)
  * `768P` - HD (default)
  * `1080P` - Full HD (6-second duration only)
</ParamField>

<ParamField body="image_urls" type="string[]">
  First frame image URL array.

  * Not provided: text-to-video
  * 1 image: image-to-video, image used as video starting frame

  Image requirements:

  * Format: JPG, JPEG, PNG, WebP
  * Size: under 20MB
  * Dimensions: short side > 300px, aspect ratio between 2:5 and 5:2

  Example: `["https://example.com/first-frame.jpg"]`
</ParamField>

<ParamField body="metadata" type="object">
  Extended parameters.

  <Expandable title="Show metadata fields">
    <ParamField body="last_frame_image" type="string">
      Last frame image URL for **first-last-frame generation mode**.

      When provided, the system generates a transition video from the first frame to the last frame.

      * When both `image_urls` (first frame) and `last_frame_image` (last frame) are provided, video dimensions follow the first frame
      * If first and last frame sizes differ, the model crops the last frame based on the first frame
      * First-last-frame mode **does not support 512P** resolution

      Image requirements are the same as `image_urls`.

      Example: `"https://example.com/last-frame.jpg"`
    </ParamField>

    <ParamField body="prompt_optimizer" type="boolean" default="true">
      Auto-optimize prompt. Set to `false` for more precise control.
    </ParamField>

    <ParamField body="fast_pretreatment" type="boolean" default="false">
      Shorten prompt optimization time. Speeds up processing when enabled.
    </ParamField>

    <ParamField body="aigc_watermark" type="boolean" default="false">
      Whether to add watermark to the generated video.
    </ParamField>

    <ParamField body="callback_url" type="string">
      Callback URL. The system will send a POST callback to this URL when task status changes.
    </ParamField>
  </Expandable>
</ParamField>

## Three Generation Modes

| Mode             |       image\_urls       | metadata.last\_frame\_image | 説明                                                 |
| ---------------- | :---------------------: | :-------------------------: | -------------------------------------------------- |
| Text-to-Video    |       Not provided      |         Not provided        | Generate video from text description               |
| Image-to-Video   |        ✅ 1 image        |         Not provided        | Generate video with image as first frame           |
| First-Last-Frame | ✅ 1 image (first frame) |   ✅ Provided (last frame)   | Generate transition video from first to last frame |

## Resolution and Duration Combinations

| Resolution | Supported Durations | Text-to-Video | Image-to-Video | First-Last-Frame |
| ---------- | ------------------- | :-----------: | :------------: | :--------------: |
| 512P       | 6s, 10s             |       ✅       |        ✅       |         ❌        |
| 768P       | 6s, 10s             |       ✅       |        ✅       |         ✅        |
| 1080P      | 6s                  |       ✅       |        ✅       |         ✅        |

## 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]` |

**Usage rules:**

* 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]"`

## レスポンス

<ResponseField name="id" type="string">
  Task ID for querying task status.
</ResponseField>

<ResponseField name="object" type="string">
  Object type, always `generation.task`.
</ResponseField>

<ResponseField name="model" type="string">
  モデル name used for this request.
</ResponseField>

<ResponseField name="status" type="string">
  Task status: `queued`, `in_progress`, `completed`, or `failed`.
</ResponseField>

<ResponseField name="created_at" type="integer">
  Task creation timestamp.
</ResponseField>

## Examples

### Text-to-Video

```json theme={null}
{
  "model": "MiniMax-Hailuo-02",
  "prompt": "City night scene, neon lights flickering, traffic flowing [Push in]",
  "duration": 6,
  "resolution": "1080P"
}
```

### Image-to-Video

```json theme={null}
{
  "model": "MiniMax-Hailuo-02",
  "prompt": "Person slowly turns around, smiling",
  "image_urls": ["https://example.com/portrait.jpg"],
  "duration": 6,
  "resolution": "768P"
}
```

### First-Last-Frame Generation

```json theme={null}
{
  "model": "MiniMax-Hailuo-02",
  "prompt": "A little girl grows up",
  "image_urls": ["https://example.com/child.jpg"],
  "duration": 6,
  "resolution": "1080P",
  "metadata": {
    "last_frame_image": "https://example.com/adult.jpg"
  }
}
```

### Camera Control

```json theme={null}
{
  "model": "MiniMax-Hailuo-02",
  "prompt": "A man picks up a book [Pedestal up], then reads [Static shot]",
  "duration": 6,
  "resolution": "768P"
}
```

### 10-Second Long Video + Fast Preprocessing

```json theme={null}
{
  "model": "MiniMax-Hailuo-02",
  "prompt": "Waves crashing on the beach at sunset, golden light shimmering on the water",
  "duration": 10,
  "resolution": "768P",
  "metadata": {
    "prompt_optimizer": true,
    "fast_pretreatment": true
  }
}
```

<Note>
  Video generation is an async task. Use [Get Video Task ステータス](../../tasks/video-status) to query progress and results.
</Note>

<RequestExample>
  ```bash cURL theme={null}
  curl --request POST \
    --url https://toapis.com/v1/videos/generations \
    --header 'Authorization: Bearer <token>' \
    --header 'Content-Type: application/json' \
    --data '{
      "model": "MiniMax-Hailuo-02",
      "prompt": "City night scene, neon lights flickering, traffic flowing",
      "duration": 6,
      "resolution": "1080P"
    }'
  ```

  ```python Python theme={null}
  import requests

  response = requests.post(
      "https://toapis.com/v1/videos/generations",
      headers={
          "Authorization": "Bearer your-ToAPIs-key",
          "Content-Type": "application/json",
      },
      json={
          "model": "MiniMax-Hailuo-02",
          "prompt": "City night scene, neon lights flickering, traffic flowing",
          "duration": 6,
          "resolution": "1080P",
      },
  )

  print(response.json())
  ```

  ```javascript JavaScript theme={null}
  const response = await fetch("https://toapis.com/v1/videos/generations", {
    method: "POST",
    headers: {
      Authorization: "Bearer your-ToAPIs-key",
      "Content-Type": "application/json"
    },
    body: JSON.stringify({
      model: "MiniMax-Hailuo-02",
      prompt: "City night scene, neon lights flickering, traffic flowing",
      duration: 6,
      resolution: "1080P"
    })
  });

  console.log(await response.json());
  ```
</RequestExample>

<ResponseExample>
  ```json 200 theme={null}
  {
    "id": "vid_01K8SGYNNNVBQTXNR4MM964S7K",
    "object": "generation.task",
    "model": "MiniMax-Hailuo-02",
    "status": "queued",
    "progress": 0,
    "created_at": 1768380224,
    "metadata": {}
  }
  ```
</ResponseExample>