# Happy Horse 1.1 API

Complete API reference for Happy Horse 1.1 video generation models by Alibaba.

## Model Variants

This API supports three model variants:

| Model                                   | ID                                   | Description                                          |
| --------------------------------------- | ------------------------------------ | ---------------------------------------------------- |
| **Happy Horse 1.1 Text to Video**       | `happyhorse-1.1-text-to-video`       | Generate videos directly from text prompts           |
| **Happy Horse 1.1 Image to Video**      | `happyhorse-1.1-image-to-video`      | Animate a single first-frame image with prompt guidance |
| **Happy Horse 1.1 Reference to Video** | `happyhorse-1.1-reference-to-video` | Generate videos guided by up to 9 reference images   |

## Quick Comparison

| Feature        | Text to Video             | Image to Video            | Reference to Video        |
| -------------- | ------------------------- | ------------------------- | ------------------------- |
| Input          | Text prompt               | First-frame image + prompt | Reference images + prompt |
| Duration Range | 3-15 seconds              | 3-15 seconds              | 3-15 seconds              |
| Resolution     | 720p, 1080p (default 1080p) | 720p, 1080p (default 1080p) | 720p, 1080p (default 1080p) |
| Aspect Ratio   | 9 supported ratios (default 16:9) | Not supported (follows input image) | 9 supported ratios (default 16:9) |
| Seed           | Optional                  | Optional                  | Optional                  |

### Supported Aspect Ratios (Text to Video & Reference to Video)

| Ratio  | Description            |
| ------ | ---------------------- |
| `16:9` | Landscape (widescreen) |
| `9:16` | Portrait (vertical)    |
| `3:4`  | Standard portrait      |
| `4:3`  | Standard landscape     |
| `4:5`  | Portrait               |
| `5:4`  | Landscape              |
| `1:1`  | Square                 |
| `9:21` | Ultra-tall portrait    |
| `21:9` | Ultra-wide landscape   |

## Happy Horse 1.1 Text to Video

### Endpoint

```
POST /api/v1/video/task
```

### Request Parameters

#### Required

| Parameter      | Type   | Description                                                        |
| -------------- | ------ | ------------------------------------------------------------------ |
| `model_name`   | string | Must be `"happyhorse-1.1-text-to-video"`                           |
| `prompt`       | string | Video generation prompt                                            |
| `duration`     | number | Video duration in seconds (3-15)                                   |
| `resolution`   | string | Output resolution: `"720p"` or `"1080p"` (default `"1080p"`)       |
| `aspect_ratio` | string | Video aspect ratio (see table above; default `"16:9"`)             |

#### Optional

| Parameter | Type   | Description                                                                        |
| --------- | ------ | ---------------------------------------------------------------------------------- |
| `seed`    | number | Random seed for reproducible generations, integer in the range `0` to `2147483647` |

### Example Request

```javascript
const response = await fetch('https://api.flaq.ai/api/v1/video/task', {
  method: 'POST',
  headers: {
    Authorization: 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model_name: 'happyhorse-1.1-text-to-video',
    prompt: 'A cat playing with a ball of yarn on a sunny windowsill',
    duration: 5,
    resolution: '1080p',
    aspect_ratio: '16:9',
    seed: 42,
  }),
});

const { data } = await response.json();
const taskId = data.task_id;
```

## Happy Horse 1.1 Image to Video

### Request Parameters

#### Required

| Parameter    | Type   | Description                                                        |
| ------------ | ------ | ------------------------------------------------------------------ |
| `model_name` | string | Must be `"happyhorse-1.1-image-to-video"`                          |
| `prompt`     | string | Video generation prompt                                            |
| `duration`   | number | Video duration in seconds (3-15)                                   |
| `resolution` | string | Output resolution: `"720p"` or `"1080p"` (default `"1080p"`)       |
| `image_url`  | string | First-frame image URL (first frame only)                           |

#### Optional

| Parameter | Type   | Description                                                                        |
| --------- | ------ | ---------------------------------------------------------------------------------- |
| `seed`    | number | Random seed for reproducible generations, integer in the range `0` to `2147483647` |

> **Note:** `aspect_ratio` is not supported for image-to-video. Output framing follows the uploaded first-frame image.

### Example Request

```javascript
const response = await fetch('https://api.flaq.ai/api/v1/video/task', {
  method: 'POST',
  headers: {
    Authorization: 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model_name: 'happyhorse-1.1-image-to-video',
    image_url: 'https://example.com/first-frame.jpg',
    prompt: 'Gentle motion; cinematic lighting',
    duration: 5,
    resolution: '1080p',
    seed: 42,
  }),
});

const { data } = await response.json();
const taskId = data.task_id;
```

## Happy Horse 1.1 Reference to Video

### Request Parameters

#### Required

| Parameter      | Type     | Description                                                        |
| -------------- | -------- | ------------------------------------------------------------------ |
| `model_name`   | string   | Must be `"happyhorse-1.1-reference-to-video"`                      |
| `prompt`       | string   | Video generation prompt. Write a standard prompt without placeholders, or optionally use the @ (AT) reference feature with `<<<image_N>>>` to explicitly reference items from the `images` array |
| `duration`     | number   | Video duration in seconds (3-15)                                   |
| `resolution`   | string   | Output resolution: `"720p"` or `"1080p"` (default `"1080p"`)       |
| `aspect_ratio` | string   | Video aspect ratio (see table above; default `"16:9"`)             |
| `images`       | string[] | Reference image URLs (1-9 images)                                  |

#### @ (AT) Reference Placeholders

The @ (AT) reference feature links reference images to the prompt through numbered `<<<image_N>>>` placeholders. Numbering starts at `1` and follows the order of the `images` array.

| Placeholder | Referenced value |
|-------------|------------------|
| `<<<image_1>>>` | `images[0]` |
| `<<<image_2>>>` | `images[1]` |
| `<<<image_3>>>` | `images[2]` |

#### Optional

| Parameter | Type   | Description                                                                        |
| --------- | ------ | ---------------------------------------------------------------------------------- |
| `seed`    | number | Random seed for reproducible generations, integer in the range `0` to `2147483647` |

### Reference Image Requirements

- Supported formats: `JPEG`, `JPG`, `PNG`, `WEBP`
- Maximum file size: 20 MB per image
- Minimum short side: 400 px
- Count: at least 1, up to 9 images

### Example Request

```javascript
const response = await fetch('https://api.flaq.ai/api/v1/video/task', {
  method: 'POST',
  headers: {
    Authorization: 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model_name: 'happyhorse-1.1-reference-to-video',
    prompt: 'Subject moves naturally while preserving reference style and appearance',
    duration: 5,
    resolution: '1080p',
    aspect_ratio: '16:9',
    images: [
      'https://example.com/ref-1.jpg',
      'https://example.com/ref-2.jpg',
    ],
    seed: 42,
  }),
});

const { data } = await response.json();
const taskId = data.task_id;
```

### @ (AT) Reference-to-Video Request Example

```javascript
const response = await fetch('https://api.flaq.ai/api/v1/video/task', {
  method: 'POST',
  headers: {
    Authorization: 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model_name: 'happyhorse-1.1-reference-to-video',
    prompt: 'Show the person from <<<image_1>>> walking beside the bicycle from <<<image_2>>> through the street in <<<image_3>>>, preserving all reference details',
    duration: 5,
    resolution: '1080p',
    aspect_ratio: '16:9',
    images: [
      'https://example.com/person-reference.jpg',
      'https://example.com/bicycle-reference.jpg',
      'https://example.com/street-reference.jpg',
    ],
    seed: 42,
  }),
});

const { data } = await response.json();
const taskId = data.task_id;
```

## Response Format

### Initial Response

```json
{
  "code": 0,
  "message": "success",
  "data": {
    "task_id": "{task_id}",
    "response_url": "https://api.flaq.ai/api/v1/video/{task_id}",
    "task_status": "submitted"
  }
}
```

### Polling Response

Poll `GET /api/v1/video/{taskId}` to check status:

```json
{
  "code": 0,
  "message": "success",
  "data": {
    "task_id": "{task_id}",
    "response_url": "https://api.flaq.ai/api/v1/video/{task_id}",
    "task_status": "succeed",
    "task_status_msg": null,
    "task_result": {
      "credit": 0.2,
      "videos": [
        {
          "url": "https://example.com/generated-video.mp4"
        }
      ]
    }
  }
}
```

### Status Values

- `submitted`: Task accepted and waiting to be processed
- `processing`: Video generation in progress
- `succeed`: Video generation completed
- `failed`: Video generation failed

## Processing Time

Typical processing time: 2-5 minutes depending on duration and queue load.

## Best Practices

1. **Describe Motion Clearly**: Add subject movement, camera movement, and scene progression to improve video dynamics.
2. **Use Short Iterations First**: Start with 3-5 second generations to validate prompt direction before running longer clips.
3. **Choose the Right Input Image**: For image-to-video, use a clear, well-lit first-frame image with a strong subject focus.
4. **Curate Reference Images**: For reference-to-video, provide consistent, high-quality reference images that clearly represent the subject or style you want to preserve.
5. **Reuse Seeds for Variants**: Keep the same `seed` when testing prompt refinements to compare outputs more consistently.
6. **Match Ratio to Delivery Channel**: Use `16:9` for landscape video, `9:16` for shorts and reels, and `1:1` for square placements.