# Gemini Omni 1.2 Flash API

Complete API reference for Google Gemini Omni 1.2 Flash video generation models.

## Model Variants

This API supports four model variants:

| Model | ID | Description |
|-------|-----|-------------|
| **Gemini Omni 1.2 Flash Text to Video** | `gemini-omni-1.2-flash-text-to-video` | Generate videos from text prompts |
| **Gemini Omni 1.2 Flash Image to Video** | `gemini-omni-1.2-flash-image-to-video` | Animate a required start image with optional end-frame guidance |
| **Gemini Omni 1.2 Flash Video Edit** | `gemini-omni-1.2-flash-video-edit` | Apply prompt-guided changes to an existing video |
| **Gemini Omni 1.2 Flash Reference to Video** | `gemini-omni-1.2-flash-reference-to-video` | Generate videos from image references, video references, or both |

## Quick Comparison

| Feature | Text to Video | Image to Video | Video Edit | Reference to Video |
|---------|---------------|----------------|------------|--------------------|
| Primary Input | Text prompt | Start image + Text prompt | Source video + Text prompt | Text prompt + At least one image or video reference |
| Duration | 3-15 seconds | 3-15 seconds; 3-10 with an end frame | Source video must be no longer than 10 seconds | 3-15 seconds |
| Resolution Options | 360p, 720p, 1080p, 4k | 360p, 720p, 1080p, 4k | 360p, 720p, 1080p, 4k | 360p, 720p, 1080p, 4k |
| Aspect Ratios | 16:9, 9:16 | 16:9, 9:16 | Not supported | 16:9, 9:16 |
| Optional Inputs | None | End image | None | Up to 10 images and 3 videos; at least one reference required |

## Shared Endpoint

All Gemini Omni 1.2 Flash variants use the video task endpoint:

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

## Gemini Omni 1.2 Flash Text to Video

### Required Parameters

| Parameter | Type | Description |
|-----------|------|-------------|
| `model_name` | string | Must be `"gemini-omni-1.2-flash-text-to-video"` |
| `prompt` | string | Text description of the video to generate |
| `aspect_ratio` | string | Output aspect ratio: `"16:9"` or `"9:16"` |
| `resolution` | string | Output resolution: `"360p"`, `"720p"`, `"1080p"`, or `"4k"` |
| `duration` | integer | Output duration in seconds, from 3 to 15 |

### 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: 'gemini-omni-1.2-flash-text-to-video',
    prompt: 'A cinematic tracking shot follows a sailboat crossing a glowing ocean at sunset',
    aspect_ratio: '16:9',
    resolution: '1080p',
    duration: 12
  })
});

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

## Gemini Omni 1.2 Flash Image to Video

### Required Parameters

| Parameter | Type | Description |
|-----------|------|-------------|
| `model_name` | string | Must be `"gemini-omni-1.2-flash-image-to-video"` |
| `prompt` | string | Text description of the desired motion and scene development |
| `image_url` | string | URL of the required start-frame image |
| `aspect_ratio` | string | Output aspect ratio: `"16:9"` or `"9:16"` |
| `resolution` | string | Output resolution: `"360p"`, `"720p"`, `"1080p"`, or `"4k"` |
| `duration` | integer | Output duration in seconds, from 3 to 15 without an end frame, or from 3 to 10 when `image_end_url` is provided |

### Optional Parameters

| Parameter | Type | Description |
|-----------|------|-------------|
| `image_end_url` | string | URL of an optional end-frame image. When provided, `duration` must be from 3 to 10 seconds |

### Example Request

```javascript
{
  model_name: 'gemini-omni-1.2-flash-image-to-video',
  prompt: 'The girl walks toward the camera while the city lights shimmer behind her',
  image_url: 'https://example.com/start-frame.jpg',
  image_end_url: 'https://example.com/end-frame.jpg',
  aspect_ratio: '9:16',
  resolution: '1080p',
  duration: 8
}
```

## Gemini Omni 1.2 Flash Video Edit

### Required Parameters

| Parameter | Type | Description |
|-----------|------|-------------|
| `model_name` | string | Must be `"gemini-omni-1.2-flash-video-edit"` |
| `prompt` | string | Text instructions describing the edit to apply |
| `video_url` | string | URL of the source video. The source video must be no longer than 10 seconds |
| `resolution` | string | Output resolution: `"360p"`, `"720p"`, `"1080p"`, or `"4k"` |

**Note:** Video Edit does not support `aspect_ratio` or `duration`. Do not include either parameter in the request.

### Example Request

```javascript
{
  model_name: 'gemini-omni-1.2-flash-video-edit',
  prompt: 'A small ball rolls into the scene and captures the attention of the cat',
  video_url: 'https://example.com/source-video.mp4',
  resolution: '1080p'
}
```

## Gemini Omni 1.2 Flash Reference to Video

Reference images and videos may be used separately or together. At least one reference image or video must be provided in `images` or `videos`.

### Required Parameters

| Parameter | Type | Description |
|-----------|------|-------------|
| `model_name` | string | Must be `"gemini-omni-1.2-flash-reference-to-video"` |
| `prompt` | string | Text description of the video to generate |
| `aspect_ratio` | string | Output aspect ratio: `"16:9"` or `"9:16"` |
| `resolution` | string | Output resolution: `"360p"`, `"720p"`, `"1080p"`, or `"4k"` |
| `duration` | integer | Output duration in seconds, from 3 to 15 |

### Optional Reference Inputs

| Parameter | Type | Description |
|-----------|------|-------------|
| `images` | string[] | Up to 10 reference image URLs. Optional when video references are provided |
| `videos` | string[] | Up to 3 reference video URLs. Each video must be no longer than 3 seconds. Optional when image references are provided |

### Example Request

```javascript
{
  model_name: 'gemini-omni-1.2-flash-reference-to-video',
  prompt: 'Use the references to create a cinematic shot of a small boat approaching from the distance',
  aspect_ratio: '16:9',
  resolution: '1080p',
  duration: 12,
  images: ['https://example.com/boat-reference.jpg'],
  videos: ['https://example.com/motion-reference.mp4']
}
```

## Response Format

### Initial Response

All models return a `task_id` for polling:

```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

## Best Practices

1. **Prompt Direction**: Describe subjects, actions, camera movement, lighting, and scene progression clearly.
2. **Required Settings**: Always provide a supported resolution and, except for Video Edit, a supported aspect ratio and duration.
3. **Image Inputs**: Use stable, publicly accessible URLs for start, end, and reference images. When providing an end-frame image, keep `duration` between 3 and 10 seconds.
4. **Video Edit Input**: Verify that the source video is no longer than 10 seconds before submitting it.
5. **Reference Limits**: Provide at least one reference image or video. Submit no more than 10 images and 3 videos, and keep every reference video at or below 3 seconds.