# Create Video Generation Task

> Happy-Horse create video generation task endpoint.

Canonical URL: https://docs.uniall.ai/models/video/happy-horse/create-task
Locale: en

This document explains Happy Horse video model call.

## Public Models

| Public Models | Capability | Resolution tier |
|---|---|---:|
| `happy-horse-720p` | text-to-video, image-to-video, reference-image-to-video | 720p |
| `happy-horse-1080p` | text-to-video, image-to-video, reference-image-to-video | 1080p |
| `happy-horse-edit-720p` | video editing | 720p |
| `happy-horse-edit-1080p` | video editing | 1080p |


Note:

- `duration` Happy Horse Public Models Yesrequired parameter,`3` `15`.
- video editingModel, `duration` billing detail andtask, editing video, up toprocessing `15`.
- generation model `aspect_ratio` text-to-videoandreference-image-to-video; image-to-video Input image.
- video editingModeldoes not support `aspect_ratio`.

## Endpoint

submit task:

```http
POST /v1/videos/generations
Authorization: Bearer <api-key>
Content-Type: application/json
```

Query Task:

```http
GET /v1/videos/generations/{task_id}
Authorization: Bearer <api-key>
```

## Parameter Reference

| Parameters | Type | Required | Model | Note |
|---|---|---:|---|---|
| `model` | string | Yes | all | Public model name |
| `prompt`| string | Yes | all | prompt, up to `2500` |
| `duration`| integer | Yes | all |`3` `15`; editingModel billing detail |
| `size`| string | No | all | Optional values: pass value: 720p Modelpass `720p`, 1080p Modelpass `1080p` |
| `seed`| integer | No | all | random seed, range `0` `2147483647` |
| `aspect_ratio`| string | No | text-to-video, reference-image-to-video | Optional values `16:9`, `9:16`, `1:1`, `4:3`, `3:4` |
| `image` | string | image-to-videoRequired | image-to-video | single source image URL |
| `images` | string[] | reference-image-to-videoRequired | reference-image-to-video | 1 9 reference image URL |
| `reference_image_urls`| string[] | reference-image-to-video | reference-image-to-video |`images` |

imageconstraints:

- image-to-video `image` supports `jpeg`, `jpg`, `png`, `bmp`, `webp`, imagesize `300px`, Ratio `1:2.5` `2.5:1`, `10MB`.
- reference-image-to-video `images` supports `jpeg`, `jpg`, `png`, `webp`, 1 9, `400px`, recommended 720p, `10MB`.
- reference-image-to-videoprompt use `character1` `character9` image.

### video editingParameters

| Parameters | Type | Required | Note |
|---|---|---:|---|
| `video` | string | Yes | video URL |
| `reference_image_urls` | string[] | No | reference image URL, up to 5 |
| `audio_setting`| string | No | Optional values `auto` or `origin`, default follows the upstream default `auto` |

 videoconstraints:

- supports `mp4`, `mov`, recommended H.264.
- video `3` `60`.
- `2160px`, `320px`.
- Ratio `1:2.5` `2.5:1`.
- `8fps`, file `100MB`.

reference imageconstraints:

- up to 5.
- supports `jpeg`, `jpg`, `png`, `webp`.
- size `300px`, Ratio `1:2.5` `2.5:1`.
- `10MB`.

## API Parameters and Examples

### Endpoint


```http
POST /v1/video/generations
```
### Header Parameters

| Name | Type | Required | Description | Example |
| --- | --- | --- | --- | --- |
| `Authorization` | string | No | | Bearer &#123;your_token&#125; |
### Request Body Parameters

| Field | Type | Required | Title | Description |
| --- | --- | --- | --- | --- |
| `model` | string | Yes | Model name | Public model name |
| `prompt`| string | Yes | prompt | prompt, up to `2500` |
| `image` | string | Yes | reference URL | single source image URL, must be public URLimage URL |
| `images` | string | Yes | reference-image-to-video | 1 9 reference image URL |
| `aspect_ratio`| string | No | Ratio | Optional values `16:9`, `9:16`, `1:1`, `4:3`, `3:4` |
| `duration`| string | No | description |`3` `15`; editingModel billing detail |
| `seed`| string | Yes | random seed | random seed, range `0` `2147483647` |
| `video` | string | Yes | video URL | must be public URL URL |
| `audio_setting`| string | Yes | | Optional values `auto` or `origin`, default follows the upstream default `auto` |
| `size` | string | No | Example field | Appears in a request example; no separate field description is provided. |
| `reference_image_urls` | array | No | Example field | Appears in a request example; no separate field description is provided. |

### Request Examples

#### text-to-video

```json
{
  "model": "happy-horse-720p",
  "prompt": "A cinematic wide shot of a white horse running across a misty grassland at sunrise, realistic motion, soft rim light.",
  "duration": 4,
  "aspect_ratio": "16:9",
  "size": "720p",
  "seed": 12345
}
```

```bash
curl -X POST "{BASE_URL}/v1/video/generations" \
 -H "Authorization: Bearer sk-***" \
 -H "Content-Type: application/json" \
 -d '{"model": "happy-horse-720p",
 "prompt": "A cinematic wide shot of a white horse running across a misty grassland at sunrise, realistic motion, soft rim light.",
 "duration": 4,
 "aspect_ratio": "16:9",
 "size": "720p",
 "seed": 12345}'
```
#### image-to-video

```json
{
  "model": "happy-horse-1080p",
  "prompt": "Animate the subject naturally, with subtle camera push-in and realistic cloth movement.",
  "image": "https://example.com/source-frame.png",
  "duration": 6,
  "size": "1080p",
  "seed": 67890
}
```

```bash
curl -X POST "{BASE_URL}/v1/video/generations" \
 -H "Authorization: Bearer sk-***" \
 -H "Content-Type: application/json" \
 -d '{"model": "happy-horse-1080p",
 "prompt": "Animate the subject naturally, with subtle camera push-in and realistic cloth movement.",
 "image": "https://example.com/source-frame.png",
 "duration": 6,
 "size": "1080p",
 "seed": 67890}'
```
#### reference-image-to-video

```json
{
  "model": "happy-horse-1080p",
  "prompt": "character1 rides character2 through a futuristic city street, keep both identities consistent.",
  "images": [
    "https://example.com/character1.png",
    "https://example.com/character2.png"
  ],
  "duration": 8,
  "aspect_ratio": "9:16",
  "seed": 24680
}
```

```bash
curl -X POST "{BASE_URL}/v1/video/generations" \
 -H "Authorization: Bearer sk-***" \
 -H "Content-Type: application/json" \
 -d '{"model": "happy-horse-1080p",
 "prompt": "character1 rides character2 through a futuristic city street, keep both identities consistent.",
 "images": ["https://example.com/character1.png",
 "https://example.com/character2.png"],
 "duration": 8,
 "aspect_ratio": "9:16",
 "seed": 24680}'
```
#### video editing

```json
{
  "model": "happy-horse-edit-720p",
  "prompt": "Change the actor jacket into a red leather jacket while preserving motion, face identity, camera movement, and background.",
  "video": "https://example.com/source-video.mp4",
  "reference_image_urls": [
    "https://example.com/jacket-reference.png"
  ],
  "duration": 4,
  "size": "720p",
  "audio_setting": "origin",
  "seed": 13579
}
```

```bash
curl -X POST "{BASE_URL}/v1/video/generations" \
 -H "Authorization: Bearer sk-***" \
 -H "Content-Type: application/json" \
 -d '{"model": "happy-horse-edit-720p",
 "prompt": "Change the actor jacket into a red leather jacket while preserving motion, face identity, camera movement, and background.",
 "video": "https://example.com/source-video.mp4",
 "reference_image_urls": ["https://example.com/jacket-reference.png"],
 "duration": 4,
 "size": "720p",
 "audio_setting": "origin",
 "seed": 13579}'
```
### Response Fields

| Field | Type | Required | Title | Description |
| --- | --- | --- | --- | --- |
| `id` | string | Yes | task ID | |
| `object` | string | Yes | Task type | |
| `model` | string | Yes | Model name | |
| `status` | string | Yes | Status | |
| `progress` | string | Yes | | |
| `created_at` | string | Yes | Created time | |
| `seconds` | string | Yes | duration | |

### Response Examples

#### Success

```json
{
  "id": "task_xxxxxxxxxxxxx",
  "task_id": "task_xxxxxxxxxxxxx",
  "object": "video.generation.job",
  "model": "happy-horse-edit-720p",
  "status": "queued",
  "progress": 0,
  "created_at": 1777355454
}
```