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

# HappyHorse 1.1

> Generate text-to-video, image-to-video, or reference-to-video tasks with HappyHorse 1.1.

HappyHorse 1.1 is Alibaba Cloud Model Studio's video-generation series. Choose the workflow that matches your input: text only, one first-frame image, or multiple reference images. All workflows submit an asynchronous task through `POST /v1/video/generations`.

<Note>
  `T2V` means text-to-video, `I2V` means image-to-video, and `R2V` means reference-to-video. Save the returned task ID and poll the [task query guide](/guides/model-api/alibaba/happyhorse-task-query) until the task completes.
</Note>

## Key capabilities

* **Synchronized audio** - All HappyHorse 1.1 workflows generate 24 fps MP4 video with audio
* **Resolution** - `720P` or `1080P`
* **Duration** - An integer from 3 to 15 seconds
* **Seed and watermark controls** - Set a seed for reproducibility and control the HappyHorse watermark

<Tabs sync={false}>
  <Tab title="Text to video">
    Use `happyhorse-1.1-t2v` to generate a video from a text prompt.

    ```bash cURL theme={null}
    curl https://www.anyfast.ai/v1/video/generations \
      -H 'Authorization: Bearer YOUR_API_KEY' \
      -H 'Content-Type: application/json' \
      -d '{
        "model": "happyhorse-1.1-t2v",
        "input": {"prompt": "A miniature cardboard city wakes up at night as a lit train passes by."},
        "parameters": {"resolution": "720P", "ratio": "16:9", "duration": 5, "watermark": false, "seed": 42}
      }'
    ```

    | Parameter               | Required | Description                                                                          |
    | ----------------------- | -------- | ------------------------------------------------------------------------------------ |
    | `input.prompt`          | Yes      | Text description; up to 5,000 non-Chinese or 2,500 Chinese characters                |
    | `parameters.ratio`      | No       | `16:9`, `9:16`, `1:1`, `4:3`, `3:4`, `4:5`, `5:4`, `9:21`, or `21:9`; default `16:9` |
    | `parameters.resolution` | No       | `720P` or `1080P`; default `1080P`                                                   |
  </Tab>

  <Tab title="Image to video">
    Use `happyhorse-1.1-i2v` with exactly one `first_frame` image. Images can be public HTTP/HTTPS URLs or Base64 data URLs in JPEG, JPG, PNG, or WEBP format. Each side must be at least 300 pixels, the aspect ratio must be between 1:2.5 and 2.5:1, and the file must not exceed 20 MB.

    ```bash cURL theme={null}
    curl https://www.anyfast.ai/v1/video/generations \
      -H 'Authorization: Bearer YOUR_API_KEY' \
      -H 'Content-Type: application/json' \
      -d '{
        "model": "happyhorse-1.1-i2v",
        "input": {"prompt": "The cat runs across the grass as the camera follows smoothly.", "media": [{"type": "first_frame", "url": "https://example.com/cat.png"}]},
        "parameters": {"resolution": "720P", "duration": 5, "watermark": false}
      }'
    ```

    <Note>The I2V workflow does not accept `parameters.ratio`; the output follows the first-frame image ratio.</Note>
  </Tab>

  <Tab title="Reference to video">
    Use `happyhorse-1.1-r2v` with 1 to 9 `reference_image` items. Reference images may be public URLs or Base64 data URLs in JPEG, JPG, PNG, or WEBP format. The shortest side must be at least 400 pixels and each file must not exceed 20 MB.

    ```bash cURL theme={null}
    curl https://www.anyfast.ai/v1/video/generations \
      -H 'Authorization: Bearer YOUR_API_KEY' \
      -H 'Content-Type: application/json' \
      -d '{
        "model": "happyhorse-1.1-r2v",
        "input": {"prompt": "The woman in [Image 1] enters the room and opens the folding fan from [Image 2].", "media": [{"type": "reference_image", "url": "https://example.com/person.jpg"}, {"type": "reference_image", "url": "https://example.com/fan.jpg"}]},
        "parameters": {"resolution": "720P", "ratio": "16:9", "duration": 5, "watermark": false}
      }'
    ```

    <Tip>The order of `input.media` determines `[Image 1]`, `[Image 2]`, and so on in the prompt.</Tip>
  </Tab>
</Tabs>

## Shared parameters

| Parameter              | Type    | Description                                             |
| ---------------------- | ------- | ------------------------------------------------------- |
| `parameters.duration`  | integer | 3-15 seconds; default `5`                               |
| `parameters.watermark` | boolean | Whether to add the HappyHorse watermark; default `true` |
| `parameters.seed`      | integer | Random seed in `[0, 2147483647]`                        |

<CardGroup cols={2}>
  <Card title="API reference" icon="code" href="/api-reference/model-api/alibaba/happyhorse-1.1">View all three HappyHorse 1.1 request formats.</Card>
  <Card title="Task query" icon="magnifying-glass" href="/guides/model-api/alibaba/happyhorse-task-query">Poll task status and retrieve the result URL.</Card>
</CardGroup>

## Official references

* [Text to video](https://help.aliyun.com/en/model-studio/happyhorse-text-to-video-api-reference)
* [Image to video](https://help.aliyun.com/en/model-studio/happyhorse-image-to-video-api-reference)
* [Reference to video](https://help.aliyun.com/en/model-studio/happyhorse-reference-to-video-api-reference)

<script src="/public/feedback.js" />