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

# Vidu Video Overview

> Official Vidu format, OpenAI format, and unified video interface organized by model series.

# Vidu Video

The Vidu video series currently provides three integration methods: the official format (`/vidu/ent/v2/*`), OpenAI-compatible `/v1/videos` (`multipart/form-data` format), and the unified video endpoints `/v1/video/create` and `/v1/video/query` (JSON).

## Official Format

Use the `/vidu/ent/v2/*` series of interfaces, which support multiple video generation modes.

<CardGroup cols={2}>
  <Card title="Text to Video" icon="clapperboard" href="/en/videos/vidu/text2video">
    `POST /vidu/ent/v2/text2video`, generates video from text only.
  </Card>

  <Card title="Image to Video" icon="image" href="/en/videos/vidu/img2video">
    `POST /vidu/ent/v2/img2video`, generates video from a first-frame image.
  </Card>

  <Card title="Start-End Frame to Video" icon="film" href="/en/videos/vidu/start-end2video">
    `POST /vidu/ent/v2/start-end2video`, generates video from start and end frames.
  </Card>

  <Card title="Reference to Video" icon="users" href="/en/videos/vidu/reference2video">
    `POST /vidu/ent/v2/reference2video`, generates video with subject reference.
  </Card>

  <Card title="Query Task" icon="hourglass" href="/en/videos/vidu/query">
    `GET /vidu/ent/v2/task/{task_id}/creations`, queries task status and results.
  </Card>
</CardGroup>

### Supported Models (Official Format)

| Model                       | Description                                                | Duration Rules       |
| --------------------------- | ---------------------------------------------------------- | -------------------- |
| `viduq3-pro`                | Efficiently generates high-quality audio and video content | Depends on the model |
| `viduq2` / `viduq2-pro`     | New model with good results and rich details               | 1-10 seconds         |
| `viduq2-turbo`              | New model with good results and fast generation            | 1-10 seconds         |
| `viduq1` / `viduq1-classic` | Clear visuals and smooth transitions                       | Depends on the model |
| `vidu2.0`                   | Fast generation speed                                      | Depends on the model |

## OpenAI Format

Use `POST /v1/videos` to submit and `GET /v1/videos/{task_id}` to query, with submission in `multipart/form-data`.

<CardGroup cols={2}>
  <Card title="Video Generation" icon="clapperboard" href="/en/videos/vidu/vidu-generation">
    `POST /v1/videos`, submits a Vidu video task.
  </Card>

  <Card title="Task Status Query" icon="hourglass" href="/en/videos/vidu/vidu-query">
    `GET /v1/videos/{task_id}`, queries task status and results.
  </Card>
</CardGroup>

### Supported Models (OpenAI Format)

| Model          | Description                                                                                                                  |
| -------------- | ---------------------------------------------------------------------------------------------------------------------------- |
| `viduq3-pro`   | Efficiently generates high-quality audio and video content, making the video more vivid, more expressive, and more immersive |
| `viduq2-pro`   | New model with good results and rich details                                                                                 |
| `viduq2-turbo` | New model with good results and fast generation                                                                              |

## Unified Video

Use `POST /v1/video/create` to create tasks, and `GET /v1/video/query?id=` for queries.

<CardGroup cols={2}>
  <Card title="Generate Video" icon="clapperboard" href="/en/videos/vidu/unified-generation">
    `POST /v1/video/create`, submits a Vidu task in the unified video format.
  </Card>

  <Card title="Query Task" icon="hourglass" href="/en/videos/vidu/unified-query">
    `GET /v1/video/query`, queries status and results by task `id`.
  </Card>
</CardGroup>

### Common Capabilities (Unified Video)

| Capability               | Parameter Passing | Description                     |
| ------------------------ | ----------------- | ------------------------------- |
| Text to Video            | `images: []`      | Text prompt only                |
| First-Frame to Video     | `images` 1 image  | First-frame image + text prompt |
| Start-End Frame to Video | `images` 2 images | First frame + end frame         |
| Reference to Video       | `subjects` array  | Subject reference images        |

## Comparison

| Item             | Official Format                             | OpenAI Format              | Unified Video             |
| ---------------- | ------------------------------------------- | -------------------------- | ------------------------- |
| Create           | `/vidu/ent/v2/*`                            | `POST /v1/videos`          | `POST /v1/video/create`   |
| Query            | `GET /vidu/ent/v2/task/{task_id}/creations` | `GET /v1/videos/{task_id}` | `GET /v1/video/query?id=` |
| Request Format   | JSON                                        | multipart/form-data        | JSON                      |
| Reference Images | `images` / `subjects`                       | `images`                   | `images`                  |
| Aspect Ratio     | `aspect_ratio`                              | `aspect_ratio`             | `aspect_ratio`            |
| Resolution       | `resolution`                                | `resolution`               | `size`                    |
| Duration         | `duration`                                  | `duration`                 | `duration`                |

## Parameter Constraints

| Field          | Available Values                    | Description                                            |
| -------------- | ----------------------------------- | ------------------------------------------------------ |
| `aspect_ratio` | `16:9`, `9:16`, `3:4`, `4:3`, `1:1` | `3:4` and `4:3` are supported only by q2 and q3 models |
| `resolution`   | `540p`, `720p`, `1080p`             | Resolution specification                               |
| `duration`     | `1`-`10`                            | Video duration (seconds), q2 defaults to 5             |
| `style`        | `general`, `anime`                  | Style (not effective for q2, q3)                       |

## Featured Capabilities

| Feature                | Description                                                             |
| ---------------------- | ----------------------------------------------------------------------- |
| Audio and Video Output | `audio: true`, outputs videos with dialogue and sound effects (q3 only) |
| Background Music       | `bgm: true`, automatically adds BGM                                     |
| Off-Peak Mode          | `off_peak: true`, generates during off-peak times for lower credits     |
| Recommended Prompts    | `is_rec: true`, the system automatically recommends prompts             |
| Watermark              | `watermark: true`, adds a fixed watermark                               |

## Related Pages

* [Video Model Support Matrix](/en/videos/model-matrix)
* [Text to Video (Official Format)](./text2video)
* [Image to Video (Official Format)](./img2video)
* [Start-End Frame to Video (Official Format)](./start-end2video)
* [Reference to Video (Official Format)](./reference2video)
* [Query Task (Official Format)](./query)
* [Video Generation (OpenAI Format)](./vidu-generation)
* [Task Status Query (OpenAI Format)](./vidu-query)
* [Generate Video (Unified Video)](./unified-generation)
* [Query Task (Unified Video)](./unified-query)