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

# Reference to Video

<a id="reference-to-video-api-q3-turbo-create-reference2video-1"></a>

## Q3 Turbo Create Task

```
POST /ent/v2/reference2video
```

## Subjects-Reference to Video

How to create subjects: [https://platform.vidu.cn/docs/subjects](https://platform.vidu.cn/docs/subjects)

### Headers

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `Authorization` | `string` | Required | Replace `{your api key}` with your token；Example: `Token {your api key}` |

### Body parameters

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `model` | `string` | Required | Model name Accepted values: `viduq3-turbo` viduq3-turbo: Supports intelligent scene switching and simultaneous audio and video output, boasts the fastest generation speed, and offers the highest cost-effectiveness |
| `auto_subjects` | `boolean` | Optional | Whether to use the intelligent subject library capability. Default is false. Accepted values: true, false true: Use the intelligent subject library capability. false: Do not use the intelligent subject library capability. |
| `subjects` | `string` | Required | When using the q3, q2, q1, and 2.0 models, only image subjects and text subjects can be used. The number of image or text subjects should not exceed 7. When using the q2-pro model, video subjects, text subjects, and image subjects can be used. The number of image or text subjects should not exceed 4. The number of video subjects should not exceed 2 (or 1 for temporary video subjects). |
| ↳ `name` | `string` | Required | Subject name specified by the user. It can be used via [@name] during generation. For；Example: `[@image1]normal` |
| ↳ `images` | `string` | Optional | Temporary subject images. Up to 3 images. Note 1: Images can be provided via Base64 encoding or image URLs (make sure they are accessible). Note 2: Images must be in PNG, JPEG, JPG, or WebP format. Note 3: Image dimensions cannot be less than 128*128 pixels, and the aspect ratio must be less than 1:4 or 4:1. Note 4: Please note that the post body of the HTTP request must not exceed 20MB, and the encoding must include an appropriate content type string. For base64,{base64_encode}normal；Example: `data:image/png` |
| ↳ `videos` | `string` | Optional | Temporary subject video. Up to one 5-second video. Note 1: Only the viduq2-pro Reference to Video model supports video subjects. Note 2: Up to one 5-second video can be uploaded. Note 3: Videos must be in MP4, AVI, or MOV format. Note 4: Video dimensions cannot be less than 128*128 pixels, and the aspect ratio must be less than 1:4 or 4:1. Note 5: Please note that the byte length after base64 decoding must be less than 20M, and the encoding must include an appropriate content type string. For base64,{base64_encode}normal；Example: `data:video/mp4` |
| ↳ `voice_id` | `string` | Optional | Voice ID Used to determine the voice character in the video. When empty, the system will automatically recommend one. For optional enumeration values, refer to the [Voice List](https://shengshu.feishu.cn/sheets/WM45sosS7hEj2mtAATvclDAWnNb). Or you can use the [Voice Cloning API](https://platform.vidu.cn/docs/voice-clone) to clone any voice. The voice_id parameters can be used interchangeably. |
| ↳ `server_id` | `string` | Optional | The subject ID obtained through the Create Subject API. Note: When server_id is not passed, it is treated as a temporary subject and will not be saved by the system. |
| `prompt` | `string` | Required | Text prompt A textual description for video generation. Note 1: The length cannot exceed 5000 characters. Note 2: Use [@subjects_name] to represent subject content. For normal；Example: `@1 and @2 are eating hot pot together, and the narrator says that everyone loves hot pot.` |
| `audio` | `boolean` | Optional | Whether to use the audio-video output capability. Default is false. Accepted values: true, false true: Use the audio-video output capability. false: Do not use the audio-video output capability. |
| `duration` | `integer` | Optional | Video duration parameter, with default values depending on the model: `viduq3-turbo`: Default is 5 seconds, available option: 3-16 |
| `seed` | `integer` | Optional | Random seed When not passed or passed as 0, a random number will be used instead. When manually set, the set seed will be used. |
| `aspect_ratio` | `string` | Optional | Defaults to `16:9`. Accepted values: 1:1, 9:16, 16:9, 3:4, 4:3 auto: Automatically recommended based on the input image or video. |
| `resolution` | `string` | Optional | Resolution parameter, with default values depending on the model and video duration: `viduq3-turbo` (1-16s): Default is 720p, available options: 540p, 720p, 1080p |
| `payload` | `string` | Optional | Transparent transmission parameters No processing, only data transmission. Note: Maximum of 1048576 characters. |
| `off_peak` | `boolean` | Optional | Off peak mode. Default: false. Accepted values: true: Generate video in off-peak mode. false: Generate video immediately. Note 1: Off-peak mode consumes fewer credits. See Pricing for details. Note 2: Tasks submitted in off-peak mode will be generated within 48 hours. Tasks that are not completed will be automatically cancelled and their credits will be refunded. Note 3: You can also [manually cancel](https://platform.vidu.cn/docs/cancel-task-api) off-peak tasks. |
| `watermark` | `boolean` | Optional | Whether to add a watermark. true: Add watermark. false: Do not add watermark. Note 1: Currently the watermark content is fixed as "Content generated by AI", and no watermark is added by default. Note 2: You can obtain the watermarked video content through the watermarked_url parameter. See the Query Task API for details. |
| `wm_position` | `integer` | Optional | Watermark position. Indicates where the watermark appears on the image. Default: 3. Options: 1: Top left 2: Top right 3: Bottom right 4: Bottom left |
| `wm_url` | `string` | Optional | Watermark content. This is an image URL. When not passed, the default watermark is used: "Content generated by AI". |
| `meta_data` | `string` | Optional | Metadata label. A JSON-formatted string. Transparent transmission field. You can customize the format or use the example format as follows: { "Label": "your_label", "ContentProducer": "yourcontentproducer", "ContentPropagator": "your_content_propagator", "ProduceID": "yourproductid", "PropagateID": "your_propagate_id", "ReservedCode1": "yourreservedcode1", "ReservedCode2": "your_reserved_code2" } When this parameter is empty, the metadata label generated by Vidu is used by default. |
| `callback_url` | `string` | Optional | Callback protocol When creating a task, you need to actively set the `callback_url` with a POST request. When the video generation task changes its status, Vidu will send a callback request to this URL, containing the latest status of the task. The structure of the callback request content will be the same as the return body of the Query Task API. The "status" in the callback response includes the following states: processing: Task is being processed. success: Task is completed (if sending fails, it will retry the callback three times). failed: Task failed (if sending fails, it will retry the callback three times). Vidu uses a callback signature algorithm for verification. See [Callback Signature](https://platform.vidu.cn/docs/callback-signature) for details. |

### Request example

```shell
curl -X POST -H "Authorization: Token {your_api_key}" -H "Content-Type: application/json" -d '
{
    "model": "viduq3-turbo",
    "subjects": [
        {
            "name": "1",
            "images":["your_image1","your_image2"]
        },
        {
            "name": "2",
            "server_id": "321321"
        },
        {
            "name": "3",
            "server_id": "456456"
        }
    ],
    "prompt": "[@1] and [@2] are eating hot pot together at [@3]",
    "duration": 8,
    "audio":true
}' https://api.vidu.com/ent/v2/reference2video
```

### Response

#### 200 OK

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `task_id` | `string` | Optional | Task ID generated by Vidu |
| `state` | `string` | Optional | Processing state Accepted values: `created` Created successfully `queueing` Task in queue `processing` Task is being processed `success` Task succeeded `failed` Task failed |
| `model` | `string` | Optional | The model name used for this call |
| `prompt` | `string` | Optional | The prompt parameter used for this call |
| `images` | `string` | Optional | The image parameter used for this call |
| `duration` | `integer` | Optional | The video duration parameter used for this call |
| `seed` | `integer` | Optional | The random seed parameter used for this call |
| `aspect_ratio` | `string` | Optional | The aspect ratio parameter used for this call |
| `resolution` | `string` | Optional | The resolution parameter used for this call |
| `payload` | `string` | Optional | The transparent transmission parameter passed in this call |
| `off_peak` | `boolean` | Optional | Whether off-peak mode is used in this call |
| `credits` | `integer` | Optional | The credits consumed by this call |
| `created_at` | `string` | Optional | Task creation time |

```json
{
  "task_id": "your_task_id_here",
  "state": "created",
  "model": "viduq3-turbo",
  "images": [""],
  "prompt": "[@1] and [@2] are eating hot pot together at [@3]",
  "duration": 5,
  "seed": random_number,
  "aspect_ratio": "3:4",
  "resolution": "720p",
  "audio": true,
  "payload":"",
  "off_peak": false,
  "credits":credits_number,
  "created_at": "2025-01-01T15:41:31.968916Z"
}

{
  "task_id": "your_task_id_here",
  "state": "created",
  "model": "viduq3-turbo",
  "images": ["https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/reference2video-1.png","https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/reference2video-2.png","https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/reference2video-3.png"],
  "prompt": "Santa Claus and the bear hug by the lakeside.",
  "duration": 5,
  "seed": random_number,
  "aspect_ratio": "3:4",
  "resolution": "540p",
  "payload":"",
  "credits":credits_number,
  "created_at": "2025-01-01T15:41:31.968916Z"
}
```

<a id="reference-to-video-api-q3-turbo-get-creations-2"></a>

## Q3 Turbo Query Creations

```
GET /ent/v2/tasks/{id}/creations
```

### Headers

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `Authorization` | `string` | Required | Replace `{your api key}` with your token；Example: `Token {your api key}` |

### Path parameters

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `id` | `string` | Required |  |

### Body parameters

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `id` | `string` | Required | Task ID. Returned by the Create Task API upon successful creation. |

### Request example

```shell
curl -X GET -H "Authorization: Token {your_api_key}" https://api.vidu.com/ent/v2/tasks/{your_id}/creations
```

### Response

#### 200 OK

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `id` | `string` | Optional | Task ID |
| `state` | `string` | Optional | Processing state Accepted values: `created` Created successfully `queueing` Task in queue `processing` Task is being processed `success` Task succeeded `failed` Task failed |
| `err_code` | `string` | Optional | Error code. See the error code table for details. |
| `credits` | `integer` | Optional | The number of credits consumed by this task. Unit: credits. |
| `payload` | `string` | Optional | The transparent transmission parameter passed in this task call |
| `off_peak` | `boolean` | Optional | Whether off-peak mode is used in this task call |
| `creations` | `array` | Optional | Generation results |
| ↳ `id` | `string` | Optional | Generation ID. Used to identify different generations. |
| ↳ `url` | `string` | Optional | Generation URL. Valid for 24 hours. |
| ↳ `cover_url` | `string` | Optional | Generation cover. Valid for 24 hours. |
| ↳ `watermarked_url` | `string` | Optional | Watermarked generation URL. Valid for 24 hours. |

```json
{
  "id":"your_task_id",
  "state": "success",
  "err_code": "",
  "credits": 4,
  "payload": "",
  "creations": [
    {
      "id": "your_creations_id",
      "url": "your_generated_results_url",
      "cover_url": "your_generated_results_cover_url",
      "watermarked_url": "your_generated_results_watermarked_url"
    }
  ]
}
```

<a id="reference-to-video-api-q3-create-reference2video-3"></a>

## Q3 Create Task

```
POST /ent/v2/reference2video
```

### Headers

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `Authorization` | `string` | Required | Example: `Token <YOUR_API_KEY>` |

### Body parameters

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `model` | `string` | Required | Model name Accepted values: `viduq3` viduq3: Supports intelligent camera switching, supports simultaneous audio and video output, and achieves superior consistency across multiple camera positions |
| `images` | `string` | Optional | Image reference supports multiple images. The model will use the subjects in the images provided in this parameter as references to generate a video with subject consistency. Different model versions support different numbers of reference images. Specific requirements are as follows: Note 1: The viduq3 series models support uploading 1 to 7 images. Note 2: Images can be provided via Base64 encoding or image URLs (make sure they are accessible). Note 3: Images must be in PNG, JPEG, JPG, or WebP format. Note 4: Image dimensions cannot be less than 128*128 pixels, and the aspect ratio must be less than 1:4 or 4:1. Note 5: Please note that the post body of the HTTP request must not exceed 20MB, and the encoding must include an appropriate content type string. For base64,{base64_encode}normal；Example: `data:image/png` |
| `prompt` | `string` | Required | Text prompt A textual description for video generation. Note: The length cannot exceed 5000 characters. |
| `duration` | `integer` | Optional | Video duration parameter, with default values depending on the model: `viduq3`: Default is 5 seconds, available option: 3-16 |
| `seed` | `integer` | Optional | Random seed When not passed or passed as 0, a random number will be used instead. When manually set, the set seed will be used. |
| `aspect_ratio` | `string` | Optional | Aspect ratio parameter. Defaults to `16:9`. Accepted values: 1:1, 9:16, 16:9, 3:4, 4:3 auto: Automatically recommended based on the input image or video. |
| `audio` | `boolean` | Optional | Whether to use the audio-video output capability. Default is true. Valid values: false: Do not use audio-video output; outputs silent video. true: Use audio-synchronized output; outputs video with sound (including dialogue and sound effects). Note: In non-subject invocation, only the q3 models support this parameter. |
| `resolution` | `string` | Optional | Resolution parameter, with default values depending on the model and video duration: `viduq3` (3-16s): Default is 720p, available options: 540p, 720p, 1080p |
| `payload` | `string` | Optional | Transparent transmission parameters No processing, only data transmission. Note: Maximum of 1048576 characters. |
| `off_peak` | `boolean` | Optional | Off peak mode. Default: false. Accepted values: true: Generate video in off-peak mode. false: Generate video immediately. Note 1: Off-peak mode consumes fewer credits. See Pricing for details. Note 2: Tasks submitted in off-peak mode will be generated within 48 hours. Tasks that are not completed will be automatically cancelled and their credits will be refunded. Note 3: You can also [manually cancel](https://platform.vidu.cn/docs/cancel-task-api) off-peak tasks. Note 4: The viduq3 model supports off-peak tasks when the audio parameter is true. |
| `callback_url` | `string` | Optional | Callback protocol When creating a task, you need to actively set the callback_url with a POST request. When the video generation task changes its status, Vidu will send a callback request to this URL, containing the latest status of the task. The structure of the callback request content will be the same as the return body of the Query Task API. The "status" in the callback response includes the following states: processing: Task is being processed. success: Task is completed (if sending fails, it will retry the callback three times). failed: Task failed (if sending fails, it will retry the callback three times). Vidu uses a callback signature algorithm for verification. See [Callback Signature](https://platform.vidu.cn/docs/callback-signature) for details. |

### Request example

```shell
curl -X POST -H "Authorization: Token {your_api_key}" -H "Content-Type: application/json" -d '
{
    "model": "viduq3",
    "images": ["https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/reference2video-1.png","https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/reference2video-2.png","https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/reference2video-3.png"],
    "prompt": "Santa Claus and the bear hug by the lakeside.",
    "duration": 5,
    "seed": 0,
    "aspect_ratio": "3:4",
    "resolution": "1080p"
}' https://api.vidu.com/ent/v2/reference2video
```

### Response

#### 200 OK

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `task_id` | `string` | Optional | Task ID generated by Vidu |
| `state` | `string` | Optional | Processing state Accepted values: `created` Created successfully `queueing` Task in queue `processing` Task is being processed `success` Task succeeded `failed` Task failed |
| `model` | `string` | Optional | The model name used for this call |
| `prompt` | `string` | Optional | The prompt parameter used for this call |
| `images` | `array` | Optional | The image parameter used for this call |
| `duration` | `integer` | Optional | The video duration parameter used for this call |
| `seed` | `integer` | Optional | The random seed parameter used for this call |
| `aspect_ratio` | `string` | Optional | The aspect ratio parameter used for this call |
| `resolution` | `string` | Optional | The resolution parameter used for this call |
| `payload` | `string` | Optional | The transparent transmission parameter passed in this call |
| `off_peak` | `boolean` | Optional | Whether off-peak mode is used in this call |
| `credits` | `integer` | Optional | The credits consumed by this call |
| `created_at` | `string` | Optional | Task creation time |

```json
{
  "task_id": "your_task_id_here",
  "state": "created",
  "model": "viduq3",
  "images": ["https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/reference2video-1.png","https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/reference2video-2.png","https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/reference2video-3.png"],
  "prompt": "Santa Claus and the bear hug by the lakeside.",
  "duration": 5,
  "seed": random_number,
  "aspect_ratio": "3:4",
  "resolution": "540p",
  "payload":"",
  "credits":credits_number,
  "created_at": "2025-01-01T15:41:31.968916Z"
}

{
  "task_id": "your_task_id_here",
  "state": "created",
  "model": "viduq3",
  "images": [""],
  "prompt": "[@1] and [@2] are eating hot pot together at [@3]",
  "duration": 5,
  "seed": random_number,
  "aspect_ratio": "3:4",
  "resolution": "720p",
  "audio": true,
  "payload":"",
  "off_peak": false,
  "credits":credits_number,
  "created_at": "2025-01-01T15:41:31.968916Z"
}
```

## Subjects-Reference to Video

> **Note**
>
> viduq3-mix does not support the subject invocation method for the time being.

How to create subjects: [https://platform.vidu.cn/docs/subjects](https://platform.vidu.cn/docs/subjects)

<a id="reference-to-video-api-q3-get-creations-4"></a>

## Q3 Query Creations

```
GET /ent/v2/tasks/{id}/creations
```

### Headers

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `Authorization` | `string` | Required | Replace `{your api key}` with your token；Example: `Token {your api key}` |

### Path parameters

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `id` | `string` | Required | Task ID. Returned by the Create Task API upon successful creation. |

### Request example

```shell
curl -X GET -H "Authorization: Token {your_api_key}" https://api.vidu.com/ent/v2/tasks/{your_id}/creations
```

### Response

#### 200 OK

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `id` | `string` | Optional | Task ID |
| `state` | `string` | Optional | Processing state Accepted values: `created` Created successfully `queueing` Task in queue `processing` Task is being processed `success` Task succeeded `failed` Task failed |
| `err_code` | `string` | Optional | Error code. See the error code table for details. |
| `credits` | `integer` | Optional | The number of credits consumed by this task. Unit: credits. |
| `payload` | `string` | Optional | The transparent transmission parameter passed in this task call |
| `off_peak` | `boolean` | Optional | Whether off-peak mode is used in this task call |
| `creations` | `array` | Optional | Generation results |
| ↳ `id` | `string` | Optional | Generation ID. Used to identify different generations. |
| ↳ `url` | `string` | Optional | Generation URL. Valid for 24 hours. |
| ↳ `cover_url` | `string` | Optional | Generation cover. Valid for 24 hours. |
| ↳ `watermarked_url` | `string` | Optional | Watermarked generation URL. Valid for 24 hours. |

```json
{
  "id":"your_task_id",
  "state": "success",
  "err_code": "",
  "credits": 4,
  "payload": "",
  "creations": [
    {
      "id": "your_creations_id",
      "url": "your_generated_results_url",
      "cover_url": "your_generated_results_cover_url",
      "watermarked_url": "your_generated_results_watermarked_url"
    }
  ]
}
```

<a id="reference-to-video-api-q3-mix-create-reference2video-5"></a>

## Q3 Mix Create Task

```
POST /ent/v2/reference2video
```

### Headers

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `Authorization` | `string` | Required | Replace `{your api key}` with your token；Example: `Token {your api key}` |

### Body parameters

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `model` | `string` | Required | Model name. Accepted value: `viduq3-mix`. `viduq3-mix`: Strong visual quality, supports intelligent scene transitions, supports simultaneous audio and video output, with good dynamic effects and the strongest overall balance. |
| `images` | `string` | Optional | Image references support multiple images. The model uses the subjects in the images provided in this parameter as references to generate a video with consistent subjects. The supported number of images varies by model. Note 1: The viduq3-mix series supports uploading 1 to 7 images. Note 2: Images can be provided as Base64-encoded data or image URLs. Ensure that the URLs are accessible. Note 3: Supported image formats: PNG, JPEG, JPG, and WebP. Note 4: Image dimensions must be at least 128 x 128 pixels, and the aspect ratio must be less than 1:4 or 4:1. Note 5: The POST body of the HTTP request must not exceed 20MB, and the encoding must include an appropriate content type string. For base64,{base64_encode}normal；Example: `data:image/png` |
| `sounds` | `string` | Optional | Audio references support uploading 1 to 3 audio files. The model uses the audio provided in this parameter as a reference to generate a video with consistent subjects. Note 1: When using the audio reference feature, a maximum of 3 audio files can be uploaded. Each audio file must be 3-12 seconds long. Note 2: Audio files must be in MP3 format. Note 3: Each audio file must not exceed 50MB. Note 4: The byte length after Base64 decoding must be less than 20MB, and the encoding must include an appropriate content type string. For base64,{base64_encode}normal；Example: `data:video/mp3` |
| `prompt` | `string` | Required | Text prompt for video generation. Note: The maximum length is 5000 characters. |
| `duration` | `integer` | Optional | Video duration parameter. Default values depend on the model. `viduq3-mix`: Default is 5 seconds, available options: 3-15. |
| `seed` | `integer` | Optional | Random seed. If omitted or set to 0, a random number is used. If manually set, the specified seed is used. |
| `aspect_ratio` | `string` | Optional | Defaults to `16:9`. Accepted values: `1:1` `9:16` `16:9` `3:4` `4:3`. `auto`: Automatically recommends an aspect ratio based on the input image or video. |
| `resolution` | `string` | Optional | Resolution parameter. Default values depend on the model and video duration. `viduq3-mix` (3-16 seconds): Default is 720p, available options: 720p and 1080p. |
| `payload` | `string` | Optional | Transparent transmission parameter. No processing is performed; data is only transmitted. Note: The maximum length is 1048576 characters. |
| `callback_url` | `string` | Optional | Callback protocol. When creating a task, you need to actively set the `callback_url` with a POST request. When the video generation task changes its status, Vidu will send a callback request to this URL, containing the latest status of the task. The structure of the callback request content will be the same as the return body of the Query Task API. The `status` in the callback response includes the following states: `processing`: Task is being processed. `success`: Task is completed. If sending fails, the callback will be retried three times. `failed`: Task failed. If sending fails, the callback will be retried three times. Vidu uses a callback signature algorithm for authentication. For details, see [Callback Signature](https://platform.vidu.cn/docs/callback-signature). |

### Request example

```shell
curl -X POST -H "Authorization: Token {your_api_key}" -H "Content-Type: application/json" -d '
        {
            "model": "viduq3-mix",
            "images": ["https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/reference2video-1.png","https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/reference2video-2.png","https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/reference2video-3.png"],
            "prompt": "Santa Claus and the bear hug by the lakeside.",
            "duration": 5,
            "seed": 0,
            "aspect_ratio": "3:4",
            "resolution": "1080p"
        }' https://api.vidu.com/ent/v2/reference2video
```

### Response

#### 200 OK

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `task_id` | `string` | Optional | Task ID generated by Vidu |
| `state` | `string` | Optional | Processing status. Available values: `created`: Task created successfully. `queueing`: Task is in the queue. `processing`: Task is being processed. `success`: Task completed successfully. `failed`: Task failed. |
| `model` | `string` | Optional | The model name used for this call |
| `prompt` | `string` | Optional | The prompt parameter used for this call |
| `images` | `array` | Optional | The image parameters used for this call |
| `duration` | `integer` | Optional | The video duration parameter used for this call |
| `seed` | `integer` | Optional | The random seed parameter used for this call |
| `aspect_ratio` | `string` | Optional | The aspect ratio parameter used for this call |
| `resolution` | `string` | Optional | The resolution parameter used for this call |
| `payload` | `string` | Optional | The transparent transmission parameter used for this call |
| `off_peak` | `boolean` | Optional | Whether off-peak mode was used for this call |
| `credits` | `integer` | Optional | The number of credits used for this call |
| `created_at` | `string` | Optional | Task creation time |

```json
{
          "task_id": "your_task_id_here",
          "state": "created",
          "model": "viduq3-mix",
          "images": ["https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/reference2video-1.png","https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/reference2video-2.png","https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/reference2video-3.png"],
          "prompt": "Santa Claus and the bear hug by the lakeside.",
          "duration": 5,
          "seed": random_number,
          "aspect_ratio": "3:4",
          "resolution": "540p",
          "payload":"",
          "credits":credits_number,
          "created_at": "2025-01-01T15:41:31.968916Z"
        }
```

<a id="reference-to-video-api-q3-mix-get-creations-6"></a>

## Q3 Mix Query Creations

```
GET /ent/v2/tasks/{id}/creations
```

### Headers

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `Authorization` | `string` | Required | Replace `{your api key}` with your token；Example: `Token {your api key}` |

### Path parameters

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `id` | `string` | Required | Task ID returned after the task creation request succeeds |

### Request example

```shell
curl -X GET -H "Authorization: Token {your_api_key}" https://api.vidu.com/ent/v2/tasks/{your_id}/creations
```

### Response

#### 200 OK

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `id` | `string` | Optional | Task ID |
| `state` | `string` | Optional | Processing status. Available values: `created`: Task created successfully. `queueing`: Task is in the queue. `processing`: Task is being processed. `success`: Task completed successfully. `failed`: Task failed. |
| `err_code` | `string` | Optional | Error code. For details, see the error code table. |
| `credits` | `integer` | Optional | The number of credits consumed by this task |
| `payload` | `string` | Optional | The transparent transmission parameter provided for this task |
| `off_peak` | `boolean` | Optional | Whether off-peak mode was used for this task |
| `creations` | `array` | Optional | Generated results |
| ↳ `id` | `string` | Optional | Generated result ID, used to identify different generated results |
| ↳ `url` | `string` | Optional | Generated result URL, valid for 24 hours |
| ↳ `cover_url` | `string` | Optional | Generated result cover URL, valid for 24 hours |
| ↳ `watermarked_url` | `string` | Optional | Watermarked generated result URL, valid for 24 hours |

```json
{
  "id":"your_task_id",
  "state": "success",
  "err_code": "",
  "credits": 4,
  "payload": "",
  "creations": [
    {
      "id": "your_creations_id",
      "url": "your_generated_results_url",
      "cover_url": "your_generated_results_cover_url",
      "watermarked_url": "your_generated_results_watermarked_url"
    }
  ]
}
```

<a id="reference-to-video-api-q3-ad-create-reference2video-7"></a>

## Q3 Ad Create Task

```
POST /ent/v2/reference2video
```

### Headers

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `Authorization` | `string` | Required | Replace `{your api key}` with your token；Example: `Token {your api key}` |

### Body parameters

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `model` | `string` | Required | Model name. Accepted value: `viduq3-ad` `viduq3-ad`: An industry fine-tuned model designed for advertising. Supports 1-7 image inputs, durations of 3-15 seconds, and 720p or 1080p resolution. For optimal results, avoid using overly similar input images. |
| `images` | `array` | Optional | Image references support multiple images. The model uses the subjects in the images provided in this parameter as references to generate a video with consistent subjects. The supported number of images varies by model. Details are as follows: Note 1: The viduq3-ad series supports uploading 1 to 7 images. Note 2: Images can be provided as Base64-encoded data or image URLs. Ensure that the URLs are accessible. Note 3: Supported image formats: PNG, JPEG, JPG, and WebP. Note 4: Image dimensions must be at least 128 x 128 pixels, and the aspect ratio must be less than 1:4 or 4:1. Note 5: The POST body of the HTTP request must not exceed 20MB, and the encoding must include an appropriate content type string. For base64,{base64_encode}normal；Example: `data:image/png` |
| `sounds` | `string` | Optional | Audio references support uploading 1 to 3 audio files. The model uses the audio provided in this parameter as a reference to generate a video with consistent subjects. Note 1: When using the audio reference feature, a maximum of 3 audio files can be uploaded. Each audio file must be 3-12 seconds long. Note 2: Audio files must be in MP3 format. Note 3: Each audio file must not exceed 50MB. Note 4: The byte length after Base64 decoding must be less than 20MB, and the encoding must include an appropriate content type string. For base64,{base64_encode}normal；Example: `data:video/mp3` |
| `prompt` | `string` | Required | Text prompt for video generation. Note: The maximum length is 5000 characters. |
| `duration` | `integer` | Optional | Video duration parameter. Default values depend on the model: `viduq3-ad`: Default is 5 seconds, available options: 3-15 |
| `seed` | `integer` | Optional | Random seed. If omitted or set to 0, a random number is used. If manually set, the specified seed is used. |
| `aspect_ratio` | `string` | Optional | Defaults to `16:9`. Accepted values: `1:1` `9:16` `16:9` `3:4` `4:3` `auto`: Automatically recommends an aspect ratio based on the input image or video |
| `resolution` | `string` | Optional | Resolution parameter. Default values depend on the model and video duration: `viduq3-ad` (3-15 seconds): Default is 720p, available options: 720p and 1080p |
| `payload` | `string` | Optional | Transparent transmission parameter. No processing is performed; data is only transmitted. Note: The maximum length is 1048576 characters. |
| `off_peak` | `boolean` | Optional | Off-peak mode. Defaults to `false`. Accepted values: `true` `false` - `true`: Generate the video during off-peak hours. - `false`: Generate the video immediately. - Note 1: Off-peak mode consumes fewer credits. For details, see product pricing. - Note 2: Tasks submitted in off-peak mode will be generated within 48 hours. Tasks that are not completed will be automatically cancelled, and the credits for the task will be refunded. - Note 3: You can also [manually cancel](https://platform.vidu.cn/docs/cancel-task-api) off-peak tasks. |
| `callback_url` | `string` | Optional | Callback protocol. When creating a task, you need to actively set the `callback_url` with a POST request. When the video generation task changes its status, Vidu will send a callback request to this URL, containing the latest status of the task. The structure of the callback request content will be the same as the return body of the Query Task API. The `status` in the callback response includes the following states: - `processing`: Task is being processed. - `success`: Task is completed. If sending fails, the callback will be retried three times. - `failed`: Task failed. If sending fails, the callback will be retried three times. Vidu uses a callback signature algorithm for authentication. For details, see [Callback Signature.](https://platform.vidu.cn/docs/callback-signature) |

### Request example

```shell
curl -X POST -H "Authorization: Token {your_api_key}" -H "Content-Type: application/json" -d '
        {
            "model": "viduq3-ad",
            "images": ["https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/reference2video-1.png","https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/reference2video-2.png","https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/reference2video-3.png"],
            "prompt": "Santa Claus and the bear hug by the lakeside.",
            "duration": 5,
            "seed": 0,
            "aspect_ratio": "3:4",
            "resolution": "1080p"
        }' https://api.vidu.com/ent/v2/reference2video
```

### Response

#### 200 OK

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `task_id` | `string` | Optional | Task ID generated by Vidu |
| `state` | `string` | Optional | Processing status - `created`: Task created successfully - `queueing`: Task is in the queue - `processing`: Task is being processed - `success`: Task completed successfully - `failed`: Task failed |
| `model` | `string` | Optional | The model name used for this call |
| `prompt` | `string` | Optional | The prompt parameter used for this call |
| `images` | `array` | Optional | The image parameters used for this call |
| `duration` | `integer` | Optional | The video duration parameter used for this call |
| `seed` | `integer` | Optional | The random seed parameter used for this call |
| `aspect_ratio` | `string` | Optional | The aspect ratio parameter used for this call |
| `resolution` | `string` | Optional | The resolution parameter used for this call |
| `payload` | `string` | Optional | The transparent transmission parameter used for this call |
| `off_peak` | `boolean` | Optional | Whether off-peak mode was used for this call |
| `credits` | `integer` | Optional | The number of credits used for this call |
| `created_at` | `string` | Optional | Task creation time |

```json
{
          "task_id": "your_task_id_here",
          "state": "created",
          "model": "viduq3-ad",
          "images": ["https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/reference2video-1.png","https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/reference2video-2.png","https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/reference2video-3.png"],
          "prompt": "Santa Claus and the bear hug by the lakeside.",
          "duration": 5,
          "seed": random_number,
          "aspect_ratio": "3:4",
          "resolution": "540p",
          "payload":"",
          "credits":credits_number,
          "created_at": "2025-01-01T15:41:31.968916Z"
        }
```

<a id="reference-to-video-api-q3-ad-get-creations-8"></a>

## Q3 Ad Query Creations

```
GET /ent/v2/tasks/{id}/creations
```

### Headers

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `Authorization` | `string` | Required | Replace `{your api key}` with your token；Example: `Token {your api key}` |

### Path parameters

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `id` | `string` | Required | Task ID returned after the task creation request succeeds |

### Request example

```shell
curl -X GET -H "Authorization: Token {your_api_key}" https://api.vidu.com/ent/v2/tasks/{your_id}/creations
```

### Response

#### 200 OK

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `id` | `string` | Optional | Task ID |
| `state` | `string` | Optional | Processing status Available values: - `created`: Task created successfully - `queueing`: Task is in the queue - `processing`: Task is being processed - `success`: Task completed successfully - `failed`: Task failed |
| `err_code` | `string` | Optional | Error code. For details, see the error code table. |
| `credits` | `integer` | Optional | The number of credits consumed by this task |
| `payload` | `string` | Optional | The transparent transmission parameter provided for this task |
| `off_peak` | `boolean` | Optional | Whether off-peak mode was used for this task |
| `creations` | `array` | Optional | Generated results |
| ↳ `id` | `string` | Optional | Generated result ID, used to identify different generated results |
| ↳ `url` | `string` | Optional | Generated result URL, valid for 24 hours |
| ↳ `cover_url` | `string` | Optional | Generated result cover URL, valid for 24 hours |
| ↳ `watermarked_url` | `string` | Optional | Watermarked generated result URL, valid for 24 hours |

```json
{
  "id":"your_task_id",
  "state": "success",
  "err_code": "",
  "credits": 4,
  "payload": "",
  "creations": [
    {
      "id": "your_creations_id",
      "url": "your_generated_results_url",
      "cover_url": "your_generated_results_cover_url",
      "watermarked_url": "your_generated_results_watermarked_url"
    }
  ]
}
```

<a id="reference-to-video-api-q3-drama-create-reference2video-9"></a>

## Q3 Drama Create Task

```
POST /ent/v2/reference2video
```

### Request Body

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `model` | `string` | Required | Model name. Accepted value: `viduq3-drama`. `viduq3-drama`: An industry fine-tuned model designed for drama production. Supports **1-7** image inputs and durations of **2-16s**. |
| `auto_subjects` | `boolean` | Optional | Whether to use the intelligent subject library capability. Defaults to `false`. Accepted values: `true` `false`. `true`: Use the intelligent subject library capability. `false`: Do not use the intelligent subject library capability. |
| `subjects` | `array` | Required | When using q3, q2, q1, and 2.0 models, only image subjects and text subjects can be used. The maximum number of image or text subjects should not exceed 7. |
| ↳ `name` | `string` | Required | The subject name specified by the user. During generation, it can be used in the format `[@name]`, for example: `[@image1]`. |
| ↳ `images` | `array` | Optional | Temporary subject images. Each temporary subject supports up to 3 images. Note 1: Images can be provided as Base64-encoded data or image URLs. Ensure that the URLs are accessible. Note 2: Supported image formats: PNG, JPEG, JPG, and WebP. Note 3: Image dimensions must be at least 128 x 128 pixels, and the aspect ratio must be less than 1:4 or 4:1. Note 4: The POST body of the HTTP request must not exceed **20MB**, and the encoding must include an appropriate content type string. For example: `data:image/png;base64,{base64_encode}` |
| ↳ `videos` | `array` | Optional | Temporary subject video. Supports at most one 5-second video. Note 1: Only the viduq2-pro model for reference-to-video supports video subjects. Note 2: Supports uploading at most **one 5-second** video. Note 3: Supported video formats: MP4, AVI, and MOV. Note 4: Video dimensions must be at least 128 x 128 pixels, and the aspect ratio must be less than 1:4 or 4:1. Note 5: The byte length after Base64 decoding must be less than 20MB, and the encoding must include an appropriate content type string. For example: `data:video/mp4;base64,{base64_encode}` |
| ↳ `voice_id` | `array` | Optional | Voice ID, used to determine the voice character in the video. If empty, the system will automatically recommend one. For accepted values, see the [New Voice List](https://shengshu.feishu.cn/sheets/EgFvs6DShhiEBStmjzccr5gonOg). You can also use the [Voice Cloning API](https://platform.vidu.cn/docs/voice-clone) to clone any voice. The `voice_id` parameter can be used interchangeably. |
| ↳ `server_id` | `string` | Optional | Subject ID obtained through the Create Subject API. Note: If `server_id` is not provided, the subject is treated as a temporary subject and will not be saved by the system. |
| `prompt` | `string` | Required | Text prompt for video generation. Note 1: The maximum length is 5000 characters. Note 2: Use `[@subjects_name]` to represent subject content. For example: `"[@1] and [@2] are eating hot pot together, and the narration says everyone loves hot pot."` |
| `audio` | `boolean` | Optional | Whether to use audio-video output capability. Defaults to `false`. Accepted values: `true` `false`. `true`: Use audio-video output capability. `false`: Do not use audio-video output capability. |
| `duration` | `integer` | Optional | Video duration parameter. Default values depend on the model. `viduq3-drama`: Default is 8s, available options: 2-16s. |
| `seed` | `integer` | Optional | Random seed. If omitted or set to 0, a random number is used. If manually set, the specified seed is used. |
| `aspect_ratio` | `string` | Optional | `viduq3-drama` (8-12s): Default is 1080p. Defaults to `16:9`. Accepted values: `1:1` `9:16` `16:9` `3:4` `4:3`. `auto`: Automatically recommends an aspect ratio based on the input image or video. |
| `resolution` | `string` | Optional | Resolution parameter. Default values depend on the model and video duration. `viduq3-turbo` (1-16 seconds): Default is 720p, available options: 540p, 720p, 1080p. `viduq3` (3-16 seconds): Default is 720p, available options: 540p, 720p, 1080p. `viduq2-pro` and `viduq2` (1-10 seconds): Default is 720p, available options: 540p, 720p, 1080p. `viduq1` (5 seconds): Default is 1080p, available option: 1080p. `vidu2.0` (4 seconds): Default is 360p, available options: 360p, 720p. |
| `payload` | `string` | Optional | Transparent transmission parameter. No processing is performed; data is only transmitted. Note: The maximum length is 1048576 characters. |
| `off_peak` | `boolean` | Optional | Off-peak mode. Defaults to `false`. Accepted values: `true` `false`. `true`: Generate the video during off-peak hours. `false`: Generate the video immediately. Note 1: Off-peak mode consumes fewer credits. For details, see product pricing. Note 2: Tasks submitted in off-peak mode will be generated within 48 hours. Tasks that are not completed will be automatically cancelled, and the credits for the task will be refunded. Note 3: You can also [manually cancel](https://platform.vidu.cn/docs/cancel-task-api) off-peak tasks. |
| `callback_url` | `string` | Optional | Callback protocol. When creating a task, you need to actively set the `callback_url` with a POST request. When the video generation task changes its status, Vidu will send a callback request to this URL, containing the latest status of the task. The structure of the callback request content will be the same as the return body of the Query Task API. The `status` in the callback response includes the following states: `processing`: Task is being processed. `success`: Task is completed. If sending fails, the callback will be retried three times. `failed`: Task failed. If sending fails, the callback will be retried three times. Vidu uses a callback signature algorithm for authentication. For details, see [Callback Signature](https://platform.vidu.cn/docs/callback-signature). |

### Headers

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `Authorization` | `string` | Required | Replace `{your api key}` with your token；Example: `Token {your api key}` |

### Body parameters

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `model` | `string` | Required | Model name. Accepted value: `viduq3-drama`. `viduq3-drama`: An industry fine-tuned model designed for drama production. Supports **1-7** image inputs, durations of **2-15s**, and **1080p** resolution. |
| `images` | `array` | Optional | Image references support multiple images. The model uses the subjects in the images provided in this parameter as references to generate a video with consistent subjects. The supported number of images varies by model. Note 1: The viduq3-drama series supports uploading 1 to 7 images. Note 2: Images can be provided as Base64-encoded data or image URLs. Ensure that the URLs are accessible. Note 3: Supported image formats: PNG, JPEG, JPG, and WebP. Note 4: Image dimensions must be at least 128 x 128 pixels, and the aspect ratio must be less than 1:4 or 4:1. Note 5: The POST body of the HTTP request must not exceed 20MB, and the encoding must include an appropriate content type string. For base64,{base64_encode}normal；Example: `data:image/png` |
| `sounds` | `array` | Optional | Audio references support uploading 1 to 3 audio files. The model uses the audio provided in this parameter as a reference to generate a video with consistent subjects. Note 1: When using the audio reference feature, a maximum of 3 audio files can be uploaded. Each audio file must be 3-12 seconds long. Note 2: Audio files must be in MP3 format. Note 3: Each audio file must not exceed 50MB. Note 4: The byte length after Base64 decoding must be less than 20MB, and the encoding must include an appropriate content type string. For base64,{base64_encode}normal；Example: `data:video/mp3` |
| `prompt` | `string` | Required | Text prompt for video generation. Note: The maximum length is 5000 characters. |
| `duration` | `integer` | Optional | Video duration parameter. Default values depend on the model. `viduq3-drama`: Default is 8s, available options: 2-15s. |
| `seed` | `integer` | Optional | Random seed. If omitted or set to 0, a random number is used. If manually set, the specified seed is used. |
| `aspect_ratio` | `string` | Optional | Defaults to `16:9`. Accepted values: `9:16` `16:9`. `auto`: Automatically recommends an aspect ratio based on the input image or video. |
| `audio` | `boolean` | Optional | Whether to use audio-video output capability. Defaults to `true`. Accepted values: `true` `false`. `false`: Outputs a silent video without direct audio-video output. `true`: Outputs a video with synchronized audio and visuals, including dialogue and sound effects. Note: For non-subject invocation, only the q3 model supports this parameter. |
| `resolution` | `string` | Optional | Resolution parameter. Default values depend on the model and video duration. `viduq3-drama` (2-15s): Default is 1080p, available options: 720p and 1080p. |
| `payload` | `string` | Optional | Transparent transmission parameter. No processing is performed; data is only transmitted. Note: The maximum length is 1048576 characters. |
| `off_peak` | `boolean` | Optional | Off-peak mode. Defaults to `false`. Accepted values: `true` `false`. `true`: Generate the video during off-peak hours. `false`: Generate the video immediately. Note 1: Off-peak mode consumes fewer credits. For details, see product pricing. Note 2: Tasks submitted in off-peak mode will be generated within 48 hours. Tasks that are not completed will be automatically cancelled, and the credits for the task will be refunded. Note 3: You can also [manually cancel](https://platform.vidu.cn/docs/cancel-task-api) off-peak tasks. |
| `callback_url` | `string` | Optional | Callback protocol. When creating a task, you need to actively set the `callback_url` with a POST request. When the video generation task changes its status, Vidu will send a callback request to this URL, containing the latest status of the task. The structure of the callback request content will be the same as the return body of the Query Task API. The `status` in the callback response includes the following states: `processing`: Task is being processed. `success`: Task is completed. If sending fails, the callback will be retried three times. `failed`: Task failed. If sending fails, the callback will be retried three times. Vidu uses a callback signature algorithm for authentication. For details, see [Callback Signature.](https://platform.vidu.cn/docs/callback-signature) |

### Request example

```shell
curl -X POST -H "Authorization: Token {your_api_key}" -H "Content-Type: application/json" -d '
        {
            "model": "viduq3-drama",
            "images": ["https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/reference2video-1.png","https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/reference2video-2.png","https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/reference2video-3.png"],
            "prompt": "Santa Claus and the bear hug by the lakeside.",
            "duration": 5,
            "seed": 0,
            "aspect_ratio": "3:4",
            "resolution": "1080p"
        }' https://api.vidu.com/ent/v2/reference2video
```

### Response

#### 200 OK

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `task_id` | `string` | Optional | Task ID generated by Vidu |
| `state` | `string` | Optional | Processing status. Available values: `created`: Task created successfully. `queueing`: Task is in the queue. `processing`: Task is being processed. `success`: Task completed successfully. `failed`: Task failed. |
| `model` | `string` | Optional | The model name used for this call |
| `prompt` | `string` | Optional | The prompt parameter used for this call |
| `images` | `array` | Optional | The image parameters used for this call |
| `duration` | `integer` | Optional | The video duration parameter used for this call |
| `seed` | `integer` | Optional | The random seed parameter used for this call |
| `aspect_ratio` | `string` | Optional | The aspect ratio parameter used for this call |
| `resolution` | `string` | Optional | The resolution parameter used for this call |
| `payload` | `string` | Optional | The transparent transmission parameter used for this call |
| `off_peak` | `boolean` | Optional | Whether off-peak mode was used for this call |
| `credits` | `integer` | Optional | The number of credits used for this call |
| `created_at` | `string` | Optional | Task creation time |

```json
{
          "task_id": "your_task_id_here",
          "state": "created",
          "model": "viduq3-drama",
          "images": ["https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/reference2video-1.png","https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/reference2video-2.png","https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/reference2video-3.png"],
          "prompt": "Santa Claus and the bear hug by the lakeside.",
          "duration": 5,
          "seed": random_number,
          "aspect_ratio": "3:4",
          "resolution": "540p",
          "payload":"",
          "credits":credits_number,
          "created_at": "2025-01-01T15:41:31.968916Z"
        }
```

#### 200 OK

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `task_id` | `string` | Optional | Task ID generated by Vidu |
| `state` | `string` | Optional | Processing status. Available values: `created`: Task created successfully. `queueing`: Task is in the queue. `processing`: Task is being processed. `success`: Task completed successfully. `failed`: Task failed. |
| `model` | `string` | Optional | The model name used for this call |
| `prompt` | `string` | Optional | The prompt parameter used for this call |
| `images` | `array` | Optional | The image parameters used for this call |
| `duration` | `integer` | Optional | The video duration parameter used for this call |
| `seed` | `integer` | Optional | The random seed parameter used for this call |
| `aspect_ratio` | `string` | Optional | The aspect ratio parameter used for this call |
| `resolution` | `string` | Optional | The resolution parameter used for this call |
| `payload` | `string` | Optional | The transparent transmission parameter used for this call |
| `off_peak` | `boolean` | Optional | Whether off-peak mode was used for this call |
| `credits` | `integer` | Optional | The number of credits used for this call |
| `created_at` | `string` | Optional | Task creation time |

```json
{
          "task_id": "your_task_id_here",
          "state": "created",
          "model": "viduq3-drama",
          "images": [""],
          "prompt": "[@1] and [@2] are eating hot pot together at [@3]",
          "duration": 5,
          "seed": random_number,
          "aspect_ratio": "3:4",
          "resolution": "720p",
          "audio": true,
          "payload":"",
          "off_peak": false,
          "credits":credits_number,
          "created_at": "2025-01-01T15:41:31.968916Z"
        }
```

## Reference to Video (Subject Invocation)

Create Subject method: [https://platform.vidu.cn/docs/subjects](https://platform.vidu.cn/docs/subjects)

<a id="reference-to-video-api-q3-drama-get-creations-10"></a>

## Q3 Drama Query Creations

```
GET /ent/v2/tasks/{id}/creations
```

### Headers

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `Authorization` | `string` | Required | Replace `{your api key}` with your token；Example: `Token {your api key}` |

### Path parameters

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `id` | `string` | Required | Task ID returned after the task creation request succeeds |

### Request example

```shell
curl -X GET -H "Authorization: Token {your_api_key}" https://api.vidu.com/ent/v2/tasks/{your_id}/creations
```

### Response

#### 200 OK

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `id` | `string` | Optional | Task ID |
| `state` | `string` | Optional | Processing status. Available values: `created`: Task created successfully. `queueing`: Task is in the queue. `processing`: Task is being processed. `success`: Task completed successfully. `failed`: Task failed. |
| `err_code` | `string` | Optional | Error code. For details, see the error code table. |
| `credits` | `integer` | Optional | The number of credits consumed by this task |
| `payload` | `string` | Optional | The transparent transmission parameter provided for this task |
| `off_peak` | `boolean` | Optional | Whether off-peak mode was used for this task |
| `creations` | `array` | Optional | Generated results |
| ↳ `id` | `string` | Optional | Generated result ID, used to identify different generated results |
| ↳ `url` | `string` | Optional | Generated result URL, valid for 24 hours |
| ↳ `cover_url` | `string` | Optional | Generated result cover URL, valid for 24 hours |
| ↳ `watermarked_url` | `string` | Optional | Watermarked generated result URL, valid for 24 hours |

```json
{
  "id":"your_task_id",
  "state": "success",
  "err_code": "",
  "credits": 4,
  "payload": "",
  "creations": [
    {
      "id": "your_creations_id",
      "url": "your_generated_results_url",
      "cover_url": "your_generated_results_cover_url",
      "watermarked_url": "your_generated_results_watermarked_url"
    }
  ]
}
```