tencent cloud

APIs

CreateAigcVideoTask

下载
聚焦模式
字号
最后更新时间: 2026-09-22 21:50:29

1. API Description

Domain name for API request: vod.intl.tencentcloudapi.com.

This API is used to generate AIGC videos. The default limit is 1 concurrent processing. API calls incur actual fees. Refer to the VOD AIGC video generation billing documentation. The settlement mode for this feature is pay-as-you-go. For daily billing customers, usage on the day is billed on the second day. For monthly billing customers, the previous month's usage fees are billed on the 1st of the next month.

A maximum of 20 requests can be initiated per second for this API.

We recommend you to use API Explorer
Try it
API Explorer provides a range of capabilities, including online call, signature authentication, SDK code generation, and API quick search. It enables you to view the request, response, and auto-generated examples.

2. Input Parameters

The following request parameter list only provides API request parameters and some common parameters. For the complete common parameter list, see Common Request Parameters.

Parameter Name Required Type Description
Action Yes String Common Params. The value used for this API: CreateAigcVideoTask.
Version Yes String Common Params. The value used for this API: 2018-07-17.
Region No String Common Params. This parameter is not required.
SubAppId Yes Integer

Video-on-demand (VOD) application ID. For customers who activate on-demand services from December 25, 2023, this field must be filled in as the app ID when accessing resources in on-demand applications (whether the default application or a newly created application).

ModelName Yes String

Model name. Parameter Value:
Kling: Kling;
Vidu;
Hailuo: Hailuo;
Hunyuan: Hunyuan;
Mingmou: Mingmou;
GV;
OS;
PixVerse;

ModelVersion Yes String

Model version. Value:
When ModelName is Hailuo, available values are 02, 2.3, 2.3-fast, H3, H3_regen, and H3-Max;
When ModelName is Kling, available values are 1.6, 2.0, 2.1, 2.5, 2.6, O1, 3.0, 3.0-Omni, 3.0-turbo, and scene;
When ModelName is Vidu, available values are q2, q2-pro, q2-turbo, q3, q3-pro, q3-turbo, q3-mix, q3-drama, q3-ad, scene, avatar-q2-pro, avatar-q2-turbo, and lip-sync;
When ModelName is GV, available values are 3.1, 3.1-fast, 3.1-lite, and omni;
When ModelName is OS, available values are 2.0;
When ModelName is Hunyuan, available values are 1.5 and 3d_2.0;
When ModelName is Mingmou, available values are 1.0;
When ModelName is PixVerse, available values are v5.6, v6, and c1;

FileInfos.N No Array of AigcVideoTaskInputFileInfo

Used to describe the resource file to be used by the model when generating a video, divided into first and last frame mode, reference image/video/sound generation, video editing, and other modes.

First and last frame video generation: The Usage field of the first frame image is FirstFrame, and the Usage field of the last frame image is LastFrame. One image is supported for each. The first frame can be passed in separately, but the last frame cannot be passed in separately. First and last frame generation uses the image ratio for reference.
Reference image/video/sound generation: Single or multiple images/videos/sounds can be passed in as references, with the Usage field set to Reference. In reference mode, the display aspect ratio of the generated video can be adjusted.
Video editing: Vidu and Kling can input a video for editing. Images can also be passed in along with the input video, with the Usage field of the image set to Reference.

Note:

  1. Image size cannot exceed 10M.
  2. Supported image formats: jpeg, jpg, png. x0b
  3. For whether a model version supports reference image/video/sound, first and last frame, video editing, and other features, you can request the document from us or refer to the original vendor's document information.
SubjectInfos.N No Array of AigcVideoTaskInputSubjectInfo

Subject input information.

LastFrameFileId No String

Media file ID used as the last frame to generate a video. The globally unique identifier of the file on VOD, assigned by the VOD backend after successful upload. You can obtain this field in the video upload completion event notification or the VOD console.

  1. When specifying this parameter, you must also specify the first frame through FileInfos.
  2. The image size must be less than 10M.
  3. The image format values are: jpeg, jpg, png, webp.
LastFrameUrl No String

URL of the media file used as the last frame to generate video. Description:

  1. When you specify this parameter, specify the first frame via FileInfos at the same time.
  2. Image size must be less than 5M.
  3. Image format values: jpeg, jpg, png, webp.
Prompt No String

Prompt for video generation.
When no reference file is passed in, no scenario type is used, ExtInfo is not empty, Prompt is required.

NegativePrompt No String

Prompt to prevent the model from generating videos.

EnhancePrompt No String

Whether to optimize Prompt content automatically. When Enabled, the passed-in Prompt will be optimized automatically to enhance generation quality. Valid values:

  • Enabled: enable;
  • Disabled: disable;
  • OutputConfig No AigcVideoOutputConfig

    Configuration of the output media file for the video task.

    InputRegion No String

    Region information of the input file. Values are as follows:

    • If the input file is stored overseas: Oversea;
    • If the input file is stored in the western United States: OverseaUSWest;
    • If the input file is stored in the Chinese mainland: Mainland.

    Default value: Mainland

    SceneType No String

    Scenario type. Values are as follows:

  • When ModelName is Kling: motion_control means action control; avatar_i2v means digital human; lip_sync means lip-sync;
  • When ModelName is Vidu: template_effect means special effect template;
  • Other ModelName values are not currently supported.
  • Procedure No String

    Task flow name. Fill in when you need to execute a task flow on the generated new video.

    Seed No Integer

    Random seed of the model.

    SessionId No String

    Identifier for deduplication. If a request with the same identifier has been sent within the past three days, an error is returned for the current request. The maximum length is 50 characters. If this is not specified or left empty, deduplication is not performed.

    SessionContext No String

    Source context. This is used to pass user request information. The audio and video quality revival completion callback returns the value of this field. The maximum length is 1000 characters.

    TasksPriority No Integer

    Task priority. The higher the value, the higher the priority. The value range is from -10 to 10. If this is not specified, the default value is 0.

    ExtInfo No String

    Reserved field, used for special purposes.
    Can be used to import special model parameters, storyboard prompts, etc.

    3. Output Parameters

    Parameter Name Type Description
    TaskId String

    Task ID.

    RequestId String The unique request ID, generated by the server, will be returned for every request (if the request fails to reach the server for other reasons, the request will not obtain a RequestId). RequestId is required for locating a problem.

    4. Example

    Example1 Trigger an AIGC Video Generation Task

    Input Example

    POST / HTTP/1.1
    Host: vod.intl.tencentcloudapi.com
    Content-Type: application/json
    X-TC-Action: CreateAigcVideoTask
    <Common request parameters>
    
    {
        "SubAppId": 251007502,
        "ModelName": "GV",
        "ModelVersion": "3.1-fast",
        "FileInfos": [
            {
                "FileId": "3704211***509819"
            }
        ],
        "LastFrameFileId": "3704211***509911",
        "Prompt": "generate a car",
        "NegativePrompt": "red",
        "EnhancePrompt": "Enabled",
        "OutputConfig": {
            "StorageMode": "Temporary",
            "AspectRatio": "9:16",
            "AudioGeneration": "Enabled",
            "PersonGeneration": "AllowAdult",
            "InputComplianceCheck": "Enabled",
            "OutputComplianceCheck": "Enabled"
        },
        "SessionId": "mysession2",
        "SessionContext": "mysessionContext",
        "TasksPriority": "10",
        "ExtInfo": "myextinfo"
    }

    Output Example

    {
        "Response": {
            "TaskId": "251007502-AigcVideo***25dacdcef7dd2b20fdt",
            "RequestId": "d68920a4-c989-4afe-ac4d-2f06de99368e"
        }
    }

    5. Developer Resources

    SDK

    TencentCloud API 3.0 integrates SDKs that support various programming languages to make it easier for you to call APIs.

    Command Line Interface

    6. Error Code

    The following only lists the error codes related to the API business logic. For other error codes, see Common Error Codes.

    Error Code Description
    FailedOperation Operation failed.
    FailedOperation.InvalidVodUser VOD service is not enabled.
    InternalError Internal error.
    InvalidParameter Parameter error.
    InvalidParameterValue.FileId FileId does not exist.
    InvalidParameterValue.SessionContextTooLong SessionContext is too long.
    InvalidParameterValue.SessionIdTooLong SessionId is too long.
    InvalidParameterValue.SubAppId Parameter value error: app ID.
    LimitExceeded.Quota The quota limit is exceeded.
    UnauthorizedOperation Unauthorized operation.

    帮助和支持

    本页内容是否解决了您的问题?

    填写满意度调查问卷,共创更好文档体验。

    文档反馈