1. API Description
Domain name for API request: vclm.intl.tencentcloudapi.com.
This API is used to submit image animation tasks. The image animation feature supports generating videos based on dance movements and images to meet the needs of scenarios such as social entertainment and interactive marketing.
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: SubmitImageAnimateJob. |
| Version | Yes | String | Common Params. The value used for this API: 2024-05-23. |
| Region | Yes | String | Common Params. For more information, please see the list of regions supported by the product. |
| ImageUrl | No | String | Image format: PNG, JPG, and JPEG formats are supported. Image resolution: The long edge resolution should not exceed 2056. Image size: The size should not exceed 10 MB. Image aspect ratio: The ratio of width to height should be in the range of 1:2 to 1:1.2. |
| ImageBase64 | No | String | Image information after Base64 encoding. Image format: PNG, JPG, and JPEG formats are supported. Image resolution: The long side resolution should not exceed 2056. Image size: The size should not exceed 10 MB. Image aspect ratio: The ratio of width to height should be in the range of 1:2 to 1:1.2. |
| TemplateId | No | String | Action template ID. ke3: kemusan; tuziwu: rabbit dance; huajiangwu: paddling dance. |
| EnableAudio | No | Boolean | Whether the generated video retains the audio in the template. The default value is true. |
| EnableBodyJoins | No | Boolean | Whether to detect 12 body parts in the input image (head, neck, right shoulder, right elbow, right wrist, left shoulder, left elbow, left wrist, right hip, left hip, left knee, and right knee). They are not detected by default. |
| EnableSegment | No | Boolean | Whether the final video retains the background of the original image. (This parameter does not take effect when TemplateId is set to tuziwu or huajiangwu.) |
| LogoAdd | No | Integer | Whether to add a mark to the generated video. The default value is 0. 1: A mark is added. 0: No mark is added. Other values: A mark is added by default. It is recommended to use an obvious mark to indicate that the video is synthesized by AI. |
| LogoParam | No | LogoParam | Mark text settings. By default, the text "Synthesized by AI" is added to the bottom right corner of the generated video. You can also use other text images. |
3. Output Parameters
| Parameter Name | Type | Description |
|---|---|---|
| JobId | 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 Successful API call example
Successful API call example
Input Example
POST / HTTP/1.1
Host: vclm.intl.tencentcloudapi.com
Content-Type: application/json
X-TC-Action: SubmitImageAnimateJob
<Common request parameters>
{
"ImageUrl": "https://xxx/image-animate/user_input/1.png",
"TemplateId": "ke3",
"EnableAudio": true
}
Output Example
{
"Response": {
"JobId": "1194931538865782784",
"RequestId": "4e6722ba-367b-454e-add0-681a5c50fe20"
}
}
5. Developer Resources
SDK
TencentCloud API 3.0 integrates SDKs that support various programming languages to make it easier for you to call APIs.
- Tencent Cloud SDK 3.0 for Python
- Tencent Cloud SDK 3.0 for Java
- Tencent Cloud SDK 3.0 for PHP
- Tencent Cloud SDK 3.0 for Go
- Tencent Cloud SDK 3.0 for Node.js
- Tencent Cloud SDK 3.0 for .NET
- Tencent Cloud SDK 3.0 for C++
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 |
|---|---|
| AuthFailure | CAM signature/authentication error. |
| FailedOperation.BodyJointsFail | Failed to detect human body keypoints. |
| FailedOperation.FaceSizeTooSmall | The face box is too small and cannot be used for face detection. |
| FailedOperation.ImageBodyJoinsUndetected | The human body in the image is obscured or incomplete. Please upload another image. |
| FailedOperation.ImageDecodeFailed | Image decoding failed. |
| FailedOperation.ImageFaceDetectFailed | Face detection failed. |
| FailedOperation.ImageNotSupported | The image file is not supported. |
| FailedOperation.ImageRatioExcceed | The image aspect ratio exceeds the limit. |
| FailedOperation.ImageResolutionExceed | The image resolution is too high. |
| FailedOperation.ImageSizeExceed | The size of the image after base64 encoding exceeds the upper limit. |
| FailedOperation.InnerError | Internal service error. Please try again. |
| FailedOperation.JobQueueFull | Too many tasks are in queue. Please try again later. |
| FailedOperation.ModerationFailed | Failed to pass the content review. |
| InvalidParameter.TemplateNotExisted | The template does not exist. |
| InvalidParameterValue.InvalidVideoResolution | The resolution is not supported. |
| InvalidParameterValue.NoFaceInPhoto | The image contains no human face. |
| InvalidParameterValue.ParameterValueError | Parameter field or value is invalid. |
| LimitExceeded | The quota limit is exceeded. |
| OperationDenied | Operation denied. |
| RequestLimitExceeded.JobNumExceed | The number of submitted tasks exceeds the maximum number of concurrent tasks. |
| ResourceNotFound | The resource does not exist. |
| UnsupportedOperation | The operation is not supported. |
Yes
No
Was this page helpful?