Virtual Model Alternation Submit API Reference
Last updated
Last updated
GET/POST /ai/virtual/model/generation/batch
The Virtual Model Alternation can automatically retain the clothing area in the model image and intelligently match the model type to generate diverse models from different countries, showcasing the best wear effect of the product. This allows for localized content targeting for cross-border markets, accurately capturing user preferences and reducing photograph costs.
This is an asynchronous interface that you need to submit the task first, then obtain the task ID and call the result query interface to get the generated result. The current API is the first step, which is the task submission API.
| Parameter | Type | Required | Description |
|---|---|---|---|
Image formats: JPEG、JPG、PNG、BMP、WEBP
Image size: no more than 4 MB
Image resolution: The size of input image should be more than 512×512 pixels and less than 3000×3000 pixels.
Category: Now the API only supports automatic segmentation and retention for the "clothing" category and does not yet support other specified product categories.
| Parameter | Type | Description |
|---|---|---|
| Error Code | Error Message | Description |
|---|---|---|
requestId
String
A unique request ID used for troubleshooting.
success
Boolean
The status of the returned request, indicating whether the request was successful.
resCode
Number
The returned result code, where 200 indicates success. For detailed error codes, please refer to the error code list.
resMessage
String
The returned request information.
data
Object
The returned JSON result data.
result
Object
The returned result data.
taskId
String
A unique task ID. It is used for subsequent result query requests.
500
system error
System error.
501
rate limit exceed
The current interface has reached the current limit. Please contact us via navigation bar or email us (aidge_support@service.alibaba.com) to increase the current limit value.
700
invalid input
The format of the input parameters does not meet the requirements, and resMessage will return detailed fields that do not meet the requirements.
801
model failed
Internal call exception, please contact us via navigation bar or email us (aidge_support@service.alibaba.com) for troubleshooting.
1000
content has sensitive data, please try other input
Content has sensitive data and cannot be handled now. Please try other input.
1001
content control failed, please retry
Content risk failed, please try other input. If an error persists,please contact us via navigation bar or email us (aidge_support@service.alibaba.com) for troubleshooting.
1002
content risk filter failed, please contact us
Content risk failed, please ccontact us via navigation bar or email us (aidge_support@service.alibaba.com).
requestParams
Object[]
Yes
imageUrl
String
No
The model image URL.
Both imageUrl and imageBase64 cannot be empty at the same time. If both imageUrl and imageBase64 are present, Base64 is preferred.
Input image size larger than 512×512 pixels, but smaller than 3000×3000 pixels.
imageBase64
String
No
The Base64 encoding of the model image.
Both imageUrl and imageBase64 cannot be empty at the same time. If both imageUrl and imageBase64 are present, Base64 is preferred.
Input image size larger than 512×512 pixels, but smaller than 3000×3000 pixels.
imageStyle
String
Yes
Specifies the content type of the model in the submitted image, such as real person model, complete mannequin, incomplete mannequin, etc. Currently, only real person model images are supported. Range of values:
realPhoto：Submit a real person model phoyo
Sample: realPhoto
model
String
Yes
Specifies the model that needs to be generated. Currently, four different models are supported. Range of values:
universal_model_1：
universal_model_2：
universal_model_3：
universal_model_4：
Sample: universal_model_1
gender
String
No
Specifies the gender of the model to be generated. If not set, the algorithm's automatic recognition result is used by default. Range of values:
MALE: male
FEMALE: female
Sample: MALE
age
String
No
Specifies the age group of the model to be generated. If not set, the algorithm's automatic recognition result is used by default. Range of values:
OLD_AGE: Old-aged about 60 years old and above
MIDDLE_AGE: middle-aged, about 30-50 years old
YOUTH: youth, about 20-30 years old
Sample: YOUTH
maskKeepbg
Boolean
No
Specifies whether to keep the original image's background. If not set, the original background is kept by default. Range of values:
true: Keep the background unchanged. No need to fill in the bgStyle parameter.
false: Change the background. The bgStyle parameter must be specified.
Sample: true
bgStyle
String
No
Specifies the background style to be generated. When selecting background replacement (maskKeepbg=false), this parameter must be filled in. Currently, four scenes are supported. Range of values:
studio: studio photography
room: room photography
European_street: street photography
beach: beach photography
Sample: studio
count
Number
No
Specifies the desired number of images to be generated. A maximum of four images can be generated per task. If not set, 2 images are generated by default.
Range of value: 1-4
Sample: 2
dimension
Number
No
Specifies the desired size of the images to be generated. The generated images will maintain the original aspect ratio, with the shortest side based on the input value. If not set, the default generated size is 768.
Range of value: 512-2048
Sample: 768
