OutfitAnyone-Parsing API reference - Alibaba Cloud Model Studio

This document applies only to the China (Beijing) region. To use the model, you must use an API key from the China (Beijing) region.

Overview

Model	Price	Rate limit (shared by account and RAM users)
Model	Price	RPS for task submission API	Concurrent tasks
aitryon-parsing-v1	$0.000574/image	10	Unlimited (sync API)

Core outputs

Calling this API returns three core outputs. The following example of parsing a top shows each parameter's meaning and use.

Input	Output
Input	Output parameter	Example	Meaning and use
Input model image Set the clothing type to top "clothes_type": ["upper"]	crop_img_url		Cropped clothing image (RGB): Clothing image of the model's top. Used for partial try-on with OutfitAnyone. URLs expire in 24 hours. Download them promptly.
	parsing_img_url		Parsed clothing image (RGBA): Visualized parsing result of the top. Used to preview and verify parsing accuracy. URLs expire in 24 hours. Download them promptly.
	bbox	bbox value: [[331, 239,641,637]] This image shows the mapping between the bbox value and the coordinates of the original image. It is not a model output.	Bounding box: Rectangular area coordinates of the parsed clothing in the input image. Format: [x1, y1, x2, y2] (upper-left and lower-right corners). Origin: (0,0) at input image's upper-left corner. Used for frontend features like product hotspots.

Scenarios

Scenario 1: Partial try-on

Objective: Replace part of the model's clothing (top or bottoms) while keeping the other part unchanged. Requires parsing the model image first.

Example: Keep the model's top and replace the bottoms

Parse the model image to extract the top
- Call this API with the model image and set clothes_type to ["upper"] to extract the top.
- The API returns the top image (crop_img_url).
Input: Model image
Output: Parsed clothing image (crop_img_url)
Generate the try-on image
- Call OutfitAnyone-Plus API reference.
- Input the model image, parsed top image, and bottoms image to generate the try-on result.
Input
Output: Try-on image
Model image
Top image
Bottoms image

Same as the parsing API input.

From the parsing API's crop_img_url.

Replacement clothing image.

Input	Output: Try-on image
Same as the parsing API input.	From the parsing API's crop_img_url.	Replacement clothing image.

Scenario 2: Get the coordinates of specific clothing

Objective: Get bbox coordinates of specific clothing on model or try-on images. Use coordinates for product labels or interactive hotspots.

Example: Get the coordinates of a top

Prepare input: Use a model image or OutfitAnyone-generated image. See OutfitAnyone-Plus API reference.

Parse to get coordinates: Set parsing type (e.g., ["upper"] for top) to obtain the bbox.

Input: Model image or try-on image	Output: Parsed clothing image and coordinate range
Request parameter "clothes_type": ["upper"]	parsing_img_url: URL of the visualized result. bbox: Bounding box coordinates (e.g., [[331, 239, 641, 637]]).

Input: Model image or try-on image

Output: Parsed clothing image and coordinate range

Request parameter "clothes_type": ["upper"]

parsing_img_url: URL of the visualized result.
bbox: Bounding box coordinates (e.g., [[331, 239, 641, 637]]).

Prerequisites

The OutfitAnyone-Parsing API supports only HTTP calls. Obtain an API key and set the API key as an environment variable.

HTTP

Request endpoint

POST https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/vision/image-process/process

Replace {WorkspaceId} with your actual workspace ID.

Request parameters

Field	Type	Location	Required	Description	Example
Content-Type	String	Header	Yes	Request type. Set to application/json.	application/json
Authorization	String	Header	Yes	The API key. Format: Bearer sk-xxxx	Bearer sk-xxxx
model	String	Body	Yes	The model to call. Set to aitryon-parsing-v1.	aitryon-parsing-v1
input.image_url	String	Body	Yes	Public URL of the model image to parse. Get a temporary URL here. File size: 5 KB to 5 MB. Dimensions: 150 to 4,096 pixels per side. Supported formats: JPG, PNG, JPEG, BMP, and HEIC. Image must contain exactly one complete person. Only HTTP and HTTPS links are supported. Local paths are not supported. For model image examples, see OutfitAnyone-Plus API reference.	http://a/a.jpg
parameters.clothes_type	List[String]	Body	No	Type of clothing to parse. Default: ["upper"] (top). List length and order determine output URL list. Valid values: ["upper"]: Upper garment. ["lower"]: Lower-body clothing. ["dress"]: Dress, jumpsuit, or full outfit. ["upper", "lower"]: Top and bottom.	["upper"]

Response parameters

Field	Type	Description	Example
output.parsing_img_url	List[String]	A list of URLs for the visualized parsed areas. List matches clothes_type length and order. Returns None/null at the position if corresponding clothing not detected. RGBA image in PNG format.	["http://a/a.png"] [null] or [None]
output.crop_img_url	List[String]	A list of URLs for cropped clothing images. List matches clothes_type length and order. Returns None/null at the position if corresponding clothing not found. RGB format.	["http://a/a.png"] [null] or [None]
output.bbox	List[List[Integer]]	A list of coordinates for the parsed areas in the original image. Sorted by clothes_type order. Each bbox: [x1, y1, x2, y2] (upper-left and lower-right corners). Origin: upper-left corner of input image.	[[10,20,30,40], [50,60,70,80]]
usage.image_count	Integer	The number of images processed per request.	1
request_id	String	The unique ID of the request.	7574ee8f-38a3-4b1e-9280-11c33ab46e51

Sample request

Parse the top from a model image

curl --location 'https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/vision/image-process/process' \
--header 'Content-Type: application/json' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--data '{
  "model": "aitryon-parsing-v1",
  "input": {
      "image_url":"https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250630/bakbqz/aitryon_parse_model.png"
  },
  "parameters": {
      "clothes_type": ["upper"]
  }
}'

Sample response

Successful response (corresponding clothing type exists)
Successful response (corresponding clothing type does not exist)
Failed response

URLs in parsing_img_url and crop_img_url expire in 24 hours. Download them within this period.

{
    "output": {
        "bbox": [[331, 239,641,637]],
        "parsing_img_url": ["http://dashscope-result-sh.oss-cn-shanghai.aliyuncs.com/example_parsing_img.png?Expires=xxxx"],
        "crop_img_url": ["http://dashscope-result-sh.oss-cn-shanghai.aliyuncs.com/example_crop_img.jpg?Expires=xxxx"]
    },
    "usage": {
        "image_count": 1
    },
    "request_id": "b68147d6-e7d0-920f-b889-xxxxxx"
}

{
    "output":{
        "bbox":[null],
        "parsing_img_url":[null],
        "crop_img_url":[null]
    },
    "usage":{
        "image_count":1
    },
    "request_id":"c56f62df-724e-9c19-96bd-308627cf5262"
}

Error codes

For general status codes, see Error codes.

​Overview

​Core outputs

​Scenarios

​Scenario 1: Partial try-on

​Example: Keep the model's top and replace the bottoms

​Scenario 2: Get the coordinates of specific clothing

​Example: Get the coordinates of a top

​Prerequisites

​HTTP

​Request endpoint

​Request parameters

​Response parameters

​Sample request

​Sample response

​Error codes

Overview

Core outputs

Scenarios

Scenario 1: Partial try-on

Example: Keep the model's top and replace the bottoms

Scenario 2: Get the coordinates of specific clothing

Example: Get the coordinates of a top

Prerequisites

HTTP

Request endpoint

Request parameters

Response parameters

Sample request

Sample response

Error codes