How to call the OutfitAnyone-Plus API - Alibaba Cloud Model Studio

aitryon-plus delivers better performance in image definition, fabric texture, and logo restoration, but requires longer generation time. This makes it better for scenarios that prioritize high-quality results over real-time performance.

Important

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

Capabilities

Multiple garment try-on

Single top try-on: The model randomly generates bottoms or keeps the model's original bottoms.
Single bottoms try-on: The model randomly generates a top or keeps the model's original top.
Top and bottoms combination try-on: Replaces the entire outfit.
Dress/Jumpsuit try-on

Fine-grained control

Face: Keep the model's original face or generate a new, random face.
Resolution: Specify the output image dimensions or use the original's.

Overview

Model	Price	Rate limit (shared by Alibaba Cloud account and RAM users)
		Task submission API RPS	Concurrent tasks
aitryon-plus	$0.071677/image	10	5

Examples

Input: Full-body, front-facing model image

Input: Flat-lay garment image

Output: Generated try-on image

test_client_tryon

Flat-lay top image

test_client_tryon

Flat-lay bottoms image

Input image requirements

High-quality input ensures high-quality output. Before you call the API, make sure your images meet the following specifications.

Model image requirements

Requirement	Details
Image	File size: 5 KB to 5 MB Resolution: Width and height must be between 150px and 4096px. Format: JPG, JPEG, PNG, BMP, and HEIC. Link: The uploaded image must be a publicly accessible HTTP or HTTPS address. Local paths are not supported.
Subject	Subject diversity: Supports images of people of different genders, skin colors, and ages (6 years and older). Pose: Full-body, front-facing photo with good lighting. The person's hands must be fully visible. Avoid poses where arms are crossed or obstructive. Subject count: The image must contain only one complete person.

Valid person images

Invalid person images

❌ Multiple people

❌ Not a full-body, front-facing photo

(Avoid side, sitting, lying, or half-body photos)

❌ Obstructed person or clothing

(Avoid holding objects, bags, etc.)

❌ Poor lighting or blurry image

Garment image requirements

Requirement	Details
Image	File size: 5 KB to 5 MB Resolution: Width and height must be between 150px and 4096px. Format: JPG, JPEG, PNG, BMP, and HEIC are supported. Link: The uploaded image must be a publicly accessible HTTP or HTTPS address. Local paths are not supported.
Garment	Type: Supports single tops, bottoms, and dresses. Supports suits and top-and-bottom combinations. Category: Supports common apparel categories. Does not support underwear, wedding dresses, or special ethnic costumes. Display: Single garment: The image must be a flat-lay photo containing only a single piece of clothing. No folds or obstructions: The clothing should be spread out, flat, and free of wrinkles or folds. Simple, clean background: The image background should be simple, clean, and have a uniform color. The main garment should be clear, without complex lighting or shadows. Large garment-to-image ratio: The garment should take up as much of the frame as possible. Avoid excessive white space around the garment, because it can reduce the quality of the try-on effect.

Valid garment images

Top
Bottoms
Dress/Jumpsuit

Invalid garment images

❌ Multiple garments	❌ Not a front-facing photo	❌ Folded or obstructed	❌ Wrinkled garment

Prerequisites

The OutfitAnyone-Plus API only supports calls over HTTP.

Get an API key and set the API key as an environment variable.

HTTP

The API provides an asynchronous operation that involves two steps:

Create a task: Create an image generation task to obtain a unique `task_id`.
Query the result: Use the `task_id` to poll the task status until the task is complete and retrieve the result.

Step 1: Create a task

Send a `POST` request to create a try-on task.

POST https://dashscope.aliyuncs.com/api/v1/services/aigc/image2image/image-synthesis

Note

Because this model has a long invocation time, tasks are created using an asynchronous invocation.
After the task is created, the system immediately returns a task_id. You must use this `task_id` to query the task result within 24 hours.

Request parameters

Field	Type	Location	Required	Description	Example
Content-Type	String	Header	Yes	The request type: application/json.	application/json
Authorization	String	Header	Yes	The API key. For example: Bearer sk-xxxx.	Bearer sk-xxxx
X-DashScope-Async	String	Header	Yes	A static field with the value `enable`, which indicates an asynchronous call.	enable
model	String	Body	Yes	Specifies the model to call.	aitryon-plus
input.person_image_url	String	Body	Yes	The public URL of the model's image. You can also get a temporary public URL. 5 KB ≤ Image file size ≤ 5 MB 150 ≤ Image edge length ≤ 4096 Supported formats: jpg, png, jpeg, bmp, heic The image must contain only one complete person. Only HTTP/HTTPS links are supported. Local paths are not supported. For examples of model images, see Model image requirements. Note Please click here to download the provided model images.	http://aaa/1.jpg
input.top_garment_url	String	Body	No	The Internet URL of the top/dress garment image. You can also get a temporary Internet URL. 5 KB ≤ Image file size ≤ 5 MB 150 ≤ Image edge length ≤ 4096 Supported formats: jpg, png, jpeg, bmp, heic Upload a flat-lay image of the garment. Make sure the garment is the only subject, is fully visible, has a clean background, and does not have excessive white space around it. Only HTTP/HTTPS links are supported. Local paths are not supported. For examples of garment images, see Garment image requirements. Note You must provide at least one of `top_garment_url` and `bottom_garment_url`. If you do not pass this field, the model randomly generates a top. For a dress or jumpsuit, enter the image URL in this field and leave `bottom_garment_url` empty.	http://aaa/2.jpg
input.bottom_garment_url	String	Body	No	The Internet URL of the lower garment image. You can also get a temporary Internet URL. 5 KB ≤ Image file size ≤ 5 MB 150 ≤ Image edge length ≤ 4096 Supported formats: jpg, png, jpeg, bmp, heic Upload a flat-lay image of the garment. Make sure the garment is the only subject, is fully visible, has a clean background, and does not have excessive white space around it. Only HTTP/HTTPS links are supported. Local paths are not supported. For garment image examples, see Garment image requirements. Note You must provide at least one of `top_garment_url` and `bottom_garment_url`. If you do not pass this field, the model randomly generates bottoms.	http://aaa/3.jpg
parameters.resolution	Int	Body	No	The resolution of the output image. Recommended values: -1 (default): The resolution is the same as the original image. 1024: 576×1024 1280: 720×1280 Note The API may accept other values. But these recommended values provide the best performance.	-1
parameters.restore_face	Bool	Body	No	Specifies whether to restore the face from the model image. true (default): Keeps the original face. false: Generates a new, random face.	true

Response parameters

Field	Type	Description	Example
output.task_id	String	The unique ID of the asynchronous task.	a8532587-fa8c-4ef8-82be-0c46b17950d1
output.task_status	String	The status of the task after submission.	PENDING
request_id	String	The unique ID of this request.	7574ee8f-38a3-4b1e-9280-11c33ab46e51

Request examples

Try on a top

Try on a top: Pass the `top_garment_url` for the top to try on. The model will randomly generate bottoms.

curl --location 'https://dashscope.aliyuncs.com/api/v1/services/aigc/image2image/image-synthesis/' \
--header 'X-DashScope-Async: enable' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model": "aitryon-plus",
    "input": {
        "person_image_url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250626/ubznva/model_person.png",
        "top_garment_url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250626/epousa/short_sleeve.jpeg"    
    },
    "parameters": {
        "resolution": -1,
        "restore_face": true
    }
 }'

Keep the model's original bottoms: This involves two steps:
1. Call the OutfitAnyone - Image Segmentation API to obtain the image URL of the model's bottoms.
2. Call the try-on API in this topic, passing the `top_garment_url` for the top to try on and the `bottom_garment_url` obtained from segmentation.

curl --location 'https://dashscope.aliyuncs.com/api/v1/services/aigc/image2image/image-synthesis/' \
--header 'X-DashScope-Async: enable' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model": "aitryon-plus",
    "input": {
        "person_image_url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250626/ubznva/model_person.png",
        "top_garment_url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250626/epousa/short_sleeve.jpeg",
        "bottom_garment_url": "Image URL from the Image Segmentation API output"    
    },
    "parameters": {
        "resolution": -1,
        "restore_face": true
    }
 }'

Try on bottoms

Try on bottoms: Pass the `bottom_garment_url` for the bottoms to try on. The model will randomly generate a top.

curl --location 'https://dashscope.aliyuncs.com/api/v1/services/aigc/image2image/image-synthesis/' \
--header 'X-DashScope-Async: enable' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model": "aitryon-plus",
    "input": {
        "person_image_url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250626/ubznva/model_person.png",
        "bottom_garment_url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250626/rchumi/pants.jpeg" 
    },
    "parameters": {
        "resolution": -1,
        "restore_face": true
    }
}'

Keep the model's original top: This involves two steps:
1. Call the OutfitAnyone - Image Segmentation API to obtain the image URL of the model's top.
2. Call the try-on API in this topic, passing the `top_garment_url` obtained from segmentation and the `bottom_garment_url` for the bottoms to try on.

curl --location 'https://dashscope.aliyuncs.com/api/v1/services/aigc/image2image/image-synthesis/' \
--header 'X-DashScope-Async: enable' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model": "aitryon-plus",
    "input": {
        "person_image_url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250626/ubznva/model_person.png",
        "top_garment_url": "Image URL from the Image Segmentation API output",
        "bottom_garment_url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250626/rchumi/pants.jpeg"     
    },
    "parameters": {
        "resolution": -1,
        "restore_face": true
    }
 }'

Try on a top and bottoms

Pass the `top_garment_url` for the top to try on and the `bottom_garment_url` for the bottoms to try on.

curl --location 'https://dashscope.aliyuncs.com/api/v1/services/aigc/image2image/image-synthesis/' \
--header 'X-DashScope-Async: enable' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model": "aitryon-plus",
    "input": {
        "person_image_url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250626/ubznva/model_person.png",
        "top_garment_url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250626/epousa/short_sleeve.jpeg",
        "bottom_garment_url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250626/rchumi/pants.jpeg" 
    },
    "parameters": {
        "resolution": -1,
        "restore_face": true
    }
}'

Try on a dress or jumpsuit

For a dress or jumpsuit, pass only `top_garment_url`.

curl --location 'https://dashscope.aliyuncs.com/api/v1/services/aigc/image2image/image-synthesis/' \
--header 'X-DashScope-Async: enable' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model": "aitryon-plus",
    "input": {
        "person_image_url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250626/ubznva/model_person.png",
        "top_garment_url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250626/odngby/dress.jpg"
    },
    "parameters": {
        "resolution": -1,
        "restore_face": true
    }
}'

Response examples

Successful response

Save the `task_id` to query the task status and result.

{
    "output": {
        "task_status": "PENDING",
        "task_id": "0385dc79-5ff8-4d82-bcb6-xxxxxx"
    },
    "request_id": "4909100c-7b5a-9f92-bfe5-xxxxxx"
}

Error response

The task creation failed. For more information, see Error messages to resolve the issue.

{
    "code": "InvalidApiKey",
    "message": "No API-key provided.",
    "request_id": "7438d53d-6eb8-4596-8835-xxxxxx"
}

Step 2: Query the result by task ID

Use the task_id from the previous step to send a GET request to query the task status and result. Replace {task_id} in the URL with your actual task ID.

GET https://dashscope.aliyuncs.com/api/v1/tasks/{task_id}

Request parameters

Field	Type	Location	Required	Description	Example
Authorization	String	Header	Yes	The API key. For example: Bearer sk-xxx.	Bearer sk-xxx
task_id	String	URL Path	Yes	The ID of the task to query.	a8532587-fa8c-4ef8-82be-0c46b17950d1

Response parameters

Field	Type	Description	Example
output.task_id	String	The ID of the queried task.	a8532587-fa8c-4ef8-82be-0c46b17950d1
output.task_status	String	The task status. Possible values include the following: PENDING PRE-PROCESSING RUNNING POST-PROCESSING SUCCEEDED FAILED UNKNOWN: The task does not exist or its status is unknown. CANCELED	SUCCEEDED
output.image_url	String	The URL of the generated try-on image. The image_url is valid for 24 hours. Download it promptly.	https://.../result.jpg?Expires=xxx
output.submit_time	String	The task submission time.	2024-07-30 15:39:39.918
output.scheduled_time	String	The task running time.	2024-07-30 15:39:39.941
output.end_time	String	The task completion time.	2024-07-30 15:39:55.080
output.code	String	The error code. This parameter is returned when the task fails.	InvalidParameter
output.message	String	The error details. This parameter is returned when the task fails.	The request is missing required parameters or in a wrong format
usage.image_count	Int	The number of images generated in this request.	1
request_id	String	The unique ID of this request.	7574ee8f-38a3-4b1e-9280-11c33ab46e51

Request example

Replace 86ecf553-d340-4e21-xxxxxxxxx with your actual task ID.

curl -X GET https://dashscope.aliyuncs.com/api/v1/tasks/86ecf553-d340-4e21-xxxxxxxxx \
--header "Authorization: Bearer $DASHSCOPE_API_KEY"

Note

You can query the task result using the `task_id` for only 24 hours after the task is created. After this period, the task is automatically purged by the system.

Response examples

Successful response

Task data, such as the task status and image URL, is retained for only 24 hours and is then automatically purged. You must save the generated image promptly.

{
    "request_id": "98d46cd0-1f90-9231-9a6c-xxxxxx",
    "output": {
        "task_id": "15991992-1487-40d4-ae66-xxxxxx",
        "task_status": "SUCCEEDED",
        "submit_time": "2025-06-30 14:37:53.838",
        "scheduled_time": "2025-06-30 14:37:53.858",
        "end_time": "2025-06-30 14:38:11.472",
        "image_url": "http://dashscope-result-hz.oss-cn-hangzhou.aliyuncs.com/tryon.jpg?Expires=xxx"
    },
    "usage": {
        "image_count": 1
    }
}

Failed response

{
    "request_id": "6bf4693b-c6d0-933a-b7b7-xxxxxx",
    "output": {
        "task_id": "e32bd911-5a3d-4687-bf53-xxxxxx",
        "task_status": "FAILED",
        "code": "InvalidParameter",
        "message": "The request is missing required parameters xxxxx"
  }
}

Error codes

For general status codes of the model service, see Error messages.

The following error codes are specific to the OutfitAnyone model:

HTTP return code	code	message	Description
400	InvalidParameter	The request is missing required parameters or has an incorrect format. Check the parameters in your request.	A required parameter is missing or the format is incorrect. Check that your request body conforms to the API specifications.
400	InvalidParameter	Download the media resource timed out during the data inspection process.	The image download timed out. Possible causes and solutions: Network issue: The network connection between your server and the Alibaba Cloud Model Studio service is unavailable. Check your network connection. OSS internal URL: The Alibaba Cloud Model Studio service cannot access internal URLs. Use an OSS Internet URL instead. Resource outside the Chinese mainland: Cross-border network access is unstable. Use a storage service in the Chinese mainland.
400	InvalidURL	The request URL is invalid. Check that the URL is available and the image format is one of the following: JPEG, JPG, PNG, BMP, or WEBP.	The image URL is invalid. Check that the URL is accessible over the Internet and the image format meets the requirements.
400	InvalidPerson	The input image does not contain a person or contains multiple people. Upload an image that contains only one person.	The model image is not compliant. Ensure that the input image contains one and only one complete person.
400	InvalidGarment	A clothing image is missing. Provide an image for at least a top or a bottom.	A clothing image is missing. Provide at least one image for a top (top_garment_url) or a bottom (bottom_garment_url).
400	InvalidInputLength	The image resolution is invalid. Make sure that the longest side of the image is less than 4096 pixels, the shortest side is greater than 150 pixels, and the file size is between 5 KB and 5 MB.	The image dimensions or file size do not meet the requirements. For more information, see Input image requirements.

FAQ

How to prepare model photos and garment images

Why are flat-lay images of garments required?
Flat-lay images provide the clearest view of a garment's cut, pattern, and silhouette. This helps the AI accurately understand the garment's structure and generate a more fitted and realistic try-on result.
What if I do not have a flat-lay image of the garment?
Place the garment flat on a clean background, such as a floor or wall, and take a photo from above. Alternatively, take a front-facing photo of a model or mannequin wearing the garment. Ensure the garment is fully visible, flat, and not obstructed.
How do I choose a suitable model photo?
Choose a clear, front-facing, full-body photo. The model should wear simple, form-fitting clothes, such as a T-shirt and shorts. Avoid long dresses, robes with wide sleeves, or multiple layers. Ensure the model's hands and feet are clearly visible and not blocked by accessories, such as bags or umbrellas.
What if I do not have a suitable model photo?
We provide a set of model reference photos that meet the requirements. You can click here to download and use them.

Unsatisfactory model results

Why is the quality of the generated image poor and lacking in detail?
The most likely cause is a low-quality input garment image. Ensure the garment image is high definition and complete. Details should not be lost because of folds or poor camera angles. High-quality input ensures high-quality output.

Feature usage

How do I generate a try-on image for a dress or jumpsuit?
Enter the image URL for the dress or jumpsuit into the input.top_garment_url field. Leave the input.bottom_garment_url field empty or do not include it in the request.