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

Capabilities

Multiple garment try-on

Single top try-on: Generates random bottoms or keeps the original.
Single bottoms try-on: Generates a random top or keeps the original.
Top and bottoms combination: Replaces the entire outfit.
Dress/Jumpsuit try-on

Fine-grained control

Face: Keep the original or generate a random face.
Resolution: Specify output dimensions or use the original.

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 person image	Input: Flat-lay garment image	Output: Generated try-on image
	Flat-lay top image
	Flat-lay bottoms image

Input image requirements

Before calling the API, ensure images meet these requirements.

Person image requirements

Requirement	Details
Image	- File size: 5 KB to 5 MB - Resolution: Width and height must each be between 150 and 4096 pixels. - Format: JPG, JPEG, PNG, BMP, and HEIC. - Link: The image must be at a publicly accessible HTTP or HTTPS URL. Local paths are not supported.
Subject	- Subject diversity: Supports people of different genders, skin colors, and ages (6 years and older). - Pose: Full-body, front-facing photo with good lighting. Hands must be fully visible. Avoid crossed arms or obstructions. - 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 garment (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 each be between 150 and 4096 pixels. - Format: JPG, JPEG, PNG, BMP, and HEIC. - Link: The image must be at a publicly accessible HTTP or HTTPS URL. Local paths are not supported.
Garment	- Type: Supports single tops, bottoms, and dresses. Also 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: Flat-lay photo with only one garment. - No folds or obstructions: Spread flat, free of wrinkles. - Simple, clean background: Uniform color, no complex lighting or shadows. - Large garment-to-image ratio: Fill the frame. Excessive white space reduces quality.

Valid garment images

Top
Bottoms
Dress/Jumpsuit

Invalid garment images

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

Prerequisites

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

HTTP

The API uses an asynchronous workflow:

Create task: Submit an image generation request and receive a task_id.
Query result: Poll task status with task_id until complete, then 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

This model has long processing time, so tasks use asynchronous submission. After creation, the system returns a task_id. Query results within 24 hours.

Request parameters

Field	Type	Location	Required	Description	Example
Content-Type	String	Header	Yes	Request type: `application/json`.	`application/json`
Authorization	String	Header	Yes	API key format: `Bearer sk-xxxx`.	`Bearer sk-xxxx`
X-DashScope-Async	String	Header	Yes	Fixed value: `enable` (asynchronous submission).	`enable`
model	String	Body	Yes	Model to call.	`aitryon-plus`
input.person_image_url	String	Body	Yes	Publicly accessible person image URL (or get a temporary URL): - File size: 5 KB to 5 MB - Resolution: 150-4096 pixels (width and height) - Formats: JPG, JPEG, PNG, BMP, HEIC - Must contain exactly one complete person - HTTP/HTTPS URLs only (no local paths) Note Download reference person images here.	`http://aaa/1.jpg`
input.top_garment_url	String	Body	No	Publicly accessible top or dress garment URL (or get a temporary URL): - File size: 5 KB to 5 MB - Resolution: 150-4096 pixels (width and height) - Formats: JPG, JPEG, PNG, BMP, HEIC - Flat-lay image: only one garment, fully visible, clean background, minimal white space - HTTP/HTTPS URLs only (no local paths) See Garment image requirements for examples. Note - Provide at least one of `top_garment_url` or `bottom_garment_url`. - If omitted, generates random top. - For dress/jumpsuit, pass URL here and omit `bottom_garment_url`.	`http://aaa/2.jpg`
input.bottom_garment_url	String	Body	No	Publicly accessible bottoms garment URL (or get a temporary URL): - File size: 5 KB to 5 MB - Resolution: 150-4096 pixels (width and height) - Formats: JPG, JPEG, PNG, BMP, HEIC - Flat-lay image: only one garment, fully visible, clean background, minimal white space - HTTP/HTTPS URLs only (no local paths) See Garment image requirements for examples. Note - Provide at least one of `top_garment_url` or `bottom_garment_url`. - If omitted, generates random bottoms.	`http://aaa/3.jpg`
parameters.resolution	Int	Body	No	The output image resolution preset. Recommended values: - `-1` (default): Same dimensions as the input person image. - `1024`: 576x1024 - `1280`: 720x1280 Note The API may accept other values, but these recommended values provide the best results.	`-1`
parameters.restore_face	Bool	Body	No	Whether to preserve the face from the person image. - `true` (default): Keeps the original face. - `false`: Generates a new, random face.	`true`

Response parameters

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

Request examples

Try on a top

Try on a top: Pass top_garment_url for the top to try on. The AI model randomly generates 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 person's original bottoms: This involves two steps:
1. Call the OutfitAnyone - Image Segmentation API to get the image URL of the person's bottoms.
2. Call the try-on API in this topic, passing top_garment_url for the top to try on and 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 bottom_garment_url for the bottoms to try on. The AI model randomly generates 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 person's original top: This involves two steps:
1. Call the OutfitAnyone - Image Segmentation API to get the image URL of the person's top.
2. Call the try-on API in this topic, passing top_garment_url obtained from segmentation and 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 top_garment_url for the top and bottom_garment_url for the 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",
        "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

Task creation failed. See Error codes 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 Step 1 to send a GET request. Replace {task_id} in the URL with 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	API key format: `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: - 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	Generated try-on image URL. Valid for 24 hours — download promptly.	`https://.../result.jpg?Expires=xxx`
output.submit_time	String	Task submission time.	`2024-07-30 15:39:39.918`
output.scheduled_time	String	Task execution start time.	`2024-07-30 15:39:39.941`
output.end_time	String	Task completion time.	`2024-07-30 15:39:55.080`
output.code	String	Error code (returned only on failure).	`InvalidParameter`
output.message	String	Error details (returned only on failure).	`The request is missing required parameters or in a wrong format`
usage.image_count	Int	Number of images generated.	`1`
request_id	String	Unique ID of this request.	`7574ee8f-38a3-4b1e-9280-11c33ab46e51`

Request example

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

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

Task results are queryable for 24 hours after creation, then automatically purged.

Response examples

Successful response

Task data is retained for 24 hours, then purged. Download 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, see Error codes.

The following error codes are specific to the OutfitAnyone-Plus 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. Verify that the request body conforms to the API specification.
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 the server and the Alibaba Cloud Model Studio service is unavailable. Check the network connection. - OSS internal URL: The Alibaba Cloud Model Studio service cannot access internal URLs. Use an OSS public 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. Verify that the URL is publicly accessible 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 person image does not meet requirements. Ensure the input image contains exactly one complete person.
400	InvalidGarment	A garment image is missing. Provide an image for at least a top or bottoms.	A garment image is missing. Provide at least one image: a top (`top_garment_url`) or bottoms (`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. See the Input image requirements section.

FAQ

How to prepare person photos and garment images

Why are flat-lay garment images 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, realistic try-on result.
What if I do not have a flat-lay garment image? Place the garment flat on a clean background, such as a floor or wall, and photograph it from above. Alternatively, take a front-facing photo of a person or mannequin wearing the garment. Ensure the garment is fully visible, flat, and not obstructed.
How do I choose a suitable person photo? Choose a clear, front-facing, full-body photo. The person should wear simple, form-fitting clothes, such as a T-shirt and shorts. Avoid long dresses, wide-sleeved robes, or multiple layers. Ensure the person's hands and feet are visible and not blocked by accessories such as bags or umbrellas.
What if I do not have a suitable person photo? Reference person photos that meet the requirements are available for download. Click here to download them.

Unsatisfactory results

Why is the generated image low quality or lacking detail? The most common cause is a low-quality input garment image. Ensure the garment image is high resolution and complete. Details should not be lost due to folds or poor camera angles. High-quality input produces high-quality output.

Feature usage

How do I generate a try-on image for a dress or jumpsuit? Pass the dress or jumpsuit image URL in the input.top_garment_url field. Leave the input.bottom_garment_url field empty or omit it from the request.