Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Alibaba Cloud / OutfitAnyone

OutfitAnyone Parsing v1

Garment segmentation model that returns cropped clothing, transparent previews and bounding boxes for partial virtual try-on.

retiredClosed weightsImage segmentation
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
27 of 36 specification fields collected
Image input limitEach image: 5 KB–5 MB; 150–4,096 pixels per side; public HTTP(S) URL. Person image must show exactly one complete person.See specification notes below
Output typesImage, Bounding boxesSee specification notes below
Input billingSee ratesAlibaba Model Studio · Beijing · retired listing
Output billingSee ratesPublished units and conditions below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected
Maximum input tokens
Not collected
Maximum output
Not collected
Output modalities
Image, Bounding boxesSource for Output modalities (opens in a new tab)

Detailed segmentation API also returns bounding boxes.

Reasoning
Not collected
Tool calling
Not supportedSource for Tool calling (opens in a new tab)

Historical model-card flag. This does not establish current service access.

Structured output
Not supportedSource for Structured output (opens in a new tab)

Historical model-card flag. This does not establish current service access.

Streaming
Not collected
Batch processing
Not supportedSource for Batch processing (opens in a new tab)

Historical model-card flag. This does not establish current service access.

Fine-tuning
Not supportedSource for Fine-tuning (opens in a new tab)

Historical model-card flag. This does not establish current service access.

Knowledge cutoff
Not collected
Parameters
Not collected
Architecture
Not collected
Languages
Not collected
Context caching
Not supportedSource for Context caching (opens in a new tab)

Historical model-card flag. This does not establish current service access.

API aliases
aitryon-parsing-v1Source for API aliases (opens in a new tab)
Published availability regions
China (Beijing)Source for Published availability regions (opens in a new tab)
Search grounding
Not supportedSource for Search grounding (opens in a new tab)

Historical model-card flag. This does not establish current service access.

Prefix completion
Not supportedSource for Prefix completion (opens in a new tab)

Historical model-card flag. This does not establish current service access.

Recommended replacement
qwen-image-3.0Source for Recommended replacement (opens in a new tab)

Provider migration recommendation, not API or checkpoint equivalence.

Request mode
Historical synchronous parsing request.Source for Request mode (opens in a new tab)
Image input limits
Each image: 5 KB–5 MB; 150–4,096 pixels per side; public HTTP(S) URL. Person image must show exactly one complete person.Source for Image input limits (opens in a new tab)
Input image formats
JPG, JPEG, PNG, BMP, HEICSource for Input image formats (opens in a new tab)
Required request fields
input.image_urlSource for Required request fields (opens in a new tab)
Garment selection
upper (default), lower, dress, upper + lowerSource for Garment selection (opens in a new tab)
Segmentation outputs
parsing_img_url: RGBA PNG preview; crop_img_url: RGB garment crop; bbox: [x1,y1,x2,y2] coordinates relative to the original image.Source for Segmentation outputs (opens in a new tab)
Output formats
RGBA PNG, RGB crop, Bounding boxesSource for Output formats (opens in a new tab)
Output list ordering
All result lists follow clothes_type length and order; absent garments return null at the corresponding position.Source for Output list ordering (opens in a new tab)
Output link expiry
Parsing and crop URLs expire after 24 hours.Source for Output link expiry (opens in a new tab)
Output billing
One input image per successful request; output is free. A successful no-garment result still reports image_count=1. Failed requests are not billed.Source for Output billing (opens in a new tab)
Usage metering
Historical native per-image tariffsSource for Usage metering (opens in a new tab)

No text-token or question estimate. Published CNY and USD rates are independent native tariffs.

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Alibaba Model Studio · Beijing · retired listing

Provider source (opens in a new tab)
API model ID
aitryon-parsing-v1
Access
Historical POST https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/vision/image-process/process. Historical synchronous parsing request. Current access is not established by this preserved contract.
Regions
China (Beijing)
Published request quota
600 requests per minute (historical)Source for Published request quota (opens in a new tab)
Task submission rate
10 submissions per second (historical)Source for Task submission rate (opens in a new tab)
Concurrent requests
No explicit synchronous concurrency capSource for Concurrent requests (opens in a new tab)
Quota scope
Per model, shared between the Alibaba Cloud account and RAM usersSource for Quota scope (opens in a new tab)
Request mode
Historical synchronous parsing request.Source for Request mode (opens in a new tab)
Free usage allowance
Domestic historical guide: 400 images. International tariff: no free quota.Source for Free usage allowance (opens in a new tab)

Dedicated guide validity: 90 days from activation. The central table instead uses the latest activation, release or approval date; preserve both scopes rather than infer account eligibility.

Tool calling
Not supportedSource for Tool calling (opens in a new tab)

Historical model-card flag. This does not establish current service access.

Structured output
Not supportedSource for Structured output (opens in a new tab)

Historical model-card flag. This does not establish current service access.

Context caching
Not supportedSource for Context caching (opens in a new tab)

Historical model-card flag. This does not establish current service access.

Batch processing
Not supportedSource for Batch processing (opens in a new tab)

Historical model-card flag. This does not establish current service access.

Fine-tuning
Not supportedSource for Fine-tuning (opens in a new tab)

Historical model-card flag. This does not establish current service access.

retirement
International listing retired October 10, 2026; current domestic access unverified.Source for retirement (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
CategoryUsageRateUnit
Historical OutfitAnyone pricingInput image1CN¥0.004image
Historical OutfitAnyone pricingInput image2$0.000574image

Rate conditions

  1. Historical published tariff, not a verified current offer. Native domestic portal tariff. Failed requests are not billed. No currency conversion or text-question quote.
  2. Historical published tariff, not a verified current offer. Native international portal tariff; no free quota. Failed requests are not billed. No currency conversion or text-question quote.
Pricing source (opens in a new tab)Pricing source (opens in a new tab)

Data & enterprise terms

Historical request and result-link facts only. Input retention, training use and current account policies are unverified.

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

Alibaba Model Studio · Beijing · retired listing

aitryon-parsing-v1
Not supported

Historical model-card flag. This does not establish current service access.

Support evidence (opens in a new tab)Caching reviewed 14 Oct 2026

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Classification inference: this separately named native Alibaba hosted release has no exact public checkpoint in the reviewed OutfitAnyone research repository, which contains only a README and demonstration media. Demo access and preset person images do not establish released weights. Exact private checkpoint lineage remains unverified.

Classification evidence (opens in a new tab)

Lifecycle dates

Model Studio release15 Jan 2025Source (opens in a new tab)
Retirement announced10 Jul 2026Source (opens in a new tab)
Retired from international Model Studio listing10 Oct 2026Source (opens in a new tab)

Sources reviewed