AnimateAnyone Detect Gen2

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

Input modalities

ImageSource for Input modalities (opens in a new tab)

Output modalities

Detection resultsSource for Output modalities (opens in a new tab)

Reasoning

Not collected

Tool calling

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

Historical card flag. Fixed API response JSON is not configurable structured generation.

Structured output

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

Historical card flag. Fixed API response JSON is not configurable structured generation.

Streaming

Not collected

Batch processing

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

Historical card flag. Fixed API response JSON is not configurable structured generation.

Fine-tuning

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

Historical card flag. Fixed API response JSON is not configurable structured generation.

Knowledge cutoff

Not collected

Release date

2024-12-10Source for Release date (opens in a new tab)

Parameters

Not collected

Architecture

Not collected

Languages

Not collected

Context caching

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

Historical card flag. Fixed API response JSON is not configurable structured generation.

API aliases

animate-anyone-detect-gen2Source for API aliases (opens in a new tab)

Published availability regions

China (Beijing)Source for Published availability regions (opens in a new tab)

Recommended replacement

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

Provider migration recommendation, not checkpoint identity or drop-in API compatibility.

Search grounding

Not supportedSource for Search grounding (opens in a new tab)

Historical card flag. Fixed API response JSON is not configurable structured generation.

Prefix completion

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

Historical card flag. Fixed API response JSON is not configurable structured generation.

Console model playground

Not supportedSource for Console model playground (opens in a new tab)

Historical card flag. Fixed API response JSON is not configurable structured generation.

Synchronous generation

SupportedSource for Synchronous generation (opens in a new tab)

Request mode

Historical synchronous image check.Source for Request mode (opens in a new tab)

Required request fields

image_urlSource for Required request fields (opens in a new tab)

Image input limits

Public HTTP(S) portrait; under 5 MB; longest side at most 4,096 pixels.Source for Image input limits (opens in a new tab)

Input image formats

JPG, JPEG, PNG, BMPSource for Input image formats (opens in a new tab)

The same repository reference later lists BMP among conversion inputs. Its request table supports BMP; this internal discrepancy remains visible.

Portrait requirements

One clear, unoccluded person facing or nearly facing the camera, with full body or at least waist-up visible; simple background preferred.Source for Portrait requirements (opens in a new tab)

Detection result fields

check_pass, bodystyle (full / half)Source for Detection result fields (opens in a new tab)

Output billing

Successful image checks are billed even if the image is rejected; output is free.Source for Output billing (opens in a new tab)

Usage metering

Historical input-image tariffSource for Usage metering (opens in a new tab)

Retired service, not a current offer. USD and CNY amounts, where present, are independent published tariffs, not currency conversions.

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

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

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.

Why it is included

Classification inference: a separately named hosted Alibaba model with no exact public checkpoint identified in the reviewed provider documentation. The official AnimateAnyone research repository has no model weights and links to a separately named public Wan-Animate successor; equivalence to the hosted Gen2 models is not established. Private checkpoint lineage remains unverified.

Lifecycle dates

Sources reviewed