Omnihuman-1.5(Subject detection)

POST

/doubao/omnihuman15/check

Detects the subject in an image and supports returning the corresponding mask image. This step can be skipped if the subject doesn't need to speak during video generation.

Price: 0 PTC

Request

Header Params

Body Params application/json

Example

{
    "image_url": "https://file.302.ai/gpt/imgs/20250731/1ead841266e9499ba6bf1ffcbc9c02cd.png"
}

Request Code Samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST 'https://api.302.ai/doubao/omnihuman15/check' \
--header 'Authorization: Bearer ' \
--header 'Content-Type: application/json' \
--data-raw '{
    "image_url": "https://file.302.ai/gpt/imgs/20250731/1ead841266e9499ba6bf1ffcbc9c02cd.png"
}'

Responses

🟢200成功

application/json

Body

Example

{
    "code": 10000,
    "data": {
        "resp_data": "{\"code\":0,\"object_detection_result\":{\"mask\":{\"url\":[\"https://xxxxx\"]}},\"status\":1}"
    },
    "message": "Success",
    "request_id": "202509231217222E094AB54EF8C50A04E3",
    "status": 10000,
    "time_elapsed": "3.964553804s"
}

Modified at 2025-11-18 02:20:20

Omnihuman-1（Get Task Results）

Omnihuman-1.5(Submit Task)