OmniHuman 1.5 subject detection

import { OmnihumanClient } from "@runapi.ai/omnihuman";

const client = new OmnihumanClient();
const result = await client.subjectDetection.run({
    model: "omnihuman-1.5-subject-detection",
    prompt: "基于这张肖像和旁白音频生成一段 720p 数字人视频，并使用主体 mask 保持人物边界稳定。",
});

import os
import requests

response = requests.post(
    "https://runapi.ai/api/v1/omnihuman/subject_detection",
    headers={"Authorization": f"Bearer {os.environ['RUNAPI_API_KEY']}"},
    json={"model":"omnihuman-1.5-subject-detection","prompt":"基于这张肖像和旁白音频生成一段 720p 数字人视频，并使用主体 mask 保持人物边界稳定。"}
)
response.raise_for_status()

<?php

$client = curl_init("https://runapi.ai/api/v1/omnihuman/subject_detection");
curl_setopt_array($client, [
    CURLOPT_HTTPHEADER => ["Authorization: Bearer " . getenv("RUNAPI_API_KEY"), "Content-Type: application/json"],
    CURLOPT_POSTFIELDS => json_encode([
        'model' => 'omnihuman-1.5-subject-detection',
        'prompt' => '基于这张肖像和旁白音频生成一段 720p 数字人视频，并使用主体 mask 保持人物边界稳定。',
    ])
]);
$response = curl_exec($client);

RunApi client = new RunApi(System.getenv("RUNAPI_API_KEY"));
Task task = client.subjectDetection().run({"model":"omnihuman-1.5-subject-detection","prompt":"基于这张肖像和旁白音频生成一段 720p 数字人视频，并使用主体 mask 保持人物边界稳定。"});
task.waitForResult();

require "runapi/omnihuman"

client = RunApi::Omnihuman::Client.new
result = client.subject_detection.run(
    model: "omnihuman-1.5-subject-detection",
    prompt: "基于这张肖像和旁白音频生成一段 720p 数字人视频，并使用主体 mask 保持人物边界稳定。"
)

client := runapi.NewClient(os.Getenv("RUNAPI_API_KEY"))
task, err := client.subjectDetection.Run({"model":"omnihuman-1.5-subject-detection","prompt":"基于这张肖像和旁白音频生成一段 720p 数字人视频，并使用主体 mask 保持人物边界稳定。"})
if err != nil { log.Fatal(err) }
task.Wait()

$ runapi generate \
    --model omnihuman-1.5-subject-detection \
    --endpoint subject_detection \
    --wait