模型市场支持← 返回应用

OmniHuman

OmniHuman 模型通过一个统一的异步任务 API 调用。用 POST /api/generate 发起任务，再轮询 GET /api/generate/{taskId} 直到完成。本系列提供 3 个端点。

概览

每个端点共享相同的外层结构 —— 只有 model 和 input 字段不同。可在模型市场的 playground 中运行任意一个。

认证

在 /api-keys 创建 API 密钥，然后作为 Bearer token 发送。已登录时从浏览器发起的请求也可通过会话 cookie 生效。

Authorization: Bearer <YOUR_API_KEY>

创建任务

POST
POST https://api.lithovas.com/api/generate

请求体：{ "model": "<slug>", "input": { … } }

响应：{ "taskId": "<id>", "state": "waiting" }

查询结果

GET
GET https://api.lithovas.com/api/generate/<taskId>

响应：{ "taskId", "state": "waiting" | "success" | "fail", "resultUrls": [ … ], "creditsConsumed", "failMsg", "balance" }

异步
创建任务返回 200 只表示任务已被接受 —— 并非已完成。请轮询此端点，直到 state 变为 success 或 fail。失败任务不计费。

端点

模型任务model slug
OmniHuman 1.5Lip Syncomnihuman-1-5
OmniHuman 1.5Lip Syncomnihuman-1-5/human-identification
OmniHuman 1.5Lip Syncomnihuman-1-5/subject-detection

OmniHuman 1.5 · Lip Sync

POSTLip Syncomnihuman-1-5
input 字段
image_urlstring必填

Portrait image URL; any aspect ratio (people, pets, anime, etc.)

mask_urlarray<string>可选

Optional mask image URLs (max 5) for subject detection

audio_urlstring必填

Audio URL; duration must be less than 60 seconds

promptstring可选

Optional text prompt (max 1000 chars); multi-language

output_resolutionenum<string>可选

Output video resolution in pixels

pe_fast_modeboolean可选

Sacrifices some quality to speed up generation

seedinteger可选

Random seed; same positive integer gives consistent results

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "omnihuman-1-5",
  "input": {
    "image_url": "https://example.com/input.jpg",
    "mask_url": [
      "https://example.com/file"
    ],
    "audio_url": "https://example.com/reference.mp3",
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "output_resolution": "1080",
    "pe_fast_mode": false,
    "seed": -1
  }
}'

OmniHuman 1.5 · Lip Sync

POSTLip Syncomnihuman-1-5/human-identification
input 字段
image_urlstring必填

Portrait image URL; JPG/PNG/JPEG, <5MB, resolution under 4096x4096

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "omnihuman-1-5/human-identification",
  "input": {
    "image_url": "https://example.com/input.jpg"
  }
}'

OmniHuman 1.5 · Lip Sync

POSTLip Syncomnihuman-1-5/subject-detection
input 字段
image_urlstring必填

Portrait image URL; supports detection of up to 5 subjects

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "omnihuman-1-5/subject-detection",
  "input": {
    "image_url": "https://example.com/input.jpg"
  }
}'