OmniHuman
OmniHuman models are called through one unified, asynchronous job API. Start a task with POST /api/generate, then poll GET /api/generate/{taskId} until it finishes. This family exposes 3 endpoints.
Overview
Every endpoint shares the same envelope — only model and the input fields change. Run any from the Models Market playground.
Authentication
Create an API key at /api-keys, then send it as a Bearer token. Requests from the browser while logged in also work via the session cookie.
Authorization: Bearer <YOUR_API_KEY>Create Task
POST https://api.lithovas.com/api/generateBody: { "model": "<slug>", "input": { … } }
Response: { "taskId": "<id>", "state": "waiting" }
Query Result
GET https://api.lithovas.com/api/generate/<taskId>Response: { "taskId", "state": "waiting" | "success" | "fail", "resultUrls": [ … ], "creditsConsumed", "failMsg", "balance" }
state becomes success or fail. Failed tasks are not billed.Endpoints
| Model | Task | model slug |
|---|---|---|
| OmniHuman 1.5 | Lip Sync | omnihuman-1-5 |
| OmniHuman 1.5 | Lip Sync | omnihuman-1-5/human-identification |
| OmniHuman 1.5 | Lip Sync | omnihuman-1-5/subject-detection |
OmniHuman 1.5 · Lip Sync
omnihuman-1-5image_urlstringrequiredPortrait image URL; any aspect ratio (people, pets, anime, etc.)
mask_urlarray<string>optionalOptional mask image URLs (max 5) for subject detection
audio_urlstringrequiredAudio URL; duration must be less than 60 seconds
promptstringoptionalOptional text prompt (max 1000 chars); multi-language
output_resolutionenum<string>optionalOutput video resolution in pixels
pe_fast_modebooleanoptionalSacrifices some quality to speed up generation
seedintegeroptionalRandom seed; same positive integer gives consistent results
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
omnihuman-1-5/human-identificationimage_urlstringrequiredPortrait image URL; JPG/PNG/JPEG, <5MB, resolution under 4096x4096
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
omnihuman-1-5/subject-detectionimage_urlstringrequiredPortrait image URL; supports detection of up to 5 subjects
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"
}
}'