OmniHuman
OmniHuman-Modelle werden über eine einheitliche, asynchrone Job-API aufgerufen. Starte einen Task mit POST /api/generate und frage dann GET /api/generate/{taskId} ab, bis er fertig ist. Diese Familie stellt 3 Endpunkte bereit.
Überblick
Jeder Endpunkt teilt sich dieselbe Hülle — nur model und die input-Felder ändern sich. Führe einen beliebigen im Playground des Modell-Markts aus.
Authentifizierung
Erstelle einen API-Schlüssel unter /api-keys und sende ihn als Bearer-Token. Anfragen aus dem Browser bei angemeldeter Sitzung funktionieren auch über das Session-Cookie.
Authorization: Bearer <YOUR_API_KEY>Task erstellen
POST https://api.lithovas.com/api/generateBody: { "model": "<slug>", "input": { … } }
Antwort: { "taskId": "<id>", "state": "waiting" }
Ergebnis abfragen
GET https://api.lithovas.com/api/generate/<taskId>Antwort: { "taskId", "state": "waiting" | "success" | "fail", "resultUrls": [ … ], "creditsConsumed", "failMsg", "balance" }
state zu success oder fail wird. Fehlgeschlagene Tasks werden nicht berechnet.Endpunkte
| Modell | 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_urlstringerforderlichPortrait image URL; any aspect ratio (people, pets, anime, etc.)
mask_urlarray<string>optionalOptional mask image URLs (max 5) for subject detection
audio_urlstringerforderlichAudio 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_urlstringerforderlichPortrait 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_urlstringerforderlichPortrait 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"
}
}'