od Kunya (HappyHorse)
Happy Horse 1.0 Text-to-Video
Alibaba Happy Horse 1.0 — native audio + lip-sync, 3–15s (legacy; see 1.1 for silent motion)
evolink-happyhorse-t2vGenerate video with this model.
/api/v1/videos/generationsGET /api/v1/videos/generations{
"model": "evolink-happyhorse-t2v",
"prompt": "A cinematic drone shot over a coastal city at sunset",
"duration": 3,
"resolution": "720p"
}curl -X POST https://kunya.ai/api/v1/videos/generations \
-H "Authorization: Bearer kunya_YOUR_API_KEY" \
-H "Content-Type: application/json"
-d '{"model":"evolink-happyhorse-t2v","prompt":"A cinematic drone shot over a coastal city at sunset","duration":3,"resolution":"720p"}'Google (Omni)
Google Gemini Omni Flash — identity-anchored video from reference images
Dokumentacja APIKunya (Kling)
Kling O1 — natural-language video editing with reference image support
Dokumentacja APIKling Direct
Kling V3 Standard via direct API — 720p text-to-video (5/10/15s)
Dokumentacja APIFAL AI (Kling)
Kling O3 Standard — generate the next shot from a reference video (3-15s, 720p)
Dokumentacja API