od FAL AI (ByteDance)
DreamActor M2.0
ByteDance motion transfer — full body, expressions, lip movement from driving video to any character (humans, animals, cartoons)
dreamactor-v2Generate video with this model.
/api/v1/videos/generationsGET /api/v1/videos/generations{
"model": "dreamactor-v2",
"prompt": "A cinematic drone shot over a coastal city at sunset",
"duration": 5,
"resolution": "720p",
"image_url": "https://example.com/start-frame.jpg"
}curl -X POST https://kunya.ai/api/v1/videos/generations \
-H "Authorization: Bearer kunya_YOUR_API_KEY" \
-H "Content-Type: application/json"
-d '{"model":"dreamactor-v2","prompt":"A cinematic drone shot over a coastal city at sunset","duration":5,"resolution":"720p","image_url":"https://example.com/start-frame.jpg"}'FAL AI (Kling)
Kling O3 Pro — reference-driven text-to-video with character consistency (3-15s, 1080p)
Dokumentacja APIGoogle Veo 3.1 — cinematic video (up to 8s, 1080p); native audio always on
Dokumentacja APIKunya (Seedance)
ByteDance Seedance 2.0 — first/last frame image-driven video with synchronized audio, up to 1080p/4k
Dokumentacja API