od Google
Gemini Omni 1.1 Reference-to-Video (Google)
Google Gemini Omni 1.1 Flash direct — identity/style-anchored video from up to 3 reference images
google-omni-1.1-ref2vGenerate video with this model.
/api/v1/videos/generationsGET /api/v1/videos/generations{
"model": "google-omni-1.1-ref2v",
"prompt": "A cinematic drone shot over a coastal city at sunset",
"duration": 3,
"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":"google-omni-1.1-ref2v","prompt":"A cinematic drone shot over a coastal city at sunset","duration":3,"resolution":"720p","image_url":"https://example.com/start-frame.jpg"}'Google Gemini Omni 1.1 Flash direct — native audio + dialogue, 360p–4K, 3–10s, stateful multi-turn edits
Dokumentacja APIGoogle Veo 3.1 — image-to-cinema (up to 8s, 1080p); native audio always on
Dokumentacja APIFAL AI (Kling)
Kling V3 Pro — cinematic text-to-video with multi-shot and native audio (3-15s, 1080p)
Dokumentacja APIFAL AI (Seedance)
ByteDance Seedance 2.0 via FAL — cinematic T2V with native audio, up to 15s at 1080p
Dokumentacja API