od FAL AI (Seedance)
Seedance 2.0 Fast Ref2V (FAL)
ByteDance Seedance 2.0 Fast via FAL — fast multimodal reference, up to 9 images + 3 videos + 3 audio
fal-seedance-2-fast-ref2vGenerate video with this model.
/api/v1/videos/generationsGET /api/v1/videos/generations{
"model": "fal-seedance-2-fast-ref2v",
"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":"fal-seedance-2-fast-ref2v","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 Standard — reference-to-video with @Element character locking + @Image style refs (3-15s, 720p)
Dokumentacja APIFAL AI (Kling)
Kling O3 Pro — best-in-class image-to-video with element referencing (3-15s, 1080p)
Dokumentacja APIxAI
GA Grok video with improved quality and native 1080p — text, image, reference, edit, and extend
Dokumentacja APIGoogle Veo 3.1 — generate video from up to 3 reference images (up to 8s, 1080p)
Dokumentacja API