od FAL AI (Kling 4)
Kling 4.0 Reference-to-Video (FAL)
Kling 4.0 on FAL — @Image/@Video/@Element refs (3–30s)
fal-kling-v4-ref2vGenerate video with this model.
/api/v1/videos/generationsGET /api/v1/videos/generations{
"model": "fal-kling-v4-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":"fal-kling-v4-ref2v","prompt":"A cinematic drone shot over a coastal city at sunset","duration":3,"resolution":"720p","image_url":"https://example.com/start-frame.jpg"}'Kunya (Seedance)
ByteDance Seedance 2.5 — multimodal @-reference: up to 30 images + 10 videos + 10 audio tracks
Dokumentacja APIGoogle (Omni)
Google Gemini Omni Flash — natural-language video editing (conversational refine)
Dokumentacja API