av FAL AI (Kling)
Kling O3 Pro Image-to-Video (FAL)
Kling O3 Pro — best-in-class image-to-video with element referencing (3-15s, 1080p)
fal-kling-o3-i2vGenerate video with this model.
/api/v1/videos/generationsGET /api/v1/videos/generations{
"model": "fal-kling-o3-i2v",
"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-kling-o3-i2v","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 4K)
Kling V3 Native 4K — professional-grade 4K video from images (3-15s)
API-dokumentationFAL AI (Minimax)
Narrative-coherent video (fixed 6s clips; use scene chaining for longer)
API-dokumentationKunya (Seedance)
ByteDance Seedance 2.0 Mini — lowest-cost image-to-video for drafts and batch tests, synchronized audio
API-dokumentationKunya (Seedance)
ByteDance Seedance 2.5 — first/last frame image-driven video with synchronized audio, up to 30s
API-dokumentation