av Kunya (Kling)
Kling O3 Reference-to-Video
Kling O3 — style/motion transfer from a reference clip (+ optional still refs). Requires referenceVideoUrls; use kling-o3-i2v for cast stills (3-10s)
kling-o3-ref2vGenerate video with this model.
/api/v1/videos/generationsGET /api/v1/videos/generations{
"model": "kling-o3-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":"kling-o3-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 1.5 — synchronized audio+video generation with lip-sync and foley (up to 12s)
API-dokumentationKunya (Wan)
Alibaba Wan 2.7 — instruction-based video editing with up to 4 reference images
API-dokumentationFAL AI (Wan)
Wan 2.2 motion transfer — replicate expressions and movements from a reference video onto a character image
API-dokumentationFAL AI (Kling 4K)
Kling O3 4K — reference-to-video with @Element character locking at native 4K. Up to 7 refs (3-15s)
API-dokumentation