av Google (Omni)
Gemini Omni Flash Reference-to-Video
Google Gemini Omni Flash — identity-anchored video from reference images
gemini-omni-flash-ref2vGenerate video with this model.
/api/v1/videos/generationsGET /api/v1/videos/generations{
"model": "gemini-omni-flash-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":"gemini-omni-flash-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 2.0 Mini — lowest-cost text-to-video for rapid iteration, synchronized audio, 4–15s
API-dokumentationKunya (Kling)
Kling O3 — style/motion transfer from a reference clip (+ optional still refs). Requires referenceVideoUrls; use kling-o3-i2v for cast stills (3-10s)
API-dokumentationFAL AI (Kling)
Kling O3 Pro — edit existing videos with element injection and style transfer (3-15s, 1080p)
API-dokumentationFAL AI (Kling 4K)
Kling V3 Native 4K — professional-grade 4K video from text (3-15s)
API-dokumentation