od Kunya (HappyHorse)
Happy Horse 1.1 Reference-to-Video
Alibaba Happy Horse 1.1 — 1–9 ordered reference images (character1, character2, …), 3–15s
evolink-happyhorse11-ref2vGenerate video with this model.
/api/v1/videos/generationsGET /api/v1/videos/generations{
"model": "evolink-happyhorse11-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":"evolink-happyhorse11-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 (Kling 4)
Kling 4.0 — edit a source clip with prompt + optional reference images; duration auto or 3–30s
Dokumentacja APIGoogle (Omni)
Google Gemini Omni Flash — identity-anchored video from reference images
Dokumentacja APIMiniMax
Hailuo H3 Max — fal-optimized fast text-to-video at 480P/768P (5–15s), ~35× faster than standard H3
Dokumentacja APIGoogle Veo 3.1 — generate video from up to 3 reference images (up to 8s, 1080p)
Dokumentacja API