av OpenRouter (Black Forest Labs)
FLUX.3 Video Reference-to-Video
Black Forest Labs FLUX.3 — generate video guided by reference images (5–20s)
flux-3-video-ref2vGenerate video with this model.
/api/v1/videos/generationsGET /api/v1/videos/generations{
"model": "flux-3-video-ref2v",
"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":"flux-3-video-ref2v","prompt":"A cinematic drone shot over a coastal city at sunset","duration":5,"resolution":"720p","image_url":"https://example.com/start-frame.jpg"}'OpenRouter (HeyGen)
Expressive talking-head from a single photo — lip-sync to your script (HeyGen TTS) or audio track, up to 1080p, emotion-aware motion
API-dokumentationOpenRouter (Black Forest Labs)
Black Forest Labs FLUX — natural-language video editing via prompt (≤15s, 720p)
API-dokumentationKunya (Wan)
Alibaba Wan 2.7 — instruction-based video editing with up to 4 reference images
API-dokumentation