Alla modellervideoGoogle Veo 3.1 Reference-to-Video (FAL)

Google Veo 3.1 Reference-to-Video (FAL)

Name: Google Veo 3.1 Reference-to-Video (FAL)
Availability: InStock
Author: FAL AI (Google Veo)

av FAL AI (Google Veo)

Testa på Kunya

video

Veo 3.1 ref2v via FAL — up to 3 reference images, optional silent output

Modell-ID:fal-veo-3.1-ref2v

API-dokumentation

Generate video with this model.

POST/api/v1/videos/generations

GET /api/v1/videos/generations

Request body

{
  "model": "fal-veo-3.1-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-exempel

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-veo-3.1-ref2v","prompt":"A cinematic drone shot over a coastal city at sunset","duration":5,"resolution":"720p","image_url":"https://example.com/start-frame.jpg"}'

Anteckningar

•Video generation is asynchronous — poll `GET /api/v1/videos/status?task_id=...` until complete.
•Supported resolutions: 720p, 1080p.
•Pass `image_url` for image-to-video generation.
•Max duration: 8s (may vary by resolution).

Fullständig API-referens OpenAPI-spec