All ModelsvideoGemini Omni 1.2 Reference-to-Video (Google)

Gemini Omni 1.2 Reference-to-Video (Google)

Name: Gemini Omni 1.2 Reference-to-Video (Google)
Availability: InStock
Author: Google (Omni direct)

by Google (Omni direct)

Try on Kunya

video

Google Gemini Omni 1.2 Flash direct — identity/style-anchored video from up to 3 reference images

Model ID:google-omni-1.2-ref2v

API Documentation

Generate video with this model.

POST/api/v1/videos/generations

GET /api/v1/videos/generations

Request body

{
  "model": "google-omni-1.2-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 example

curl -X POST https://kunya.ai/api/v1/videos/generations \
  -H "Authorization: Bearer kunya_YOUR_API_KEY" \
  -H "Content-Type: application/json"
  -d '{"model":"google-omni-1.2-ref2v","prompt":"A cinematic drone shot over a coastal city at sunset","duration":3,"resolution":"720p","image_url":"https://example.com/start-frame.jpg"}'

Notes

•Video generation is asynchronous — poll `GET /api/v1/videos/status?task_id=...` until complete.
•Supported resolutions: 720p, 1080p, 4k.
•Pass `image_url` for image-to-video generation.
•Max duration: 15s (may vary by resolution).

Full API reference OpenAPI spec