Google Releases Gemini Omni Flash 1.2 Video Model With Native Audio

At a glance

Google has released Gemini Omni Flash 1.2, a new version of its video model. It creates clips with built-in sound and can extend an existing video. Higgsfield has made the model available on its own platform.

Key points

1. 1

   You can make videos from text, images, or video.

2. 2

   Each generation runs 3 to 15 seconds, at resolutions from 360p up to 4K.

3. 3

   You can use up to 6 reference images and up to 3 short reference videos.

4. 4

   You can extend a video from its end in 3 to 10 second steps, up to 30 seconds total.

Why it matters

Creating short videos with sound is now easier, since the model makes audio along with the picture.