5h ago

Google DeepMind's Omni applies photorealistic AR transformations to arbitrary video footage as an on-demand filter rather than a conventional video generator

Demonstrations turn a hand and arm into metallic robotic limbs with matching reflections.

——0——
Original post
OPBilawal Sidhu#1909Bilawal Sidhu@BILAWALSIDHU

Omni is pretty nuts. It is NOT seedance. Any input in/out. It’s more than nano banana for video - it’s quite literally industrial light & magic. Now effectively reduced to an insanely realistic AR filter that you can apply on demand to anyone’s footage.

8:20 PM · May 20, 2026 View on X
QUOTE POSTAlex Volkov#1245Alex Volkov@ALTRYNE

Omni isn't Veo/Seddance!

I had the awesome pleasure to have breakfast with @JeffDean during #googleio and ask him about Omni and how it differs from "video models" in the classic sense like Veo, Seedance and HappyHorse

Huge thanks to the deepmind team for the invite!

Bilawal SidhuBilawal Sidhu@bilawalsidhu

Omni is pretty nuts. It is NOT seedance. Any input in/out. It’s more than nano banana for video - it’s quite literally industrial light & magic. Now effectively reduced to an insanely realistic AR filter that you can apply on demand to anyone’s footage.

3:20 AM · May 21, 2026 · 16.3K Views
4:17 AM · May 21, 2026 · 13.5K Views
Google DeepMind's Omni applies photorealistic AR transformations to arbitrary video footage as an on-demand filter rather than a conventional video generator · Digg