Limitations:
Omni provides 10-second video generations at present, with longer durations coming quickly.Importing audio references and scene extension isn’t but supported within the Gemini API for this mannequin.Video references as much as 3 seconds in length are accepted by the API schema however aren’t accurately processed by the mannequin presently.Character consistency when altering scenes or panning actions has some limitations however we’re working to make this higher.
Gemini Omni is accessible in public preview beginning right now in Google AI Studio and the Gemini API. To see the complete listing of mannequin capabilities and regional particular limitations try the developer docs.
Construct with each fashions right now
The true magic occurs once you chain these fashions collectively. Use Nano Banana 2 Lite as a high-speed picture era mannequin, then go that picture as a reference to Gemini Omni Flash to animate it right into a high-quality video. Plus, through the use of the Interactions API for these multi-turn experiences, you possibly can keep session historical past and context so customers can stack as much as three sequential edits.
That can assist you get began we created just a few demo apps you possibly can remix that allow you to expertise how one can pair each Nano Banana 2 Lite and Gemini Omni Flash into one workflow.
