Final yr, Nano Banana introduced Gemini’s intelligence to picture technology and modifying. Since then, it’s helped thousands and thousands of individuals restore previous images, design from sketches and visualize concepts in ways in which weren’t potential earlier than. From the beginning we constructed Gemini to be natively multimodal from the bottom up, and now we’re taking the following step.
We’re introducing Gemini Omni, the place Gemini’s potential to purpose meets the power to create. Omni is our new mannequin that may create something from any enter — beginning with video. With Omni, you possibly can mix photos, audio, video and textual content as enter and generate high-quality movies grounded in Gemini’s real-world information. You may also simply edit your movies by means of dialog.
At the moment, we’re rolling out the primary mannequin within the Omni household: Gemini Omni Flash, to the Gemini app, Google Circulation and YouTube Shorts. In time we are going to assist output modalities like picture and audio. Right here’s a few of what makes Omni particular:
Edit your movies by means of dialog
Gemini Omni offers you a neater method to edit video — with pure language. Each instruction builds on the final. Your characters keep constant, the physics maintain up and the scene remembers what got here earlier than.
Rework the world round you. Change particular issues, or change every little thing. Your video turns into the place to begin for one thing you by no means might have filmed your self.
