Google AI Releases Gemini Omni 1.1 Flash: 40-Second Scene Extension, First/Last Frame Control, and 4K Upscaling
Google has launched Gemini Omni 1.1 Flash (gemini-omni-1.1-flash), a manufacturing replace to its native multimodal video era and modifying mannequin. The launch strikes Omni from a succesful generator to a directable one: scene extension now reads as much as 10 seconds of prior context as a substitute of a single ultimate body, first and final frames could be pinned to regulate digicam motion, drafts render in 360p at a 3rd of 720p value, finals upscale to 4K, and video clips could be handed as references for character consistency.
Gemini Omni Flash is constructed on three properties Google distinguishes from prior video fashions: native multimodality (textual content, picture, audio, and video processed collectively), conversational modifying by way of the Interactions API, and world information inherited from Gemini. Editing is stateful — you go previous_interaction_id and the mannequin applies your change whereas preserving what you didn’t point out, with out re-uploading the prior video.
Is it deployable?
It is out there by way of the Gemini API in Google AI Studio and the Gemini Enterprise Agent Platform, with Adobe, Figma Weave, GMI Cloud, and Runway already named as manufacturing customers.
