Google is also making the model available globally to AI Plus, Pro and Ultra subscribers through Google Flow.
Google is rolling out the model across its AI platforms
Photo Credit: Google
Google has unveiled Gemini Omni 1.1 Flash, an updated generative AI model that adds new video creation and editing capabilities. The model can extend existing scenes, generate footage between specified first and last frames, use short video references and produce videos at up to 4K resolution. Google also added a 360p mode for faster, cheaper drafts. Gemini Omni 1.1 Flash is rolling out through Google's developer platforms and is also available to subscribers through Google Flow and the Gemini app.
Gemini Omni 1.1 Flash can now analyse up to 10 seconds of preceding footage when extending an existing video, the company said in a blog post. Earlier versions could use only the final second of a clip for this purpose. Developers can add footage in 10-second increments, with extensions supporting a cumulative duration of up to 40 seconds. This gives creators more scope to continue an existing sequence while keeping its visual and narrative elements consistent.
Developers can also define the beginning and end of a shot and have the model generate the footage needed to connect the two frames. The feature supports complex movements such as camera orbits and zooms, along with transitions that can be used to create continuous or looping footage.
The model accepts up to three seconds of video as a reference for a new generation. This can help carry over details such as character appearance and the visual setting from the reference material. Google has shown the capability being used with multiple reference clips to recreate different movements within one continuous video.
Gemini Omni 1.1 Flash also introduces a 360p option for developers who want to test ideas before generating higher-resolution footage. Google says these lower-resolution drafts can be created up to 60 percent faster than 720p versions and cost one-third as much. The mode is aimed at tasks such as rapid prototyping and storyboard development.
After a sequence has been finalised, developers can generate it at 1080p or 4K resolution for higher-quality output.
Developers can use Gemini Omni 1.1 Flash through the Gemini API in Google AI Studio, while enterprise users can build with it via the Agent Platform API. Google has also published documentation, a cookbook and prompting guides for the new video-generation tools.
Google is also making the model available globally to AI Plus, Pro and Ultra subscribers through Google Flow, with scene extension also available to these subscribers in the Gemini app.
The company said Gemini Omni Flash is already being integrated into video workflows by Adobe, Figma Weave, GMI Cloud and Runway.
Get your daily dose of tech news, reviews, and insights, in under 80 characters on Gadgets 360 Turbo. Connect with fellow tech lovers on our Forum. Follow us on X, Facebook, WhatsApp, Threads and Google News for instant updates. Catch all the action on our YouTube channel.