Start building with Nano Banana 2 Lite and Gemini Omni Flash

Google has released two new generative AI models, Nano Banana 2 Lite and Gemini Omni Flash, designed to improve the speed and efficiency of multimedia development. Nano Banana 2 Lite is the fastest and most cost-effective image model in the Nano Banana family, capable of generating text-to-image outputs in four seconds. It is intended for high-volume workflows and rapid prototyping, replacing the legacy Nano Banana model with better performance and lower costs.

Gemini Omni Flash is now available for developers to create and edit high-quality videos using natural language. This model supports multimodal inputs, allowing users to combine text, images, and video to generate 10-second clips. It features conversational editing capabilities and integrates Gemini’s reasoning to synchronize text and graphics with video actions. Both models are accessible through Google AI Studio, the Gemini API, and the Gemini Enterprise Agent Platform.

These models are designed to be used together to create end-to-end multimedia experiences. Developers can use Nano Banana 2 Lite to generate images and then pass those images to Gemini Omni Flash to animate them into cinematic video clips. Both models include SynthID watermarking to ensure content transparency and are built on Google’s secure infrastructure. These tools are also rolling out across various consumer products, including the Gemini app, Search, and Google Photos.