Google expands AI portfolio with Nano Banana 2 Lite and Gemini Omni Flash

Nano Banana 2 Lite focuses on speed, functioning as a cost-effective image generator for users of the original Nano Banana architecture. Google claims the model can render images within four seconds of receiving a text prompt, positioning it as a primary tool for rapid prototyping. It is currently accessible via the Gemini API, the Gemini app, and the AI Mode integration within Google Search.

Gemini Omni Flash arrives as a public preview, introducing capabilities for video generation and editing. Users can provide text, video, or natural language instructions to manipulate clips, though the tool remains in a nascent stage. Current limitations restrict video output to 10 seconds, and the company acknowledges that maintaining character consistency across scene transitions remains a technical challenge for the system. Interested developers can experiment with the model through the Gemini API and Google Flow.