Start building with Nano Banana 2 Lite and Gemini Omni Flash

Google has released two new generative media models, Nano Banana 2 Lite and Gemini Omni Flash, to help developers build and scale multimedia applications. Nano Banana 2 Lite is the fastest and most cost-efficient image model in the Nano Banana family, designed for high-volume workflows and rapid prototyping. It delivers text-to-image outputs in approximately four seconds at a cost of $0.034 per 1,000 images, making it a practical replacement for the legacy Nano Banana model.

Gemini Omni Flash is now available for developers to create and edit videos using natural language, text, images, and video inputs. Priced at $0.10 per second of video output, the model supports conversational video editing and uses Gemini’s multimodal reasoning to synchronize text and graphics with video actions. While it currently supports 10-second video generations, it provides a new tool for developers to build complex, end-to-end creative experiences.

These models are designed to work together, allowing developers to chain high-speed image generation with video animation. By using these tools, creators can build interactive applications that transform static images into cinematic clips or animated sequences. Both models are integrated into Google AI Studio and the Gemini API, and they include SynthID watermarking to ensure transparency and content verification across Google’s platforms.