Google has expanded its Gemini artificial intelligence portfolio with the launch of two new models, Nano Banana 2 Lite and Gemini Omni Flash, aimed at accelerating image and video creation while lowering costs for developers and businesses.
The technology giant said on Tuesday that Nano Banana 2 Lite is its fastest and most cost-efficient image generation model to date, while Gemini Omni Flash has been designed for video generation and conversational editing.
According to Google, Nano Banana 2 Lite can generate text-to-image outputs in around four seconds at a cost of $0.034 per 1,000-resolution image. The model is now available through Google AI Studio, the Gemini API and the Gemini Enterprise Agent Platform.
Google added that the model is also being rolled out across several of its consumer products, including AI Mode in Search, the Gemini app, NotebookLM, Google Photos, Stitch, Google Flow and Google Ads.
Meanwhile, Gemini Omni Flash enables users to generate and edit videos using text, image and video prompts. The service is priced at $0.10 per second of video output and currently supports video clips of up to 10 seconds, with longer durations planned in future updates.
The company said Gemini Omni Flash leverages Gemini’s knowledge across a wide range of subjects, including history and biology, to produce contextually accurate video content.
Google noted that the two models are designed to complement one another. Images created with Nano Banana 2 Lite can be transferred directly into Gemini Omni Flash, where they can be animated into videos.
To demonstrate the combined workflow, the company released three showcase applications named Anywhere, Space Lift and Omni Product Studio.
Both models incorporate Google’s SynthID watermarking technology to help identify AI-generated content and are built on the company’s existing AI infrastructure.
Google also recommended that developers currently using the original Nano Banana model migrate to Nano Banana 2 Lite, which it described as its preferred replacement.
Gemini Omni Flash entered public preview on Tuesday through Google AI Studio and the Gemini API as the company continues to expand its portfolio of generative AI tools for developers, enterprises and consumers.
