Google has announced its new image generation model, dubbed Nano Banana 2 Lite. The tech giant says Nano Banana 2 Lite is its fastest and most cost-efficient Gemini image model yet. It is designed for developers who need to create large numbers of images quickly while keeping costs low. Alongside the new image model, Google is also rolling out Gemini Omni Flash, its AI model for video generation and editing, for developers.
According to Google, Nano Banana 2 Lite is built for “high throughput, speed and scale.” The company says the model can generate images from text prompts in about four seconds. Google also says Nano Banana 2 Lite is the recommended replacement for the original Nano Banana image model.
Also read: Anthropic Claude Sonnet 5 is here: Key capabilities, availability and other details
“Despite prioritising speed, Nano Banana 2 Lite retains reliable prompt adherence, strong character consistency and legible in-image text rendering,” the tech giant explained in a blogpost.
The company has made Nano Banana 2 Lite available through Google AI Studio, the Gemini API and the Gemini Enterprise Agent Platform. It is also rolling out on Gemini app, AI Mode in Search, NotebookLM, Google Photos, Stitch, Google Flow and Google Ads.
Also read: Microsoft layoffs: Thousands from Xbox and other teams may lose their jobs
Google has also announced that Gemini Omni Flash is now rolling out to developers through Google AI Studio and the Gemini API. The model was first introduced at Google I/O. As per the tech giant, Omni Flash lets users edit videos using natural language. It can also combine text, images and video inputs to create more consistent results. Omni Flash uses Gemini’s knowledge to generate more meaningful videos.
However, Google says the model still has some limitations. It currently supports video generation of up to 10 seconds. Audio reference uploads and scene extension are not available through the Gemini API. Video references longer than three seconds are also not fully supported.
Google says the two new AI models are designed to make creative workflows faster. The company believes developers can use them together to quickly generate images and then turn those visuals into AI-generated videos with less effort.
Also read: Did Samsung tease Galaxy Z Fold 8 on social media? Here is what we know
“The real magic happens when you chain these models together. Use Nano Banana 2 Lite as a high-speed image generation model, then pass that image as a reference to Gemini Omni Flash to animate it into a high-quality video,” the tech giant said.