Google recently took the wraps off the Nano Banana Pro (Gemini 3 Pro Image), its improved image generation and editing model built on the Gemini 3 Pro that promises to “transform your vision into studio-quality designs with unprecedented control, flawless text rendering, and advanced world knowledge.” It’s a step up from the surreal 3D sculptures that caused the original image model to go viral in September shortly after launch.
The best part is that starting today it’s free to try globally by selecting “Create Image” with the “Thinking” model inside the Gemini app.
Google says Nano Banana Pro can help create context-rich infographics and diagrams that can help visualize real-time information like weather or sports. And its ability to render legible text directly onto an image – as a short tagline or a long paragraph – makes it suitable for producing posters or invitations in a variety of language translations. It also supports blending multiple elements into a single composition, using up to 14 images and up to five people.
And because it excels at model editing, the Nano Banana Pro also promises new advanced creative controls. Thus, you can select any part of the image and edit it locally, adjust the camera angle, add Bokeh, change the focus, color grade, or change the lighting from day to night. Resolutions up to 4K are supported in a variety of aspect ratios.
Specifically, images created or edited with Nano Banana Pro models will have C2PA metadata embedded. Once the industry unifies, it should eventually become easier to spot generative AI or deepfakes in search results and social media feeds. TikTok said this week it would also use C2PA metadata to invisibly watermark AI-generated content.
Users of the free Nano Banana Pro tier will be limited to a quota, which is extended to Google AI Plus, Pro, and Ultra customers. It’s also available for AI mode in Search in the US if you subscribe to Google AI Pro or Ultra, or for users of NotebookLM Research Assistant globally.