Google’s Nano Banana Pro is available on the Gemini app and website.
Google has made Nano Banana Pro available to those on the free tier
Photo Credit: Google
Google released Nano Banana Pro on Thursday. Also known as Gemini 3 Pro Image, it is an artificial intelligence (AI) tool that excels in prompt-based image generation and editing. It comes with several improvements, such as better text rendering, higher output quality, improved contextual reasoning, increased image input capacity, and more. The Mountain View-based tech giant has rolled the tool globally to all users; however, it can be tricky to find where it is and how to use it, or even what to do with it. Here we have shared the details.
Nano Banana Pro is available inside the Gemini app and in Google's developer tools. To use it in the app, open “Create images” and choose “Thinking” from the model menu, which switches you from the standard Nano Banana to the Pro model. From there, you can either type a text prompt or upload one or more reference images to edit or composite. The same Pro model is exposed to developers through the Gemini API/Vertex AI and via Google AI Studio for experimentation and integration.
For the ease of readers, here is a step-by-step guide:
Nano Banana Pro is the second generation of Google's new image generation and editing tool that is capable of making granular changes to an image without impacting the rest of the elements. The first version was powered by the Gemini 2.5 Pro model, while this version benefits from the capabilities of the more advanced Gemini 3 Pro.
Nano Banana Pro brings a set of straightforward upgrades to Google's image-generation lineup. The model now lets users combine up to 14 images in a single prompt and keep the appearance of up to five people consistent across outputs. Editing is more flexible too, and you can target specific areas of an image, shift the camera angle, change focus, or adjust lighting, including flipping a scene from day to night. The system also supports higher-resolution results, up to 2K and 4K.
Text rendering gets an update as well. The model is now able to handle longer passages and a wider range of fonts and languages, which broadens its use for posters, diagrams and other text-heavy visuals. Additionally, every image carries an invisible SynthID marker, and most users will also see a visible watermark unless they're on the Ultra tier or an enterprise client.
Get your daily dose of tech news, reviews, and insights, in under 80 characters on Gadgets 360 Turbo. Connect with fellow tech lovers on our Forum. Follow us on X, Facebook, WhatsApp, Threads and Google News for instant updates. Catch all the action on our YouTube channel.