Gemini 3-Powered ‘Nano Banana Pro’ Image Editing Tool Unveiled by Google

Google on Thursday officially unveiled Nano Banana Pro, an advanced image-creation and editing engine that represents a major step forward in the company’s expanding suite of AI tools. The launch closely follows the release of Google’s updated Gemini artificial intelligence model, which significantly boosted investor confidence earlier in the week. Powered by the Gemini 3 Pro system, Nano Banana Pro is designed to offer highly accurate, versatile, and detailed visual output, making it a significant upgrade over previous image-generation models.

The tool is now available within the Gemini app, where users can experiment with a limited number of free image generations. It seamlessly integrates with various Google platforms, including the writing assistant NotebookLM, as well as the company’s wider developer, enterprise, and advertising ecosystems. In addition, Google has reserved access to AI Mode in Google Search for subscribers to the AI Pro and Ultra plans, with Ultra users expected to experience these features first through Flow, Google’s AI-driven video creation platform.

Coinciding with the launch, Google introduced a detection feature within the Gemini app, enabling users to verify whether an image was produced by Google’s AI systems. Crucially, images generated from free Nano Banana Pro accounts will automatically include a watermark, which can only be removed by subscribing to the AI Ultra plan. This feature aims to enhance transparency and traceability in AI-generated content.

Nano Banana Pro’s core purpose is to simplify the transformation of creative ideas into refined, professional visuals. Users can either describe the type of image they want, allowing the system to generate it from scratch, or upload an existing photo for highly specific modifications. According to Google, the model interprets user instructions with improved clarity thanks to the advanced reasoning capabilities of Gemini 3 Pro. When necessary, the system can also pull real-time data from Google Search, including live weather updates or ongoing sports results, to ensure accurate and context-aware image generation.

One of Nano Banana Pro’s standout strengths is its ability to produce clear, readable text within images—a challenging task for many AI models. The tool supports multiple languages and can generate everything from small labels to long text blocks, making it valuable for creating posters, social media graphics, project visuals, and other text-rich designs.

Google further emphasizes the high level of creative control the tool offers. Users can adjust fine visual details such as lighting, angle, depth of field, and background elements. It also allows for selective editing, meaning individual components of an image can be modified without affecting the entire composition. Nano Banana Pro supports up to 4K image quality, which enhances its utility for professional creators, designers, and illustrators.

Another notable capability is its consistency across multiple images. Google states that Nano Banana Pro maintains stable appearances of faces and objects, can blend elements from up to fourteen different sources, and preserve the likeness of as many as five people. This is particularly beneficial for designers working with product catalogues, themed visual campaigns, or sequential concept art.

The tool is widely available through the Gemini app’s image creation feature. Free-tier users receive a small generation quota, while paid subscribers to Google AI Plus, Pro, or Ultra gain expanded usage. It is also accessible via AI Mode in Google Search for US-based Pro and Ultra subscribers and through NotebookLM for users globally.