MOUNTAIN VIEW, CA – Google announced today the official launch of Nano Banana Pro, its new flagship AI image generation and editing model. The advanced tool, powered by the recently unveiled Gemini 3 Pro, is designed to provide creators, professionals, and enterprise customers with a higher degree of control, resolution, and accuracy in visual content creation. The new model begins its global rollout today across various Google platforms.
Nano Banana Pro introduces a suite of significant upgrades over its predecessor, which gained viral popularity. According to Google, the new model leverages the state-of-the-art reasoning and real-world knowledge of Gemini 3 Pro to deliver studio-quality results. Key enhancements include the ability to generate images at up to 4K resolution, a substantial improvement in rendering legible text in multiple languages, and maintaining the consistency of up to five characters across different images.
“Nano Banana Pro excels in visual design, world knowledge, and text generation,” a Google spokesperson stated in a Google Cloud Blog post. The company emphasized its ability to help create “more accurate, context-rich visual assets” by connecting to Google Search for real-world context. This allows for the generation of precise diagrams, maps, and infographics. For instance, internal testers have successfully used the tool to convert resumes and code snippets into polished infographics.
The new model also offers advanced creative controls, allowing users to adjust camera angles, lighting, focus, and color grading. A notable feature is the ability to blend up to 14 reference images, such as logos, color palettes, and product shots, into a single composition to ensure brand fidelity. In a move aimed at professional creators, Google is also offering its highest-tier “AI Ultra” subscribers the option to remove the AI watermark from generated images.
The rollout of Nano Banana Pro will be tiered. While a version is available to free users of the Gemini app with a limited number of generations, subscribers to Google AI Plus, Pro, and Ultra will receive higher usage limits. The model is also being integrated into Google Workspace applications, including Slides and Vids, and is available for developers through Vertex AI and the Gemini API. The launch signals Google’s move to compete more aggressively in the professional AI image generation space, targeting creators, agencies, and commercial workflows.