Google's Nano Banana Pro Delivers Unprecedented Accuracy in Text and Infographic Generation

Google has officially launched Nano Banana Pro, its latest state-of-the-art image generation and editing model, promising significant advancements in instruction following and text fidelity. The new model, built on the Gemini 3 Pro Image foundation, was introduced on November 20, 2025, and is designed to create high-fidelity visuals, including complex infographics with accurate spelling and properly rendered text. This release positions Nano Banana Pro as a leading tool for both casual creators and professionals, integrating sophisticated AI capabilities across Google's ecosystem.

Prominent technologist Simon Willison lauded the new model, stating in a recent tweet, > "Nano Banana Pro, released this morning, is clearly the best image generation model. Superb instruction following, plus it can generate full infographics (with correct spelling and properly rendered text!) from a short prompt based on running extra searches." This highlights the model's ability to not only follow complex instructions but also to integrate web search capabilities for factually accurate content creation. The model's enhanced reasoning features allow it to connect to Google Search's vast knowledge base, enabling the generation of context-rich educational explainers and diagrams.

A core improvement in Nano Banana Pro is its superior handling of text within images. Google DeepMind product manager Naina Raisinghani emphasized that it is "the best model for creating images with correctly rendered and legible text directly in the image, whether you’re looking for a short tagline, or a long paragraph," according to SiliconANGLE. This capability extends to multilingual text generation, making it ideal for international content and marketing campaigns. Users can also exercise fine control over aspects like camera angles, lighting, and color grading, alongside the ability to output images in specific aspect ratios.

Nano Banana Pro is being rolled out across numerous Google platforms, including the Gemini app, Google Ads, Google AI Studio, and Google Slides. While free users will have limited access, Google AI Plus, Pro, and Ultra subscribers will benefit from higher generation thresholds and additional features, such as access within NotebookLM and the Flow AI filmmaking tool. To maintain transparency, all images generated by the model include an invisible SynthID watermark, and a new feature in the Gemini app allows users to verify if an image was created by Google AI.

This release comes months after OpenAI's gpt-image-1, signaling an intensifying competition in the AI image generation space, particularly in areas like text and educational content. Nano Banana Pro's multi-turn editing allows for iterative refinement, enabling users to add or remove elements and transfer styles between images. Its integration into developer tools like the Gemini API and Antigravity IDE further underscores Google's commitment to making advanced AI imaging widely accessible for diverse applications, from design mock-ups to automated creative pipelines.