Google launched its new state-of-the-art image generation and editing model—the Nano Banana Pro. The editing model is based on the latest Gemini 3 Pro, which uses enhanced reasoning and real-world knowledge to visualise information better.

What can Nano Banana Pro do?

The previous model, the Nano Banana, which was the Gemini 2.5 Flash Image model, was able to generate pictures, restore old images and create mini figurines. 

The latest model is now capable of creating accurate educational explainers to learn more about a new subject, like context-rich infographics and diagrams based on the content one provides or facts from the real world.

Nano Banana Pro can also connect to Google Search's vast knowledge base. This means one can create a snapshot of searches and also visualise real-time information like weather or sports.

Nano Banana Pro’s massive update, according to Google, is creating images with correctly rendered and legible text directly in the image, regardless of text length. Therefore, it is now possible to create more detailed text in mockups or posters with a wider variety of textures, fonts and calligraphy. As Gemini is equipped with enhanced multilingual reasoning, images with texts can be created in multiple languages or localised and translated the content to scale internationally and share content more easily. 

Google, in its blog, says that one can now blend more elements—up to 14 images and maintain the consistency and resemblance of up to 5 people. The Pro version is also equipped to select, refine and transform any part of an image with improved localised editing. One can adjust camera angles, change the focus and apply sophisticated colour grading, or even transform scene lighting. 

How to identify AI-generated images in the Gemini app?

All media generated by Google’s tools are embedded with our imperceptible SynthID digital watermark. One can upload an image into the Gemini app and simply ask if it was generated by Google AI. “ We are starting with images, but will expand to audio and video soon,” the blog read. 

In addition to SynthID, a visible watermark (the Gemini sparkle) is on images generated by free and Google AI Pro tier users, to make images even easier to detect as Google AI-generated. Yet, Google has also provided the option to remove the visible watermark from images generated by Google AI Ultra subscribers and within the Google AI Studio developer tool.

Is Nano Banana Pro free to use? Who all can access it?

The model has been rolling out globally in the Gemini app when you select ‘Create images’ with the ‘Thinking’ model. The free-tier users will receive limited free quotas, after which they will revert to the original Nano Banana model. Google AI Plus, Pro and Ultra subscribers receive higher quotas. For AI Mode in Search, Nano Banana Pro is available in the U.S. for Google AI Pro and Ultra subscribers. For NotebookLM, Nano Banana Pro is also available for subscribers globally. Filmmakers and marketers who use Flow, the AI filmmaking tool, will get access if they are Google AI Ultra subscribers. 

What are Nano Banana Pro’s limitations?

In another blog, Google clarifies that while the new model is an upgrade from the previous generation, there are still areas in need of improvement:

Visual and text fidelity: Rendering small text, fine details, and producing accurate spellings may not work perfectly.

Data and factual accuracy: Always verify the factual accuracy of data-driven visuals like diagrams and infographics.

Translation and localisation: Multilingual text generation may make grammar mistakes or miss specific cultural nuances.

Complex edits and image blending: Advanced editing tasks like blending or lighting changes can sometimes produce unnatural artefacts.

Character features: While usually reliable, character consistency across edits may vary.