Google just unveiled its Nano Banana Pro image generation platform, which is also going by the name Gemini 3 Pro Image. The company promises this is an improvement over previous versions of the software in nearly every way. Google says it will “turn your visions into studio-quality designs with unprecedented control, flawless text rendering and enhanced world knowledge.”
The text rendering portion seems to have gotten a big upgrade here, as Nano Banana Pro can create context-rich infographics and diagrams. The software can render legible text on top of a pre-existing image, making it a good option for generating posters and stuff like that. Google says that this feature is available in multiple languages.
Google also says it can blend multiple elements into a single composition, with the ability to use up to 14 images at once. There are plenty of new editing controls. Users can select and edit any part of a created image. This can be used to adjust camera angles, change focus, adjust the color grade and even swap out the lighting from day to night.
Images created with Nano Banana Pro will have C2PA metadata embedded. This should, in time, make it easier to spot generative AI or deepfakes out there in the world. We’ll have to see how that plays out. TikTok recently announced it would be using this metadata to better label AI-generated content, of which it currently does a very bad job at.
Nano Banana Pro is actually free to use. Free users are limited to a daily quota of images, with the number expanding for Google AI, Plus, Pro and Ultra subscribers. Just open up the Gemini app and create an image, but be sure to use the “Thinking” model. It’s also available in Search and NotebookLM for some subscribers. This is all part of the recently-launched Gemini 3 model.
