Now with actual words

Google’s new image-generator model is available to try globally today.

Credit: Google

Google’s meme-friendly Nano Banana image-generation model is getting an upgrade. The new Nano Banana Pro is rolling out with improved reasoning and instruction following, giving users the ability to create more accurate images with legible text and make precise edits to existing images. It’s available to everyone in the Gemini app, but free users will find themselves up against the usage limits pretty quickly.

Nano Banana Pro is part of the newly launched Gemini 3 Pro—it’s actually called Gemini 3 Pro Image in the same way the original is Gemini 2.5 Flash Image, but Google is sticking with the meme-y name. You can access it by selecting Gemini 3 Pro and then turning on the “Create images” option.

Nano Banana Pro: Your new creative partner.

Google says the new model can follow complex prompts to create more accurate images. The model is apparently so capable it can generate an entire usable infographic in a single shot with no weird AI squiggles in place of words. Nano Banana Pro is also better at maintaining consistency in images. You can blend up to 14 images with this tool, and it can maintain the appearance of up to five people in outputs.

Prompt: Create an image showing the phrase “How much wood would a woodchuck chuck if a woodchuck could chuck wood” made out of wood chucked by a woodchuck.

Credit: Google

Prompt: Create an image showing the phrase “How much wood would a woodchuck chuck if a woodchuck could chuck wood” made out of wood chucked by a woodchuck. Credit: Google

Google also promises better editing. You can refine your AI images or provide Nano Banana Pro with a photo and make localized edits without as many AI glitches. It can even change core elements of the image like camera angles, color grading, and lighting without altering other elements. Google is pushing the professional use angle with its new model, which has much improved resolution options. Your creations in Nano Banana Pro can be rendered at up to 4K.

Detecting less sloppy slop

Google is not just blowing smoke—the new image generator is much better. Its grasp of the world and the nuance of language is apparent, producing much more realistic results. Even before this, AI images were getting so good that it could be hard to spot them at a glance. Gone are the days when you could just count fingers to identify AI. Google is making an effort to help identify AI content, though.

Images generated with Nano Banana Pro continue to have embedded SynthID watermarks that Google’s tools can detect. The company is also adding more C2PA metadata to further label AI images. The Gemini app is part of this effort, too. Starting now, you can upload an image and ask something like “Is this AI?” The app won’t detect just any old AI image, but it will tell you if it’s a product of Google AI by checking for SynthID.

Gemini can now detect its own AI images.

At the same time, Google is making it slightly harder for flesh and blood humans to know an image was generated with AI. Operating with the knowledge that professionals may want to generate images with Nano Banana Pro, Google has removed the visible watermark from images for AI Ultra subscribers. These images still have SynthID, but only the lower tiers have the Gemini twinkle in the corner.

While everyone can access the new Nano Banana Pro today, AI Ultra subscribers will enjoy the highest usage limits. Gemini Pro users will get a bit less access, and free users will get the lowest limits before being booted down to the non-pro version.

Ryan Whitwam is a senior technology reporter at Ars Technica, covering the ways Google, AI, and mobile technology continue to change the world. Over his 20-year career, he’s written for Android Police, ExtremeTech, Wirecutter, NY Times, and more. He has reviewed more phones than most people will ever own. You can follow him on Bluesky, where you will see photos of his dozens of mechanical keyboards.