Nano Banana 2 is here: what’s changed in Google’s popular AI photo tool


Google can’t let Samsung do that All the fun and attention this week. The Gemini maker dropped the Nano Banana 2 on Thursday, the second generation of its widely used AI photo editing tool.

You may remember the Nano Banana from last fall, when it was created Many fans and AI users were shocked With its realistic capabilities. It has quickly outperformed AI photo tools from competitors like Midjourney and OpenAI, especially with its ability to deftly handle photo edits as well as create entirely new images. The professional version was released a few months later Built on those capabilities With better text generation. And now Google promises that the Nano Banana 2, like Hannah Montana, is the best of both worlds.

CNET AI Atlas badge; Click to see more

The Nano Banana 2 leverages Google’s core AI photo model. The company said it should have the speed of the original model with the precision and detail work of the Pro version. It uses world-class know-how built into Gemini 3, which was previously limited to the Pro model. This means that AI images should be more rooted in reality and less prone to hallucinations.

Creating text in images, such as when creating greeting cards, should also be clearer. Consistency of character, something like that The creators said that the Nano Banana excels atalso gets a boost. Google said the new base model “delivers more vibrant lighting, richer textures, and sharper details,” along with the ability to produce in different aspect ratios and at resolutions up to 4K.

Read more: AI Slop is destroying the Internet. These are the people fighting to save her

Since the launch of Nano Banana, and in part because of it, we’ve all been eagerly grappling with the role that AI-generated content plays in our online ecosystems. Advanced models like those offered by Google create fabricated photos and videos that are virtually indistinguishable from the real thing. Low-quality AI content, sometimes called “slob,” has flooded social media. The vast majority of social media users believe they see AI-generated posts, but less than half (44%) are confident they can detect them. CNET poll found. Realistic images like the kind the Nano Banana can create are a big part of this problem.

The new model is now available everywhere you use Gemini. The Nano Banana 2 will replace the original, so you’ll have to choose between it and the Pro variant. If you create AI-powered images using the new model, Google will attach invisible watermarks called content credentials to them. So, if you want to know if a photo was taken using AI, you can upload it to Gemini’s website, and it might be able to recognize it. This only works if it is Made using Google AIthough.



Leave a Reply

Your email address will not be published. Required fields are marked *