- Google’s Nano Banana 2 AI Image Generator Appears in Preview
- The new model promises smarter, self-correcting image generation
- The new model mimics a multi-step human workflow.
Google is preparing to take another step into advanced AI imaging with Nano Banana 2. The follow-up to the original Nano Banana model will be part of the Gemini app, according to the preview that unexpectedly appeared and was shared on X.
Nano Banana 2 seeks to provide better control of angles and points of view of images, with more color accuracy. There will also be the option to correct the text in the image without altering the rest of the result.
So Nano Banana 2 will be more than just a resolution increase. Nano Banana 2’s biggest change may be its mindset. Leaked previews suggest that the model now adopts a multi-step workflow where it will plan the image before creating it, analyze it for errors, fix them, and repeat the process until it is ready.
That kind of built-in autocorrect is new to Google’s image tools. Behind the quirky fruit moniker, Google appears to be treating AI image generation as a true design assistant, one that draws drafts, detects flaws, and only hands you the final product after making sure it’s not terrible.
Nano Banana 2 is now in preview 👀currently on Media IO pic.twitter.com/VNmQM3PAFPNovember 8, 2025
Images shared by those with access to the preview show cleaner lines, sharper angles, and fewer telltale errors from the AI images.
“Nano Banana Pro” has started appearing in GitHub commits and code references, suggesting that Google is already preparing a more premium version of the model for high-level or high-resolution tasks.
Attractive AI images
In the wild, Nano Banana 2, known internally as GEMPIX 2, has also started to appear in places beyond the main Gemini app. Testers have found traces of the model in experimental tools like Whisk Labs, part of Google’s ongoing effort to integrate AI creativity into all of its tools. If the past is any indication, this multi-surface drop will follow the same playbook as the original Banana drop, and users will suddenly find that their photos look better.
The fact that Nano Banana 2 goes through a self-correction cycle before delivering the final image marks a philosophical shift. It is no longer just reactive. Google is teaching its model to notice its own mistakes and proactively correct them. That sounds small, but it reflects the human creative process more than previous AI tools.
Better scene understanding, angle control, and text clarity should mean you’re more likely to get the image you really want. Considering how Nano Banana went viral for making Action figure versions of people that looked like real products, it will be worth watching to see how well Nano Banana 2 pulls off similar visuals set in the real world. Judging by some of the images shared and their consistency in sticking to that character’s likeness, you’ll soon see some truly realistic and unrealistic depictions of people and places.
Follow TechRadar on Google News and add us as a preferred source to receive news, reviews and opinions from our experts in your feeds. Make sure to click the Follow button!
And of course you can also follow TechRadar on TikTok for news, reviews, unboxings in video form and receive regular updates from us on WhatsApp also.
The best business laptops for every budget
