Follow ZDNET: Add us as a favorite source On Google.
ZDNET Highlights
- The new Nano Nano 2 promises better image generation.
- The new model aims to produce high quality photos much faster.
- The Nano Banana 2 is now the default model on all Google apps and sites.
Last year, Google made a big splash in the world of AI-powered image generation with its Nano Banana model. Now the next generation has debuted. And it promises a number of enhancements for individuals, professionals and businesses to generate photos, illustrations, diagrams, infographics and other images.
Google announced on Thursday nano banana 2 (Officially dubbed Gemini 3.1 Flash). Accessible to free and paid users, the new model replaces the first Nano Banana everywhere. This means it is now the default on Gemini websites and apps, Google Search, Google Flow, AI Studio, and Gemini API for developers.
Also: Best AI Image Generators of 2026: There’s Now Only One Clear Winner
So what is it that makes the second banana so much better than the first? Here’s what’s new, according to Google.
1. Advanced world knowledge. Nano Banana 2 uses Gemini’s real-world knowledge and images derived from web searches to try to create your images more accurately. Google said this skill will help AI create better infographics, turn your notes into diagrams, and visualize your data.
2. Consistency. One drawback of AI image generation is the lack of uniformity across multiple images. Ask AI to recreate an image or create a new image based on a previous image, and the characters and other elements do not always remain the same. The goal of Nano Banana 2 is to ensure that a maximum of five characters and a maximum of 14 objects in an image remain consistent during each iteration.
3. Better text rendering. Generating text in AI images can also be hit or miss, with unclear or inconsistent results. The Nano Banana 2 will attempt to create more accurate and legible text, which will help in designing images such as greeting cards and mockups for advertising campaigns. The new model can also translate text in an image, so you can share variations of the same thing in different languages.
4. Better at following your instructions. Another weakness with AI image generators is that they don’t always follow your instructions correctly, especially if your description is complex. The Nano Banana 2 is designed to avoid this problem by capturing the tones and nuances of your signal, so you get the image you want.
Also: How to spot an AI image: 6 clear signs it’s fake – and my free detector
5. Fast pace. With the previous generation of Bananas, you had to choose between quality and speed. Nano Banana Pro will produce a high-quality image, but it may take some time. Making the flash flash will speed up the process, but the resulting image may not be as good. The new version tries to combine the best of both worlds by generating high-quality images at a faster speed.
6. High fidelity. With Nano Banana 2, Google said your images will have sharper details, richer textures, and more vibrant lighting. And this process goes faster than before.
7. Quality ready for production: Do you want to create a logo, infographic, ad, or other image that needs to look professional? With Nano Banana 2, you can control the aspect ratio of the image to make sure it’s the right size for the medium. To produce clear images, you can set the resolution anywhere from 512px to 4K.
It all feels good. But is the new Nano Banana all that Google promises? I tried a few different requests to see how it performed. These were prompts that Gemini themselves suggested to test text rendering and character consistency.
Also: I tested the new ChatGPT images – it’s an amazing improvement, and extremely fun
For the first one, I submitted the following prompt:
“A vintage-style travel poster for a lunar colony on the Moon. In the center, a sleek 1950s-style rocket is landing near a glass dome. At the top, in a bold, cream-colored Art Deco font, feature the words ‘Visit the Lunar City.’ At the bottom, in small but clear script, add the phrase “The Gateway to the Stars.” Use a palette of deep navy, light orange and silver. High resolution, professional graphic design style. Use the 16:9 aspect ratio and create the image in 1080p.”
The resulting image captured the correct style and font for the text. The AI also followed my instructions for colors, aspect ratio, and resolution.
For the second one, I submitted two separate requests to test character consistency from one image to the next.
The first sign read:
“Create a character sheet for ‘Captain Nova’, a female space explorer who has short, bright purple hair, a bright blue mechanical eyepiece over her left eye, and a silver and white flight suit with a gold sun emblem on the chest. Show her from the front, side, and back against a plain gray background. Create the image at 4K in a 21:9 aspect ratio.”
Here, the AI followed my instructions with a sheet that showed the character and highlighted several important details.
But the real test was in my next prompt, which read:
“Using the same character from ‘Captain Nova’, show her running through a neon-lit cyberpunk market. She’s looking over her shoulder with a determined expression, her purple hair blowing in the wind. Keep her mechanical eyepieces and the gold sun symbol on her suit exactly the same. Cinematic lighting, shallow depth of field. Again, keep the image at 4K in a 21:9 aspect ratio.”
This kept the character consistent in style and appearance, so she looked the same in both images.
Based on these indications, the Nano Banana 2 appears to be a worthwhile upgrade over the previous generation. This is good news as it is now the default across the board. Google AI Pro and Ultra customers can still use the older Nano Banana Pro for more specialized tasks. Otherwise, one can try the latest banana flavor and see what images it evokes.
