AI Detection and Watermarks: Can You Trust Nano Banana Pro Images?
Google's original Nano Banana image editing and generation tool made a big splash this year, earning our Technical Excellence award for its ability to effortlessly create entirely new images from scratch, remove unwanted objects in photos, and more. Now, the company has unveiled an upgraded version: Nano Banana Pro. But what exactly can it do, and how does it improve upon the original iteration? Here's a complete breakdown.
Nano Banana, as an umbrella term, refers to Gemini's image editing and generation functionality. Neither Nano Banana Pro nor Nano Banana is a technical name, but rather Google's respective nicknames for its current generation (Gemini 3) and previous generation (Gemini 2.5) of AI image models.
Both the original Nano Banana and Nano Banana Pro can edit and generate all kinds of images. The former earned recognition for its ability to blend images together and edit photos with consistency, whereas the latter offers expanded editing controls, lets you combine more images at once, and generates far clearer text. Although Nano Banana Pro is the best version of Google's AI image technology yet, the original Nano Banana can still be exceptional if you use it correctly.
You can use Nano Banana via the Gemini chatbot app or website, as well as in Google Search's AI mode. Nano Banana Pro is exclusive to paid Gemini users in Google Search, but it's available to both free and paid users within Gemini itself. Just keep in mind that paid users get priority access; Google restricts the number of generations you can perform with Nano Banana Pro, reverting you to the original Nano Banana if you reach the cap.
You can toggle Nano Banana from within Gemini's central text field, but you also automatically make use of it when you prompt Gemini to create or edit images. If you select "Fast" from the model selector, you engage Nano Banana (with its 2.5 Flash technology). Picking "Thinking with 3 Pro" engages Nano Banana Pro (with its 3 Pro technology).
All that's left to do after is write a prompt and upload any relevant images. You can use natural language in your prompts and be as descriptive as you want. For example, you can upload an image with a hand blocking out a portion of it and prompt Gemini to "remove the hand." Nano Banana will then get to work and present a new image with the hand removed.
Nano Banana Pro generally excels at creating and editing images. To get a sense of Pro's upgrades, I focused on what Google presents as its key abilities: blending multiple images, editing controls, and text generation. Like with all AI model testing, your experience might differ from mine.
To start, I provided both Nano Banana and Nano Banana Pro with a picture of a tree and asked Gemini to create an infographic based on it. As you can see below, the information in the infographics is the same. However, whereas Nano Banana's text (second slide) has issues in a few places, Nano Banana Pro (first slide) renders everything flawlessly. It's hard to overstate quite how much of an achievement this is because I've seen garbled AI-generated text countless times.
Next, I gave Nano Banana and Nano Banana Pro original pictures of four video game characters (Aloy, Andrew Ryan, Nathan Drake, and Shadowheart) alongside myself and prompted them to create an image of all five people hanging out. Nano Banana Pro (first slide) manages this just fine, but Nano Banana (second slide) struggles with the appearances of Aloy and Drake, while also completely omitting Shadowheart.
Nano Banana Pro's image above came out in a vertical aspect ratio, so I prompted both models to turn it into a traditional 16:9 image. Nano Banana Pro managed this largely without issue, as shown below, but Nano Banana kept reverting to the original. Google's promise of better control over your edits across a range of available aspect ratios with Nano Banana Pro seems to ring true.
One more upgrade I noticed with Nano Banana Pro is in the resolution of outputs. With the original, Gemini's creations usually came in at around 720p. With Nano Banana Pro, images routinely clock in at about 2K resolution, which is a major increase. As you might expect, this upgrade makes Nano Banana Pro images generally sharper and more detailed. It also helps reduce the subtle blurring effect that either model can introduce.
For all that Nano Banana Pro gets right, it gets some things wrong, too, just like the original version.
For example, when I tested its blending ability, I first tried to submit a picture of my living room, alongside pictures of a variety of products I found on Amazon (a bookcase, a couch, a display case, and a speaker stand), to see if Nano Banana Pro could replace my existing items. It would only do this in reverse, though, replacing the pictured Amazon items with my own. Changing the titles of my images and spelling out explicitly what I wanted didn't help.
When I settled on incorporating pictures of characters together, Nano Banana Pro struggled with my original prompt, generating an image of Andrew Ryan and me combined. After making some minor adjustments to my prompt, which boil down to including a sentence instructing it to make each character distinct, I was able to achieve better results. Still, it's disappointing to see such a small difference in language cause issues.
Once or twice, I noticed some issues with the quality of Nano Banana Pro. While its output images are much higher in resolution than the original's, they don't always look sharper. Some even look slightly blurrier. This didn't happen frequently, so it's likely a generation bug, but I'd prefer to see fewer of these issues. Google also says Nano Banana Pro can output in 4K, but I wasn't able to make that happen.
As AI image generation (and editing) gets better and better, leveraging AI to spread misinformation or for other nefarious purposes becomes more and more of a concern. To combat this, Google employs the SynthID AI watermark system. This is distinct from the Gemini icon you see at the bottom right of Gemini's images, which is easy to remove for free online.
The core concept behind SynthID is that it's an invisible digital watermark that humans can't see but that computers can detect. Google is working on a SynthID detector that allows you to upload images and check if they contain SynthID. Currently, you can upload images to Gemini and ask if they contain SynthID.
I applaud the aim of this system, and it appears to be working well. In testing, I ran an image I generated with Gemini through an online watermark removal tool to remove the visual watermark. Then, I ran it through two separate SynthID removal tools. Gemini still detected SynthID in the image. However, it's hard to imagine that these removal tools won't get better over time.
Ultimately, Nano Banana Pro offers meaningful improvements over the original Nano Banana, which is great to see in light of other disappointing major AI model updates (I'm looking at you, GPT-5). As somebody who interacts with a lot of AI image generators, I can confidently say I see the appeal of Nano Banana Pro, especially when it comes to text generation within images. That said, I'm not sure if AI image generation is worth a monthly subscription fee for most people, even when it works well. Of course, if you're a creative type who needs to visualize something you wrote or are trying to write, it's absolutely worth trying.