Gemini’s ‘Nano Bananas’ AI Picture Modifying Is Enjoyable, however I Ran Into Too Many Slipups

0
geminis-nano-bananas-hero.png


I have been making an attempt out the picture modifying capabilities in Google’s newest generative AI mannequin, and you may, too. Named Gemini 2.5 Flash Picture, it upgrades the power to edit your pictures natively in Gemini. 

AI lovers have referred to it because the “nano bananas” mannequin, spurred on by a collection of teasers from Google execs. Google has been investing closely in its generative media fashions this 12 months, dropping up to date variations of its picture and video generator fashions at its annual I/O builders convention. Google’s AI video generator Veo 3 shocked with synchronized audio, a primary among the many AI giants. And creators have made greater than 100 million AI movies with Google’s AI filmmaker software, Move. 

I’ve spent a number of time testing AI inventive software program, and I used to be excited to see Google’s newest drop amid all of the banana fanfare. However my testing of two.5 Flash Picture confirmed that simply because one thing has a flashy entrance does not imply it’s going to at all times lives as much as its hype. This is how my expertise with Gemini nano bananas went: the nice, the unhealthy and the irritating.

What labored

The Gemini bananas mannequin is spookily good at including components to present photographs, mixing AI-generated components nicely into any image you snapped. It additionally maintains a decently steady stage of character consistency — that means the individuals in my pictures weren’t too distorted or wonky after going by the AI processing. These are each vital distinctions for AI picture packages, and one thing Google stated it had labored to enhance.

You’ll be able to see each of those traits on this image of my sister and me. Our normal appearances are unchanged within the edited model (proper), displaying off that character consistency. I requested Gemini so as to add a 3rd sister who seemed much like the 2 of us, which it did scarily nicely by including a 3rd girl in between the 2 of us.

two images side by side. the left is the original with two dark haired girls smiling holding buckets of apples in front of a mountain. the right image is AI-edited to include a third dark haired woman

Welcome to the household, scarily accurate-looking AI sister.

Katelyn Chedraoui/Gemini

I used to be additionally fairly impressed with how rapidly Gemini may spit out accomplished photographs. Anyplace below a minute will get a gold star from me, and Gemini was recurrently dealing with requests in below 15 seconds. I additionally appreciated the way it added a watermark to all the photographs it created and edited — even when I do not love how tech corporations have corrupted the sparkles emoji for AI, it is extraordinarily vital to have some markers of AI-generated content material. Google’s SynthID and behind-the-scenes work additionally assist differentiate AI content material from human-created imagery.

Gemini is sweet at wholesale AI picture creation, too, however I like to recommend utilizing its Imagen 4 or one other AI picture generator as an alternative — they’ve extra hands-on controls and settings that get you nearer to what you need with much less work.

What actually did not work

There are severe limitations to Gemini bananas. It routinely generated sq. photographs, and follow-up prompts asking for photographs to be tailored into different dimensions have been ignored or failed.

I additionally seen that Gemini diminished the decision of a lot of my pictures. I primarily take pictures with my iPhone 16, which has stellar cameras, however after going by the Gemini bananas mannequin, these wonderful particulars have been usually blurred. That is annoying and will not win over any photographers.

two images side by side, the left is an original showing an axe in a wooden target's bullseye. the left is AI-edited and similar, but with less fine details in the ring colors and wood grain

Regardless of my request to brighten up the goal’s rings, the unique photograph (left) has extra richness and texture than the AI-edited one (proper).

Katelyn Chedraoui/Gemini

I attempted repeatedly to get Gemini to deal with photograph edits that will’ve been tough for me to do manually. That is one space in photograph modifying the place AI is meant to excel — automating mundane however detail-intensive edits. Sadly, Gemini actually struggled with immediate adherence right here, that means it did not do what I requested. 

I attempted many occasions to get Gemini to take away reflections from a snap of a Freakier Friday film poster, however they stubbornly remained. And the extra I attempted to get it to take away the reflections, the poorer the standard of the picture turned with each immediate. As soon as-clear textual content was in the end illegible after I lastly gave up, to not point out the unintentional, scary-looking harm executed to the faces of Lindsey Lohan and Jamie Lee Curtis.

Gemini nano bananas struggled to generate photographs in several dimensions. Resizing and cropping photographs is a core photograph modifying course of, however Gemini did not — or could not — deal with easy sizing pointers in my prompts.

two images side by side. the left is the original shot of a Freakier Friday movie poster on a brick wall. the right is AI-edited and looks nearly the same except the faces and words are distorted

All I needed was for Gemini to take away the reflection within the upper-right nook of the poster, however as an alternative it warped the film tag line and faces.

Katelyn Chedraoui/Gemini

I reached out to Google concerning the decision and dimension points and a spokesperson stated the tech firm is “conscious and actively engaged on each points. It has been an enormous replace from our earlier mannequin however we’ll proceed to enhance on the mannequin.”

Total, Gemini nano bananas proved to me that Google is severe about persevering with to dominate in generative media. But it surely has important pitfalls, with too huge a deal with producing new components quite than utilizing AI to enhance and tweak widespread photograph points. For now, the nano bananas mannequin is finest suited to Gemini followers who wish to make huge edits rapidly. For these of us in search of extra exact instruments, we’ll have to attend for Google’s subsequent huge replace or discover one other program.

Gemini nano bananas availability, pricing and privateness

You need not do something to entry the brand new mannequin; it is routinely added to the bottom Gemini 2.5 Flash mannequin. Gemini is on the market without cost, with extra fashions and better utilization caps accessible in Google’s AI plans beginning at $20 per thirty days

Should you’re a paying subscriber, you might also have the ability to entry the mannequin by Google AI Studio. From there, all it’s a must to do is add a picture and kind out your immediate. Every immediate makes use of wherever from one to 2 thousand tokens, relying on the extent of element required. Adobe Categorical and Firefly customers also can entry the brand new mannequin now. 

Google’s Gemini privateness coverage says it might use the data you add for enhancing its AI merchandise, which is why the corporate recommends avoiding importing delicate or personal info. The corporate’s AI prohibitive use coverage additionally outlaws the creation of unlawful or abusive materials.

For extra, take a look at the finest AI picture turbines and every thing introduced on the Made by Google Pixel 10 occasion.



Leave a Reply

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