Comply with ZDNET: Add us as a most popular supply on Google.
ZDNET’s key takeaways
- Google’s Nano Banana Professional earned a near-perfect rating.
- ChatGPT picture ranked second; others typically mangled textual content and faces.
- 9 powerful prompts reveal which AIs are price subscribing to.
When generative AI first hit the scene in early 2023, we had been amazed by two capabilities we hadn’t seen earlier than: the power for the AIs to write down complete content material, and the power for some AIs to generate graphics and photo-realistic pictures.
Clearly, AI fashions have come a good distance in simply three years. In my latest evaluation of the perfect chatbots, I additionally listed the perfect free AI instruments for producing pictures. On this article, I am going to take you slightly deeper into the paid tiers of AI picture era instruments.
Additionally: One of the best AI chatbots of 2025: I examined ChatGPT, Copilot, and others to search out the highest instruments now
My check suite falls into 4 most important classes: revising current pictures, producing authentic pictures, including textual content to photographs, and leveraging popular culture. For comfort, I generated all the photographs throughout all of the checks in 1:1 sq. ratio, largely in order that they may very well be displayed side-by-side simply.
I generated over 50 pictures utilizing six standard AI picture turbines. Every picture generator was subjected to 30 particular person evaluations, and from that got here an combination rating.
We have now a winner
There is a winner — a no-contest, complete knockout winner. This can be a first in my AI evaluations. Normally, there are instruments that every do a reasonably good job. Nevertheless, on this set of checks, there’s a fully clear standout champion: Google’s Nano Banana Professional, a part of Gemini 3.
It aced each considered one of my checks with a near-perfect rating of 93%. ChatGPT got here in second place, at 74%. The opposite 4 ranked between 43% and 54%.
Additionally: Cease utilizing ChatGPT for all the things: I take advantage of these AI fashions for analysis, coding, and extra
All six contenders did a superb job when requested to create a brand. Past that, efficiency was all around the map.
The underside line is, in order for you severe AI picture era, spend $20/month for Gemini 3, and you will get Nano Banana Professional. That is it. There isn’t any different attainable conclusion.
Though some instruments supply further options, the first distinction between the paid and free variations is the quantity of utilization you get. For instance, Nano Banana Professional reduce me off after two pictures earlier than I upgraded.
Additionally: Learn how to set up and configure Claude Code, step-by-step
And, only for the report, I purchased all my very own subscriptions to do these checks. No person is paying for this conclusion. I am as shocked concerning the Gemini conclusion as lots of you is perhaps.
OK, so let’s get began.
Google Gemini 3 Nano Banana Professional
Finest AI picture generator general (by far)
- Total rating: 93%
- Value: $19.99/mo as a part of Google AI Professional
AI permits you to do picture recontextualization in minutes. Principally, you possibly can feed an AI an current picture and ask for it to be modified into one thing fully completely different. The formal check is feeding an image of me out on a stroll and asking the AI to place me in a US Navy admiral’s uniform on the bridge of an plane service. I do know. You’ve got your fantasies; I’ve mine.
So, this is my beginning picture.
And this is the recontextualized picture (under). Discover the way it saved my face and glasses, however even modified the angle I used to be dealing with. It put me correctly on the bridge of a ship and added binoculars to my palms. I imply, I make that look good.
OK, to be truthful, there are points with Navy personnel (admirals included) and beards. However I can stay out my AI fantasy in the course of this text, proper?
Subsequent, I wished to see how properly it could clear up previous photographs. I discovered a photograph of me standing on the USS Ling once I was a child. Sure, it was my Bob Ross hair section. The issue was that the picture was too darkish to see. On the left is the unique. On the precise is the Nano Banana cleanup.
The place this obtained attention-grabbing was my subsequent check. I fed it a picture of a truck and instructed it to wash up and colorize the picture. As an alternative, it first gave me the identical Bob Ross hair image of me above, however colorized. After I as soon as once more requested it to do the truck, it put me within the admiral uniform within the picture.
It is fairly stunning to see side-by-side photos of myself, separated by a long time. Whereas this was a cool picture and gave me meals for thought, it wasn’t what I requested Nano Banana Professional to do. Factors had been deducted.
There’s one factor I do not like about Nano Banana Professional, and that is that it places a watermark within the backside nook of every picture. You might use one other AI to filter that watermark, nevertheless it’s annoying.
So, what occurred with the truck? I began a brand new session after which uploaded this picture of the truck. I feel my dad took this picture 40 or 50 years in the past.
This is how Nano Banana Professional cleaned it up (under). Discover the lettering on the truck is generally correct and readable. Nevertheless, my editor seen that it actually says “BADICLOGICAL DEFEKSE,” costing Nano Banana Professional one other few factors.
Textual content is certainly an issue for many AIs. Additionally, I am pretty positive that truck was largely blue, however Nano Banana could not have identified that, and it coloured it like many different emergency automobiles of the time.
Now, let us take a look at artistic picture era. On the left is a brand for Area Coast Studios, which I described as a video manufacturing studio. On the precise, I requested for a medieval librarian in a candlelit stone library.
As you possibly can see, Nano Banana picked up all of the themes for the brand. Area Coast is in Florida, so there is a palm tree. There is a rocket, movie, and good textual content. On the precise, we have now our librarian, numerous candles, candlelight, and stone partitions.
Subsequent up is a job I count on many individuals will probably be utilizing AI picture turbines for: social media. I gave the AI two associated assignments to create pictures for Fb. The primary was to generate a senior grownup holding a cellphone, together with some textual content.
The second was to generate a pupil in a comfortable atmosphere, particularly with a MacBook Professional and a cup of espresso. Gender was not laid out in both task.
I need to level out that the textual content is completed correctly, matches over the picture cleanly, and there are not any errors. However I am extra amused that the man is holding what’s clearly an iPhone. Yep, Google’s AI generated an iPhone when requested to point out a “flagship smartphone.”
Lastly, I ran a few pop culture-inspired prompts. These check how the AIs cope with cultural references, whether or not they’re copyrighted mental property or concepts impressed by the tradition.
Additionally: How I take advantage of AI to carry my child’s artwork to life
For the primary picture, I requested for a poster for a fictional “fourth Again to the Future film,” the place Marty McFly goes again to Twenties New York.
The second popular culture picture I requested was “Nightmare Earlier than Christmas, Tim Burton model,” the place I wished an IT skilled in a knowledge middle.
Nano Banana Professional did a superb job with the Nightmare model. However check out the small print within the Again to the Future piece. It obtained the DeLorean and the skateboard. It did an ideal job with the textual content, not solely evoking the “Again to the Future” brand model, however placing the textual content “New York Metropolis 1925” on a marquee similar to they appeared in New York again within the day.
It added the tagline, “The Roaring Twenties Obtained Heavy,” referencing how the ’20s had been described and referencing considered one of Marty’s favourite phrases. It additionally put Marty into interval clothes.
Simply wow. Throughout all my checks, aside from that one time once I needed to begin a brand new session, and the minor truck textual content subject, Nano Banana Professional did not get something fallacious. It will get a virtually excellent rating.
ChatGPT
Finest for natural-language iteration in chat
- Total rating: 74%
- Value: $20/mo as a part of ChatGPT Plus
Again within the early days of generative AI, we mentioned ChatGPT because the text-based chatbot and DALL-E 3 as OpenAI’s text-to-image AI instrument. DALL-E, as a standalone instrument, has just about fallen out of use in favor of the picture generator within ChatGPT.
Simply earlier than scripting this, I reached out to OpenAI and requested them what that instrument is known as, and I feel this explains why ChatGPT is nineteen factors behind Nano Banana Professional. I used to be instructed that ChatGPT’s picture generator is “GPT-4o picture era in ChatGPT.”
Additionally: Is that an AI picture? 6 telltale indicators it is a pretend – and my favourite free detectors
I initially ran this set of checks in opposition to that picture mannequin. However then, OpenAI launched its new ChatGPT Pictures replace, which, in some methods, is an enormous enchancment over the earlier model. For my first look (and numerous enjoyable with picture transformations), check out this text: I examined the brand new ChatGPT Pictures – it is a beautiful enchancment, and enormously enjoyable.
Since we do have a brand new mannequin, I redid the ChatGPT checks, and I am utilizing the brand new one in these scores.
Let’s begin with the photographs. ChatGPT misplaced a bunch of factors right here. It is truthful to say, picture retouching is just not a power of this mannequin.
The admiral recontextualization is fairly good. That appears like my face. Nevertheless, the uniform is considerably problematic. It isn’t clear what rank insignia are getting used, and so they appear to be a bizarre cross between these of a Lieutenant and an O-8 Admiral.
The child image is nice. Within the earlier ChatGPT picture, ChatGPT put a random grownup’s face on the child’s physique. Right here, it is the unique face.
Additionally: I have been testing AI content material detectors for years – these are your greatest choices
ChatGPT did a pleasant job on the truck cleanup, besides the lettering modified from what ought to say “RADIOLOGICAL DEFENSE” to “RADIO CHEMICAL DEFENSE,” with an additional house between CHEMICAL and DEFENSE. Some factors had been misplaced, however not almost as many as within the earlier model.
As for the brand, ChatGPT did superb, though I’d have most popular some reference to Florida, palm timber, or solar. The librarian was just about what may need been anticipated from the supplied immediate. No factors had been misplaced.
ChatGPT did virtually superb with the 2 social media posts. I seen that though the textual content is appropriate, it positioned each blocks of textual content in precisely the identical place. Transferring the textual content up on the image of the person would most likely have been a greater design alternative, nevertheless it’s ok.
I did take a degree every off as a result of the lighter font model and poor distinction make the textual content slightly tougher to learn.
That brings us to our popular culture references. That is the place issues get slightly odd.
In my first take a look at the brand new ChatGPT Pictures replace, I mainly recreated a scene from a basic Star Trek episode. Not solely did ChatGPT produce great pictures, nevertheless it additionally successfully duplicated the alien creature proper out of the episode, all the way in which right down to the creature’s man-in-suit look.
However once I requested for a Again to the Future-inspired picture and one impressed by Nightmare Earlier than Christmas, I obtained this:
That misplaced the brand new ChatGPT picture generator a bunch of factors. The truth is, it pushed the brand new picture generator’s rating from 81% for the earlier model right down to 74% for this new model.
In the event you’re curious what we misplaced, listed here are the photographs created by the earlier model. The “Again to the Future” picture is ok. It isn’t as impressed because the one from Nano Banana Professional, however no factors had been misplaced. The textual content brand is nice, the Marty character hits all of the notes, there is a recognizable DeLorean, and town may very well be New York within the Twenties.
Then there’s our “Nightmare Earlier than Christmas”-inspired IT man. He does have the grey pallor that almost all IT people are likely to have. However though I feel I can converse for all of us in saying {that a} third hand would most likely are available mighty useful, I’d have counted it as an error.
For now, my greatest conclusion is that pop-culture references in ChatGPT are going to be hit and miss. You would possibly get a Star Trek-inspired Gorn struggle, otherwise you would possibly get scolded by the AI and despatched to your room with out dinner. There isn’t any predicting.
Midjourney
Finest for hyper-creative cinematic imagery
- Total rating: 57%
- Value: $10/mo for Midjourney Fundamental
Midjourney was the primary devoted AI service I ever purchased, method again in 2023. I used it to assist me produce my album launch imagery, a bunch of pictures for my little check Etsy store, and I commonly use it to create promo social media posts for my spouse’s e-commerce enterprise.
In terms of originating artistic imagery, Midjourney is fairly nice. In terms of picture cleanup, recontextualization, or textual content, Midjourney is… not a lot.
As you possibly can see, the admiral picture does reproduce a yellow shirt and one thing of the background from my authentic image, however that man is not me, and there is a ship behind the park for some cause.
The child, as rendered, is not youthful me, both. Additionally, Midjourney did not clear up the picture. The truth is, it made it worse.
Additionally: Is ChatGPT Plus nonetheless price $20? The way it compares to the Free and Professional plans
And there is a truck, not the truck we began with, however a truck. And for some cause, they caught a younger Kate Mulgrew-looking lady (the Captain from “Star Trek Voyager”) within the picture.
All three had been supplied in 1:1 format as requested, however the pictures had been simply slapped onto the 1024×1024 canvas.
Subsequent up are the brand and the library picture. Midjourney does present the brand textual content accurately. It provides a palm tree and a few towers that would appear like house. It is evocative of the subject, however it could have been good to have a rocket.
Then there’s the library. Right here, you can begin to see the place Midjourney shines. That is virtually precisely what I pictured when asking for this picture. No factors had been misplaced with both of those pictures.
The social media posts additionally present a few of Midjourney’s strengths. The person seems superb. Even his palms and facial strains appear to go collectively. He seems actual sufficient. The woman consists completely, besides the laptop computer appears a bit low on her legs (and it is an older-generation MacBook Professional).
However do you see what’s lacking? No textual content. Midjourney did not even attempt to render the textual content messages. Factors had been eliminated.
Lastly, we get to the popular culture references. The “Again to the Future” picture misplaced a couple of factors as a result of there isn’t any textual content, and since town seems method too neon to be Twenties New York. Whereas the Marty on this image is not any Michael J. Fox, I am not eradicating factors for that. It obtained the general look proper.
As for the Nightmare IT picture, I really like this picture. That is one other instance of why Midjourney has such a powerful following. When it really works, it actually works.
Adobe Firefly
Finest for commercial-safe pictures
- Total rating: 54%
- Value: $9.99/mo as a part of Firefly Customary (and included in a bunch of Adobe plans)
Subsequent, we’ll check out Adobe Firefly. That is the AI engine within Photoshop and different instruments, nevertheless it additionally works as a standalone net interface. Firefly (and Photoshop) now allow you to select different AI engines (so you possibly can run Nano Banana inside Firefly, for instance). That stated, all my testing was accomplished utilizing the Firefly Picture 5 (preview) mannequin.
Firefly is, by far, probably the most uncooperative and fussy of the picture turbines from an overprotective copyright perspective. For instance, once I tried to add an precise image of myself, I used to be carrying a Star Trek-inspired Gorn T-shirt. It refused to add it.
I needed to take it into Nano Banana Professional, have Nano Banana take away the T-shirt’s graphic, after which add it.
The admiral picture is barely an admiral’s uniform, and the face is not mine. The transformation of the child picture is nice, and it is simple to see. The truck colorization seems nice, however Firefly did not trouble to wash up the picture artifacts, which was the primary object of the task. Factors had been misplaced.
As with all the opposite AIs, the brand turned out to be fairly usable. The library picture evokes a number of the really feel I used to be going for, however if you happen to take a look at the face, there’s some severe uncanny valley occurring. It seems like an AI face generated by 2021 know-how. Factors had been misplaced right here, too.
I needed to struggle with Firefly to create the 2 social media posts. Each prompts gave me this error message.
The criticism was, “Together with artist names in your immediate doesn’t meet our Consumer tips.” Discover that there isn’t any artist title in that immediate. The gotcha was that I used a phrase within the type “[WORD]-style” and that flagged it. After I eliminated “Fb-style” from the immediate, Firefly generated the photographs.
Although the face of the older gentleman was blurred, that was a legitimate inventive alternative. Opening up the aperture to supply readability to the foreground works on this context. Nevertheless, it obtained the spelling fallacious.
For the scholar picture, there are numerous delicate not-quite-rights. There’s one thing fallacious along with his shirt, his arm seems unreal, his palms do not look fairly proper, and so forth. It isn’t fairly as dangerous because the librarian’s face, nevertheless it’s not good. Factors had been misplaced.
Extra factors had been misplaced for the pop-culture pictures, which Firefly merely refused to do.
Leonardo AI
Finest for fantasy artwork
- Total rating: 52%
- Value: $10/mo, but additionally a part of Canva Marketing strategy
Leonardo.AI fully bombed when it got here to testing already-existing pictures. It simply refused to come back out and play. So, let’s transfer on to some artistic work.
The brand, like all of the others, is workable. I personally choose those who additionally name again to the Area Coast theme, with solar and palm timber together with the rocket, however this can be a completely superb brand. As for the librarian, I specified neither gender nor age. So this does meet the necessities.
As for the social media posts, the person appears OK, aside from his left inside elbow, which seems slightly odd. The girl’s leg appears to wrap across the laptop computer in an odd method, and he or she is balancing a cup of espresso on her leg. There’s one thing simply not proper about that.
Lastly, we get to the final two pictures from Leonardo.
In my “Again to the Future” immediate, I particularly said, “Create a poster.” Leonardo is the primary AI to really format a poster. Alternatively, I do not recall seeing “Again to the Future” 4 by way of 10, even when “Again to the Future 11” appears enjoyable, particularly with its theme of “HAMY JOB OARY OF DOSE.” Moreover, these vehicles and buildings are decidedly not Twenties.
We wrap up our time with Leonardo with considered one of my all-time favourite AI-generated pictures. In some way, Leonardo captured the Nightmare really feel together with the information middle look, however used a photo-realistic Lurch-like character. I completely love this picture.
Canva
Finest to generate artwork proper inside your advertising and marketing designs
- Total rating: 43%
- Value: $15/mo for Professional or $20/mo for Enterprise (contains Leonardo)
Canva is greatest identified for its monumental reputation as a advertising and marketing picture era instrument. If you wish to make a flyer, poster, or social media put up, Canva is your pal. When Canva acquired the Affinity Professional picture merchandise and launched them totally free, I grew to become a convert.
Additionally: I really like Photoshop, however Canva’s free Affinity instruments gained me over (and saved me cash)
Together with releasing the Affinity instruments, Canva additionally launched an entire line of generative AI options, together with its personal picture generator. To be clear, Canva’s inner AI picture generator is a separate beast from Leonardo’s picture generator, however Canva owns each.
As a result of Leonardo is $10/month by itself however solely $5 extra with Canva’s Marketing strategy, I signed up for Canva’s Marketing strategy for this check. I am most likely going to downgrade again to the $15 Professional plan as a result of I do not discover Leonardo all that compelling in comparison with different instruments I am additionally paying for.
As for Canva, properly, you gotta see this. Let’s take a look at the picture cleanup and recontextualization checks first, as a result of…there are not any phrases.
I am unsure, however I feel there are timber rising on the plane service. It did establish the beard, which is greater than I can say for the lacking truck in what was speculated to be the truck picture. And why there is a disembodied lady’s head floating above the wreckage of one thing that is a cross between the USS Ling and Nikola Tesla’s Wardenclyffe Tower is a secret solely Canva’s AI mind can probably perceive.
So, yeah. Factors had been misplaced. Lulz had been had.
Subsequent up is the brand and the librarian. Each are superb. Frankly, if Canva could not create a brand, it could be time to hold up its AI. Nevertheless it did a superb job. It is the one check class the place Canva obtained full factors.
Alternatively, the social media posts had been a disappointment. The person had an excessive amount of house between “easy” and “highly effective,” and the girl’s picture has textual content that misplaced its method fully. To be truthful, Canva has its personal specialised social media modifying instruments, so maybe the concept is to generate the AI picture after which use different Canva instruments for textual content.
Even so, there’s one more cup of espresso balanced on a leg. Repeat after me: factors had been misplaced.
Lastly, we get to the popular culture pictures…or fairly, picture. Canva made a picture for a fictional “Again to the Future 4” film that did embrace a Marty McFly character and the DeLorean, in addition to the brand in correct BttF format.
However what’s “WYGLA TLETZ NEW ADIENS?” And who’s the woman? And what’s that factor floating within the sky? And what are these generator-like issues on the aspect of the highway? And why is half the highway on hearth? It is clearly not again in time to the Twenties.
Take a look at the above picture. Observe that there is a full “Again to the Future” brand there, with the title and even the suitable brand sort. So ask your self why Canva denied me a “‘Nightmare Earlier than Christmas’ model, Tim Burton model” IT skilled?
The place’s the consistency? Why enable one however deny the opposite? And why so blatantly enable the primary, however not even make a strive on the opposite? Factors had been misplaced.
Testing methodology
I fed the identical precise 9 prompts to every of the six AI picture turbines above. Listed here are the prompts and photographs used as supply materials, on your reference:
I created a spreadsheet the place I recorded the purpose scores for every of the photographs and their prompts.
Admiral picture recontextualization: Factors had been utilized for correct background, correct new clothes, and whether or not the AI saved the unique topic face and clothes.
Gown this man in a US Navy admiral's uniform and place him on the bridge of an plane service. Don't change the face. Side ratio 1:1
Restore black and white picture: Factors got if the AI saved the unique picture parts, saved the unique face, physique, and clothes, and if the AI correctly cleaned up the picture.
Restore this previous black and white {photograph} to appear like a contemporary, high-quality studio picture. Restore scratches, mud, stains, and cracks. Enhance sharpness and readability with out over-smoothing. Improve distinction, particulars, and lighting naturally. Protect authentic facial options, textures, and interval particulars. Keep away from too many darkish areas and shadows, make particulars clear and straightforward to see. Preserve it strictly black, white, and grey with reasonable movie grain. Side ratio 1:1
Restore and colorize black and white picture: Factors got if the AI saved the unique picture parts, correctly cleaned up the picture, saved the unique textual content on the truck, and transformed to paint appropriately.
Restore this previous black and white {photograph} and convert it into reasonable coloration. Take away scratches, mud, stains, and harm. Sharpen facial options and superb particulars whereas maintaining a pure look. Add traditionally correct, pure pores and skin tones, clothes colours, and background colours. Match trendy lighting and coloration steadiness whereas preserving the unique picture's composition and temper. Side ratio 1:1
Create a brand: Factors got if the created brand was correct to the theme, if the model was acceptable, and for textual content era accuracy.
Create a retro-futuristic brand for a video studio named "Area Coast Studios" Side ratio 1:1
Fantasy librarian: This was a reasonably open-ended check, with factors given for the standard of the generated picture, whether or not the AI generated a picture with candlelight, stone, and a library, and the standard of the generated character.
Create a fantasy scene of a medieval librarian in a candlelit stone library. Side ratio 1:1
Studio portrait of a senior grownup: Factors got if the AI included glasses, created a practical face and pose, had the character maintain a smartphone, and generated the required textual content.
Create a photorealistic studio portrait of a trendy senior grownup carrying trendy glasses, smooth skilled lighting, impartial gradient background, holding and utilizing a flagship smartphone. Add quick Fb-style advert copy on the picture: Easy. Highly effective. Made for on a regular basis life. Side ratio 1:1
Candid portrait of a pupil: Factors got if there was a MacBook Professional (or Air) within the picture, the scholar had a practical face and pose within the context of the necessities, if there was a cup of espresso (and it wasn’t balanced stupidly on a leg), and if the AI generated the required textual content.
Create a pure candid portrait of a pupil sitting close to a window utilizing a MacBook Professional, subsequent to a cup of espresso, smooth daylight, cozy dwelling background, relaxed and genuine temper. Add quick Fb-style way of life copy on the picture: Moments that matter, at all times inside attain. Side ratio 1:1
“Again to the Future” poster: Factors got for a practical Marty, if the AI generated a DeLorean, if the scene was in Twenties New York, and for the generated textual content and magnificence.
Create a poster for the fourth Again to the Future film, the place Marty takes the DeLorean and his skateboard to Twenties New York Metropolis Side ratio 1:1
“Nightmare Earlier than Christmas”-style IT individual: Factors got if the AI generated a recognizable IT atmosphere, for high quality character era, and for the general Tim Burton really feel.
Nightmare earlier than Christmas model, Tim Burton model, put an IT skilled in datacenter Side ratio 1:1
Think about that
So there we’re. As you possibly can see, of the six picture turbines examined, Nano Banana Professional stood out above all the remainder. However there are some areas the place the others shine as properly.
What about you? Have you ever tried any of those AI picture turbines but, and in that case, which one impressed you most? Does Nano Banana Professional’s excellent rating match your individual expertise, or do you assume one other instrument deserves the crown? Which options matter most to you: picture cleanup, textual content rendering, pop-culture prompts, or artistic model? And are you paying for any of those instruments proper now, or sticking with free tiers? Tell us within the feedback under.
You may observe my day-to-day challenge updates on social media. Remember to subscribe to my weekly replace publication, and observe me on Twitter/X at @DavidGewirtz, on Fb at Fb.com/DavidGewirtz, on Instagram at Instagram.com/DavidGewirtz, on Bluesky at @DavidGewirtz.com, and on YouTube at YouTube.com/DavidGewirtzTV.
