We found 8 Nano Banana Pro images that show Google is the new benchmark in AI art

Julio Franco

Julio Franco

Posts: 9,322   +2,257
Staff member
First look: Google's latest generative model comes with a ridiculous name, but it's powered by a surprisingly serious engine. Nano Banana Pro recently debuted inside Gemini bringing a major jump in image generation quality – and judging by the last week's worth of community samples, Google's image outputs aren't just competent… they're worryingly impressive, too.

For months, sentiment in the AI community has been shifting. After years of trailing models like DALL-E, Midjourney, and OpenAI's latest, creators are now saying Google has caught up in key benchmarks and visual fidelity. And in image generation specifically, it suddenly looks like Google may have the most convincing lead of all.

Nano Banana Pro focuses on the kinds of things image models have historically whiffed on: fine-grained prompt reasoning, subtle editing, and treating typography as actual type rather than "AI hieroglyphic," a.k.a. AI slop.

We've tried Nano Banana and we can assure results will heavily depend on a good prompt (here's the prompt used for this story's top image), but there are plenty of community samples showing the model interpreting long prompts with uncanny consistency and clarity. The results are reproducible, too.

Character Consistency in Nano Banana Pro using a reference image

Nano Banana Pro brings new features like merging up to 14 reference images, while retaining identifiable features from as many as five individuals for more accurate multi-person compositions. Face geometry, color tone, and style motifs carry over from image to image, making it easier to build cohesive sets inside a single session.

Editing no longer nukes the original. Upload a photo and tweak only what matters: shadows, camera angle, color grade, or background design. The rest stays untouched. Early testers have shared iterative shots that feel like a human designer slowly dialing in revisions, not a generative roulette wheel spinning a whole new interpretation every time.

A clever workflow is also making the rounds: having Gemini analyze an image, convert it into a JSON-style structural prompt, and then feeding it back to Nano Banana Pro for highly specific, granular adjustments. Instead of reimagining the entire scene – the way most GenAI models still do – the system isolates changes to exactly the parts you specify.

With support for 4K renders, Nano Banana Pro pushes beyond "cool demo." Users are posting infographics, technical diagrams, marketing concepts, and product mockups generated in a single pass. Watermarking is also baked in using SynthID embed, an important safeguard as image quality improves enough that it's becoming harder to differentiate generated photos from real life.

The broader consensus forming in the final stretch of 2025 is that Google's AI is finally catching up. Not just on image generation, but in broader model quality – even as it also positions its TPU strategy as a long-term alternative to Nvidia for data-center-grade compute.

Nano Banana Pro lives inside Gemini, gated by subscription tiers. Free users can experiment, but with tightly limited throughput – likely the reason this hasn't turned into Google's big AI, culture-defining "Ghibli moment." Still, if the community demos keep rolling in at the current pace, the "banana model" may go down as the inflection point where Google's image generation started looking like the standard.

Permalink to story:

We found 8 Nano Banana Pro images that show Google is the new benchmark in AI art

 
The Blade Runner 2049 picture demonstrates it well but subtly, taking an iconic shot of K and Joi outside the city, around the time she flickers, and placing it back in the city, along with neon reflections of the cityscape on K's window.
 
I did not have that great of results when I first tried nano banana. As for stuff that can run on a local machine, Z image turbo (aka ZIT) is looking promising.
 
My mom loves to send me old photos of family and I've been plugging them into Gemini to fix and modernize. It usually does a decent job and I send them back to her, then she's amazed at how skilled I am and how fast I did it. I haven't had the heart to tell her that it's AI doing it yet.
 
  • Like
Reactions: murkiewaters, BogdanR and VBKing
antiproduct said:
My mom loves to send me old photos of family and I've been plugging them into Gemini to fix and modernize. It usually does a decent job and I send them back to her, then she's amazed at how skilled I am and how fast I did it. I haven't had the heart to tell her that it's AI doing it yet.
Click to expand...
Could an informed bystander, that is informed that AI is possibly used for this cleanup, be able to distinguish between the Gemini-fixed photos and a control group of manually edited photos? Asking because this could be one of the few legitimate uses to pay for this service.
 
  • Like
Reactions: murkiewaters
Revolution 11 said:
Could an informed bystander, that is informed that AI is possibly used for this cleanup, be able to distinguish between the Gemini-fixed photos and a control group of manually edited photos? Asking because this could be one of the few legitimate uses to pay for this service.
Click to expand...
I'm just using the free version, so they all have the watermark in the bottom corner. My mom doesn't notice. Aside from that, I'm not sure about the image resolution. All the images are coming to me in a text message, so probably not the highest resolution, then downloaded from the app on my phone. I'd imagine this might not be a limitation in the paid version. Idk. Finally, I will say sometimes it screws up and doesn't do what I asked at all. One B&W picture my mom sent came out with someone that had a shirt with one color on one half their body and a different color on the other half. Aside from that, the restoration looked great. It can also try really hard to make the photo look as if it was taken today, which can cause some differentiation in the faces from the original, probably often because it needs to create facial features that were hard to distinguish due to damage or just poor original image quality. Considering it's like 5 free per a day, it's worth the try.
 
  • Like
Reactions: Revolution 11
You must log in or register to reply here.

Similar threads

S
Google launches Nano Banana 2 Lite for fast, low-cost AI image generation
Replies
3
Views
27
Julio Franco
Julio Franco
midian182
Google unveils Gemini's "nano banana" model, taking AI image generation to the next level
Replies
9
Views
370
CaptainClankers
C
midian182
Google Gemini's nano banana AI image generator is blowing up online - take a look at what it can do
2
Replies
27
Views
918
toooooot
T

Latest posts

Back