Live data from Hacker News

Nano Banana Pro

blog.google

151–160 of 718 posts

Re: Nano Banana Pro

#151

I...worked on the detailed Nano Banana prompt engineering analysis for months ( https://news.ycombinator.com/item?id=45917875 )...and...Google just...Google released a new version. Nano Banana Pro should work with my gemimg package ( https://github.com/minimaxir/gemimg ) without pushing a new version by passing: g = GemImg(model="gemini-3-pro-image-preview") I'll add the new output resolutions and other features ASAP…

this is pretty cool! have you found success with image editing in nano banana - i mean photoshop-like stuff. from your article i seem to wonder if nano banana is good for editing versus generating new images.

Re: Nano Banana Pro

#152

Earlier quoted context omitted.

Mostly highly specific images in blog posts but I also use it for occasional comics. https://mordenstar.com/portfolio/gorgonzo https://mordenstar.com/portfolio/brawny-tortillas https://mordenstar.com/portfolio/ms-frizzle-lava

I'm kind of reading between the lines, but sounds like "for fun" which makes sense / what I generally expected for why people use it

I think that's a fair assessment. I write a lot of bizarre fiction in my spare time, so Text2Image tools are a fun way to see my visions visualized.

Like this one:

A piano where the keyboard is wrapped in a circular interface surrounding a drummer's stool connected to a motor that spins the seat, with a foot-operated pedal to control rotation speed for endless glissandos.

Re: Nano Banana Pro

#153

Earlier quoted context omitted.

If there was a standardized identifier, there would be software dedicated to just removing it. I don't see how it would defeat the cat and mouse game.

It doesn't have to be perfect to be helpful. For example, it's trivial to post an advertisement without disclosure. Yet it's illegal, so large players mostly comply and harm is less likely on the whole.

You'd need a similar law around posting AI photos/videos without disclosure. Which maybe is where we're heading.

It still won't prevent it, but it would prevent large players from doing it.

Re: Nano Banana Pro

#154

Is there an "in joke" to this name that I am too old to get? Or it's just a whimsically random name?

I believe it’s an internal code name that stuck.

To expand, it comes from the stealth name it was given on LMArena I believe. The model made news while still in "stealth mode" and so Google capitalised on the PR they'd already built around that and just launched it officially with the same name.

Re: Nano Banana Pro

#155
post #103

Maybe I'm an obscure case, but I'm just not sure what I'd use an image generation model for. For people that use them (regularly or not), what do you use them for?

Nano Banana is more of an image editing model, which probably has more broad use cases for non-generative applications: interior decorating, architecture, picking wardrobes, etc.

Definitely, but don't sleep on its generative capacities either. You can give it a image and instruct it "Use the attached image purely as a stylistic reference" and then proceed to use it as a regular generative model.

Re: Nano Banana Pro

#156
post #79

Earlier quoted context omitted.

If there was a standardized identifier, there would be software dedicated to just removing it. I don't see how it would defeat the cat and mouse game.

I don't think it will be easy to just remove it. It's built into the image and thus won't be the same every time. Plus, any service good at reverse-image search (like Google) can basically apply that to determine whether they generated it. There will always be a way to defeat anything, but I don't see why this won't work for like 90% of cases.

It would be like standardizing a captcha, you make a single target to defeat. Whether it is easy or hard is irrelevant.

Re: Nano Banana Pro

#157

The interesting tidbit here is SynthID. While a good first step, it doesn't solve the problem of AI generated content NOT having any kind of watermark. So we can prove that something WITH the ID is AI generated but we can't prove that something without one ISN'T AI generated. Like it would be nice if all photo and video generated by the big players would have some kind of standardized identifier on them - but now you…

Some days it feels like I'm the only hacker left who doesn't want government mandated watermarking in creative tools. Were politicians 20 years ago as overreative they'd have demanded Photoshop leave a trace on anything it edited. The amount of moral panic is off the charts. It's still a computer, and we still shouldn't trust everything we see. The fundamentals haven't changed.

Politicians absolutely were doing this 20-30 years ago. Plenty of folks here are old enough to remember debates on Slashdot around the Communications Decency Act, Child Online Protection Act, Children's Online Privacy Protection Act, Children's Internet Protection Act, et al.

https://en.wikipedia.org/wiki/Communications_Decency_Act

Re: Nano Banana Pro

#158

Earlier quoted context omitted.

Some days it feels like I'm the only hacker left who doesn't want government mandated watermarking in creative tools. Were politicians 20 years ago as overreative they'd have demanded Photoshop leave a trace on anything it edited. The amount of moral panic is off the charts. It's still a computer, and we still shouldn't trust everything we see. The fundamentals haven't changed.

> It's still a computer, and we still shouldn't trust everything we see. The fundamentals haven't changed. I think that by now it should be crystal clear to everyone that it matters a lot the sheer scale a new technology permits for $nefarious_intent. Knives (under a certain size) are not regulated. Guns are regulated in most countries. Atomic bombs are definitely regulated. They can all kill people if used badly, th…

> Knives (under a certain size) are not regulated. Guns are regulated in most countries. Atomic bombs are definitely regulated

I don’t think this is a good comparison: knives are easy to produce, guns a bit harder, atomic bombs definitely harder. You should find something that is as easy to produce as a knife, but regulated.

Re: Nano Banana Pro

#159

I...worked on the detailed Nano Banana prompt engineering analysis for months ( https://news.ycombinator.com/item?id=45917875 )...and...Google just...Google released a new version. Nano Banana Pro should work with my gemimg package ( https://github.com/minimaxir/gemimg ) without pushing a new version by passing: g = GemImg(model="gemini-3-pro-image-preview") I'll add the new output resolutions and other features ASAP…

this is pretty cool! have you found success with image editing in nano banana - i mean photoshop-like stuff. from your article i seem to wonder if nano banana is good for editing versus generating new images.

That IS the use-case for Nano Banana (as opposed to pure generative like Imagen4).

In my benchmarks, Nano-Banana scores a 7 out of 12. Seedream4 managed to outpace it, but Seedream can also introduce slight tone mapping variations. NB is the gold standard for highly localized edits.

Comparisons of Seedream4, NanoBanana, gpt-image-1, etc.

https://genai-showdown.specr.net/image-editing

Re: Nano Banana Pro

#160

Earlier quoted context omitted.

You do know that every color copier comes with the ability to identify US currency and would refuse to copy it? And that every color printer leaves a pattern of faint yellow dots on every printout that uniquely identifies the printer?

And that's not a good thing.

I'm just responding to this by OP:

> Were politicians 20 years ago as overreative they'd have demanded Photoshop leave a trace on anything it edited.

Post reply on HN