Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Nano Banana Pro

blog.google

Post reply on HN
Print view View original

141–150 of 718 posts

Re: Nano Banana Pro

#141

Post by rcarr »

aqme28 wrote: post #79
slashdev wrote: post #55

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.

You could probably just stick your image in another model or tool that didn't watermark and have it regenerate the image as accurately as possible.

Re: Nano Banana Pro

#143

Post by potsandpans »

mlmonkey wrote: post #132
akersten wrote: post #112

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.

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.

Re: Nano Banana Pro

#144

Post by darkwater »

akersten wrote: post #112
theoldgreybeard wrote: post #43

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.

> 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, though.

When a photo was faked/composed with old tech, it was relatively easy to spot. With photoshop, it became more complicated to spot it but at the same time it wasn't easy to mass-produce altered images. Large models are changing the rules here as well.

Re: Nano Banana Pro

#146

Post by ovo101 »

Nano Banana Pro sounds like classic Google branding: quirky name, serious tech underneath. I’m curious whether the “Pro” here is about actual professional‑grade features or just marketing polish. Either way, it’s another reminder that naming can shape expectations as much as specs.

Re: Nano Banana Pro

#147

Post by sabatonfan »

mlmonkey wrote: post #132
akersten wrote: post #112

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.

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?

Is this something strictly with the US currency notes or is the same true for other countries currency as well?

Re: Nano Banana Pro

#148

Post by zaidf »

theoldgreybeard wrote: post #43

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…

This is what C2PA is trying to do: https://c2pa.org/

Re: Nano Banana Pro

#149

Post by minimaxir »

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. However, looking at the pricing (https://ai.google.dev/gemini-api/docs/pricing#standard_1), I'm definitely not changing the default model to Pro as $0.13 per 1k/2k output will make it a tougher sell.

EDIT: Something interesting in the docs: https://ai.google.dev/gemini-api/docs/image-generation#think...

> The model generates up to two interim images to test composition and logic. The last image within Thinking is also the final rendered image.

Maybe that's partially why the cost is higher: it's hard to tell if intermediate images are billed in addition to the output. However, this could cause an issue with the base gemimg and have it return an intermediate image instead of the final image depending on how the output is constructed, so will need to double-check.

Re: Nano Banana Pro

#150

Post by dpark »

akersten wrote: post #112
theoldgreybeard wrote: post #43

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.

I suspect watermarking ends up being a net negative, as people learn to trust that lack of a watermark indicates authenticity. Propaganda won’t have the watermark.
Post reply on HN