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

Nano Banana 2: Google's latest AI image generation model

blog.google

Post reply on HN
Print view View original

481–490 of 593 posts

Re: Nano Banana 2: Google's latest AI image generation model

#481

Post by kevincox »

toraway wrote: post #480
kevincox wrote: post #52

Earlier quoted context omitted.

I actually think this was a good thing. Manipulating images incredibly convincingly was already possible but the cost was high (many hours of highly skilled work). So many people assumed that most images they were seeing were "authentic" without much consideration. By making these fake images ubiquitous we are forcing people to quickly learn that they can't believe what they see on the internet and tracking down sour…

In reality: millions of boomers are scrolling FB this very minute reacting to the most obviously fake rage/surprise/love bait AI slop you've ever seen.

They were scrolling through fake bait long before generative AI

Re: Nano Banana 2: Google's latest AI image generation model

#482

Post by kevincox »

ByThyGrace wrote: post #472
kevincox wrote: post #52

Earlier quoted context omitted.

I actually think this was a good thing. Manipulating images incredibly convincingly was already possible but the cost was high (many hours of highly skilled work). So many people assumed that most images they were seeing were "authentic" without much consideration. By making these fake images ubiquitous we are forcing people to quickly learn that they can't believe what they see on the internet and tracking down sour…

> By making these fake images ubiquitous we are forcing people to quickly learn That's quite the high opinion on the self-improvement ability of your Average Joe. This kind of behavior only comes with an awareness, previously learned, and an alertness of mind. You need the population at large to be able to do this. How if not, say, teaching this at schools and waiting for the next generation to reach adulthood, would…

I agree that improvement for the Average Joe will be very hard. I also think that taking more attention to teach the younger generation is vitally important. But mostly I don't see an alternative. I don't think we can protect people from fake information without giving up our freedom, and that isn't a viable alternative in my mind. So what is left but trying our hardest to teach people to think critically?

Re: Nano Banana 2: Google's latest AI image generation model

#483

Post by dzhiurgis »

blibble wrote: post #331
fwip wrote: post #292

Earlier quoted context omitted.

In what way? Certainly not for the models, who lose their income/job. Probably not better for the consumer, either.

or the taxpayer the high end probably pay the same sort of tax as professional footballers

Sex work shouldn't be shunned, but it's not a normal profession either. Mental health, addiction and abuse is just as much of a problem online and in countries where prostitution is legal and normalized.

Re: Nano Banana 2: Google's latest AI image generation model

#484

Post by whattheheckheck »

shinycode wrote: post #438
slumberlust wrote: post #386

Earlier quoted context omitted.

Not understanding how consciousness is created doesn't make it divine. Do you think it's an impossible task or just one we need more time to figure out?

Physicalists say consciousness emerges from matter. The other camp says matter comes from consciousness. Federico Faggin, inventor of the microprocessor, says consciousness cannot emerge from matter because matter is inert and not self-conscious, so it cannot produce consciousness. Who’s right and who’s wrong? Time will tell. But it is also wrong to claim that consciousness emerges from matter until it is proven (aka…

So some kind of ether conscious energy animated cells to fight entropy?

Re: Nano Banana 2: Google's latest AI image generation model

#485

Post by vunderba »

UnknownBanana wrote: post #446
vunderba wrote: post #76

I've only had a brief opportunity to try out NB Pro 2 (`gemini-3.1-flash-image-preview`), so I haven't had a chance to update GenAI Showdown. Here's some of my captions that tend to trip up even state-of-the-art models. https://mordenstar.com/other/nb-pro-2-tests So far it does feel more iterative than an entirely new leap in terms of capabilities, but I haven't run it through the more multimodal aspects such as edit…

I love your website, art and projects!

Thanks I appreciate it!

Re: Nano Banana 2: Google's latest AI image generation model

#486

Post by notnullorvoid »

There's something odd feeling about many of the latest AI image models (NB and NB2 included), they feel almost too polished, calculated, and rigid. It doesn't take much effort to get some art with a sense of originality or flow from Stable Diffusion, but I can't seem to prompt NB to get similar results. SD definitely struggles with details especially when trying photo realism, but it'd be nice if newer models could get back some of the roughness that made SD good.

Re: Nano Banana 2: Google's latest AI image generation model

#487

Post by ctmnt »

anabab wrote: post #374
ctmnt wrote: post #204

Earlier quoted context omitted.

“Still” isn’t the right word. Once Polaroid stopped making the film, closed their factories, and sold or junked their machines, their supplies did the same, and so some of the components stopped being manufactured and available for purchase. What’s sold now as Polaroid film was a reinvention of the same idea. And it’s notably not as good. The dwindling stock of unused true Polaroid film is getting absurdly expensive…

> The dwindling stock of unused true Polaroid film is getting absurdly expensive as a result. what's the point? ain't all of this stock expired, with photos ending up just blobs or being gamble at best? (even for film stored in freezers)

It’s always a gamble, but no, lots of it is still good. There are many photographers still working with it. Jean-Andre Antoine [1] is one of the more famous; if you’re ever in NY, go see him in SoHo, he’s a super nice guy and a fantastic photographer. And he uses a Speed Graphic!

1: https://www.jeanandreantoine.com/

Re: Nano Banana 2: Google's latest AI image generation model

#488

Post by rcxdude »

shinycode wrote: post #438
slumberlust wrote: post #386

Earlier quoted context omitted.

Not understanding how consciousness is created doesn't make it divine. Do you think it's an impossible task or just one we need more time to figure out?

Physicalists say consciousness emerges from matter. The other camp says matter comes from consciousness. Federico Faggin, inventor of the microprocessor, says consciousness cannot emerge from matter because matter is inert and not self-conscious, so it cannot produce consciousness. Who’s right and who’s wrong? Time will tell. But it is also wrong to claim that consciousness emerges from matter until it is proven (aka…

I mean, the nature of subjectivity prevents you from knowing anything but your own experience. There is not any objective evidence that could truly distinguish solipsism from panpsychism, so philosophically you need to ask a different question to hope to get a useful answer.

Re: Nano Banana 2: Google's latest AI image generation model

#489

Post by empath75 »

ACCount37 wrote: post #323
avmich wrote: post #269

Earlier quoted context omitted.

I mostly disagree. > 1... The narrative/life of the artist becomes a lot more important. When I watch a movie, I don't care about the artist's life. I care about character life, that's very different. > 2... Originality matters more than ever. By design, these tools can only copy and mix things that already exist. It's like you assigning to humans divine capabilities :) . Hyperbolizing a little, humans also only copy…

It's kind of like the difference between something being enjoyable for you, and something being widely popular? In a hypothetical world of "AI can produce a lot of extremely high quality art", you can easily find (or commission) AI art you would absolutely love. But it probably wouldn't be something that anyone else would find a lot of value in? There will be no AI-generated Titanic. There will be many AI-generated m…

I think because art is usually so difficult to create that “popularity” is sort of an unstated metric that most people use to judge its quality, but ai can make disposable art for one person on demand and if doesn’t matter at all if anyone else sees it, let alone likes it.

If someone makes a dumb video that they got an AI to make of a panda surfing on mac and cheese, giggles and deletes it, that’s maybe good art? I don’t know. The scale they are able to produce stuff is unbelievable and changes a lot of assumptions you make about the way that world works.

The future isn’t watching TV, it’s talking to your tv show while it is created in real time based on your feedback.

Re: Nano Banana 2: Google's latest AI image generation model

#490

Post by javier123454321 »

avaer wrote: post #424
javier123454321 wrote: post #370

Earlier quoted context omitted.

> It's like you assigning to humans divine capabilities :) I can't tell if you're being facetious. But being an embodied consciousness with the ability to create is as divine as it gets. We'd do well to remember.

> being an embodied consciousness with the ability to create is as divine as it gets This is a very, very weak criterion for divinity. If this is truly it, we should prepare with great haste for the arrival of our artificial gods. Because by this (IMO silly) metric it seems they will be more divine than us.

Yeah id argue that all existence is equally sacred. But consciousness is where that is manifest most visibly.
Post reply on HN