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

421–430 of 593 posts

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

#421

Post by WheatMillington »

keiferski wrote: post #237

Some random predictions about what AI image generation tools will do/are doing to art: 1. The narrative/life of the artist becomes a lot more important. The most successful artists are ones that craft a story around their life and art, and don't just create stuff and stop. This will become even more important. 2. Originality matters more than ever. By design, these tools can only copy and mix things that already exis…

>2. Originality matters more than ever. By design, these tools can only copy and mix things that already exist. But they aren't alive, they don't live in the world and have experiences, and they can't create something truly new.

How can you say this? These models can trivially create things that have never existed, and you can easily test this yourself.

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

#422

Post by fc417fc802 »

jacquesm wrote: post #209
hypeatei wrote: post #179

Earlier quoted context omitted.

I'll just be extremely candid: a lot of people don't give a shit about these art pieces or art in general. It's okay if you do, there is nothing wrong with that, but it's a myopic view that the world would be worse off if we didn't have a portrait of Mona Lisa.

Yes, who gives a shit about culture, after all humanity doesn't really need it...

If culture revolves solely around exclusivity of technique then indeed, who should give a shit about it? I don't think that's the case though.

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

#423

Post by selridge »

bjackman wrote: post #276
keiferski wrote: post #237

Some random predictions about what AI image generation tools will do/are doing to art: 1. The narrative/life of the artist becomes a lot more important. The most successful artists are ones that craft a story around their life and art, and don't just create stuff and stop. This will become even more important. 2. Originality matters more than ever. By design, these tools can only copy and mix things that already exis…

> The narrative/life of the artist becomes a lot more important. Less the narrative of the art's production and more the message that it's conveying. I don't mean (necessarily) a political message or a message that can be put in to words. But the abstract sense of connecting with the human who created it some way. This isn't just art though. An example: soon, Sora will be able to generate very convincing footage of a…

The problem is, we have no real understanding of what people will or will not do with this technology. Will humans only be interested in “real“ activity?

We have no idea, and most people are just guessing in a way that flatters some understanding of art that they have. We also frankly have no idea what the permanent relationship of humans to art is even without AI.

The television is less than 100 years old. There aren’t very many, but there are some people alive today who were alive before the television was created. The computer is about 80 years old. The whole idea of photography and of recorded audio is less uthan 150 years old.

We are still living in the aftershocks of industrial production of art. It is foolish to imagine that in the midst of this chaos, we can point the way forward with ease.

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

#424

Post by avaer »

javier123454321 wrote: post #370
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 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.

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

#425

Post by avmich »

javier123454321 wrote: post #420
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?

Being alive is divine. It doesn't matter if you understand it or not. It's a beautiful thing to have a consciousness in this world, and to have the ability to create, to love. It takes a huge intellectual effort to try to trick yourself out of believing something so intuitive as that.

There are many examples when scientists strongly believed something to be obviously impossible and yet being wrong - Poisson spot or heavier-than-air flight machines coming to mind. So what you believe might be intuitive - that doesn't preclude it from potentially being wrong, unless you proved the impossibility.

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

#426

Post by jpadkins »

keiferski wrote: post #237

Some random predictions about what AI image generation tools will do/are doing to art: 1. The narrative/life of the artist becomes a lot more important. The most successful artists are ones that craft a story around their life and art, and don't just create stuff and stop. This will become even more important. 2. Originality matters more than ever. By design, these tools can only copy and mix things that already exis…

> 4. Taste continues to be the single most important thing. The vast, vast majority of AI art out there is...not very good. It's not going to get better, because the lack of taste isn't a technical problem.

I agree on current AI art taste, but disagree that it can't be improved. I think art AI companies can hire skilled "taste makers" and use their feedback loop as RL for AI art models. I think this area will always be in flux, and will vary by subpopulation so it will be a job role always in demand.

Do you think taste is something that cannot be taught/learned? Are certain individuals just born with good taste; it's an immutable property?

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

#427

Post by pixl97 »

gambiting wrote: post #411
rvnx wrote: post #409

Earlier quoted context omitted.

We can't know if consciousness emerges but does it actually matter ? These entities, whoever they are, they act on our world, they are real, and more and more over time they will get independent from humans, eventually becoming different species that can self-replicate. For now they need legs and arms to interact with the physical world but I am certain that 100 years from now they will be an integral part of the soc…

>>These entities, whoever they are, they act on our world, they are real, and more and more over time they will get independent from humans, eventually becoming different species that can self-replicate. See, I don't believe that for even one second. They are just very clever calculators, that's all. But they are also dumb like a brick most of the time. It's a pretend intelligence at best.

We will never prove machines are intelligent.

We will only prove humans are not.

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

#428

Post by vunderba »

micw wrote: post #407
vunderba wrote: post #316

Earlier quoted context omitted.

NB Pro can do some seriously impressive edits around interior decorating - see the prompt that replaces the window with a mirror which correctly reflects the room. It's not perfect, but it's still damn impressive. https://mordenstar.com/blog/edits-with-nanobanana

I'm deeply impressed, especially with the "replace window by mirror". It did not only do the window thing right, it also changed the illumination of the whole room while keeping all the other details unchanged.

Right? That part kind of blew my mind too - the multimodal model actually altered the overall lighting in the room by eliminating all the reflections and specular highlights when the natural light was taken away WITHOUT being asked in the prompt.

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

#429

Post by the_af »

mrec wrote: post #364
the_af wrote: post #287

Earlier quoted context omitted.

> except The Mandalorian Mandalorian started strong, with cool spaghetti Western vibes, and then ended up devolving into mediocrity too. In my opinion. Haven't watched Andor yet.

Andor is fantastic, but I think it's important to set expectations before going in. Compared to other SW content it's much slower-paced and more restrained/cerebral. Mandalorian didn't do much for me; too gamey/Marvel-ey/cartooney.

I've heard Andor described as having the same vibe as The Mandalorian's episode "The Convert"; the one about the former Imperial scientist being rehabilitated and living in an apartment block with other former Imperials.

If so, I will like Andor. I really liked "The Convert".

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

#430

Post by divan »

What is annoying about Nano Banana, is how bad is experience when you try to iterate or, especially, repeat same task for another photo. After second of third image it starts randomly ansering with complete nonsense like "I'm just a language mode and can't assist with that" or "I can't do that" (with absolutely the same prompt it had no issues 2 photos in a row in the same chat).

It also gaslights me, when I point out on an error. I tried to create a cartoon portrait of the person from photo and use background from another photo. It got wrong the order of photos. I provided filenames and explicitly told which one is for person and which for bg. It generated it wrong again, and all attempts to explain that it got it wrong were met with "No, it's YOU incorrect". So frustrating.

Post reply on HN