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

71–80 of 593 posts

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

#71

Post by coldtea »

wordpad wrote: post #43
jacquesm wrote: post #21

What a great thing this didn't exist in the past. We likely wouldn't have had any of the amazing artworks that we have now. Imagine an AI generated Mona Lisa, Nightwatch or Sistine Chapel ceiling because prompting would have been so much cheaper than paying Leonardo, Rembrandt or Michelangelo... Now extrapolate to all other artforms. Sculpture seems safe, for now, but only barely so.

I feel like the complete opposite is true. Artists aren't doing it for the money. With advanced tools like these they wouldve iterated much faster and created much grander designs. Art is about pushing limits of what's possible and AI just raises those limits.

>Art is about pushing limits of what's possible

That's engineering, if that.

Art isn't, and has never been about that.

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

#72

Post by whynotmaybe »

garbawarb wrote: post #38
yakattak wrote: post #16

I think this tech is cool, from an engineering perspective. I’m trying to figure out if there’s any justification for using it in a business world outside of: “We don’t want to pay an artist.” You can argue things like code generation are an extension of the engineer wielding it. Image generation just seems like a net negative overall if it’s used at scale. Edit: By scale, I mean large corporations putting content in…

Advertising? "We don't want to pay an artist" goes a long way for a small business with a limited budget.

We're using voice generation from clipchamp for our promotional videos.

It's an ethical conundrum because we're not paying anyone, but we don't have the money to pay anyone, and it's good enough for our budget.

But we're getting used to the process of changing a part of the text in a few seconds without any artist involved and for 0$.

I guess that soon we'll be able to create voice sample from know personalities for a few $ with prices based on the popularity of the artist and some sanity check based on the artist preferences.

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

#74

Post by techjamie »

jacquesm wrote: post #21

What a great thing this didn't exist in the past. We likely wouldn't have had any of the amazing artworks that we have now. Imagine an AI generated Mona Lisa, Nightwatch or Sistine Chapel ceiling because prompting would have been so much cheaper than paying Leonardo, Rembrandt or Michelangelo... Now extrapolate to all other artforms. Sculpture seems safe, for now, but only barely so.

Ironically we live in a time that, overall, is probably better for artists than the world any of those guys grew up in. People have always valued art but not the artists, and many artists through history, including the famous ones, died broke with their works only posthumously attaining value.

These days, through commissions, art is a much more viable profession than it ever was.

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

#75

Post by KK7NIL »

hmokiguess wrote: post #50

The Chinese are so much ahead in this space, their models are way better at this stuff. For example, https://hunyuan.tencent.com/image/en?tabIndex=0 and https://seed.bytedance.com/en/seedream5_0_lite

Kind of a pointless comment without a link to such a model.

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

#76

Post by vunderba »

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 editing existing images.

That being said, it actually managed the King Louie jump rope test which surprised me.

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

#77

Post by kristjansson »

fasteddie31003 wrote: post #59

I'm building my personal home right now. The AI image models have been a game-changer in designing the look of the house. My architect did an OK job, but the details that Nano Banana added really bring the house up a notch. I just do hundreds of renders from the basic 3D models and I find looks that I like and iterate from there. We are implementing the renders from Nano Banana over our Interior Designers designs. We…

Part of the job of interior design is delivering the promised images in … yknow, physical reality? How are you going from nano banana images to actual plans, materials, finishes, products, paint codes, … ?

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

#78

Post by lm28469 »

wordpad wrote: post #43
jacquesm wrote: post #21

What a great thing this didn't exist in the past. We likely wouldn't have had any of the amazing artworks that we have now. Imagine an AI generated Mona Lisa, Nightwatch or Sistine Chapel ceiling because prompting would have been so much cheaper than paying Leonardo, Rembrandt or Michelangelo... Now extrapolate to all other artforms. Sculpture seems safe, for now, but only barely so.

I feel like the complete opposite is true. Artists aren't doing it for the money. With advanced tools like these they wouldve iterated much faster and created much grander designs. Art is about pushing limits of what's possible and AI just raises those limits.

Have you talked to "artists"? In my experience the vast majority say the opposite of what you worded here.

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

#79

Post by coldtea »

ahtihn wrote: post #49
jacquesm wrote: post #21

What a great thing this didn't exist in the past. We likely wouldn't have had any of the amazing artworks that we have now. Imagine an AI generated Mona Lisa, Nightwatch or Sistine Chapel ceiling because prompting would have been so much cheaper than paying Leonardo, Rembrandt or Michelangelo... Now extrapolate to all other artforms. Sculpture seems safe, for now, but only barely so.

Would anyone even care about Mona Lisa if the exact same painting was done by a random nobody? It's just a portrait.

Most people no. Then again most people are idiots barely aware of the world they live in, much less culture.

People who actually care about art, if given a chance to see it, yes.

Of course, it being done by Davinci is not some random fact about the painting - as if a painting is a mere artifact.

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

#80

Post by awepofiwaop »

rm_-rf_slash wrote: post #45
garbawarb wrote: post #38

Earlier quoted context omitted.

Advertising? "We don't want to pay an artist" goes a long way for a small business with a limited budget.

It can also backfire. AI slop ads and marketing material imply cut corners and poor quality products. If a bakery isn’t going to bother touching up its AI slop banner, I don’t expect their cookies to be great either.

The amount of lost revenue due to the implication of cut corners needs to be higher than the cost of hiring an artist by enough of a margin that the managers who make the decision start to care, and enough that they're willing to put the effort into hiring an artist.
Post reply on HN