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

421–430 of 718 posts

Re: Nano Banana Pro

#421

Post by minimaxir »

LaurensBER wrote: post #373
vunderba wrote: post #327

Earlier quoted context omitted.

If it's just the API you're interested in, Fal.ai has put Nano-Banana-Pro up for both generative and editing. A great deal less annoying to sign up for them since they're a pretty generalized provider of lots of AI related models. https://fal.ai/models/fal-ai/nano-banana-pro

In general a better option, in the early days of AI video I tried to generate a video of a golden retriever using Google's AI Studio. It generated 4 in the highest quality and charged me 36 bucks. Not a crazy amount but definitely an unwelcome suprise. Fal.ai is pay as you go and has the cost right upfront.

Vertex AI Studio setting a default of 4 videos where each video is several dollars to generate is a very funny footgun.

Re: Nano Banana Pro

#422

Post by azeirah »

bobbylarrybobby wrote: post #402
mlsu wrote: post #317

Earlier quoted context omitted.

We are just very sharp when it comes to seeing small differences in images. I'm reminded of when the air force decided to create a pilot seat that worked for everyone. They took the average body dimensions of all their recruits and designed a seat to fit the average. It turned out, the seat fit none of their recruits. [1] I think AI image generation is a lot like this. When you train on all images, you get to this we…

What determines which “average” AI models latch onto? At a pixel level, the average of every image is a grayish rectangle; that's obviously not what we mean and AI does not produce that. At a slightly higher level, the average of every image is the average of every subject every photographed or drawn (human, tree, house, plate of food, ...) in concept space; but AI still doesn't generate a human with branches or a ho…

Isn't the space you're talking about the input images that are close to the textual prompt?

These models are trained on image+text pairs. So if you prompt something like "an apple" you get a conceptual average of all images containing apples. Depending on your dataset, it's likely going to be a photograph of an apple in the center.

Re: Nano Banana Pro

#423

Post by xmprt »

logankilpatrick wrote: post #419
ceroxylon wrote: post #306

Google has been stomping around like Godzilla this week, and this is the first time I decided to link my card to their AI studio. I had seen people saying that they gave up and went to another platform because it was "impossible to pay". I thought this was strange, but after trying to get a working API key for the past half hour, I see what they mean. Everything is set up, I see a message that says "You're using Paid…

First off, apologies for the bad first impression, the team is pushing super hard to make sure it is easy to access these models. - On permission issue, not sure I follow the flow that got you there, pls email me more details if you are able too and happy to debug: Lkilpatrick@google.com - On overall friction for billing: we are working on a new billing experience built right into AI Studio that will make it super ea…

Please make sure that the new billing experience has support for billing limits and prepaid balance (to avoid unexpected charges)!

Re: Nano Banana Pro

#424

Post by brandon272 »

logankilpatrick wrote: post #419
ceroxylon wrote: post #306

Google has been stomping around like Godzilla this week, and this is the first time I decided to link my card to their AI studio. I had seen people saying that they gave up and went to another platform because it was "impossible to pay". I thought this was strange, but after trying to get a working API key for the past half hour, I see what they mean. Everything is set up, I see a message that says "You're using Paid…

First off, apologies for the bad first impression, the team is pushing super hard to make sure it is easy to access these models. - On permission issue, not sure I follow the flow that got you there, pls email me more details if you are able too and happy to debug: Lkilpatrick@google.com - On overall friction for billing: we are working on a new billing experience built right into AI Studio that will make it super ea…

Just a note that your HN bio says "Developer Relations @OpenAI"

Re: Nano Banana Pro

#425

Post by marcellus23 »

withinboredom wrote: post #283
Jabrov wrote: post #275

Earlier quoted context omitted.

I don't know if that's so much a mistake as it is ambiguity though? To me, using the viewer's perspective in this case seems totally reasonable. Does it still use the viewer's perspective if the prompt specifies "Put a strawberry in the _patient's left eye_"? If it does, then you're onto something. Otherwise I completely disagree with this.

“The right socket” can only be implied one way when talking about a body just like you only have one right hand despite the fact that it is on my left when looking at you.

I think the fact that anyone in this thread thinks it's ambiguous is proof by definition that it's ambiguous.

Re: Nano Banana Pro

#426

Post by fwip »

simonw wrote: post #346
fwip wrote: post #252

Earlier quoted context omitted.

Competent digital watermarks usually survive the 'analog hole'. Screen-cam resistant watermarks have been in use since at least 2020, and if memory serves, back to 2010 when I first starting reading about them, but I don't recall what it was called back then.

I just tried asking Gemini about a photo I took of my screen showing an image I edited with Nano Banana Pro... and it said "All or part of the content was generated with Google AI. SynthID detected in less than 25% of the image". Photo-of-a-screen: https://gemini.google.com/share/ab587bdcd03e It reported 25-50% for the image without having been through that analog hole: https://gemini.google.com/share/022e486fd6bf

Thanks for testing it!

Re: Nano Banana Pro

#427

Post by apt-apt-apt-apt »

egypturnash wrote: post #285

Everyone who worked on this is a traitor to the human race. Why do we need to make it impossible to make a living as an artist? Who thinks an endless tsunami of garbage “content” churned out by machines dropping the bottom out of all artistic disciplines is a good idea?

On the flip side, it can be good for the environment. Instead of spending tons of resources burning a car or doing a bunch of setup to get a shot, we can prompt it using relatively fewer energy resources.

Re: Nano Banana Pro

#428

Post by nrhrjrjrjtntbt »

simonw wrote: post #193

This thing's ability to produce entire infographics from a short prompt is really impressive, especially since it can run extra Google searches first. I tried this prompt: Infographic explaining how the Datasette open source project works Here's the result: https://simonwillison.net/2025/Nov/20/nano-banana-pro/#creat...

Game changer for architecture diagrams.

Re: Nano Banana Pro

#429

Post by cyanf »

mlsu wrote: post #317
Bjorkbat wrote: post #289

Something I find weird about AI image generation models is that even though they no longer produce weird "artifacts" that give away that the fact that it was AI generated, you can still recognize that it's AI due to stylistic choices. Not all examples they gave were like this. The example they gave of the word "Typography" would have fooled me as human-made. The infographics stood out though. I would have immediately…

We are just very sharp when it comes to seeing small differences in images. I'm reminded of when the air force decided to create a pilot seat that worked for everyone. They took the average body dimensions of all their recruits and designed a seat to fit the average. It turned out, the seat fit none of their recruits. [1] I think AI image generation is a lot like this. When you train on all images, you get to this we…

Tragedy of the aggregate.

Re: Nano Banana Pro

#430

Post by fwip »

potsandpans wrote: post #297
fwip wrote: post #162

Earlier quoted context omitted.

Why not? Like, genuinely.

I generally don't think that's it's good or just for a government to collude with manufacturers to track/trace it's citizens without consent or notice. And even if notice was given, I'd still be against it The arguments put forward by people generally I don't find compelling -- for example, in this thread around protecting against counterfeit. The "force" applied to address these concerns is totally out of proportion…

Gotcha, thanks for the explanation. I think that personally, I agree with your stance that it's a bad kind of thing for government to do, but in practice I find that I'm in favor of the effects of this specific law. (Perhaps I need to do some thinking.)
Post reply on HN