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

541–550 of 718 posts

Re: Nano Banana Pro

#541

Post by rl3 »

ants_everywhere wrote: post #455
echelon wrote: post #412

Earlier quoted context omitted.

There's the solution right there. Google is still growing its AI "sea legs". They've turned the ship around on a dime and things are still a little janky. Truly a "startup mode" pivot. While we're on this subject of "Google has been stomping around like Godzilla", this is a nice place to state that I think the tide of AI is turning and the new battle lines are starting to appear. Google looks like it's going to lay w…

This is also my take on the market, although I also thought it looked like they were going to win 2 years ago too. > How are we feeling about Google putting everyone out of work and owning the future? It's starting to feel that way to me. Not great, but if one company or nation is going to come out on top in AI then every other realistic alternative at the moment is worse than Google. OpenAI, Microsoft, Facebook/Meta…

>OpenAI, Microsoft, Facebook/Meta, and X all have worse track records on ethics.

I'd argue Google is evil as OpenAI (at least lately), but I otherwise generally agree with your sentiment.

If Google does lay waste to its competitors, then I hope said competitors open source their frontier models before completely sinking.

Re: Nano Banana Pro

#542

Post by delifue »

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…

Maybe the AI feeling is illusion because you already know it's AI-generated, just confirmation bias. Like wine tastes better after knowing it's expensive. In real world AI-generated images have passed Turing test. Only by double blind test do you can be really sure.

Re: Nano Banana Pro

#543

Post by energy123 »

nrhrjrjrjtntbt wrote: post #428
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.

I'm finding it bad at instruction following for architectural specs (physical not software), where you tell it what goes where, and it ignores you and does some average-ish thing it's seen before. It looks visually appealing though.

Re: Nano Banana Pro

#544

Post by rl3 »

vunderba wrote: post #396

Alright results are in! I've re-run all my editing based adherence related prompts through Nano Banana Pro. NB Pro managed to successfully pass SHRDLU, the M&M Van Halen test (as verified independently by Simon), and the Scorpio street test - all of which the original NB failed. Model results 1. Nano Banana Pro: 10 / 12 2. Seedream4: 9 / 12 3. Nano Banana: 7 / 12 4. Qwen Image Edit: 6 / 12 https://genai-showdown.spec…

"Remove all the trash from the street and sidewalk. Replace the sleeping person on the ground with a green street bench. Change the parking meter into a planted tree."

Three sentences that do a great job summing up modern big tech. The new model even manages to [digitally] remove all trash.

Re: Nano Banana Pro

#545

Post by jofzar »

vunderba wrote: post #512
sefrost wrote: post #484

Earlier quoted context omitted.

Have you ever considered a “partial pass”? Perhaps it would be an easy cop out of making a decision if you had to choose something outside of pass/fail.

That's not a bad suggestion. I thought about adding a numerical score but it felt like it was bit overwhelming at the time. Maybe I should revisit it though in the form of: Fail = 0 points Partial = 0.5 points Success = 1 point There's definitely a couple of pictures where I feel like I'm at the optometrist and somehow failing an eye exam (1 or 2, A... or B).

I agree with this, some of those are "passing" and others are really passing. Specially with how much better some of the new model is compared to old ones.

I think the paws one is a good example where I think the new model got 100% while the other was more like 75%

Re: Nano Banana Pro

#546

Post by red75prime »

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…

The model "averages" in the latent space. That is in the space of packed image representations. I put "averages" into scare quotes, because I think it might be due to legal reasons. The model training might be organized in such a way as to push its default style away from styles of prominent artists. I might be wrong though.

Re: Nano Banana Pro

#547

Post by al_be_back »

A houseplant with tiny turtles for leaves… very informative if under the influence of some substances.

It’s not a Hello World equivalent.

So much around generative ai seems to be around “look how unrealistic you can be for not-cheap! Ai - cocaine for your machine!!”

No wonder there’s very little uptake by businesses (MIT state of ai 2025, etc)

Re: Nano Banana Pro

#548

Post by Wolf_Larsen »

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…

Hi, is your team planning on adding a spending cap? Last I tried, there was no reasonable way to do this. It keeps me away from your platform because runaway inference is a real risk for any app that calls LLMs programatically.

Re: Nano Banana Pro

#549

Post by egypturnash »

AstroBen wrote: post #507
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?

To try to put a positive spin on it.. It enables smaller teams to put out better quality products Imagine you're an artist that wants to create a video game but you suck at development. You could leverage AI to get good enough code and have amazing art On the other side someone who invested their entire skill tree in development can have amazing code and passable art The more I think about it the more it seems this A…

I am an artist. I have friends who like to code. I could leverage talking to my friends and saying "hey anyone wanna fool around and make some games". I could get Unreal and one of the 800 game templates available on their store for prices ranging from $0 to a few hundred bucks and start plopping my art in there and fiddling around. There's a bazillion art assets on there for the programmer with no art skills, too. And there's a section on the Unreal forums for people to say "hey I have this set of skills, who wants to make a game with me?".

Or we could all just generate a bunch of completely unmaintanable code or some uncopyrightable art, sounds great.

Re: Nano Banana Pro

#550

Post by t-writescode »

AstroBen wrote: post #507
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?

To try to put a positive spin on it.. It enables smaller teams to put out better quality products Imagine you're an artist that wants to create a video game but you suck at development. You could leverage AI to get good enough code and have amazing art On the other side someone who invested their entire skill tree in development can have amazing code and passable art The more I think about it the more it seems this A…

Undertale Exists.

Baba is You Exists.

Nethack Exists (and similar games).

Dwarf Fortress Exists.

Mountains of Indie Horror games made of Unity Store assets exist.

Coal, LLC exists.

Cookie Clicker Exists.

Balatro Exists.

Post reply on HN