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

271–280 of 718 posts

Re: Nano Banana Pro

#271

Post by mikepurvis »

OtherShrezzing wrote: post #225
arresin wrote: post #197

Earlier quoted context omitted.

Is the infographic accurate in terms of the way datasette wprks?

It’s subtly incorrect. R/w permissions for example are described incorrectly on some nodes.

Then the question becomes, can it incorporate targeted feedback, or is it a oneshot-or-bust affair?

My experience is that ChatGPT is very good at iterating on text (prose, code) but fairly bad at iterating on images. It struggles to integrate small changes, choosing instead to start over from scratch, with wildly different results. Thinking especially here of architectural stuff, where it does a great job laying out furniture in a room, but when I ask it to keep everything the same but change the colour of one piece, it goes completely off the rails.

Re: Nano Banana Pro

#272

Post by skeeter2020 »

minimaxir wrote: post #149

I...worked on the detailed Nano Banana prompt engineering analysis for months ( https://news.ycombinator.com/item?id=45917875 )...and...Google just...Google released a new version. Nano Banana Pro should work with my gemimg package ( https://github.com/minimaxir/gemimg ) without pushing a new version by passing: g = GemImg(model="gemini-3-pro-image-preview") I'll add the new output resolutions and other features ASAP…

>> - Put a strawberry in the left eye socket. >>- Put a blackberry in the right eye socket.

>> All five of the edits are implemented correctly

This is a GREAT example of the (not so) subtle mistakes AI will make in image generation, or code creation, or your future knee surgery. The model placed the specified items in the eye sockets based on the viewers left/right; when we talk relative in this scenario we usually (always?) mean from the perspective of the target or "owner". Doctors make this mistake too (they typically mark the correct side with a sharpie while the patient is still alert) but I'd be more concerned if we're "outsourcing" decision making without adequate oversight.

https://minimaxir.com/2025/11/nano-banana-prompts/#hello-nan...

Re: Nano Banana Pro

#273

Post by s1mon »

creata wrote: post #228
riskable wrote: post #68

Earlier quoted context omitted.

On the contrary, it's encouraging to know that maliciously greedy companies like Adobe are getting screwed for being so malicious and greedy :thumbsup: I had second thoughts about this comment, but if I stopped typing in the middle of it, I would've had to pay a cancellation fee.

Adobe, for all their faults, can hardly be said to be more malicious or greedy than Google. Adobe, at least, makes money by selling software. Google makes money by capturing eyeballs; only incidentally does anything they do benefit the user.

Adobe makes money by renting software, not selling it. There are many creatives that would disagree with your ranking of who is more malicious or greedy.

Re: Nano Banana Pro

#274

Post by johnecheck »

ashleyn wrote: post #256

Does anyone know if this is predicting the entire image at once, or if it's breaking it into constituent steps i.e. "draw text in this font at this location" and then composing it from those "tools"? It would be really interesting if they've solved the garbled text problem within the constraint of predicting the entire image at once.

I strongly suspect it's the latter, though someone please chime in if I'm wrong.

Even so, this is a real advancement. It's impressive to see existing techniques combined to meaningfully improve on SOTA image generation.

Re: Nano Banana Pro

#275

Post by Jabrov »

skeeter2020 wrote: post #272
minimaxir wrote: post #149

I...worked on the detailed Nano Banana prompt engineering analysis for months ( https://news.ycombinator.com/item?id=45917875 )...and...Google just...Google released a new version. Nano Banana Pro should work with my gemimg package ( https://github.com/minimaxir/gemimg ) without pushing a new version by passing: g = GemImg(model="gemini-3-pro-image-preview") I'll add the new output resolutions and other features ASAP…

>> - Put a strawberry in the left eye socket. >>- Put a blackberry in the right eye socket. >> All five of the edits are implemented correctly This is a GREAT example of the (not so) subtle mistakes AI will make in image generation, or code creation, or your future knee surgery. The model placed the specified items in the eye sockets based on the viewers left/right; when we talk relative in this scenario we usually (…

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.

Re: Nano Banana Pro

#276

Post by aqme28 »

famouswaffles wrote: post #136
aqme28 wrote: post #79

Earlier quoted context omitted.

I don't think it will be easy to just remove it. It's built into the image and thus won't be the same every time. Plus, any service good at reverse-image search (like Google) can basically apply that to determine whether they generated it. There will always be a way to defeat anything, but I don't see why this won't work for like 90% of cases.

It's an image. There's simply no way to add a watermark to an image that's both imperceptible to the user and non-trivial to remove. You'd have to pick one of those options.

That is patently false.

Re: Nano Banana Pro

#277

Post by CGMthrowaway »

skeeter2020 wrote: post #272
minimaxir wrote: post #149

I...worked on the detailed Nano Banana prompt engineering analysis for months ( https://news.ycombinator.com/item?id=45917875 )...and...Google just...Google released a new version. Nano Banana Pro should work with my gemimg package ( https://github.com/minimaxir/gemimg ) without pushing a new version by passing: g = GemImg(model="gemini-3-pro-image-preview") I'll add the new output resolutions and other features ASAP…

>> - Put a strawberry in the left eye socket. >>- Put a blackberry in the right eye socket. >> All five of the edits are implemented correctly This is a GREAT example of the (not so) subtle mistakes AI will make in image generation, or code creation, or your future knee surgery. The model placed the specified items in the eye sockets based on the viewers left/right; when we talk relative in this scenario we usually (…

>This is a GREAT example of the (not so) subtle mistakes AI will make in image generation, or code creation, or your future knee surgery.

The mistake is in the prompting (not enough information). The AI did the best it could

"What's the biggest known planet" "Jupiter" "NO I MEANT IN THE UNIVERSE!"

Re: Nano Banana Pro

#278

Post by skeeter2020 »

sib wrote: post #124
throwacct wrote: post #87

Google needs to pace themselves. AI studio, Antigravity, Banana, Banana Pro, Grape Ultra, Gemini 3, etc. This information overload don't do them any good whatsoever.

Stock market seems to agree with their strategy....

Maybe? or lemmings following BH purchase of $4B in Google stock this week assuming "Buffett only buys value stocks; it must be ready to grow!"

https://finance.yahoo.com/news/warren-buffetts-berkshire-hat...

Re: Nano Banana Pro

#279

Post by scoopertrooper »

ashleyn wrote: post #256

Does anyone know if this is predicting the entire image at once, or if it's breaking it into constituent steps i.e. "draw text in this font at this location" and then composing it from those "tools"? It would be really interesting if they've solved the garbled text problem within the constraint of predicting the entire image at once.

The previous nano banana was using composing tools. It was really obvious by some of the janky outputs it made. Not sure about this one, but presumably they built off it.

Re: Nano Banana Pro

#280

Post by ComputerGuru »

Jabrov wrote: post #275
skeeter2020 wrote: post #272

Earlier quoted context omitted.

>> - Put a strawberry in the left eye socket. >>- Put a blackberry in the right eye socket. >> All five of the edits are implemented correctly This is a GREAT example of the (not so) subtle mistakes AI will make in image generation, or code creation, or your future knee surgery. The model placed the specified items in the eye sockets based on the viewers left/right; when we talk relative in this scenario we usually (…

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.

“Eye on the left” is different from “the left eye”. First can be ambiguous, second really isn’t.
Post reply on HN