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

11–20 of 718 posts

Re: Nano Banana Pro

#11

Post by matsemann »

hbn wrote: post #7

I wouldn't trust any of the info in those images in the first carousel if I found them in the wild. It looks like AI image slop and I assume anyone who thinks those look good enough to share did not fact check any of the info and just prompted "make an image with a recipe for X"

Yeah, the weird yellow tint, the kerning/fonts etc still immediately gives it away.

But I wouldn't mind being easily able to make infographics like these, I'd just like to supply the textual and factual content myself.

Re: Nano Banana Pro

#13

Post by eminence32 »

> Generate better visuals with more accurate, legible text directly in the image in multiple languages

Assuming that this new model works as advertised, it's interesting to me that it took this long to get an image generation model that can reliably generate text. Why is text generation in images so hard?

Re: Nano Banana Pro

#15

Post by saretup »

Interesting they didn’t post any benchmark results - lmarena/artificial analysis etc. I would’ve thought they’d be testing it behind the scenes the same way they did with Gemini 3.

Re: Nano Banana Pro

#17

Post by awillen »

fouronnes3 wrote: post #10

I guess the true endgame of AI products is naming them. We still have quite a way to go.

Honestly I give Google credit for realizing that they had something that people were talking about and running with it instead of just calling it gemini-image-large-with-text-pro

Re: Nano Banana Pro

#19

Post by VladVladikoff »

nickdonnelly wrote: post #9
varbhat wrote: post #3

Can anyone please explain me the invisible watermarking mentioned in the said promo?

It's called Synth ID. It's a watermark that proves an image was generated by AI. https://deepmind.google/models/synthid/

Super important for Google as a search engine so they can filter out and downrank AI generated results. However I expect there are many models out there which don’t do this, that everyone could use instead. So in the end a “feature” like this makes me less likely to use their model because I don’t know how Google will end up treating my blog post if I decide to include an AI generated or AI edited image.
Post reply on HN