Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Gemini 2.5 Flash Image

developers.googleblog.com

Post reply on HN
Print view View original

191–200 of 504 posts

Re: Gemini 2.5 Flash Image

#191

Post by vunderba »

ceroxylon wrote: post #81
fariszr wrote: post #60

This is the gpt 4 moment for image editing models. Nano banana aka gemini 2.5 flash is insanely good. It made a 171 elo point jump in lmarena! Just search nano banana on Twitter to see the crazy results. An example. https://x.com/D_studioproject/status/1958019251178267111

It seems like every combination of "nano banana" is registered as a domain with their own unique UI for image generation... are these all middle actors playing credit arbitrage using a popular model name?

They're almost all scams. Nano banana AI image generator sites were showing up when this model was still only available in LM Arena.

Re: Gemini 2.5 Flash Image

#192

Post by __rito__ »

I am glad that I never decided to become a photoshop pro. I always contemplated about it, seemed attractive for a while, but glad that I decided against it. RIP r/photoshopbattles.

It was in the endless list of new shiny 'skills' that feels good to have. Now I can use nano-banana instead. Other models will soon follow, I am sure.

Re: Gemini 2.5 Flash Image

#193

Post by qingcharles »

kamranjon wrote: post #53
knicholes wrote: post #45

Earlier quoted context omitted.

[flagged]

Would you consider writing a blog post about this experience? I'm incredibly interested in learning more details about how this unfolded.

I think the comment is a joke. Their bio is satirical at least :)

Re: Gemini 2.5 Flash Image

#194

Post by debugnik »

3036e4 wrote: post #138
daemonologist wrote: post #82

Earlier quoted context omitted.

I suspect the "voice" is a language model with a bad system prompt. (Possibly the author's own words run through an LLM, to be charitable.)

It's medium.com. YouTube comments quality text packaged as clickbait articles for some revenue share. It was always slop, even without LLMs. Do they even bother with paying human authors now or is the entire site just generated? That would probably be cheaper and improve quality.

> Do they even bother with paying human authors now

I thought Medium was a stuck up blogging platform. Other than for paid subscriptions, why would they pay bloggers? Are they trying to become the next HuffPost or something?

Re: Gemini 2.5 Flash Image

#195

Post by vunderba »

skybrian wrote: post #177

Like most image generators, it didn’t pass the piano keyboard test. (Black keys are wrong.) https://aistudio.google.com/app/prompts?state=%7B%22ids%22:%...

Anything that is heavily periodic can definitely trip up image gen - that being I just used Flux Kontext T2I and got a got pretty close (disregard the hammers though since thats a right mess). Only towards the upper register did it start to make mistakes.

https://imgur.com/a/fyX42my

Re: Gemini 2.5 Flash Image

#196

Post by echelon »

__rito__ wrote: post #192

I am glad that I never decided to become a photoshop pro. I always contemplated about it, seemed attractive for a while, but glad that I decided against it. RIP r/photoshopbattles. It was in the endless list of new shiny 'skills' that feels good to have. Now I can use nano-banana instead. Other models will soon follow, I am sure.

Programming and everything else will eventually fall to automation, too. It's just a matter of time.

Engineering probably takes a while (5 years? 10 years?) because errors multiply and technical debt stacks up.

In images, that's not so much of a big deal. You can re-roll. The context and consequences are small. In programs, bad code leads to an unmaintainable mess and you're stuck with it.

But eventually this will catch up with us too.

Re: Gemini 2.5 Flash Image

#197

Post by qingcharles »

appenz wrote: post #133
bonoboTP wrote: post #107

Earlier quoted context omitted.

The hype is about image editing, not pure text-to-image. Upload an input image, say what you want changed, get the output. That's the idea. Much better preservation of characters and objects.

I tested it against Flux Pro Kontext (also image editing) and while it's a very different style and approach I overall like Flux better. More focus on image consistency, adjusts the lighting correctly, fixes contradictions in the image.

I've been testing it against Flux Pro Kontext for several weeks. I would say it beats Flux in a majority of tests, but Flux still surprises from time-to-time. Banana definitely isn't the best 100% of the time -- it falls a bit short of that. Evolution, not revolution.

Re: Gemini 2.5 Flash Image

#198

Post by qingcharles »

SirMaster wrote: post #142
bonoboTP wrote: post #107

Earlier quoted context omitted.

The hype is about image editing, not pure text-to-image. Upload an input image, say what you want changed, get the output. That's the idea. Much better preservation of characters and objects.

Can it edit the photo at the original resolution? Most of my photos these days are 48MP and I don't want to lose a ton of resolution just to edit them.

I don't know. All the testing I've done has output the standard 1024x1024 that all these models are set to output. You might be able to alter the output params on the API or AI Studio.

Re: Gemini 2.5 Flash Image

#199

Post by quantumHazer »

echelon wrote: post #196
__rito__ wrote: post #192

I am glad that I never decided to become a photoshop pro. I always contemplated about it, seemed attractive for a while, but glad that I decided against it. RIP r/photoshopbattles. It was in the endless list of new shiny 'skills' that feels good to have. Now I can use nano-banana instead. Other models will soon follow, I am sure.

Programming and everything else will eventually fall to automation, too. It's just a matter of time. Engineering probably takes a while (5 years? 10 years?) because errors multiply and technical debt stacks up. In images, that's not so much of a big deal. You can re-roll. The context and consequences are small. In programs, bad code leads to an unmaintainable mess and you're stuck with it. But eventually this will ca…

Both of you are wrong and this is not good discussion level for HN

Re: Gemini 2.5 Flash Image

#200

Post by psbp »

skybrian wrote: post #177

Like most image generators, it didn’t pass the piano keyboard test. (Black keys are wrong.) https://aistudio.google.com/app/prompts?state=%7B%22ids%22:%...

Doesn't pass the analog clock test either.
Post reply on HN