Gemini 2.5 Flash Image • Hacker News Board

Re: Gemini 2.5 Flash Image

#401

Post by betterhealth12 » Wed, Aug 27, 2025, 3:48 AM UTC

adidoit wrote: post #38

Very impressive. I have to say while I'm deeply impressed by these text to image models, there's a part of me that's also wary of their impact. Just look at the comments beneath the average Facebook post.

I think it's time to build a new system - something that can annotate the post the user is on, if there's at least another savvy user (or AI system) that can pick up on the uncanny signals. This youtube video about the "Walker Family" sham on Facebook is particularly relevant here:

Don’t Pay This AI Family To Write You a Song - https://www.youtube.com/watch?v=u-DDHSfBBeo

Re: Gemini 2.5 Flash Image

#402

Post by prawn » Wed, Aug 27, 2025, 3:49 AM UTC

knicholes wrote: post #311

lionkor wrote: post #47

Earlier quoted context omitted.

Not to victim-shame or anything, but that sounds more like more than one safety mechanism failed, the convincing tech only being a rather small part of it?

Yes, more than one safety mechanism failed. Coinbase actually flagged the transaction, but I was so desperate to get it to go through, I went through their facial validation process to expedite the transaction. If I hadn't for just a couple more minutes, I'd have realized it was a scam.

Scams usually have an element of urgency so you don't stop to think.

Why did you and your graduate friends think an insanely rich man with a huge number of staff needed your financial help in testing transactions? This reminds me of those people that fall for celebrity love scams, where a rich celebrity needs their money - just baffling.

Re: Gemini 2.5 Flash Image

#403

Post by prawn » Wed, Aug 27, 2025, 3:51 AM UTC

pennaMan wrote: post #54

knicholes wrote: post #45

Earlier quoted context omitted.

[flagged]

hey, I got a bridge to sell you, was $20k but we can lower it to $15k if you pay in BTC

He would sell tunnels, not bridges!

Re: Gemini 2.5 Flash Image

#404

Post by Quiark » Wed, Aug 27, 2025, 3:55 AM UTC

greatgib wrote: post #356

All images created or edited with Gemini 2.5 Flash Image will include an invisible SynthID digital watermark, so they can be identified as AI-generated or edited. Obviously I understand what is the purpose and the good intention, but I think sad to see that we are not not anymore responsible adults but big corps deciding for us what we can and what we cannot do. Snitching on your back.

Me and you are but that guy over there isn't

Re: Gemini 2.5 Flash Image

#405

Post by danpalmer » Wed, Aug 27, 2025, 3:57 AM UTC

carlosbaraza wrote: post #350

Unfortunately, it suffers from the same safetyism than other many releases. Half of the prompts get rejected. How can you have character consistency if the model is forbidden from editing any human. And most of my photo editing involves humans, so basically this is just a useless product. I get that Google doesn't want to be responsible for deep fake advances, but that seems inevitable, so this is just slightly delay…

I've done ~20 prompts so far and not had one be rejected so far. What sort of things are you asking it to do? I've tried things like changing clothing and accessories on people.

Re: Gemini 2.5 Flash Image

#406

Post by ahmeni » Wed, Aug 27, 2025, 3:59 AM UTC

Really like how they were so excited to release this that they managed to break existing SKUs and cause a bunch of GCP customers to get billed at 100x rates for text tokens as flash image generation tokens.

Re: Gemini 2.5 Flash Image

#407

Post by cwmoore » Wed, Aug 27, 2025, 4:11 AM UTC

echelon wrote: post #268

spaceman_2020 wrote: post #203

Earlier quoted context omitted.

If you compare to the amount of effort required in Photoshop to achieve the same results, still a vast improvement

Vibe coding might not be real, but vibe graphics design certainly is. https://imgur.com/a/internet-DWzJ26B Anyone can make images and video now.

Are those oil derricks, or wind turbines? Who cares! Graphic design is easy now!

Re: Gemini 2.5 Flash Image

#408

Post by UltraSane » Wed, Aug 27, 2025, 4:32 AM UTC

atleastoptimal wrote: post #384

I can imagine an automated blackmail bot that scrapes image, video, voice samples from anyone with the most meagre online presence, which then creates high resolution videos of that person doing the most horrid acts, then threatening to share those videos with that person's family, friends and business contacts unless they are paid $5000 in a cryptocurrency to an anonymous address. And further, I can imagine some per…

But these new amazing AI image generators lets you just say "It wasn't me, it is an AI fake". Long term they will seriously devalue blackmail material.

I read a scifi novel where they invented a wormhole that only light could pass through but it could be used as a camera that could go anywhere and eventually anytime and there was absolutely no way to block it. So some people adapted to this fact by not wearing clothes anymore.

Re: Gemini 2.5 Flash Image

#409

Post by UltraSane » Wed, Aug 27, 2025, 4:33 AM UTC

ahmeni wrote: post #406

Really like how they were so excited to release this that they managed to break existing SKUs and cause a bunch of GCP customers to get billed at 100x rates for text tokens as flash image generation tokens.

Ouch. that is not going to be fun to clean up.

Re: Gemini 2.5 Flash Image

#410

Post by jari_mustonen » Wed, Aug 27, 2025, 4:37 AM UTC

Is it capable of generating white males?

Given that this has been a serious problem with Google models, I would guess it would have been a good thing to at least add one such example in the marketing material. If the marketing material is to be believed, the model really prefers black females.