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

ChatGPT Images 2.5

openai.com

Post reply on HN
Print view View original

401–410 of 474 posts

Re: ChatGPT Images 2.5

#401

Post by tyrust »

jjcm wrote: post #244
jjcm wrote: post #205

I use gpt image 2 very heavily for my current project (ai UI design tool). The biggest improvement I'm seeing with this is in speed. I've generated around 50k images with gpt-image-2 via api, the the average latency has held at around 104s. It's wild how much of a difference this is - images are coming in at around 35-40s. Very noticable, and makes a difference when you're iterating quickly: https://jjcm.org/gpt-imag…

Some UI tests with it: Warcraft 3 style agentic dev interface: https://image.non.io/cd9ea5cd-8ed7-44e0-ad3f-480ff0e51875.we... Overall it used the reference images I gave it a bit better than gpt-image-2. I noticed 2 had issues getting the blue button just right. 2.5 nailed it. A "John Politics" meme site: https://image.non.io/d2922164-fa96-4d07-a141-2febadb02939.we... Did very well modifying the pose while keeping t…

The WC3 one is fun. Definitely feels close to what I remember.

Re: ChatGPT Images 2.5

#402

Post by Auracle »

tyjen wrote: post #77

The Facebook Marketplace experience for used items has depreciated considerably with the widespread adoption of LLMs. Between placing attractive models in photos to help sell items to "improving" the visual condition of items that completely misrepresent the real condition of the item, it's becoming a trickier landscape to navigate to find what you're looking for.

I just saw a Twitter thread of someone calling out realtors with absolutely egregious editing examples. Think pools and landscaping being added to backyards, a background being changed to a mountainous region, and furniture being “staged” in an attic space that definitely couldn’t fit that furniture.

A realtor in the comments said they legally need to also post the same images but unedited, but I’m sure when you’re doing this the first 50 are the edited ones and the last 50 are the unedited. How many people make it to the unedited?

Re: ChatGPT Images 2.5

#403

Post by Auracle »

VladVladikoff wrote: post #228
vgalin wrote: post #64

The introductory video is a bit... daring. Generating tattoos that clearly look AI-generated is not one of the use-cases I'd try to sell.

It hit me just now that people might actually getting tattooed with AI slop. That’s… depressing

I mean, it would probably be better than many tattoo artist’s art. At the very least it’s not a bad way to see how something would look on you before you permanently do it.

Re: ChatGPT Images 2.5

#404

Post by rs_rs_rs_rs_rs »

HDBaseT wrote: post #347
rs_rs_rs_rs_rs wrote: post #35

Earlier quoted context omitted.

Having a lot of fun with my son using an image of him and dressing him in all kinds of costumes. How is that depressing to you?

This is really depressing to me. I think this is abusive. Your son has no concept of the implications of his body, face and identifying features being used here. He has no ability to opt-out, refuse consent, and avoid his data (biometric features) being swooped up in a data-centers for further training, further data collection & further monetization. Your son didn't agree to the privacy policy of OpenAI. This is an e…

You're insane.

Re: ChatGPT Images 2.5

#406

Post by ta8903 »

hirvi74 wrote: post #377
ActionHank wrote: post #141

Earlier quoted context omitted.

[flagged]

Why is that such a bad thing? Imagination is not truly useful for anything without skills to complement it, at least not in my experience.

>Imagination is not truly useful for anything without skills to complement it

techbro final boss

Re: ChatGPT Images 2.5

#407

Post by Hoftheater »

This is a nice showcase of what it can do but so little of it seems to be actually useful or rather odd choices. Some examples were already mentioned, but also the Gdocs presentation: apart from the terrible layout, why would one use fake photos of the sun in a "science" talk when there is an abundance of real high-res photos available? For educational purposes these are even free to use.

Re: ChatGPT Images 2.5

#408

Post by madaxe_again »

pibaker wrote: post #399
xp84 wrote: post #286

Earlier quoted context omitted.

Trying to be as least cynical as possible, imagine if you were a party with 3 or more people, and you really wanted a nice pic like that to commemorate the night, but never got to take one all together because someone left early, and you were in the bathroom when they announced their departure. Yes, it's a major first-world problem to not get a photo, but to the right person, it could mean a lot to them to "fix" the…

What's the point of having a photo like that? Is spending time with your friends not enough in 2026? Do we must provide photographic evidence of all the fun you have been having or it did not happen?

Did you miss the last 15 years of social media?

So many people I just stopped spending time with altogether as instead of being present they’d be posing for their 90th instagram shot by 10am - and then of course they want you to pose, too.

So no. Spending time with your friends is not enough in 2026. I’m not even convinced people have friends now - just colleagues and mutual parasites.

Re: ChatGPT Images 2.5

#409

Post by madaxe_again »

AyanamiKaine wrote: post #170
jodacola wrote: post #158

Earlier quoted context omitted.

I’m less concerned about faking being at a party with friends and more with the 2006 timestamp on said photo! Can you imagine finding a stack of photos in the basement with timestamps of the Before AI times and wondering whether they are real or just got swapped with generated and printed fakes? Scary! It’s cool, folks… nothing bad is going to happen. Right? Right?!

True, I didn't thought about that. Just imagine the scale of "historic" images that will be created over the next 100 years.

There won’t be a next 100 years.

Re: ChatGPT Images 2.5

#410

Post by gloxkiqcza »

lopatin wrote: post #183
gloxkiqcza wrote: post #132

Earlier quoted context omitted.

I wouldn't feel comfortable uploading a picture of my child to OpenAI servers (for fun nonetheless), but you do you.

I'm not following the news. Why should we not upload pictures of family members to OpenAI? Are any other cloud providers safe?

I wouldn't/don't really feel comfortable uploading private pictures to any other cloud provider either :). I find OpenAI especially untrustworthy because of their known business practices, unestablished business model and unknown future capabilities and role in society. You cannot take that data back once they have it. The condescending tone was unasked for, apologies to OP for that.
Post reply on HN