ChatGPT Images 2.0 • Hacker News Board

Re: ChatGPT Images 2.0

#101

Post by dktp » Tue, Apr 21, 2026, 9:05 PM UTC

arjie wrote: post #96

dktp wrote: post #72

Earlier quoted context omitted.

I don't know tbh. I've tried it on 10-20 various level of famous standups and Gemini refuses every time Just for testing, I just tried this https://i.ytimg.com/vi/_KJdP4FLGTo/sddefault.jpg ("Redesign this image in a brutalist graphic design style"). Gemini refuses (api as well as UI), OpenAI does it

It's not super deterministic but it didn't fail once on my attempts. See: https://imgur.com/a/james-acaster-cold-lasagne-1R7fpzQ

Very interesting. It fails every single time for me. I'm in Germany, maybe Google is stricter here?

See https://imgur.com/a/77BRDQv

Re: ChatGPT Images 2.0

#102

Post by honzaik » Tue, Apr 21, 2026, 9:09 PM UTC

thelucent wrote: post #91

It seems to still have this gpt image color that you can just feel. The slight sepia and softness.

I was just wondering about that. Did they embrace it as a “signature look”? it cant be accidental, right?

Re: ChatGPT Images 2.0

#103

Post by joegibbs » Tue, Apr 21, 2026, 9:16 PM UTC

The quality of the text is really impressive and I can’t seem to see any artefacts at all. The fake desktop is particularly good: Nano Banana would definitely slip up with at least a few bits of the background.

Re: ChatGPT Images 2.0

#104

Post by wahnfrieden » Tue, Apr 21, 2026, 9:17 PM UTC

bitnovus wrote: post #8

No gpt-5.5

Thursday

Re: ChatGPT Images 2.0

#105

Post by jinushaun » Tue, Apr 21, 2026, 9:22 PM UTC

Vachyas wrote: post #77

lehmacdj wrote: post #49

Earlier quoted context omitted.

So do you think there will be a better image model in a year?

I'm honestly unsure what could be improved at this point. Consistency? So it fails less often? Based on the released images, (especially the one "screenshot" of the Mac desktop) I feel like the best images from this model are so visually flawless that the only way to tell they're fake is by reasoning about the content of the image itself (ex. "Apple never made a red iPhone 15, so this image is probably fake" or "Cost…

Cost? Speed?

Re: ChatGPT Images 2.0

#106

Post by arjie » Tue, Apr 21, 2026, 9:28 PM UTC

Melatonic wrote: post #98

arjie wrote: post #78

Earlier quoted context omitted.

That has to be the wrong stock image included or something, bloody hell. magick image-l.webp image-r.jpg -compose difference -composite -auto-level -threshold 30% diff.png It's practically all dark except for a few spots. It's the same image just different size compression whatever. I can't find it in any stock image search, though. Surely it could not have memorized the whole image at that fidelity. Maybe I just did…

Or the image was generated with AI in the first place and a test for Images 2.0

Haha! That would really take the cake. If it is, congratulations to them! I could never have known.

Re: ChatGPT Images 2.0

#107

Post by kibibu » Tue, Apr 21, 2026, 9:28 PM UTC

Genuine question: what positive use cases are sufficient to accept the harm from image generators?

One that i can think of:

- replacing photography of people who may be unable to consent or for whom it may be traumatic to revisit photographs and suitable models may not be available, e.g. dementia patients, babies, examples of medical conditions.

Most other vaguely positive use cases boil down to "look what image generators can do", with very little "here's how image generators are necessary for society.

On the flip side, there are hundreds of ways that these tools cause genuine harm, not just to individuals but to entire systems.

Re: ChatGPT Images 2.0

#108

Post by arjie » Tue, Apr 21, 2026, 9:28 PM UTC

dktp wrote: post #101

arjie wrote: post #96

Earlier quoted context omitted.

It's not super deterministic but it didn't fail once on my attempts. See: https://imgur.com/a/james-acaster-cold-lasagne-1R7fpzQ

Very interesting. It fails every single time for me. I'm in Germany, maybe Google is stricter here? See https://imgur.com/a/77BRDQv

That makes sense to me. I just Googled around like a fool and got here https://en.wikipedia.org/wiki/Personality_rights#Germany

It seems like they're trying to follow local law. What a nightmare to have to manage all jurisdictions around such a product. Surprised it didn't kill image generation entirely.

Re: ChatGPT Images 2.0

#109

Post by QuantumGood » Tue, Apr 21, 2026, 9:30 PM UTC

rqa129 wrote: post #26

esafak wrote: post #17

https://openai.com/index/introducing-chatgpt-images-2-0/

Thanks, all displayed images look horrible and artificial. This will fail like Sora.

Your single other comment is simplistic hyperbole as well, so this is presumably a bot account.

Re: ChatGPT Images 2.0

#110

Post by kibibu » Tue, Apr 21, 2026, 9:38 PM UTC

sho_hn wrote: post #35

In 5 years and 3 months between DALL-E and Images 2.0 we've managed to progress from exuberant excitement to jaded indifference.

Because we are all seeing the harm these tools are being used for.

It's just another step into hell.