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

GPT Image 1.5

openai.com

Post reply on HN
Print view View original

211–220 of 272 posts

Re: GPT Image 1.5

#211

Post by KeplerBoy »

vunderba wrote: post #102

Okay results are in for GenAI Showdown with the new gpt-image 1.5 model for the editing portions of the site! https://genai-showdown.specr.net/image-editing Conclusions - OpenAI has always had some of the strongest prompt understanding alongside the weakest image fidelity. This update goes some way towards addressing this weakness. - It's leagues better at making localized edits without altering the entire image's ae…

"Remove all the trash from the street and sidewalk. Replace the sleeping person on the ground with a green street bench. Change the parking meter into a planted tree."

What a prompt and image.

Re: GPT Image 1.5

#212

Post by concats »

echelon wrote: post #141
irishcoffee wrote: post #140

Earlier quoted context omitted.

> the only model that legitimately passed the Giraffe prompt. 10 years ago I would have considered that sentence satire. Now it allegedly means something. Somehow it feels like we’re moving backwards.

> Somehow it feels like we’re moving backwards. I don't understand why everyone isn't in awe of this. This is legitimately magical technology. We've had 60+ years of being able to express our ideas with keyboards. Steve Jobs' "bicycle of the mind". But in all this time we've had a really tough time of visually expressing ourselves. Only highly trained people can use Blender, Photoshop, Illustrator, etc. whereas almos…

“I've come up with a set of rules that describe our reactions to technologies:

1. Anything that is in the world when you’re born is normal and ordinary and is just a natural part of the way the world works.

2. Anything that's invented between when you’re fifteen and thirty-five is new and exciting and revolutionary and you can probably get a career in it.

3. Anything invented after you're thirty-five is against the natural order of things.”

― Douglas Adams

Re: GPT Image 1.5

#214

Post by impjohn »

blurbleblurble wrote: post #43

It's really weird to see "make images from memories that aren't real" as a product pitch

This is what struck me as well. I got weird undertones of 'Now you don't even need to have real memories! Just fabricate them.' They even prominently showcase edits of placing you with another person, further deepening disingenuous or parasocial relationships

Re: GPT Image 1.5

#215

Post by ygouzerh »

encroach wrote: post #182

This outperforms Gemini 3 pro image (nano banana pro) on Text-to-Image Arena and Image Edit Arena. I'm surprised they didn't mention this leaderboard in the blog post. I like this benchmark because its based upon user votes, so overfitting is not as easy (after all, if users prefer your result, you've won). https://lmarena.ai/leaderboard/text-to-image https://lmarena.ai/leaderboard/image-edit

The score are really, really close, it might be why

Re: GPT Image 1.5

#216

Post by walrus01 »

KeplerBoy wrote: post #211
vunderba wrote: post #102

Okay results are in for GenAI Showdown with the new gpt-image 1.5 model for the editing portions of the site! https://genai-showdown.specr.net/image-editing Conclusions - OpenAI has always had some of the strongest prompt understanding alongside the weakest image fidelity. This update goes some way towards addressing this weakness. - It's leagues better at making localized edits without altering the entire image's ae…

"Remove all the trash from the street and sidewalk. Replace the sleeping person on the ground with a green street bench. Change the parking meter into a planted tree." What a prompt and image.

I've already seen images on the MLS uploaded by real estate agents that look like this is the same concept as what they've been doing, generally, to bait people into coming and touring houses.

Re: GPT Image 1.5

#217

Post by pbmonster »

mmh0000 wrote: post #80
KaiserPro wrote: post #59

Is there a watermarking, or some other way for normal people to tell if its fake?

I know OpenAI watermarks their stuff. But I wish they wouldn't. It's a "false" trust. Now it means whoever has access to uncensored/non-watermarking models can pass off their faked images as real and claim, "Look! There's no watermark, of course, it's not fake!" Whereas, if none of the image models did watermarking, then people (should) inherently know nothing can be trusted by default.

Yeah, I'd go the other way. Camera manufacturers should have the camera cryptographically sign the data from the sensor directly in hardware, and then provide an API to query if a signed image was taken on one of their cameras.

Add an anonymizing scheme (blind signatures or group signatures), done.

Re: GPT Image 1.5

#218

Post by imdsm »

KeplerBoy wrote: post #211
vunderba wrote: post #102

Okay results are in for GenAI Showdown with the new gpt-image 1.5 model for the editing portions of the site! https://genai-showdown.specr.net/image-editing Conclusions - OpenAI has always had some of the strongest prompt understanding alongside the weakest image fidelity. This update goes some way towards addressing this weakness. - It's leagues better at making localized edits without altering the entire image's ae…

"Remove all the trash from the street and sidewalk. Replace the sleeping person on the ground with a green street bench. Change the parking meter into a planted tree." What a prompt and image.

A way it could be...

Re: GPT Image 1.5

#219

Post by boredhedgehog »

vunderba wrote: post #102

Okay results are in for GenAI Showdown with the new gpt-image 1.5 model for the editing portions of the site! https://genai-showdown.specr.net/image-editing Conclusions - OpenAI has always had some of the strongest prompt understanding alongside the weakest image fidelity. This update goes some way towards addressing this weakness. - It's leagues better at making localized edits without altering the entire image's ae…

I disagree with gpt-image-1.5's grade on the worm sign. It moved some of the marks around to accommodate the enlarged black area, but retained the overall appearance of the sign.

Re: GPT Image 1.5

#220

Post by quietbritishjim »

vunderba wrote: post #102

Okay results are in for GenAI Showdown with the new gpt-image 1.5 model for the editing portions of the site! https://genai-showdown.specr.net/image-editing Conclusions - OpenAI has always had some of the strongest prompt understanding alongside the weakest image fidelity. This update goes some way towards addressing this weakness. - It's leagues better at making localized edits without altering the entire image's ae…

Absolutely fabulous work.

Ludicrously unnecessary nitpick for "Remove all the brown pieces of candy from the glass bowl":

> Gemini 2.5 Flash - 18 attempts - No matter what we tried, Gemini 2.5 Flash always seemed to just generate an entirely new assortment of candies rather than just removing the brown ones.

The way I read the prompt, it demands that the candies should change arrangement. You didn't say "change the brown candies to a different color", you said "remove them". You can infer from the few brown ones that you can see that there are even more underneath - surely if you removed them all (even just by magically disappearing them) then the others would tumble down into a new location? The level of the candies is lower than before you started, which is what you'd expect if you remove some. Maybe it's just coincidence, but maybe this really was its reasoning. (It did unnecessarily remove the red candy from the hand though.)

I don't think any of the "passes" did as well as this, including Gemini 3.0 Pro Image. Qwen-Image-Edit did at least literally remove one of the three visible brown candies, but just recolored the other two.

Post reply on HN