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

ChatGPT Images 2.0

openai.com

Post reply on HN
Print view View original

401–410 of 1001 posts

Re: ChatGPT Images 2.0

#401

Post by mirekrusin »

simonw wrote: post #37
simonw wrote: post #15

I've been trying out the new model like this: OPENAI_API_KEY="$(llm keys get openai)" \ uv run https://tools.simonwillison.net/python/openai_image.py \ -m gpt-image-2 \ "Do a where's Waldo style image but it's where is the raccoon holding a ham radio" Code here: https://github.com/simonw/tools/blob/main/python/openai_imag... Here's what I got from that prompt. I do not think it included a raccoon holding a ham radio…

I just got a much better version using this command instead, which uses the maximum image size according to https://github.com/openai/openai-cookbook/blob/main/examples... OPENAI_API_KEY="$(llm keys get openai)" \ uv run 'https://raw.githubusercontent.com/simonw/tools/refs/heads/main/python/openai_image.py' \ -m gpt-image-2 \ "Do a where's Waldo style image but it's where is the raccoon holding a ham radio" \ --quali…

Can it generate non halloween version though?

This lower-is-better danse macabre, nightmares inducing ratio feels like interesting proxy for models capability.

Re: ChatGPT Images 2.0

#402

Post by muyuu »

vunderba wrote: post #358
muyuu wrote: post #121

I wonder if this will be decent at creating sprite frame animations. So far I've had very poor results and I've had to do the unthinkable and toil it out manually.

I created this little demo of an animated sprite sheet using generative AI. It's not great, but it is passable. https://mordenstar.com/other/hobbes-animation/

Looks good to me. Would be nice to see the process. I'm having trouble with parts of the stride when the far leg is ahead. Doing 8-directional isometric right now.

Re: ChatGPT Images 2.0

#403

Post by nerdsniper »

simonw wrote: post #15

I've been trying out the new model like this: OPENAI_API_KEY="$(llm keys get openai)" \ uv run https://tools.simonwillison.net/python/openai_image.py \ -m gpt-image-2 \ "Do a where's Waldo style image but it's where is the raccoon holding a ham radio" Code here: https://github.com/simonw/tools/blob/main/python/openai_imag... Here's what I got from that prompt. I do not think it included a raccoon holding a ham radio…

That is a devilishly difficult prompt for current diffusion tasks. Kudos.

Re: ChatGPT Images 2.0

#404

Post by rafael-lua »

davebren wrote: post #381
rafael-lua wrote: post #336

Earlier quoted context omitted.

It is not the making of the diagram that is the problem, but often the fact I have no idea how to put it visually. AI is awesome at this. Now, does that justify the harm? Not for me, but this issue is way out of my league.

The point of a diagram is that you have something in your head to turn into the diagram. There's no point if you can't do it yourself and the image generator is coming up with it for you.

I disagree. Diagrams are a type of visual communication, and not everyone is good at translating things to visual. I open an excalidraw with clear concepts in my head, but nothing comes out of it. I try C4 or flow diagrams, and I spend an excessive amount of time refactoring them to end up mediocre anyway. Not just me, I know MANY developers that are amazing at explaining things but are mind-blocked when drawing simple circles and arrows.

Helping us navigate things we aren't good at has been one of the main selling points of AI.

Re: ChatGPT Images 2.0

#405

Post by nerdsniper »

M3L0NM4N wrote: post #237
makira wrote: post #61

Earlier quoted context omitted.

Fed into a clear Claude Code max effort session with : "Inspect waldo2.png, and give me the pixel location of a raccoon holding a ham radio.". It sliced the image into small sections and gave: "Found the raccoon holding a ham radio in waldo2.png (3840×2160). - Raccoon center: roughly (460, 1680) - Ham radio (walkie-talkie) center: roughly (505, 1650) — antenna tip around (510, 1585) - Bounding box (raccoon + radio):…

We would need a larger sample size than just myself, but the raccoon was in the very first spot I looked. Found it literally immediately, as if that's where my eyes naturally gravitated to first. Hopefully that's just luck and not an indictment of the image-creating ability, as if there is some element missing from this "Where's Waldo" image, that would normally make Waldo hard to find.

There seemed to be more space around the raccoon than most other subjects. Zoomed out it appears as almost a “halo” highlighting the raccoon.

Re: ChatGPT Images 2.0

#406

Post by rootusrootus »

bryanhogan wrote: post #324
overgard wrote: post #216

Pretty mixed feelings on this. From the page at least, the images are very good. I'd find it hard to know that they're AI. Which I think is a problem. If we had a functioning congress, I wonder if we might end up with legislation that these things need to be watermarked or otherwise made identifiable as AI generated.. I also don't like that these things are trained on specific artist's styles without really crediting…

Trying to watermark or otherwise label them as AI generated is a lost fight, we should assume every image and video we see online may be AI generated.

This helps the segment of society that is interested in applying critical thinking to what they see. I am not sure that is anything like a majority or even a significant plurality. It seems like just about every image or video gets accused of being AI these days, but predictably the accusations depend on the ideology of the accuser.

Re: ChatGPT Images 2.0

#407

Post by schneehertz »

Generating a 4096x4096 image with gemini-3.1-flash-image-preview consumes 2,520 tokens, which is equivalent to $0.151 per image.

Generating a 3840x2160 image with gpt-image-2 consumes 13,342 tokens, which is equivalent to $0.4 per image.

This model is more than twice as expensive as Gemini.

Re: ChatGPT Images 2.0

#409

Post by strangescript »

schneehertz wrote: post #407

Generating a 4096x4096 image with gemini-3.1-flash-image-preview consumes 2,520 tokens, which is equivalent to $0.151 per image. Generating a 3840x2160 image with gpt-image-2 consumes 13,342 tokens, which is equivalent to $0.4 per image. This model is more than twice as expensive as Gemini.

this is apples to oranges, the flash version version a full version

this thing is like 5x better than flash at fine grain detail

Re: ChatGPT Images 2.0

#410

Post by apparent »

Havoc wrote: post #373
apparent wrote: post #328

I find the video to be very annoying. Am I supposed to freeze frame 4x per second to be able to see whether the images are actually good? I've never before felt stressed watching a launch video.

Yeah same. At first I thought they're using it to conceal quality, but pausing it they do actually look really good, so strange choice. Maybe it's meant to convey pace & hype

Maybe so, but to me it conveys a headache.
Post reply on HN