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

491–500 of 1001 posts

Re: ChatGPT Images 2.0

#491

Post by breezybottom »

bsenftner wrote: post #327
mcmcmc wrote: post #159

Earlier quoted context omitted.

So the use case is just IP theft so you can get more Paw Patrol? AI aside, if you’ve truly exhausted all the simple readers, maybe she should move on to more advanced books instead of repeating more of the same and gamifying it, which seems a great way to destroy a child’s natural curiosity.

That is not IP theft, that's private use. If (s)he tries to sell those coloring books, that's then theft. You're free to do anything you want with IP in privacy, it's only when selling or exhibiting to the public IP law is triggered. Knock yourself out with protected IP in private.

You're thinking of fair use, and that's the worst interpretation of it I've seen.

Re: ChatGPT Images 2.0

#492

Post by m_kos »

vunderba wrote: post #83

OpenAI’s gpt-image-1.5 and Google’s NB2 have been pretty much neck and neck on my comparison site which focuses heavily on prompt adherence, with both hovering around a 70% success rate on the prompts for generative and editing capabilities. With the caveat being that Gemini has always had the edge in terms of visual fidelity. That being said, gpt-image-1.5 was a big leap in visual quality for OpenAI and eliminated m…

Very useful website. Would you have insight into what models are best at editing existing images?

I often have to make very specific edits while keeping the rest of the image intact and haven't yet found a good model. These are typically abstract images for experiments.

I asked gpt-image-2 to recolor specific scales of your Seedream 4 snake and change the shape of others. It did very poorly.

Re: ChatGPT Images 2.0

#493

Post by breezybottom »

kakapo5672 wrote: post #385
Jtarii wrote: post #255

Earlier quoted context omitted.

So the benefits are that something that was already being mass produced with no issue is slightly easier to mass produce? It's not a particularly compelling argument.

No, the benefits are that something can be mass produced magnitudes faster and easier, which in turn also creates more latitude for creativity and new spaces. It's a true state-change, which makes the argument pretty compelling IMO.

Weird how it's the least creative people who use it then.

Re: ChatGPT Images 2.0

#494

Post by Barbing »

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…

>I think that image cost 40 cents.

Kinda made me sad assuming the author didn't license anything to OpenAI.

I recognize it could revert (99% of?) progress if all the labs moved to consent-based training sets exclusively, but I can't think of any other fair way.

$.40 does not represent the appropriate value to me considering the desirability of the IP and its earning potential in print and elsewhere. If the world has to wait until it’s fair, what of value will be lost? (I suppose this is where the big wrinkle of foreign open weight models comes in.)

Re: ChatGPT Images 2.0

#495

Post by hackable_sand »

vova_hn2 wrote: post #422
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…

Thanks for the image, I will see their faces in my nightmares.

What about the faces of the people ChatGPT killed?

Re: ChatGPT Images 2.0

#496

Post by prvc »

I hope they will consider releasing DALL-E 2 publicly, now that there has been so much progress since it was unveiled. It had a really nice vibe to it, so worth preserving.

Re: ChatGPT Images 2.0

#497

Post by vunderba »

what wrote: post #486
vunderba wrote: post #83

OpenAI’s gpt-image-1.5 and Google’s NB2 have been pretty much neck and neck on my comparison site which focuses heavily on prompt adherence, with both hovering around a 70% success rate on the prompts for generative and editing capabilities. With the caveat being that Gemini has always had the edge in terms of visual fidelity. That being said, gpt-image-1.5 was a big leap in visual quality for OpenAI and eliminated m…

Where can I see the actual prompts and follow ups you fed each model?

So the prompts are tuned and adjusted on a per-model basis. If you look at the number of attempts, each receives a specific prompt variation depending on the model. This honestly isn't as much of an issue these days because SOTA models natural language parsing (particularly the multimodal ones) has eliminated a lot of the byzantine syntax requirements of the SD/SDXL days.

The template prompt seen in each comparison gets adjusted through a guided LLM which has fine-tuned system prompts to rewrite prompts. The goal is to foster greater diversity while preserving intent, so the image model has a better chance of getting the image right.

Getting to your suggestion for posting all the raw prompts, that's actually a great idea. Too bad I didn't think about it until you suggested it. And if you multiply it out - there's 15 distinct test cases against 22 models at this point, each with an average of about 8 attempts so we’re talking about thousands of prompts many of which are scattered across my hard drive. I might try to do this as a future follow-up.

Re: ChatGPT Images 2.0

#498

Post by andy_ppp »

prvc wrote: post #496

I hope they will consider releasing DALL-E 2 publicly, now that there has been so much progress since it was unveiled. It had a really nice vibe to it, so worth preserving.

Yes, I’ve always thought of AI companies as sentimental. They will definitely do this :-/

Re: ChatGPT Images 2.0

#499

Post by zulban »

Gigachad wrote: post #196
zulban wrote: post #170

Earlier quoted context omitted.

Nobody can be bothered to make my cat out of Lego and the size of mount Everest but if an AI did I'd sure love to see it. Your quip is pithy but meaningless.

I'm not saying it's worthless for yourself, it's worthless to me as a viewer. AI content is great for your own usage, but there is no point posting and distributing AI generation. I could have generated my own content, so just send the prompt rather than the output to save everyone time.

Maybe reread my comment. Would you not want to see a mount Everest sized Lego cat? Even if it were my cat?

Again - your quip sounds good but when you think about it, it's flatly wrong.

Post reply on HN