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

4o Image Generation

openai.com

Post reply on HN
Print view View original

411–420 of 629 posts

Re: 4o Image Generation

#411

Post by bb88 »

wes-k wrote: post #407
bb88 wrote: post #393

My experience with these announcements is that they're cherry picking the best results from a maybe several hundred or a thousand prompts. I'm not saying that it's not true, it's just "wait and see" before you take their word as gold. I think MS's claim on their quantum computing breakthrough is the latest form of this.

The examples they show have little captions that say "best of #", like "best of 8" or "best of 4". Hopefully that truly represents the odds of generating the level of quality shown.

I'm not doubting it's an improvement, because it looks like it is.

I guess here's an example of a prompt I would like to see:

A flying spaghetti monster with a metal colander on its head flying above New York City saving the world from and very very evil Pope.

I'm not anti/pro spaghetti monster or catholicism. But I can visualize it clearly in my head what that prompt might look like.

Re: 4o Image Generation

#412

Post by wes-k »

lxgr wrote: post #100

Is there any way to see whether a given prompt was serviced by 4o or Dall-E? Currently, my prompts seem to be going to the latter still, based on e.g. my source image being very obviously looped through a verbal image description and back to an image, compared to gemini-2.0-flash-exp-image-generation. A friend with a Plus plan has been getting responses from either. The long-term plan seems to be to move to 4o comple…

My images say "Created with DALLE" below them, and a little info icon tells me they are rolling out the new one soon.

Re: 4o Image Generation

#413

Post by Maxion »

bb88 wrote: post #406
kilroy123 wrote: post #402

Earlier quoted context omitted.

Have you tried it? It's crazy good.

No offense but after years of vaporware and announcements that seemed more plausible than implausible, I'll remain skeptical. I will also not give them my email address just to try it out.

Why are you making blanket statements on things that you haven't even tried? This is leaps and bounds better than before.

Re: 4o Image Generation

#414

Post by bb88 »

Maxion wrote: post #413
bb88 wrote: post #406

Earlier quoted context omitted.

No offense but after years of vaporware and announcements that seemed more plausible than implausible, I'll remain skeptical. I will also not give them my email address just to try it out.

Why are you making blanket statements on things that you haven't even tried? This is leaps and bounds better than before.

No offense but do you believe it when microsoft announces they have solved quantum computing?

And to prove it they only need your email address, birth date, credit card number, and rights to first born child?

Re: 4o Image Generation

#416

Post by jay_kyburz »

nestorD wrote: post #382
jay_kyburz wrote: post #322

Earlier quoted context omitted.

So I spent a good few hours investigating the current state of the art a few weeks ago. I would like to generate a collection of images for the art in a video game. It is incredibly difficult to develop an art style, then get the model to generate a collection of different images in that unique art style. I couldn't work out how to do it. I also couldn't work out how to illustrate the same characters or objects in di…

Short answer: the model is good at consistency. You can use it to generate a set a style reference images, then use those as reference for all your subsequent generations. Generating in the same chat might also help it have further consistency between images.

Sorry that wasn't a question, I was saying they models were not good at constancy in my evaluation.

Re: 4o Image Generation

#417

Post by rhubarbtree »

mtillman wrote: post #415

The fact that it nailed the awkward engineer high five (image 2) is pretty impressive as someone who only gives awkward high fives.

One of the fingers is the wrong way around… it’s a big improvement but it’s easy to find major problems, and these are the best of 8 images and presumably cherry picked.

Re: 4o Image Generation

#419

Post by StefanBatory »

This technology should have never existed. Thank you OpenAI for being a contributing factor to destroying politics in future.

And I hope that people who worked on this know this. They are pure evil.

Re: 4o Image Generation

#420

Post by computergert »

It does extremely well at creating images of copyrighted characters. Dall-e couldn't generate images of Miffy, this one can. Same for "Kikker en vriendjes" - a dutch children's book. There seems to be copyright protection at all?
Post reply on HN