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

521–530 of 629 posts

Re: 4o Image Generation

#521

Post by theptip »

Taek wrote: post #486
wegfawefgawefg wrote: post #435

Earlier quoted context omitted.

almost all of the models are wrong about their own architecture. half of them claim to be openai and they arent. you cant trust them about this

Can you find me a single official source from OpenAI that claims that GPT 4o is generating images pixel-by-pixel inside of the context window? There are lots of clues that this isn't happening (including the obvious upscaling call after the image is generated - but also the fact that the loading animation replays if you refresh the page - and also the fact that 4o claims it can't see any image tokens in its context w…

Just read the release post, or any other official documentation.

https://openai.com/index/hello-gpt-4o/

Plenty was written about this at the time.

Re: 4o Image Generation

#522

Post by h8hawk »

echelon wrote: post #25
jjmarr wrote: post #22

Earlier quoted context omitted.

Yeah, but then it no longer replaces human artists. Controlnet has been the obvious future of image-generation for a while now.

We're not trying to replace human artists. We're trying to make them more efficient. We might find that the entire "studio system" is a gross inefficiency and that individual artists and directors can self-publish like on Steam or YouTube.

Yeah, it’s just ComfyUI replacing Photoshop

Re: 4o Image Generation

#523

Post by blixt »

gspr wrote: post #508
blixt wrote: post #268

Earlier quoted context omitted.

This argument could be made for every level of abstraction we've added to software so far... yet here we are commenting about it from our buggy apps!

> This argument could be made for every level of abstraction we've added to software so far... yet here we are commenting about it from our buggy apps! No. Not at all. Those levels of abstractions – whether good, bad, everything in between – were fully understood through-and-through by humans. Having an LLM somewhere in the stack of abstractions is radically different, and radically stupid.

Every component of a deep neural network is understood by many people, it's the interaction between the numbers trained that we don't always understand. Likewise, I would say that we understand the components on a CPU, and the instructions it supports. And we understand how sets of instructions are scheduled across cores, with hyperthreading and the operating system making a lot of these decisions. All the while the GPU and motherboard are also full of logical circuits, understood by other people probably. And some (again, often different) people understand the firmware and dynamically linked libraries that the users' software interfaces with. But ultimately a modern computer running an application is not through and through understood by a single human, even if the individual components could be.

Anyway, I just think it's fun to make the thought experiment that if we were here 40 years ago, discussing today's advanced hardware and software architecture and how it interacts, very similar arguments could be used to say we should stick to single instructions on a CPU because you can actually step through them in a human understandable way.

Re: 4o Image Generation

#524

Post by theptip »

jjbinx007 wrote: post #130
blixt wrote: post #104

What's important about this new type of image generation that's happening with tokens rather than with diffusion, is that this is effectively reasoning in pixel space. Example: Ask it to draw a notepad with an empty tic-tac-toe, then tell it to make the first move, then you make a move, and so on. You can also do very impressive information-conserving translations, such as changing the drawing style, but also stuff l…

It still can't generate a full glass of wine. Even in follow up questions it failed to manipulate the image correctly.

Nope, it can.

Got it in two requests, https://chatgpt.com/share/67e41576-8840-8006-836b-f7358af494... for the prompts.

Re: 4o Image Generation

#525

Post by arrowsmith »

ksec wrote: post #511

Can someone explain what is going with 4o and Anime with Ghibli Style? Why is it suddenly all over x/twitter?

Someone posted a mildly amusing tweet that blew up and went really viral. Now lots of other people are copying the idea.

This dynamic happens on Twitter every day. Tomorrow it'll be a different craze.

Re: 4o Image Generation

#526

Post by brrrrrm »

thehappypm wrote: post #496
aurareturn wrote: post #428

Earlier quoted context omitted.

If you look at the examples given, this is the first time I've felt like AI generated images have passed the uncanny valley. The results are ground breaking in my opinion. How much longer until an AI can generate 30 successive images together and make an ultra realistic movie?

One day you’ll just give it a script and get a movie out

a premise*

Re: 4o Image Generation

#527

Post by hansmayer »

blixt wrote: post #104

What's important about this new type of image generation that's happening with tokens rather than with diffusion, is that this is effectively reasoning in pixel space. Example: Ask it to draw a notepad with an empty tic-tac-toe, then tell it to make the first move, then you make a move, and so on. You can also do very impressive information-conserving translations, such as changing the drawing style, but also stuff l…

A lot of convoluted explanations about something we don't even know if it really works all the time. I feel like in the third year of LLM-Hype and after reminde-me-how-many billions of dollars burned, we should by now not have to imagine what 'might happen' down to road, it should have been happening already. The use-case you are describing, sure sounds very interesting, until I remember asking asked Copilot for a simple scaffolding structure in React, and it spat out something which lacked half of imports and proper visual alignments. A few years ago I was excited about the possibility of removing all the scaffolding and templating work so we can write the cool parts, but they cannot even do that right. It's actually a step back compared to automatic code generators of the past, because those at least produced reproducible results every single time you used them. But hey sure, the next generation of "AI" (it's not really AI) will probably solve it.

Re: 4o Image Generation

#528

Post by suddenlybananas »

beala wrote: post #505
RobinL wrote: post #449

It's very impressive. It feels like the text is a bit of a hack where they're somehow rendering the text separately and interpolating it into the image. Not always, I got it to render calligraphy with flourishes, but only for a handful of words. For example, I asked it to render a few lines of text on a medieval scroll, and it basically looked like a picture of a gothic font written onto a background image of a scrol…

This doesn't explain the whiteboard example at the link. The handwritten text on the whiteboard does not look like a font at all.

You could have a model that receives the generated raw text and then is trained to display it in whatever style. Whether it looks like a font or not is irrelevant.

Re: 4o Image Generation

#529

Post by algo_trader »

vunderba wrote: post #370

Ran through some of my relatively complex prompts combined with using pure text prompts as the de-facto means of making adjustments to the images (in contrast to using something like img2img / inpainting / etc.) https://mordenstar.com/blog/chatgpt-4o-images It's definitely impressive though once again fell flat on the ability to render a 9-pointed star.

Have u had any luck with engineering/schematics/wireframe diagrams such as [1] ??

[1] https://techcrunch.com/wp-content/uploads/2024/03/pasted-ima...

Re: 4o Image Generation

#530

Post by electroly »

snickell wrote: post #347
Retr0id wrote: post #346

Earlier quoted context omitted.

Do you have any demo videos?

No, I wasn't planning to post this for a couple weeks, but I saw the comment and was like "eh, why not?". You can watch "sped up" past sessions by other people who used this demo here, which is kind of like a demo video: https://universal.oroborus.org/gallery But the gallery feature isn't really there today, it shows all the "one-click and bounce sessions", and its hard to find signal in the noise. I'll probably subm…

Seconding the need for a video. We need a way to preview this without it costing you money. I had to charge you a few dimes to grasp this excellent work. The description does not do it justice; people need to see this in motion. The progressive build-up of a single frame, too. I encourage you to post the Show HN soon.
Post reply on HN