> I wasn’t able to generate the image because the combination of abstract elements and stylistic blending [...] may have triggered content filters related to ambiguous or intense visuals.
nah. i pass and stick with midjourney.
4o Image Generation
421–430 of 629 posts
Re: 4o Image Generation
#422Earlier quoted context omitted.
https://i.imgur.com/xsFKqsI.png "Draw a picture of a full glass of wine, ie a wine glass which is full to the brim with red wine and almost at the point of spilling over... Zoom out to show the full wine glass, and add a caption to the top which says "HELL YEAH". Keep the wine level of the glass exactly the same."
Can't replicate. Maybe the rollout is staggered? Using Plus from Europe, it's consistently giving me a half full glass.
The EU got the drunken version. And a good drunk know not to top of a glass of wine ever. In that context the glass is already "full".
But aside from that it would only be comparable if would compare your prompts.
Re: 4o Image Generation
#423Earlier quoted context omitted.
US-ian, as in from the United States.
So should we be using Eusians for citizens of the Estados Unidos Mexicanos?
Why?
The Americas are quite a bit larger than the USA, so I disagree with 'american' being a word for people and things from mainland USA. Usian seems like a reasonable derivative of USA and US, similar to how mexican follows from Mexico and Estados Unidos Mexicanos.
Re: 4o Image Generation
#424What'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…
> 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. I do not think that this is correct. Prior to this release, 4o would generate images by calling out to a fully external model (DALL-E). After this release, 4o generates images by calling out to a multi-modal model that was trained alongside it. You c…
>You can ask 4o about this yourself. Here's what it said to me:
>"So while I’m deeply multimodal in cognition (understanding and coordinating text + image), image generation is handled by a linked latent diffusion model, not an end-to-end token-unified architecture."
Models don't know anything about themselves. I have no idea why people keep doing this and expecting it to know anything more than a random con artist on the street.
Re: 4o Image Generation
#425Earlier quoted context omitted.
> truly generative UI, where the model produces the next frame of the app I built this exact thing last month, demo: https://universal.oroborus.org (not viable on phone for this demo, fine on tablet or computer) Also see discussion and code at: http://github.com/snickell/universal I wasn't really planning to share/release it today, but, heck, why not. I started with bitmap-style generative image models, but because t…
This is super cool! I think new kinds of experiences can be built with infinite generative UIs. Obviously there will need to be good memory capabilities, maybe through tool use. If you end up taking this further and self hosting a model you might actually achieve a way faster “frame rate” with speculative decoding since I imagine many frames will reuse content from the last. Or maybe a DSL that allows big operations…
What I'm currently doing is caveman: I ask the LLM to attach a unique id= to every element, and I gave it an attribute (data-use-cached) it can use to mark "the contents of this element should be loaded from the preivous frame": https://github.com/snickell/universal/blob/47c5b5920db5b2082...
For example, this specifies that #my-div should be replaced with the value from the previous frame (which itself might have been cached):
This lowers the render time /substantially/, for simple changes like "clicked here, pop-open a menu" it can do it in 10s, vs a full frame render which might be 2 minutes (obviously varies on how much is on the screen!).
I think using HAML etc is an interesting idea, thanks for suggesting it, that might be something I'll experiment with.
The challenge I'm finding is that "fancy" also has a way of confusing the LLM. E.g. I originally had the LLM produce literal unified diffs between frames. I reasoned it had seem plenty of diffs of HTML in its training data set. It could actually do this, BUT image quality and intelligence were notably affected.
Part of the problem is that at the moment (well 1mo ago when I last benchmarked), only Claude is "past the bar" for being able to do this particular task, for whatever reason. Gemini Flash is the second closest. Everything else (including 4o, 4.5, o1, deepseek, etc) are total wipeouts.
What would be really amazing is if say Llama 4 turns out to be good in the visual domain the way claude is, and you can run it on one of the LLM-on-silicon vendors (cerebrus.ai, grok, etc) to get 10x the token rate.
LMK if you have other ideas, thanks for thinking about this and taking a look!
Re: 4o Image Generation
#426Earlier quoted context omitted.
Yes, and it shows you believing what the bot is telling you, therefore I asked. It is giving you some generic function call with a generic name. Why would you believe that is actually what happens with it internally? By the way when I repeated your prompt it gave me another name for the module.
Please share your chat I also just confirmed via the API that it's making an out of band tool call EDIT: And googling the tool name I see it's already been widely discussed on twitter and elsewhere
Posts like this are terrifying to me. I spend my days coding these tools thinking that everyone using them understands their glaring limitations. Then I see people post stuff like this confidently and I'm taken back to 2005 and arguing that social media will be a net benefit to humanity.
The name of the function shows up in: https://github.com/openai/glide-text2im which is where the model probably learned about it.
Re: 4o Image Generation
#427Earlier quoted context omitted.
Please share your chat I also just confirmed via the API that it's making an out of band tool call EDIT: And googling the tool name I see it's already been widely discussed on twitter and elsewhere
Posts like this are terrifying to me. I spend my days coding these tools thinking that everyone using them understands their glaring limitations. Then I see people post stuff like this confidently and I'm taken back to 2005 and arguing that social media will be a net benefit to humanity. The name of the function shows up in: https://github.com/openai/glide-text2im which is where the model probably learned about it.
The tool name is not relevant. It isn't the actual name, they use an obfuscated name. The fact that the model believes it is a tool is good evidence at first glance that it is a tool, because the tool calls are typically IN THE PROMPT.
You can literally look at the JavaScript on the web page to see this. You've overcorrected so far in the wrong direction that you think anything the model says must be false, rather than imagining a distribution and updating or seeking more evidence accordingly
Re: 4o Image Generation
#428OpenAI's livestream of GPT-4o Image Generation shows that it is slowwwwwwwwww (maybe 30 seconds per image, which Sam Altman had to spin "it's slow but the generated images are worth it"). Instead of using a diffusion approach, it appears to be generating the image tokens and decoding them akin to the original DALL-E ( https://openai.com/index/dall-e/ ), which allows for streaming partial generations from top to botto…
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?
Re: 4o Image Generation
#429Earlier quoted context omitted.
> 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. I do not think that this is correct. Prior to this release, 4o would generate images by calling out to a fully external model (DALL-E). After this release, 4o generates images by calling out to a multi-modal model that was trained alongside it. You c…
>You can ask 4o about this yourself. Here's what it said to me: >"So while I’m deeply multimodal in cognition (understanding and coordinating text + image), image generation is handled by a linked latent diffusion model, not an end-to-end token-unified architecture." Models don't know anything about themselves. I have no idea why people keep doing this and expecting it to know anything more than a random con artist o…
This is overly cynical. Models typically do know what tools they have access to because the tool descriptions are in the prompt. Asking a model which tools it has is a perfectly reasonable way of learning what is effectively the content of the prompt.
Of course the model may hallucinate, but in this case it takes a few clicks in the dev tools to verify that this is not the case.
Re: 4o Image Generation
#430Earlier 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 not use a fake email address?