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

51–60 of 629 posts

Re: 4o Image Generation

#51

Post by afro88 »

tetris11 wrote: post #44
afro88 wrote: post #40

Edit: Please ignore. They hadn't rolled the new model out to my account yet. The announcement blog post is a bit misleading saying you can try it today. -- Comparison with Leonardo.Ai. ChatGPT: https://chatgpt.com/share/67e2fb21-a06c-8008-b297-07681dddee... ChatGPT again (direct one shot): https://chatgpt.com/share/67e2fc44-ecc8-8008-a40f-e1368d306e... ChatGPT again (using word "photorealistic instead of "photo"): ht…

Is the ”2D animation style" part you put at the beginning and then changed an attempt to see how well the AI responds to gas lighting?

My bad, I was trying the conversational aspect, but that's not an apples to apples conparison. I have put a direct one shot example in the original post as well.

Re: 4o Image Generation

#52

Post by afro88 »

elicash wrote: post #50
afro88 wrote: post #40

Edit: Please ignore. They hadn't rolled the new model out to my account yet. The announcement blog post is a bit misleading saying you can try it today. -- Comparison with Leonardo.Ai. ChatGPT: https://chatgpt.com/share/67e2fb21-a06c-8008-b297-07681dddee... ChatGPT again (direct one shot): https://chatgpt.com/share/67e2fc44-ecc8-8008-a40f-e1368d306e... ChatGPT again (using word "photorealistic instead of "photo"): ht…

What did the prompt look like for Leonard.ai? I'm curious if you said 2d animation style for both or just for chatgpt. Edit: Your second version of chatgpt doesn't say photorealistic. Can you share the Leonard.ai prompt?

Added photorealistic, which made it worse.

Leonardo prompt: A golden cocker spaniel with floppy ears and a collar that says "Sunny" on it

Model: Phoenix 1.0 Style: Pro color photography

Re: 4o Image Generation

#53

Post by minimaxir »

aantix wrote: post #28

Still seems to have problems with transparent backgrounds.

That's expected with any image generating models because they aren't trained with an alpha channel.

It's more pragmatic to pipeline the results to a background removal model.

EDIT: It appears GPT-4o is different as there is a video demo dedicated to transparancy.

Re: 4o Image Generation

#54

Post by coherentpony »

> we’ve built our most advanced image generator yet into GPT‑4o. The result—image generation that is not only beautiful, but useful.

Sorry, but how are these useful? None of the examples demonstrate any use beyond being cool to look at.

The article vaguely mentions 'providing inspiration' as possible definition of 'useful'. I suppose.

Re: 4o Image Generation

#55

Post by afro88 »

afro88 wrote: post #52
elicash wrote: post #50

Earlier quoted context omitted.

What did the prompt look like for Leonard.ai? I'm curious if you said 2d animation style for both or just for chatgpt. Edit: Your second version of chatgpt doesn't say photorealistic. Can you share the Leonard.ai prompt?

Added photorealistic, which made it worse. Leonardo prompt: A golden cocker spaniel with floppy ears and a collar that says "Sunny" on it Model: Phoenix 1.0 Style: Pro color photography

Saying "pro color photography" to ChatGPT doesn't get it any better either unfortunately: https://chatgpt.com/share/67e2fd91-8d24-8008-b144-92c832ed0b...

Re: 4o Image Generation

#56

Post by afro88 »

wodenokoto wrote: post #47
afro88 wrote: post #40

Edit: Please ignore. They hadn't rolled the new model out to my account yet. The announcement blog post is a bit misleading saying you can try it today. -- Comparison with Leonardo.Ai. ChatGPT: https://chatgpt.com/share/67e2fb21-a06c-8008-b297-07681dddee... ChatGPT again (direct one shot): https://chatgpt.com/share/67e2fc44-ecc8-8008-a40f-e1368d306e... ChatGPT again (using word "photorealistic instead of "photo"): ht…

In all fairness you _did_ say 2D animation style

True. I had that conversation before deciding to compare to others. I have updated the post with other fairer examples. Nowhere near Leonardo Phoenix or Flux for this simple image at least.

Re: 4o Image Generation

#57

Post by kh_hk »

> Introducing 4o Image Generation: [...] our most advanced image generator yet

Then google:

> Gemini 2.5: Our most intelligent AI model

> Introducing Gemini 2.0 | Our most capable AI model yet

I could go on forever. I hope this trend dies and apple starts using something effective so all the other companies can start copying a new lexicon.

Re: 4o Image Generation

#58

Post by drew-y »

afro88 wrote: post #40

Edit: Please ignore. They hadn't rolled the new model out to my account yet. The announcement blog post is a bit misleading saying you can try it today. -- Comparison with Leonardo.Ai. ChatGPT: https://chatgpt.com/share/67e2fb21-a06c-8008-b297-07681dddee... ChatGPT again (direct one shot): https://chatgpt.com/share/67e2fc44-ecc8-8008-a40f-e1368d306e... ChatGPT again (using word "photorealistic instead of "photo"): ht…

The ChatGPT examples don't look like the new Image Gen model yet. The text on the dog collar isn't very good.

Re: 4o Image Generation

#60

Post by minimaxir »

pton_xd wrote: post #12

Can you specify the output dimensions? EDIT: Seems not, "The smallest image size I can generate is 1024x1024. Would you like me to proceed with that, or would you like a different approach?"

I suspect you can prompt aspect ratios.
Post reply on HN