News for hackers. Stuff that matters.
Re:Introducing Images 2.6 by minimaxir on Wednesday November 04, 2026 @07:13PM (#50373260)
I would caution against using the webapp to test the quality of this new model because OpenAI does not indicate which image model and effort is being used to generate the image, to my continued frustration.
Re:Introducing Images 2.6 by CharlesW on Wednesday November 04, 2026 @07:23PM (#50373342)
This one looks pretty good and so may have been generated with the new model. In any case, hiding model provenance just makes OpenAI look like amateurs. https://chatgpt.com/s/cx_6aebcb5b67008191bdb265f3c04ac2fe
Re:Introducing Images 2.6 by xp84 on Wednesday November 04, 2026 @07:37PM (#50373451)
Wow. Are those the correct Pokemon and everything? Quite cool.
Re:Introducing Images 2.6 by minimaxir on Wednesday November 04, 2026 @07:46PM (#50373540)
Yes, the Pokemon are correct. Compare to my attempt a year ago with Nano Banana Pro, which plagiarized the images, didn't do interesting things with the background, and got 271 wrong: https://minimaxir.com/2025/12/nano-banana-pro/pokemongrid_hu...

When I did a similar prompt with ChatGPT 2.0 it was worse, so interesting to see improvement.

Re:Introducing Images 2.6 by Computer0 on Wednesday November 04, 2026 @07:58PM (#50373626)
On the back end a language model is effectively writing a long detailed prompt describing this image exactly right? The image model can't know this.
Re:Introducing Images 2.6 by minimaxir on Wednesday November 04, 2026 @08:06PM (#50373709)
ChatGPT Images (and some others like Nano Banana) are autoregressive models, and the text model generates the tokens in the same way which are then passed in the correct form for an image model to decode. That is how it can reason the prime numbers + Pokemon + art style conditional.

It is different from earlier image models which just use a simple text encoder and struggle with conditional logic if not explicitly trained for it.

Re:Introducing Images 2.6 by jackbrookes on Thursday November 05, 2026 @05:59AM (#50377713)
If you look at the thinking steps it clearly includes:

> * Mapped Pokémon primes > * Organized the grid

before generating the image.

So really it is first figuring out the exact specification of the layout, then prompting the image generation tool with this specification - perhaps unless you do it with an "instant" model.

Re:Introducing Images 2.6 by weird-eye-issue on Wednesday November 04, 2026 @08:24PM (#50373838)
Yes it thinks about it and then calls the image tool with the detailed prompt with exactly what to include in the image
Re:Introducing Images 2.6 by vunderba on Wednesday November 04, 2026 @10:33PM (#50374803)
I think it's more impressive that it managed so much coherence in a single image than anything else. Very few problems with each of the pokemon anatomically speaking. Mew's kind of a mess but the rest are pretty accurate.

That being said, the ukiyo-e artwork looks more like a standard colored pencil illustration, and it sort of tried to cheat by adding some vaguely Japanese natural scenery.

See this Kickstarter all the way back in 2013 for a great example of what Pokémon might actually look like as ukiyo-e woodblock prints.

https://www.kickstarter.com/projects/1499165518/ukiyo-e-hero...

https://ricedigital.co.uk/this-japanese-ukiyo-e-pokemon-art-...

Re:Introducing Images 2.6 by mitchdoogle on Wednesday November 04, 2026 @11:18PM (#50375128)
I remember that Kickstarter. I follow the woodblock carver who worked with the artist. His name is David Bull and he has some great videos on woodblock carving on YouTube: https://m.youtube.com/@seseragistudio
Re:Introducing Images 2.6 by vunderba on Wednesday November 04, 2026 @11:28PM (#50375190)
Oh, thanks for showing me these videos! The way that he presents is so calm - he's like a woodprint Bob Ross.