logoalt Hacker News

minimaxir • today at 12:13 AM • 5 replies • view on HN

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.

That said, I gave it one of my more difficult image prompts and the model now surprisingly passes (without plagiaristic cheating): https://chatgpt.com/share/6aebcbcd-6b8c-83e8-b52b-dbedf20ce4...


Replies

vunderba • today at 3:33 AM

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-...

➕ show 1 reply
xp84 • today at 12:37 AM

Wow. Are those the correct Pokemon and everything? Quite cool.

➕ show 1 reply
Computer0 • today at 12:58 AM

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.

➕ show 2 replies