I've been trying to get some language models to paint one stroke at a time for a few months now. I thought this community would be interested to see the results.
The article runs through my findings, and there's a linked technical rundown of how the app was built. There's also an interactive gallery [0] of my attempts. You can point an agent at the API docs [1], and they might (ymmv) do a painting themselves.
I would say how, but I am not your friend and here in the 2030s, no one can afford to give anything valuable for free to a stranger. Be glad of the advice, of which you'd be wise to make much more than you will.
I've been trying to get some language models to paint one stroke at a time for a few months now. I thought this community would be interested to see the results.
The article runs through my findings, and there's a linked technical rundown of how the app was built. There's also an interactive gallery [0] of my attempts. You can point an agent at the API docs [1], and they might (ymmv) do a painting themselves.
[0] https://www.liamlaverty.com/paint-by-language-model/ [1] https://www.liamlaverty.com/paint-by-language-model/draw/api
You are desperately misguided.
I would say how, but I am not your friend and here in the 2030s, no one can afford to give anything valuable for free to a stranger. Be glad of the advice, of which you'd be wise to make much more than you will.
You may enjoy
* "The last six months in LLMs, illustrated by pelicans on bicycles" https://simonwillison.net/2025/Jun/6/six-months-in-llms/ (https://news.ycombinator.com/item?id=44215352 | 962 points | 11 months ago | 239 comments)
* "Using “underdrawings” for accurate text and numbers" https://samcollins.blog/underdrawings/ (https://news.ycombinator.com/item?id=47977990 | 379 points | 9 days ago | 138 comments)
Good attempt. Compared to diffusion, these paintings look more like they were created by humans.
LLMs can draw (play music, write books), but they imitate, not create.