You may not know, but I also know how to code :)
This is something that I have wanted to share for ages, but it feels outdated with so many generative images crawling the Internet these days.
There must be hundreds of artists trying to mix art and computing. It is interesting computationally speaking (there are tons of math and engineering involved), visually (computed generated art is usually impressive) and conceptually (is it actually art? how we define art?).
This @anastasiaopara’s tweet inspired me to try my own thing in 2020. It is a project to make computer draw images. She has published her code so that we all can play around with it. I wanted to understand how it works and try my own ideas, so that I ended forking and trying my own code.
This may not feel spectacular today with so many LLMs (what it is widely known as AI nowadays): LLMs are trained on available data. They "just" generate the next word or images based on our instructions and the previous generated word or image. It's may feel magical, but in my opinion there is no art there, as there is no intention.
This algorithm tries to simulate the process of a painter that is learning to paint using an image as inspiration. I used one my photos with Samantha Vottari. It simulates the strokes that a painter would apply when trying to use that image as reference. Mistakes included, which are fixed with following strokes that will hide those mistakes. Isn't it magical?
If you missed the gif running at the beginning, reload this page 🙏