It is true that when a picture one makes doesnt work sometimes it seems only to be a "tolerably good imitation of something else; in...

As I didn't go to art school (shame, I wanted to, but did medicine instead and then worked on the origin of life and now do artificial...

Ultimately I wanted to get more information into each picture than is present in a typical CLIP guided image. Here are some attempts to...

Some experiments here in treating the output of Arnheim 3.0 as Max Ernst might have treated the marks on a piece of wood or those found...

Just as Atari and Go are good test environments for reinforcement learning, there are some nice test environments for generative art, the...

"In my Image" , November 2021 "The Baptism of Christ", November 2021 "David Hockney", November 2021

I've been reading "Return to Sri-Lanka: Travels in a Paradoxical Land" by Razeen Sally who had a strangely similar life to me having...

I used to come and see Richard Dadd's paintings at the Tate Britain as a child. I loved the hierarchical complexity of it, and associated...

Thanks to Gregory Bateson for his beautiful book "Steps to an Ecology of Mind". As I'm still in the process of trying to understand what...

Our new code (which modifies the Arnheim 2.0 code we open-sourced today) allows us to make collages using CLIP as an evaluator. Some very...

Today I submitted these two pieces to the RA summer show. All the work is done by Arnheim 1.0, in the sense that it is Arnheim 1.0 that...

What is a good composition? There are many theories, to take one, consider Arnheim's book "The Power of the Center" which proposes that...

Using Arnheim 1.0 [see prev. blog post and paper here] I've been doing some experiments today with overpainting on photographs. Can A1.0...

The image below was produced by a neural L-system evolved to produce images that satisfy the text description "Jungle in the Tiger"...

At first it seemed I was a paranoid doctor who was being treated for a heart condition, a serious one. But then I think I was his son. My...

The doodle is a fascinating thing. It is produced unconsciously. Maybe it is the visual equivalent of stream of consciousness thinking,...

This post continues to think about generative procedures G which the artificial artist could use to produce marks. All the images I'd...

What generative rules (G) can the artificial artist use to produce images? During my recovery from coronavirus in April 2020 confined to...

It was a pleasure to find the work of Aaron Hertzman via the Neurips 2020 workshop on creativity. His talk addresses some issues...

Let us generalize the work of Tom White and others who have used stochastic search to produce art works (images) that optimize the class...