Here, in this space between the river and the shore, in this time adrift, is Pelican Stairs.



Pelican Stairs is a multimedia art project started during the depths of lockdown in 2020. I took photos of my local neighbourhood, Wapping in London, on my daily walks between March and September. I often visited the Thames shore area by climbing a set of steps known as Pelican Stairs. Using those photos, I generated new fake images with a computer program, which are the images you see on this website paired with excerpts from my diary during the same period.


I fed the 1,100 real photos and videos I took during this six-month period into a computer program called a Generative Adversarial Network (GAN). The GAN produced the unsettling, almost-realistic images you can see on this website. The diary entries are real, though I’ve changed names.

I used RunwayML’s StyleGAN2 to train my model–you can train a model too, even if you’re not a programmer. RunwayML is designed for point-and-click data science for everyone.


Hello! I’m Caitlin McDonald: artist, strategist, anthropologist, high school dropout, PhD.

You can find out more about my work, volunteering, and other creative projects I’ve worked on over at


2020 was a turning point, and a strange one, for all of us. In a time adrift from my usual life patterns I used my daily walks as a routine to give focus and structure to my day. I had high anxiety about going outside during the early days of the pandemic and I felt especially far from my family overseas, who I knew I might not be able to see for a very long time. Giving myself the assignment of taking interesting photos of my daily walks was a way of keeping track of a bizarre period in my life, a stimulus to get out of the house despite my fears, and a reason for regularly checking in with new content to share with my parents.

The distortions and surreality introduced by feeding the images through a GAN represent the blurred, overlapping, confusing nature of that time. Pairing them with real extracts from my diary entries during that period captures the counterpoint between the attempts at everyday normalcy and an ever more uncertain outside reality.

More and more of our interactions with others are mediated through digital technologies. Closeness is both facilitated and occluded through these digitized windows into each other’s worlds. The GAN images, based on reality but not real in themselves, amplify the distortions and communicative frictions that accompany our digital communication tools.

The original photographs of real objects and landscapes remain hidden. Only the manipulated images are available to the public, an exploration of what we share and how we present ourselves online.

The GAN model can generate a theoretically infinite number of new images based on my original collection of photos. I chose to bound this project within the six months between the announcement of lockdown and my move from London to Edinburgh, but for as long as life remains disrupted, I can continue to generate new images that smear out the initial confusion and blurriness of that time to infinite strange new futures.

Find Pelican Stairs at…

  • Creativity & Cognition 2022, the Association for Computing Machinery’s 14th annual international conference where arts meet science. 20-23 June 2022.
  • Generative Art 2021, the 24th annual international festival of generative art. 15-17 December 2021.
  • DigiFest 2021, the Faculty of Art and Design Digital Festival by Durban University. 19-21 October 2021. Winner, Best Individual Presentation.

Pelican stairs from the sand

The only way is up…