The piece is in no way a good representation of the current state of the art, and it uses a borrowed scraper to collect a dataset for a borrowed GAN implementation with output that looks strikingly similar to that of the original code's author.
A computer generated portrait has been sold for $432,500 at auction at Christie's in New York. It was created by a GAN (Generative Adversarial Network) algorithm that was seeded with 15,000 portraits painted between the 14th and 20th centuries.
I've been doing some Voronoi Stippling experiments today, including the rare inverted stippling, and decoupling of resolution and ink coverage. Also a rudimentary webcam capture. Check it out at https://beta.observablehq.com/@jobleonard/untitled
A social space for anyone in data, visualization, creative coding, and related arts and research. Share your work, discuss, critique, and ask for help! Come one, come all:
→ creative coders
→ data scientists and visualizers
→ generative artists
→ visual researchers, curators, and critics
→ anyone else data- or visualization-adjacent
If you are curious about the world and creativity, you are welcome here. Learn more.