![]() But the critiques that Salle offered did help improve the machine’s intelligence enough to surprise the artist. Some of the first experiments were underwhelming: blobby landscapes, figures drawn without brush strokes, flat abstraction. Davis, the engineer, then introduced dozens of detailed snapshots of Salle’s paintings to the program so it would learn to “think like a painter.” The algorithm’s “training” to become the next David Salle started with a diffusion model to develop a general understanding of visual images based on hundreds of the artist’s paintings. Experts say that increased matchmaking improves accuracy but also stymies the machine’s ability to produce the unexpected. through a short sequence of numbers known as “latent space.”īut learning artistic style requires going beyond simple pattern recognition. Its knowledge is then stored in the parameters of the model, which is translated to the A.I. On another page of his art treatise, Salle delivered a grand theory of creativity: “ Form is the raw material, and style is the forge.”Īrtificial intelligence has a limitless vault of forms, thanks to the billions of online images it studies through a process called diffusion, in which the algorithm learns the structure of an image - and then learns to create variations. He recalled asking the painter Alex Katz to make a list of his own influences Katz said the list started with Jackson Pollock and ended with “the guy who made Nefertiti.” “Every major artist is an amalgamation or synthesis of diverse sympathies and influences,” Salle wrote in his 2018 book “How to See” about making and viewing art. He has also juxtaposed photography with painting. He is often grouped with the appropriation artists of the 1980s, including Richard Prince and Cindy Sherman, who have questioned the primacy of authorship in contemporary culture. The results have sometimes been described as memories that barely hold together, and as attempts to ascribe significance to the foggy afterimages of art history. ![]() He, in turn, was trained by the conceptualist John Baldessari at the California Institute of the Arts in the 1970s and has a style that absorbs a diverse set of influences, from the Italian painter Giorgio de Chirico to the New Yorker cartoonist Peter Arno. Salle is one of the first traditional artists to embed on the front lines of artificial intelligence. ![]() The process can repeat itself like that until he’s satisfied.” Then David starts drawing on top of them. “And we generate lots of images before selecting the ones we like. “Our process starts with very imaginative prompts,” Davis said. Prompts also have been sourced from another friend, the writer Sarah French. With permission from Ben Lerner, a friend of Salle’s, the group has been feeding bits of poetry from his new book, “The Lights,” to evoke more fantastical images of cities growing within organic cells, and patterns of interlocking barbules. Salle was something like a guinea pig for Wand, teaching its program how to paint while developing his own series of digital images. platform for artists that promises to help them streamline their operations with faster imaging through text prompts and sketching. Danika Laszuk runs a program called E.A.T_WORKS, for the venture capital firm Betaworks, that pairs artists and engineers on projects where her company might earn a percentage of the profits. The experiment was a mutually beneficial arrangement. It was not a perfect clone, but it was superior - and it surprised him, after 50 years of art-making.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |