Using advanced algorithms, artists like Sophia Crespo or Robbie Barat revisit their artistic creations using artificial intelligence. A revolution?
“It’s like a ballet between man and machine“In most cases, these digital artists work with programs known as supercomputers and generative adversarial networks,” said Jason Bailey, collector and one of the most famous crypto-art bloggers. Competes to provide a complete image: Man first provides the source image and adjusts the parameters to obtain from it, a result that interests him.
Sophia Crespo, 30, uses it to recreate animals. Purpose “Not to avoid the real nature, but to create a connection with nature through a medium where we spend a lot of time, which is a digital medium.He told AFP in a video interview from Lisbon that his insects were strangely hyper-realistic, with antennae, wings and bodies that appeared to be out of an entomology textbook. Went through
The astonishing advances in AI suggest a world where computers would be able to learn and create like humans. But, for the moment, he still needs to be guided. The Sophia Crespore series of insects required countless round trips between the artist and the proposed models of the neural network. Whether “Computers are an integral part of the creative process“,”The ability to create realistic pictures does not make everyone an artist“, A quality that guesses”A critical and innovative abilityAccording to Camille Langlois, curator of the Pompidou Center in Paris.
Robbie Barrett began his career in 2018, as Sophia Crespo. He enters thousands of classic art nudes on his computer, and starts a conversation with the machine, until he finds what he was looking for: a series of half-shapeless busts between Salvador Dali and Francis Bacon.
“When I work this way, I don’t create an image. I’m building a system that can reproduce images. Somehow I made a tool“She is OK. Nude Portrait # 7 Frame # 64It sold for more than 700,000 euros at Sotheby’s in March
A lawyer’s chair?
But today, simple new algorithms called “Transformers” are preparing to wreak havoc on this new universe. There was a problem so far “Input text and output imageExplain AFP Hugo Caselles-Dupré and Gauthier Vernier from the clear sum.
In particular, the instrument needs to be able to take astronomical quantities of all kinds of images with descriptions. A Titanic task is only accessible for economically well-off projects, such as the DAL-E2 model from California start-up OpenAI, specifically Elon Musk, or Imagine, funded by a competing project from Google Research.
From a simple sentence, the machine is then able to mix ideas and create a “different representation of it”.Radish couple skateboarding“, A”Lawyer’s chair“, Or a”Astronaut monkey“, In the style of all photographic, comic book styles, or the Flemish painter of the 17th century.”This is generally the best in terms of image generationSophia Crespo, who gained experience with Dal-e, believes.
Experts believe that these programs could revolutionize the entire image creation and editing industry. Many examples have already spread on social networks, including the annoying presentation of an animal at the junction of shrimp and centaur from a laboratory called Midjarni. On the other hand, OpenAI and Google have not yet released or marketed any consumer tools directly, especially due to the risk of malicious use.