Listly by Jean-Louis Paquelin
When AI meets Art. This list is a small collection of articles related to the incursions of artificial intelligence [AI] in the realm of human creation as painting, sculpture, music or poetry.
The auction house Christie’s will make art history by selling its first AI portrait, a piece created by the French group Obvious. The portrait has an unusual backstory: it was made using partially borrowed code, and it has been the target of criticism from members of the AI art community.
An artificial-intelligence “artist” got a solo show at a Chelsea gallery. Will it reinvent art, or destroy it?
Code and data for paper "Deep Painterly Harmonization"
“Photograph of The Beatles as they arrive in New York City in 1964” from the Wikimedia Foundation and the United States Library of Congress‘s Prints and Photographs division. This work is in the public domain in the United States because it was published in the United States between 1924 and 1977 without a copyright notice.
It is a kind of mask made of brass, contoured to the shape of the face. The three elements on it make the human face unrecognizable by the camera. This project was preceded by a long-term study on the shape, size and location of mask elements, so that it actually fulfilled its task.
AI Portraits does an amazing job of creating original portraits based on photos of faces. The generative network was trained with 45,000 portrait images.
Snell’s piece, named Dio, follows the basic methodology of these earlier works. Machine learning algorithms are used to scan and digest a database of historical artworks, and then attempt to reproduce the data they’ve seen, with their output guided by the artist.
Artificial Intelligence, or AI, is being used everyday for a wide variety of uses online, so it’s no surprise that music is being generated using it. While it might not win any awards, in most cases it’s at least passable. But music is mathematical by nature, which makes it a good candidate for AI creation. Lyrics, on the other hand, are a different kettle of fish that AI still can’t get its arms around.
Our dataset consisted of about a hundred Christmas tunes and was collected in MIDI format. A MIDI-file is a text file containing the notes and length and loudness of each note. Because of this, the MIDI format is suitable for doing machine learning tasks. For converting we used Music21, an open source library to read and write playable MIDI files.