Artist Used Neural Network To Create These Portraits
Claudia Fuggetti’s research sees the creation of images as the endpoint of a visual investigation balanced between the real and the unreal, intending to propose new reading keys to interpreting the contemporary. Continue reading »
Someone Fed Facebook Emojis Into A Neural Net And Made Them in Style of Zdzisław Beksiński
Zdzisław Beksiński (24 February 1929 – 21 February 2005) was a Polish painter, photographer and sculptor specializing in the field of dystopian surrealism. Continue reading »
Person Uses Artificial Intelligence To Make Anime And Cartoon Characters Look More Realistic
Cartoons and anime have been and are a big part of a lot of people’s lives. They offer us grand adventures, fun, and exciting plotlines and storylines, unique, driven, and lovable characters. But have you ever wondered what the characters we all know and love would look like if they were realistic? Continue reading »
#FleshEmoji: Enthusiasts Fed Emojis Into a Neural Net and Made Them Human, Creepy Results Will Be Sold as NFTs
#FleshEmoji is the inaugural NFT project from the art collective ArtEveryDay. Each artwork is based on the Unicode emoji faces, with each one being fed through a neural network trained on human faces. Continue reading »
Face Depixelizer Neural Network “Brings Back The Sharpness” Of Photos In Low Resolution, And The Results Are Very Unexpected
A new digital tool built to depixelize photos sounds scary and bad. Another way to remove privacy from the world. But this tool is also being used for a sillier and not terrible purpose: Depixelizng old game characters. The results are…nevermind, this is also a terrible use of this tool. Continue reading »
A Neural Network Invented A Bunch Of New Paint Colors That Are Hilariously Wrong
At some point, we’ve all wondered about the incredibly strange names for paint colors. Research scientist and neural network goofball Janelle Shane took the wondering a step further. Shane decided to train a neural network to generate new paint colors, complete with appropriate names. The results are possibly the greatest work of artificial intelligence I’ve seen to date.
Writes Shane on her Tumblr, “For this experiment, I gave the neural network a list of about 7,700 Sherwin-Williams paint colors along with their RGB values. (RGB = red, green, and blue color values.) Could the neural network learn to invent new paint colors and give them attractive names?”
By the first checkpoint, the neural network has learned to produce valid RGB values – these are colors, all right, and you could technically paint your walls with them. It’s a little farther behind the curve on the names, although it does seem to be attempting a combination of the colors brown, blue, and gray.
By the second checkpoint, the neural network can properly spell green and gray. It doesn’t seem to actually know what color they are, however. Continue reading »
