AI Jukebox is a fascinating project from OpenAI that uses cutting-edge neural neworks to perform all sorts of musical magic -- it can take a clip of a song and continue it in a new way, sing text lyrics in any artist's voice, make a song sound like it's being sung by someone else. My favorite? Tell it to generate music by an artist without any other info, and it will produce a gibberish song with nonsense lyrics... that still sounds 100% real and just like the actual singer or band with their unique style. You can hear instruments, melodies, sometimes an audience, the breathing of the lead singer -- but the whole thing is generated completely from scratch by the AI, not with samples or digital sounds. It's not flawless -- some of the songs ramble, with glitchy effects or a mutating voice. But these just add to the vibe, like it's from a dream or a parallel universe. I went through their database to find the best examples of these tracks from the most famous artists, then turned them into an audio quiz on Sporcle -- complete with AI-generated art of the artists I made to serve as hints in the second round. How many of the artists can you name? [more inside]
I trained a StyleGAN2 neural network on street art but ended up creating something totally new that generates dark and twisted imagery in its own unique style. The full-size 'signed' digital artwork is for sale to support producing more VOLE.wtf nonsense.
I trained a StyleGAN neural network using official photos of UK Members of Parliament, then generated a whole new load of them along with names and constituencies (using segments from real MP names and structures of actual constituency names). The results are often blandly white, male & middle-aged, and occasionally very weird.