Google’s incredible prowess with artificial intelligence and neural networks does not always have to be put to revolutionary, life-changing uses. Sometimes, it can be used to make a robot write a song, or to turn your favorite art of family photo into the stuff of nightmares via Deep Dream. The same technology that allows machines to learn and confront new stimuli intelligently, when thrown at the all too human and organic pursuit of art, can make for some very unique stuff. Case in point; Google’s newest deep learning venture, Project Muze, uses the same technology as Deep Dream, but instead of using a base image and image input and search trends, it uses fashion trends, user input, and a few nifty additions from over 600 top names in the fashion design world.
High-end fashion design of the sort that you simply won’t see in a Wal-Mart is never completely conventional; good fashion designers know that stretching the definition of unique and walking the line between quirky and far too weird are risks that must be taken. Project Muze seems to throw that notion out the window and leap boldly into the weird side of things. When you boot up the design program, which will require a decent machine and a browser with hardware acceleration available, you will be given the option to view a gallery of other works, or to create your own. Users are asked a number of questions, such as their mood, favorite style of music, favorite art movement and other assorted personal bits and bobs, and then asked to draw something on top of a virtual mannequin. Project Muze spits out the result.
Using data from so many different sources in such a complex algorithm is not going to produce something exact, intricate, or least of all, conforming to design norms. As you can see in the pictures attached below, the machine tends to spit out some seriously strange designs, but with an element of cool and human to them because of their inspirations and origins. An option is presented to answer more questions and further customize a given design, as well; this option matches the user up with a whole new pattern, style, or shape, and shows how that trait would apply to the outfit on show. While some of these are downright impractical and most of them would get you more than a few strange looks in public, the fact that a machine is capable of this sort of thing at all speaks volumes about the hard work that many talented people have put into the field of machine learning down the years. If you have a capable machine and browser and feel like giving Project Muze a go, head on through the source link to take the world by storm with your own designs, with some robot assistance.
