This is a JavaScript implementation of Magenta's sketch-rnn model, using TensorFlow.js for GPU-accelerated inference.
sketch-rnn is a generative recurrent neural network capable of producing sketches of common objects, with the goal of training a machine to draw and generalize abstract concepts in a manner similar to humans. This Sketch RNN model was trained on a dataset of hand-drawn sketches, each represented as a sequence of motor actions controlling a pen: which direction to move, when to lift the pen up, and when to stop drawing. In doing so, the created potentially has many applications, from assisting the creative process of an artist, to helping teach students how to draw.
Try out the interactive predict demo here.
Read more in Teaching Machines to Draw, and A Neural Representation of Sketch Drawings.