MUSE: Textual Attributes Guided Portrait Painting Generation

We propose a novel approach, MUSE, to automatically generate portrait paintings guided by textual attributes. MUSE takes a set of attributes written in text, in addition to facial features extracted from a photo of the subject as input. We propose 11 attribute types to represent inspirations from a subject's profile, emotion, story, and environment. Then we design a novel stacked neural network ar...