Figure 1: We collect thousands of portraits by capturing video of a subject while they watch movie clips designed to elicit a range of positive emotions. We use crowdsourcing and machine learning to train models that can predict attractiveness scores of different expressions. These models can be used to select a subject’s best expressions across a range of emotions, from more serious professional portraits to big smiles. We describe a method for providing feedback on portrait expres-sions, and for selecting the most attractive expressions from large video/photo collections. We capture a video of a subject’s face while they are engaged in a task designed to elicit a range of pos-itive emotions. We then use crowdsourcing to score the captured expressions for their attractiveness. We use these scores to train a model that can automatically predict attractiveness of different ex-pressions of a given person. We also train a cross-subject model that evaluates portrait attractiveness of novel subjects and show how it can be used to automatically mine attractive photos from personal photo collections. Furthermore, we show how, with a little bit ($5-worth) of extra crowdsourcing, we can substantially improve the cross-subject model by ”fine-tuning ” it to a new individual using active learning. Finally, we demonstrate a training app that helps people learn how to mimic their best expressions.