Fader network architecture: Original galaxy images are input to an encoder E(x) which performs a mapping to a latent space of fixed dimension. The associated physical property is binarized into a label y. The parametres E(x) and y are input to a decoder D(E(x), y) which tries to reconstruct the original input image. The discriminator Dis(E(x)) tries to predict the label y from the latent code E(x). Below, we show two examples of changing a single attribute in latent space using a fader network: the aging of a human face learned from age labels (using a pretrained model; Lample et al. 2017), and the lowering of the sSFR of a galaxy using sSFR labels.