Deep Meditations: Controlled navigation of latent space

02/27/2020

∙

by   Memo Akten, et al.

∙

18

∙

share

We introduce a method which allows users to creatively explore and navigate the vast latent spaces of deep generative models. Specifically, our method enables users to discover and designtrajectories in these high dimensional spaces, to construct stories, and produce time-based media such as videos—with meaningful control over narrative. Our goal is to encourage and aid the use of deep generative models as a medium for creative expression and story telling with meaningful human control. Our method is analogous to traditional video production pipelines in that we use a conventional non-linear video editor with proxy clips, and conform with arrays of latent space vectors. Examples can be seen at <http://deepmeditations.ai>.