Recently, there have been some very impressive advances in generative models for sound, text and images. In this talk, I will look into applications of generative models to Lattice QCD. The models I will consider are flows, which are families of diffeomorphisms transforming simple base distributions into complicated target distributions. Traditional ML flows are on vector spaces, which is different from our setup where we need to deal with products of SU(N). I will give details on how we built these flows, and explain how known symmetries of LQCD can be incorporated into them.