With the recent rapid progress in the study of deep generative models (DGMs), there is a need for a framework that can implement them in a simple and generic way. In this research, we focus on two features of DGMs: (1) deep neural networks are encapsulated by probability distributions, and (2) models are designed and learned based on an objective function. Taking these features into account, we propose a new Python library to implement DGMs called Pixyz. This library adopts a step-by-step implementation method with three APIs, which allows us to implement various DGMs more concisely and intuitively. In addition, the library introduces memoization to reduce the cost of duplicate computations in DGMs to speed up the computation. We demonstrate experimentally that this library is faster than existing probabilistic programming languages in training DGMs.

Check out Pixyz/PixylMawthz's commissions and portfolio! | Hello! I'm Pix, a furry artist and animator! Been a long-time Vtuber fan and so excited to be able to contribute to the community now! ...

Send a request while they're still accepting!

Check out Pixyz's characters on Toyhouse!

Another quick project, practicing my new game-ready workflow using Plasticity for the bulk of the modeling. Cleaned up in Pixyz and Maya, textured in Painter. 3 draw calls 41k tris It's been so fas...

Pixyz is designed to optimize 3D models for various tasks: Converting BRep and Nurbs CAD models to Mesh for printing or rendering; Mesh optimization for a