Continuous Semi-Implicit Models

TL;DR

CoSIM introduces a continuous semi-implicit framework that enables efficient training and improves diffusion model acceleration, demonstrating superior image generation performance without slow convergence issues.

Contribution

It extends hierarchical semi-implicit models into a continuous domain, enabling simulation-free training and distributional consistency for generative model distillation.

Findings

CoSIM achieves competitive or superior image generation results.

It accelerates diffusion models effectively.

The model demonstrates distributional consistency with a designed transition kernel.

Abstract

Semi-implicit distributions have shown great promise in variational inference and generative modeling. Hierarchical semi-implicit models, which stack multiple semi-implicit layers, enhance the expressiveness of semi-implicit distributions and can be used to accelerate diffusion models given pretrained score networks. However, their sequential training often suffers from slow convergence. In this paper, we introduce CoSIM, a continuous semi-implicit model that extends hierarchical semi-implicit models into a continuous framework. By incorporating a continuous transition kernel, CoSIM enables efficient, simulation-free training. Furthermore, we show that CoSIM achieves consistency with a carefully designed transition kernel, offering a novel approach for multistep distillation of generative models at the distributional level. Extensive experiments on image generation demonstrate that CoSIM performs on par or better than existing diffusion model acceleration methods, achieving superior performance on FD-DINOv2.