GAS: Improving Discretization of Diffusion ODEs via Generalized Adversarial Solver

TL;DR

This paper introduces the Generalized Adversarial Solver, a simple and effective method to improve the quality of diffusion model sampling by combining a new ODE parameterization with adversarial training, reducing artifacts and preserving details.

Contribution

The paper proposes a novel, training-trick-free ODE solver parameterization combined with adversarial training, enhancing diffusion sampling quality without complex training procedures.

Findings

Outperforms existing solvers in quality under similar resource constraints

Reduces artifacts and improves detail fidelity in generated samples

Does not require additional training tricks

Abstract

While diffusion models achieve state-of-the-art generation quality, they still suffer from computationally expensive sampling. Recent works address this issue with gradient-based optimization methods that distill a few-step ODE diffusion solver from the full sampling process, reducing the number of function evaluations from dozens to just a few. However, these approaches often rely on intricate training techniques and do not explicitly focus on preserving fine-grained details. In this paper, we introduce the Generalized Solver: a simple parameterization of the ODE sampler that does not require additional training tricks and improves quality over existing approaches. We further combine the original distillation loss with adversarial training, which mitigates artifacts and enhances detail fidelity. We call the resulting method the Generalized Adversarial Solver and demonstrate its superior performance compared to existing solver training methods under similar resource constraints. Code is available at https://github.com/3145tttt/GAS.