Bespoke Non-Stationary Solvers for Fast Sampling of Diffusion and Flow Models
This provides a faster and more efficient sampling method for generative AI applications like image and audio generation, though it is incremental as it builds on existing solver distillation approaches.
The paper tackled the problem of slow sampling in diffusion and flow models by introducing Bespoke Non-Stationary Solvers, which improved sample efficiency, achieving 45 PSNR and 1.76 FID with 16 NFE on ImageNet-64.
This paper introduces Bespoke Non-Stationary (BNS) Solvers, a solver distillation approach to improve sample efficiency of Diffusion and Flow models. BNS solvers are based on a family of non-stationary solvers that provably subsumes existing numerical ODE solvers and consequently demonstrate considerable improvement in sample approximation (PSNR) over these baselines. Compared to model distillation, BNS solvers benefit from a tiny parameter space ($<$200 parameters), fast optimization (two orders of magnitude faster), maintain diversity of samples, and in contrast to previous solver distillation approaches nearly close the gap from standard distillation methods such as Progressive Distillation in the low-medium NFE regime. For example, BNS solver achieves 45 PSNR / 1.76 FID using 16 NFE in class-conditional ImageNet-64. We experimented with BNS solvers for conditional image generation, text-to-image generation, and text-2-audio generation showing significant improvement in sample approximation (PSNR) in all.