Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Efficient Score Pre-computation for Diffusion Models via Cross-Matrix Krylov Projection

About

This paper presents a novel framework to accelerate score-based diffusion models. It first converts the standard stable diffusion model into the Fokker-Planck formulation which results in solving large linear systems for each image. For training involving many images, it can lead to a high computational cost. The core innovation is a cross-matrix Krylov projection method that exploits mathematical similarities between matrices, using a shared subspace built from ``seed" matrices to rapidly solve for subsequent ``target" matrices. Our experiments show that this technique achieves a 15.8\% to 43.7\% time reduction over standard sparse solvers. Additionally, we compare our method against DDPM baselines in denoising tasks, showing a speedup of up to 115$\times$. Furthermore, under a fixed computational budget, our model is able to produce high-quality images while DDPM fails to generate recognizable content, illustrating our approach is a practical method for efficient generation in resource-limited settings.

Kaikwan Lau, Andrew S. Na, Justin W.L. Wan• 2025

Related benchmarks

TaskDatasetResultRank
Single Image DenoisingCelebA 128x128
Training Time (s)166.1
4
Single Image DenoisingCelebA 64x64 (test)
Training Time (s)80.04
4
Single Image DenoisingCIFAR-10 32x32
Training Time (s)16.75
4
Showing 3 of 3 rows

Other info

Follow for update