Recognition: unknown
Efficient Score Pre-computation for Diffusion Models via Cross-Matrix Krylov Projection
read the original abstract
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.
This paper has not been read by Pith yet.
Forward citations
Cited by 1 Pith paper
-
PhyloSDF: Phylogenetically-Conditioned Neural Generation of 3D Skull Morphology via Residual Flow Matching
PhyloSDF generates novel 3D skull morphologies for Darwin's finches via phylogenetically-conditioned residual flow matching, achieving 88-129% of real intra-species variation from few specimens and enabling phylogenet...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.