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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Single Image Denoising | CelebA 128x128 | Training Time (s)166.1 | 4 | |
| Single Image Denoising | CelebA 64x64 (test) | Training Time (s)80.04 | 4 | |
| Single Image Denoising | CIFAR-10 32x32 | Training Time (s)16.75 | 4 |