Restart Sampling for Improving Generative Processeshttps://github.com/Newbeeer/diffusion_restart_sampling
A new algorithm called Restart has been developed to improve the speed and quality of generative processes. These processes use complex differential equations, which usually has a trade-off between quick results and accuracy. Existing methods like ODE and SDE samplers either work fast but reach a performance limit or offer better quality at a slower rate. The Restart algorithm outperforms these existing methods by better managing these sampling errors. In tests, it produced faster and higher quality results, surpassing SDE results on different platforms and maintaining better balance in large-scale model testing.