Quasi-Taylor Samplers for Diffusion Generative Models based on Ideal Derivatives

no code implementations • 26 Dec 2021 • Hideyuki Tachibana, Mocho Go, Muneyoshi Inahara, Yotaro Katayama, Yotaro Watanabe

Diffusion generative models have emerged as a new challenger to popular deep neural generative models such as GANs, but have the drawback that they often require a huge number of neural function evaluations (NFEs) during synthesis unless some sophisticated sampling strategies are employed.

Denoising Image Generation +1