Diffusion Probabilistic Models (DPMs) have achieved considerable success in generation tasks. As sampling from DPMs is equivalent to solving diffusion SDE or ODE which is time-consuming, numerous fast sampling methods built upon improved differential equation solvers are proposed.

SEEDS outperform or are competitive with previous SDE solvers.

Code is available at https://github.com/wl-zhao/UniPC . In this paper, we propose a training-free framework for the fast sampling of DPMs called UniPC .

One approach for tackling this problem is rectified flows, which iteratively learn smooth ODE paths that are less susceptible to truncation error. However, rectified flows still require a relatively large number of function evaluations (NFEs). In this work, we propose improved techniques for training rectified flows, allowing them to compete with knowledge distillation methods even in the low NFE setting.

H . (32) We refer to ( H

As outlined in Sec. 3, thep-th TTM is simply thep-th order Taylor polynomialapplied to an ODE.

Denoising diffusion models (DDMs) have emerged as a powerful class of generativemodels.

Neural Information Processing Systems http://nips.cc/

The synergistic combination of hypersolvers and Neural ODEs allows for cheap inference and unlocks a newfrontierforpractical application ofcontinuous-depth models.

Based onourformulation, weproposeDPM-Solver,afastdedicated high-order solver for diffusion ODEs with the convergence order guarantee.