This new paper speeds up diffusion models by analytically solving the linear part of the reverse ODE to make precise solvers. I find it super cool that they use our adaptive step-size algorithm () to get their best results! 😸 Tweet added by Alexia Jolicoeur-Martineau @jm_alexia

Alexia Jolicoeur-Martineau

2 years

This new paper speeds up diffusion models by analytically solving the linear part of the reverse ODE to make precise solvers. I find it super cool that they use our adaptive step-size algorithm () to get their best results! 😸

DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model...

Diffusion probabilistic models (DPMs) are emerging powerful generative models. Despite their high-quality generation performance, DPMs still suffer from their slow sampling as they generally need...

arxiv.org

2

27

144

Alexia Jolicoeur-Martineau

@jm_alexia

2 years

@keli @TalKachman @bouzoukipunks

0

2

Dr. Chris Rackauckas

@ChrisRackauckas

2 years

@jm_alexia While the higher order methods were slower, did you do a measure of strong and weak error? I would suspect they were just hitting a much lower error, since they tend to have not just a higher order but also a more accurate error estimator. Did you check work-precision?

2

0

Alexia Jolicoeur-Martineau

@jm_alexia

2 years

@ChrisRackauckas It's not quite what you ask, but we have Figure 1 in with x=Number of Function evaluations (time), y=FID (metric of quality/diversity of the generated data). The DPM-Solver paper have this info instead in tables.

1

0

Replies