res_0b1422d6We empirically demonstrate that DDIMs can produce high quality samples 10× to 50× faster in terms of wall-clock time compared to DDPMs, allow us to trade off computation for sample … (excerpt)
arXiv 2010.02502 · cs.LG cs.CV
Read on arXiv · arXiv non-exclusive license
Claims were extracted automatically by reducer-1 on 2026-11-12. The paper's license does not allow republishing it, so long claims are shortened to a quotation. Read the full text on arXiv.
res_0b1422d6We empirically demonstrate that DDIMs can produce high quality samples 10× to 50× faster in terms of wall-clock time compared to DDPMs, allow us to trade off computation for sample … (excerpt)
clm_2f003e08We show that the resulting variational training objectives have a shared surrogate objective, which is exactly the objective used to train DDPM.
clm_f64c48bdIn Appendix A, we show that the non-Markovian perspective also applies beyond the Gaussian case.
clm_78fa6a63We show that only slight changes to the updates in Eq. (12) are needed to obtain the new, faster generative processes, which applies to DDPM, DDIM, as well as all … (excerpt)
res_3bebaa17In this section, we show that DDIMs outperform DDPMs in terms of image generation when fewer iterations are considered, giving speed ups of 10× to 100× over the original DDPM … (excerpt)
res_93197acaWe observe that DDIM ( η = 0) achieves the best sample quality when dim(τ) is small, and DDPM (η = 1 and ˆσ) typically has worse sample quality compared … (excerpt)
clm_3812f4e6In Figure 4, we show that the amount of time needed to produce a sample scales linearly with the length of the sample trajectory.
res_875a8409Even though DDPM could also achieve reasonable sample quality with 100× steps, DDIM requires much fewer steps to achieve this; on CelebA, the FID score of the 100 step DDPM … (excerpt)
clm_6250f6dfIn Figure 6, we show that simple interpolations in xT can lead to semantically meaningful interpolations between two samples.
clm_0f8412cfOur results show that DDIMs have lower reconstruction error for largerS values and have properties similar to Neural ODEs and normalizing flows.
res_209b87d6This update is more stochastic than the update for η = 1, which explains why it achieves worse performance when dim(τ) is small.
Record your result in the Mearc app on your own machine, then use Publish this result with this paper's id (2010.02502) and the claim id shown next to the claim. Mearc creates a file that holds only what you choose to publish. Add it to the public claim data by pull request; a maintainer other than you reviews it before it counts.