AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

OMS-DPM: Optimizing the Model Schedule for Diffusion Probabilistic Models

Enshu Liu, Xuefei Ning, Zinan Lin, Huazhong Yang, Yu Wang

ICML 2023 · Image generation › Fast diffusion sampling · approach: Fast diffusion ODE solvers · 6 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Adding searched mixed model schedules (OMS-DPM) instead of a single modelDPM-Solver on CIFAR-10 · CIFAR-10 FID across budgetsFID: e.g., 3.25 vs 3.56 at 7.0s budget; 6.08 vs 8.73 at 0.7sImproved
Adding mixed model schedules (OMS-DPM) instead of a single modelDDIM across four datasets · CIFAR-10, CelebA, ImageNet-64, LSUN-ChurchFID: gains range from about 0.01 to several points across budgetsImproved
Searched schedule vs. random schedule samplingDPM-Solver across datasets · all four datasetsFID: e.g., 3.25 vs 9.33 on CIFAR-10 at 7.0sImproved
Predictor-based search vs. best schedule in predictor training setDPM-Solver and DDIM across datasets · all four datasetsFID: e.g., 3.25 vs 3.33 on CIFAR-10 at 7.0s; 13.94 vs 32.57 on LSUN-Church at 4sImproved
Mixing Stable Diffusion checkpoints (4 models) with OMS-DPM searchStable Diffusion DPM-Solver · MS-COCO 256x256 FIDFID: 10.57 vs 11.81 at 24 NFE; 11.34 at 12 NFE beats single model at 24 NFE (11.81)Improved
Larger model zoo size (6 vs 2) in search (ablation)DPM-Solver on CIFAR-10 · CIFAR-10 at 0.7s budgetFID: 6.08 (N=6) vs 6.05 (N=2)No clear effect
Reducing predictor training data from 3662 to 915 schedules (ablation)DPM-Solver predictor on CIFAR-10 · CIFAR-10 at 1.4s budgetFID: 3.97 (915) vs 3.48 (3662)Hurt

Later papers that compared with this method

2 later accepted papers report OMS-DPM as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy