AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models

Wenliang Zhao, Lujia Bai, Yongming Rao, Jie Zhou, Jiwen Lu

NeurIPS 2023 · Image generation › Fast diffusion sampling · approach: Training-free diffusion acceleration · 33 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

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
Use UniPC instead of DPM-Solver++diffusion sampler · ImageNet 256x256 guided, NFE=10FID: 9.56 -> 7.51Improved
Add UniC corrector to DDIM (ablation)DDIM · CIFAR10 NFE=5FID: 55.04 -> 47.22Improved
Add UniC corrector to DPM-Solver++(2M) (ablation)DPM-Solver++(2M) · CIFAR10 NFE=5FID: 33.86 -> 31.23Improved
Add UniC corrector to DPM-Solver++(3S) (ablation)DPM-Solver++(3S) · CIFAR10 NFE=5FID: 51.49 -> 50.62Improved
Add UniC corrector to DPM-Solver++(3M) (ablation)DPM-Solver++(3M) · CIFAR10 NFE=5FID: 29.22 -> 25.50Improved
Use B(h)=h instead of B(h)=e^h-1 (ablation)UniPC · CIFAR10 and FFHQ, NFE 5-6FID: 26.20 -> 23.22 (CIFAR10 NFE5)Improved
Use B(h)=e^h-1 instead of B(h)=h (ablation)UniPC · CIFAR10, NFE=10FID: 3.97 -> 3.87Improved
Use B(h)=h instead of e^h-1 in guided sampling (ablation)UniPC · guided samplingFIDHurt
Recompute eps for corrected sample (UniC-oracle, 2x NFE) (ablation)UniC · LSUN Bedroom 5 stepsFID: 13.79 -> 6.06Improved
Customize order schedule 123432 instead of default 123321 (ablation)UniPC · CIFAR10 NFE=6FID: 10.33 -> 9.03Improved
Increase order at every step (123456) (ablation)UniPC · CIFAR10 NFE=6FID: 10.33 -> 22.98Hurt
Use UniPC instead of DPM-Solver++diffusion sampler · CIFAR10 NFE=5Inception Score: 7.27 -> 7.55Improved

Later papers that compared with this method

13 later accepted papers report UniPC as a baseline in their results tables; 13 of them report a better number on most of the results they share with it.

5 more not listed.

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