AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

CHORDS: Diffusion Sampling Accelerator with Multi-core Hierarchical ODE Solvers

Jiaqi Han, Haotian Ye, Puheng Li, Minkai Xu, James Zou, Stefano Ermon

ICCV 2025 · Image generation › Fast diffusion sampling · approach: Fast diffusion ODE solvers · 0 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 theory-derived initialization sequence instead of uniform (ablation)CHORDS · HunyuanVideo, 8 coresspeedup: 2.6 -> 2.9Improved
use theory-derived initialization sequence instead of uniform (ablation)CHORDS · HunyuanVideo, 6 coresspeedup: 2.1 -> 2.5Improved
use theory-derived initialization sequence instead of uniform (ablation)CHORDS · HunyuanVideo, 4 coresspeedup: 1.8 -> 2.1Improved
use theory-derived initialization sequence instead of uniform (ablation)CHORDS · Flux, 8 coresspeedup: 2.2 -> 2.4Improved
use theory-derived initialization sequence instead of uniform (ablation)CHORDS · HunyuanVideo, 8 coresVBench quality: 84.0% -> 84.1%No clear effect
increase diffusion steps from 50 to 100CHORDS · HunyuanVideo, 8 coresspeedup: 2.9 -> 3.6Improved
increase diffusion steps from 50 to 100CHORDS · HunyuanVideo, 8 coresVBench quality: 84.1% -> 84.6%Improved
increase diffusion steps from 50 to 100CHORDS · HunyuanVideo, 8 coreslatent RMSE: 0.068 -> 0.076Hurt
increase number of cores from 4 to 8CHORDS · HunyuanVideospeedup: 2.1 -> 2.9Improved
use CHORDS instead of SRDS with four coresSRDS · video diffusion modelsspeedup: 1.3x on average -> ~2xImproved
use CHORDS instead of ParaDIGMSParaDIGMS · HunyuanVideo, 8 coreslatent RMSE: 0.202 -> 0.068Improved
use CHORDS parallel sampling instead of sequentialSequential solver · HunyuanVideo, 8 coresVBench quality: 84.4% -> 84.1%No clear effect

Later papers that compared with this method

1 later accepted paper reports CHORDS 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