AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

SeaCache: Spectral-Evolution-Aware Cache for Accelerating Diffusion Models

Jiwoo Chung, Sangeek Hyun, MinKyu Lee, Byeongju Han, Geonho Cha, Dongyoon Wee, Youngjun Hong, Jae-Pil Heo

CVPR 2026 · Image generation › Fast diffusion sampling · approach: Training-free diffusion acceleration · 6 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
filter features with SEA filter before computing cache distance (vs TeaCache raw distance, d=0.3)TeaCache · FLUX.1-devPSNR: 20.762 -> 26.285Improved
filter features with SEA filter (vs TeaCache, d=0.12)TeaCache · HunyuanVideoPSNR: 23.40 -> 32.39Improved
filter features with SEA filter (vs TeaCache, d=0.09 vs 0.2)TeaCache · Wan2.1 1.3BPSNR: 20.84 -> 26.60Improved
filter features with SEA filter at aggressive budget (vs TeaCache d=0.6 vs 0.6)TeaCache · FLUX.1-devPSNR: 17.214 -> 21.332Improved
use complementary 1-SEA filter instead of SEA filter (ablation)SeaCache · FLUX and HunyuanVideoPSNR vs refresh ratioImproved
add gain normalization to the SEA filter (ablation)SeaCache · FLUX and HunyuanVideoPSNR vs refresh ratioImproved
use timestep-dependent SEA filter instead of static low-pass filter (LPF 30%) (ablation)SeaCache · FLUX and HunyuanVideoPSNR vs refresh ratioImproved
apply SEA filter to DiCache block featuresDiCache · FLUXPSNR at same refresh ratioImproved
use SeaCache instead of TeaCache/TaylorSeer on CycleRewardFLUX.1-dev 50% budget · DrawBenchaverage rank (lower better): 2.01 -> 1.91Improved
use SeaCache instead of MagCache at matched 50% refresh ratioMagCache · Wan2.1 1.3B T2VPSNR: 25.55 -> 29.55Improved
use SeaCache instead of MagCache at matched 52% refresh ratioMagCache · FLUX.1-devPSNR: 29.96 -> 30.37Improved
use SeaCache instead of TeaCache in VBench average rank (30% budget)TeaCache · Wan2.1 1.3Baverage rank (lower better): 1.53 -> 2.13Hurt

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