AI Paper Atlas

Research map / Video / Video generation

S²Flow: Towards Fast and Authentic Training-Free High-Resolution Video Generation

Chaoqun Wang, Shaobo Min, Xu Yang

AAAI 2026 · Video › Video generation · approach: Autoregressive long video generation · 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 LR-guided adaptive windows instead of fixed uniform windows at 50% sparsity (ablation)LRG-WinAttn · VBench window sparsity ablationgeneration success: Fail to Generate -> 0.7389Improved
use 50% LR-guided window instead of full attention (ablation)S2Flow · VBench window sparsity ablationmean score / speedup: 0.7416 -> 0.7389, 1x -> 4xMixed
reduce window sparsity from 50% to 25% (ablation)LRG-WinAttn · VBench window sparsity ablationmean score: 0.7389 -> 0.6797Hurt
increase window sparsity from 50% to 75% (ablation)LRG-WinAttn · VBench window sparsity ablationmean score: 0.7389 -> 0.7404, 4x -> 1.8xNo clear effect
use second-order instead of first-order solver (ablation)LRI-HiSolver · VBench solver order ablationmean score: 0.7319 -> 0.7389Improved
use third-order instead of second-order solver (ablation)LRI-HiSolver · VBench solver order ablationmean score: 0.7389 -> 0.7390No clear effect
upsample at step 30 instead of step 40 (ablation)S2Flow · VBench upsampling step ablationmean score: 0.6080 -> 0.7389Improved
upsample at step 30 instead of step 20 (ablation)S2Flow · VBench upsampling step ablationmean score: 0.7332 -> 0.7389Improved
upsample at step 30 instead of step 10 (ablation)S2Flow · VBench upsampling step ablationmean score: 0.6939 -> 0.7389Improved
apply S2Flow to HunyuanVideo at 2560x1536HunyuanVideo · VBench (473 prompts, 2560x1536)inference time / mean score: 61 -> 15 minutes, 0.6963 -> 0.7389Improved
S2Flow vs MACSS2Flow · VBench (473 prompts, 2560x1536)mean score: 0.7366 -> 0.7389Improved
S2Flow transformer-level speed at 2560x1536S2Flow · Runtime per 10 denoising stepsseconds: 733.0s -> 96.4sImproved

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