AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

S$^2$-Guidance: Stochastic Self-Guidance for Training-Free Enhancement of Diffusion Models

Chubin Chen, Jiashu Zhu, Xiaokun Feng, Nisha Huang, Chen Zhu, Meiqi Wu, Fangyuan Mao, Jiahong Wu, Xiangxiang Chu, Xiu Li

ICLR 2026 · Image generation › Fast diffusion sampling · approach: Guidance for conditional diffusion

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
add S2-Guidance (stochastic block-dropping self-guidance) on top of CFGSD3 · HPSv2.1 avgscore (%): 30.48 -> 31.09Improved
add S2-Guidance on top of CFGSD3.5 · HPSv2.1 avgscore (%): 30.82 -> 31.56Improved
add S2-GuidanceSD3 · T2I-CompBench Colorscore (%): 53.61 -> 59.63Improved
add S2-GuidanceSD3.5 · T2I-CompBench Colorscore (%): 51.29 -> 57.57Mixed
add S2-GuidanceSiT-XL · ImageNet 256x256 FIDFID: 2.15 -> 2.03Improved
add S2-GuidanceWan1.3B · VBench Totalscore: 80.29 -> 80.93Improved
add S2-GuidanceWan14B · VBench Totalscore: 82.65 -> 82.84Improved
use APG guidance instead of CFGWan1.3B · VBench Totalscore: 80.29 -> 70.83Hurt
compare S2-Guidance with CFG given equal compute (1.4x NFE) (ablation)Flux de-distilled · HPSv2.1 avgscore (%): 30.13 -> 30.26Improved
drop more than ~3 of 24 blocks (ablation)S2-Guidance SD3.5 · aesthetic scoreQalign: 4.652 -> 4.531Hurt
drop 1 block vs no dropping (ablation)S2-Guidance SD3.5 · aesthetic scoreQalign: 4.618 -> 4.652Improved
use a single block-drop per step instead of naive multiple sub-networks (ablation)S2-Guidance · aesthetic scoreaesthetic scoreNo clear effect

Later papers that compared with this method

1 later accepted paper reports S2 Guidance 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