AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Replication in Visual Diffusion Models: A Survey and Outlook

Wenhao Wang, Yifan Sun, Zongxin Yang, Zhengdong Hu, Zhentao Tan, Yi Yang

TPAMI 2026 · Image generation › Autoregressive and latent generation · approach: Reconstruction-based diffusion image detection · 17 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
raise classifier-free guidance scale from 1.0 to 15.0 (ablation)Stable Diffusion v1.5 · CFG sweepduplication rate at tau=0.9: 2.2% -> 85.6%Hurt
raise classifier-free guidance scale from 1.0 to 15.0 (ablation)Stable Diffusion v1.5 · CFG sweepCLIP text-image score: 0.274 -> 0.327Improved
raise CFG scale from 10.0 to 15.0 (ablation)Stable Diffusion v1.5 · CFG sweepCLIP text-image score: 0.327 -> 0.327No clear effect
name an artist in the prompt instead of a generic promptStable Diffusion v1.5 · Intra-artist style consistencyGram: 0.581 -> 0.734Improved
name an artist in the prompt instead of a generic promptStable Diffusion v1.5 · Intra-artist style consistencyCLIP: 0.688 -> 0.799Improved
apply semantic deduplication (SemDeDup) to training dataStable Diffusion · Mitigation comparisonreplication rate: 1.9% -> 0.8%Improved
train with DP-SGD at eps=1 instead of no mitigationStable Diffusion · Mitigation comparisonFID: 12.4 -> 28.7Hurt
tighten DP budget from eps=10 to eps=1DP-SGD · Mitigation comparisonreplication rate / FID: 0.4% -> 0.1%; FID 18.2 -> 28.7Mixed
apply ESD concept unlearningStable Diffusion · Mitigation comparisonreplication rate: 1.9% -> 0.3%Improved
use SalUn instead of ESDunlearning · Mitigation comparisonreplication rate: 0.3% -> 0.2%Improved

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