AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

MosaicDiff: Training-free Structural Pruning for Diffusion Model Acceleration Reflecting Pretraining Dynamics

Bowei Guo, Shengkun Tang, Cong Zeng, Zhiqiang Shen

ICCV 2025 · Image generation › Fast diffusion sampling · approach: Training-free diffusion acceleration · 3 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
add SNR-aware calibration data (ablation)MosaicDiff · DiT-XL/2 20 stepsFID: 3.96 -> 3.22Improved
add SNR-aware calibration data (ablation)MosaicDiff · DiT-XL/2 20 stepsIS: 227.3 -> 266.1Improved
add score-based three-stage division instead of no division (ablation)MosaicDiff · DiT-XL/2 20 steps, sparsity 0.3FID: 40.89 -> 3.20Improved
use proposed stage division instead of uniform division (ablation)MosaicDiff · DiT-XL/2 20 stepsFID: 33.21 -> 3.20Improved
choose threshold M=0.55 instead of 0.45 (ablation)MosaicDiff · DiT-XL/2 20 stepsFID: 3.36 -> 3.20Improved
choose threshold M=0.55 instead of 0.70 (ablation)MosaicDiff · DiT-XL/2 20 stepsFID: 3.71 -> 3.20Improved
increase sparsity in Stage 2 (0.04 to 0.15) (ablation)MosaicDiff · DiT-XL/2 20 stepsFID: 3.22 -> 10.20Hurt
increase sparsity in Stage 3 (0.1 to 0.4) without SNR refinement (ablation)MosaicDiff · DiT-XL/2 20 stepsFID: 3.22 -> 4.18Hurt
increase sparsity in Stage 1 (0.6 to 0.9) (ablation)MosaicDiff · DiT-XL/2 20 stepsFID: 3.22 -> 3.53No clear effect
raise total sparsity from 0.30 to 0.50 (ablation)MosaicDiff · DiT-XL/2 20 stepsFID: 3.20 -> 5.27Hurt
raise total sparsity from 0.10 to 0.30 (ablation)MosaicDiff · SDXL COCOFID-5K: 23.18 -> 28.37Hurt
add MosaicDiff pruning to DeepCache-N=3DeepCache · SDXLFID-5K: 24.61 -> 23.88Improved

Later papers that compared with this method

1 later accepted paper reports MosaicDiff 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