# Importance-Aware OBS Pruning for Diffusion Models

Source: [Importance-Aware OBS Pruning for Diffusion Models](<https://www.sota2.com/research/paper/6a61a006ef5cfba72b4981ac>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-07-24T05:00:05.476Z

Authors: Ba-Thinh Lam, Srijan Das, Hieu Le

Published: 2026-07-22T11:42:42.000Z

## Abstract

We propose importance-aware pruning for diffusion models, a training-free framework that prioritizes preserving parameters critical to semantically salient image regions. To do so, we incorporate spatial importance maps -- derived from conditioning signals or model attention -- into the pruning objective. This produces parameter rankings aligned with perceptual relevance rather than uniform reconstruction error. On MS-COCO dataset, our proposed approach consistently retains subject fidelity and structural correctness at high compression ratios where conventional pruning causes visible degradation. These results demonstrate that content-aware objectives are key to perceptually faithful compression of generative models.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2607.20048>)

[PDF](<https://arxiv.org/pdf/2607.20048.pdf>)