paper-with-me

Papers

Cross-Resolution Diffusion Models via Network Pruning

2026-04-07 · Jiaxuan Ren, Junhan Zhu, Huan Wang arxiv

Diffusion models have demonstrated impressive image synthesis performance, yet many UNet-based models are trained at certain fixed resolutions. Their quality tends to degrade when generating images at out-of-training resolutions. We trace this issue to resolution-dependent parameter behaviors, where weights that function well at the default resolution can become adverse when spatial scales shift, weakening semantic alignment and causing structural instability in the UNet architecture. Based on this analysis, this paper introduces CR-Diff, a novel method that improves the cross-resolution visual consistency by pruning some parameters of the diffusion model. Specifically, CR-Diff has two stages. It first performs block-wise pruning to selectively eliminate adverse weights. Then, a pruned output amplification is conducted to further purify the pruned predictions. Empirically, extensive experiments suggest that CR-Diff can improve perceptual fidelity and semantic coherence across various diffusion backbones and unseen resolutions, while largely preserving the performance at default resolutions. Additionally, CR-Diff supports prompt-specific refinement, enabling quality enhancement on demand.

📄 PDF Abstract BibTeX arXiv:2604.05524

Code (0)

등록된 구현이 없습니다.

Tasks

Network Pruning

Similar Papers 제목 키워드 기반

PGP-DiffSR: Phase-Guided Progressive Pruning for Efficient Diffusion-based Image Super-Resolution

2025-12-02 · Zhongbao Yang, Jiangxin Dong, Yazhou Yao, Jinhui Tang 외 arxiv

Although diffusion-based models have achieved impressive results in image super-resolution, they often rely on large-scale backbones such as Stable Diffusion XL (SDXL) and Diffusion Transformers (DiT), which lead to exce…

Image Super-Resolution

CoReDiT: Spatial Coherence-Guided Token Pruning and Reconstruction for Efficient Diffusion Transformers

2026-05-13 · Zhuojin Li, Hsin-Pai Cheng, Hong Cai, Shizhong Han 외 arxiv

Diffusion Transformers (DiTs) deliver remarkable image and video generation quality but incur high computational cost, limiting scalability and on-device deployment. We introduce CoReDiT, a structured token pruning frame…

Video Generation

Forcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion Models

2026-05-10 · Yicheng Ji, Zhizhou Zhong, Jun Zhang, Qin Yang 외 arxiv

Autoregressive (AR) video diffusion models adopt a streaming generation framework, enabling long-horizon video generation with real-time responsiveness, as exemplified by the Self Forcing training paradigm. However, exis…

Video Generation

TinySR: Pruning Diffusion for Real-World Image Super-Resolution

2025-08-24 · Linwei Dong, Qingnan Fan, Yuhang Yu, Qi Zhang 외 arxiv

Real-world image super-resolution (Real-ISR) focuses on recovering high-quality images from low-resolution inputs that suffer from complex degradations like noise, blur, and compression. Recently, diffusion models (DMs) …

Image Super-Resolution

RS-Prune: Training-Free Data Pruning at High Ratios for Efficient Remote Sensing Diffusion Foundation Models

2025-12-29 · Fan Wei, Runmin Dong, Yushan Lai, Yixiang Yang 외 arxiv

Diffusion-based remote sensing (RS) generative foundation models are cruial for downstream tasks. However, these models rely on large amounts of globally representative data, which often contain redundancy, noise, and cl…

Scene Classification