Diffusion Model Pruning

Follow this topic Ask about this topic

Latest papers

13 papers1 paper in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

HiFiPix: Bringing High-Fidelity Real-World Super-Resolution Back to Pixel Space
Oct 26, 2026Wenjie Li, Du Chen, Hui Wang +8Image Super-Resolution Pixel-Space Diffusion Models
Beijing University of Posts and Telecommunications · vivo BlueImage Lab · Zhejiang University
DIET: Deletion-response Expert Trimming for Video Diffusion Transformers
Sep 29, 2026Jiachang Zhang, Teng Hu, Bohao Feng +4Mixture-of-Experts Pruning Video Diffusion Models
Xi’an Jiao Tong University, China · Shanghai Jiao Tong University, China · Alibaba Token Hub, Alibaba Group, China +1
Importance-Aware OBS Pruning for Diffusion Models
Jul 22, 2026Ba-Thinh Lam, Srijan Das, Hieu LeDiffusion Model Pruning Neural Network Compression
Department of Computer Science UNC Charlotte NC, USA
Efficient Text-to-Audio Generation via Pruning
Jul 14, 2026Arshdeep Singh, Yi Yuan, Yun Chen +2Text-to-Audio Generation Latent Diffusion Models
1King’s College London (KCL) · University of Surrey, UK
Bridging Diffusion Pruning and Step Distillation with Teacher-Aligned Repair
Jul 7, 2026Jincheng Ying, Li Wenlin, Minghui Xu +1Diffusion Model Distillation Few-Step Diffusion Sampling
School of Big Data and Artificial Intelligence Guangdong University of Finance and Economics Guangzhou, China · School of Computer Science Shandong University Qingdao, China · GDUFE-UCM Joint Institute Guangdong University of Finance and Economics Guangzhou, China
TMP: Tree-structured Mixed-policy Pruning for Large-scale Image Generation and Editing
Jun 25, 2026Peizhen Zhang, Yang Li, Xunsong Li +10Model Compression Diffusion Model Pruning
Multimodal Model Department, Tencent
PeLAP-A: Adaptive Latent Pruning for Lightweight Latent Diffusion Models
Jun 22, 2026Kissa Zahra, Zaib Un NisaLatent Diffusion Models Diffusion Model Pruning
Department of Computer Science, National University of Computer and Emerging Sciences
PARE: Pruning and Adaptive Routing for Efficient Video Generation
May 26, 2026Yutong Wang, Yunke Wang, Tianfan Xue +4Video Diffusion Models Diffusion Transformer
The University of Sydney · The Chinese University of Hong Kong · Shanghai AI Laboratory
CoReDiT: Spatial Coherence-Guided Token Pruning and Reconstruction for Efficient Diffusion Transformers
May 13, 2026Zhuojin Li, Hsin-Pai Cheng, Hong Cai +2Diffusion Transformer Visual Token Pruning
Qualcomm AI Research†
Cross-Resolution Diffusion Models via Network Pruning
Apr 7, 2026Jiaxuan Ren, Junhan Zhu, Huan WangDiffusion Model Pruning Image Generation
University of Electronic Science and Technology of China · Westlake University
Diff-ES: Stage-wise Structural Diffusion Pruning via Evolutionary Search
Mar 5, 2026Zongfang Liu, Shengkun Tang, Zongliang Wu +2Diffusion Model Pruning Diffusion Model Inference Acceleration
Zhejiang University · Westlake University · Mohamed bin Zayed University of Artificial Intelligence
Sink-Aware Pruning for Diffusion Language Models
Feb 19, 2026Aidar Myrzakhan, Tianyi Li, Bowei Guo +2LLM Pruning Diffusion Model Pruning
VILA Lab, MBZUAI
TinySR: Pruning Diffusion for Real-World Image Super-Resolution
Aug 24, 2025Linwei Dong, Qingnan Fan, Yuhang Yu +4Diffusion Models for Image Restoration Diffusion Model Pruning
Zhejiang University · Vivo Mobile Communication Co. Ltd · Zhejiang Lab

Oct 26, 2026J/K move · Enter open · S save

HiFiPix: Bringing High-Fidelity Real-World Super-Resolution Back to Pixel Space

Wenjie Li, Du Chen, Hui Wang, Linlong Fan+7

Beijing University of Posts and Telecommunications · vivo BlueImage Lab · Zhejiang University

Image Super-Resolution Pixel-Space Diffusion Models Diffusion Model Pruning

Open paper AskPDF arXiv

Diffusion-based real-world image super-resolution suffers from limited reconstruction fidelity due to information loss in VAE-based latent representations. Recently, pixel-space diffusion models offer a promising high-faithfulness alternative by avoiding latent compression, but adapting them to Real-ISR remains challenging due to inherent patch boundary artifacts and degraded generative capability. To address the issues and maximize the potential of pretrained pixel-space diffusion models, we propose HiFiPix, a pixel-space Real-ISR framework capable of ultra high-fidelity reconstruction and fine-grained visual generation effects. To suppress patch boundary artifacts, we penalize unrealistic high-frequency periodic components with a Cross-Scale Wavelet Discriminator (CWSD) for image-level supervision, and Mixup Contrastive Self-Distillation (MixCSD) for intermediate representation regularization. Furthermore, we uncover a heterogeneous generation-fidelity trade-off across low-rank adapters (LoRA) and propose Selective LoRA Pruning (LoRA-SP) to adaptively prune LoRA layers, enhancing generative capability with minimal deterioration of reconstruction fidelity. Extensive experiments demonstrate that HiFiPix consistently outperforms existing state-of-the-art latent space methods in terms of both restoration accuracy and perceptual quality by a large margin. Code and models will be released.