cs.LGNov 17, 2026

LoopPrune: Recurrent Pruning for Looped Diffusion Transformers

Authors: Weizhong Huang, Huaijia Kou, Yan Zhang, Fei Chao, Xiawu Zheng, Liujuan Cao

Organizations: Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, 361005, P.R. China.

Abstract

Looped diffusion Transformers reuse shared blocks to deepen computation and match larger models with fewer parameters, reducing storage and deployment burdens. Yet repeated attention and MLP computations remain costly. Pruning reduces storage and computation by removing redundant parameters or units. Training-free methods struggle to resolve recurrent contributions, while training-based methods lack explicit constraints on position-specific errors affecting later inputs and final outputs. We propose LoopPrune, a pruning and recovery framework addressing these requirements. Recurrent importance estimation combines shared-removal effects and position variation to select a shared structure; shared reconstruction pools recurrent input statistics to compensate weights. Loop-position recovery compares complete denoising predictions at identical student states and matches text guidance, updating all student parameters against a fixed dense teacher. Extensive experiments across four open-source models, six benchmarks, and three pruning paradigms demonstrate effectiveness. At 30% structured parameter pruning, Looped-DiT B/16 retains 93.14% of dense six-benchmark average accuracy, exceeding the best baseline by 9.49%. Across PyTorch, vLLM-Omni, and SGLang Diffusion, pruned SDXSv3 reduces peak allocated GPU memory by 34.36-44.64% and accelerates denoising 1.46-1.74x over dense models.

Figures & tables

Explore similar work

CardsList
  1. Post-Training Pruning for Diffusion Transformers

    Jul 1, 2026Chengzhi Hu, Xuewen Liu, Jing Zhang +3Diffusion TransformerDiffusion-Based Image Generation

  2. Looped Uniform Diffusion Language Models

    Oct 21, 2026Saiteja Utpala, Chieh-Hsin Lai, Yuki Mitsufuji +1Diffusion Language ModelsDiffusion Language Model Training