Unveiling Redundancy in Diffusion Transformers (DiTs): A Systematic Study

Auto-encoding variational bayes

Original

Diederik P Kingma and Max Welling · 2013

Earlier work this paper cites.

U-net: Convolutional networks for biomedical image segmentation

Olaf Ronneberger, Philipp Fischer, and Thomas Brox · 2015

Earlier work this paper cites.

Denoising diffusion implicit models

Original

Jiaming Song, Chenlin Meng, and Stefano Ermon · 2020

Earlier work this paper cites.

Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps

Cheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen, Chongxuan Li, and Jun Zhu · 2022

Earlier work this paper cites.

Scalable diffusion models with transformers

William Peebles and Saining Xie · 2023

Earlier work this paper cites.

Q-diffusion: Quantizing diffusion models

Xiuyu Li, Yijiang Liu, Long Lian, Huanrui Yang, Zhen Dong, Daniel Kang, Shanghang Zhang, and Kurt Keutzer · 2023

Earlier work this paper cites.

Pixart- α \alpha : Fast training of diffusion transformer for photorealistic text-to-image synthesis

Original

Junsong Chen, Jincheng Yu, Chongjian Ge, Lewei Yao, Enze Xie, Yue Wu, Zhongdao Wang, James Kwok, Ping Luo, Huchuan Lu, et al · 2023

Earlier work this paper cites.

Frdiff: Feature reuse for exquisite zero-shot acceleration of diffusion models

Original

Junhyuk So, Jungwon Lee, and Eunhyeok Park · 2023

Earlier work this paper cites.

Ld-pruner: Efficient pruning of latent diffusion models using task-agnostic insights

Thibault Castells, Hyoung-Kyu Song, Bo-Kyeong Kim, and Shinkook Choi · 2024

Earlier work this paper cites.

One-step diffusion distillation via deep equilibrium models

Zhengyang Geng, Ashwini Pokle, and J Zico Kolter · 2024

Cited alongside, same era.

Pipefusion: Patch-level pipeline parallelism for diffusion transformers inference, 2024

Jiarui Fang, Jinzhe Pan, Jiannan Wang, Aoyu Li, and Xibo Sun · 2024

Cited alongside, same era.

xdit: an inference engine for diffusion transformers (dits) with massive parallelism, 2024

Jiarui Fang, Jinzhe Pan, Xibo Sun, Aoyu Li, and Jiannan Wang · 2024

Cited alongside, same era.

Learning-to-cache: Accelerating diffusion transformer via layer caching

Original

Xinyin Ma, Gongfan Fang, Michael Bi Mi, and Xinchao Wang · 2024

Cited alongside, same era.

Cross-attention makes inference cumbersome in text-to-image diffusion models

Original

Wentian Zhang, Haozhe Liu, Jinheng Xie, Francesco Faccio, Mike Zheng Shou, and Jürgen Schmidhuber · 2024

Cited alongside, same era.

Deepcache: Accelerating diffusion models for free

Xinyin Ma, Gongfan Fang, and Xinchao Wang · 2024

Closest in time.

\ d ​ e ​ l ​ t ​ a \backslash delta -dit: A training-free acceleration method tailored for diffusion transformers

Original

Pengtao Chen, Mingzhu Shen, Peng Ye, Jianjian Cao, Chongjun Tu, Christos-Savvas Bouganis, Yiren Zhao, and Tao Chen · 2024

Closest in time.

Ditfastattn: Attention compression for diffusion transformer models

Original

Zhihang Yuan, Pu Lu, Hanling Zhang, Xuefei Ning, Linfeng Zhang, Tianchen Zhao, Shengen Yan, Guohao Dai, and Yu Wang · 2024

Closest in time.

Flux.1-dev

Black Forest Lab · 2024

Closest in time.

Pixart-xl-2-1024-ms

PixArt Alpha · 2024

Closest in time.

stable-diffusion-3-medium

Stabilityai · 2024