HART: Efficient Visual Generation with Hybrid Autoregressive Transformer

Haotian Tang; Yecheng Wu; Shang Yang; Enze Xie; Junsong Chen; Junyu Chen; Zhuoyang Zhang; Han Cai; Yao Lu; Song Han

doi:10.48550/arxiv.2410.10812

ICLR2025顶会

HART: Efficient Visual Generation with Hybrid Autoregressive Transformer

Haotian Tang, Yecheng Wu, Shang Yang, Enze Xie, Junsong Chen, Junyu Chen, Zhuoyang Zhang, Han Cai, Yao Lu, Song Han

arXiv DOI 出版方

2025年份

34顶会引用

摘要

Throughput (img/s) 7.7x higher Figure 1 : HART is an early autoregressive model that can directly generate 1024×1024 images with quality comparable to diffusion models, while offering significantly improved efficiency. It achieves 4.5-7.7× higher throughput, 3.1-5.9× lower latency (measured on A100), and 6.9-13.4× lower MACs compared to state-of-the-art diffusion models. Check out our online demo and video.