SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer

Enze Xie; Junsong Chen; Yuyang Zhao; Jincheng Yu; Ligeng Zhu; Yujun Lin; Zhekai Zhang; Muyang Li; Junyu Chen; Han Cai; Bingchen Liu; Daquan Zhou; Song Han

2025 ICML ICML 2025

SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Computer Vision

Authors

Enze Xie, Junsong Chen, Yuyang Zhao, Jincheng Yu, Ligeng Zhu, Yujun Lin, Zhekai Zhang, Muyang Li, Junyu Chen, Han Cai, Bingchen Liu, Daquan Zhou, Song Han

Topics

Deep Learning > Architectures > Transformers Deep Learning > Models > Diffusion Models Computer Vision > Generation > Image Generation

Keywords

diffusion transformer 8-bit optimizer depth-growth paradigm model depth pruning repeated sampling strategy text-image alignment score

Download PDF