AI RESEARCH
EdgeDiT: Hardware-Aware Diffusion Transformers for Efficient On-Device Image Generation
arXiv CS.AI
•
ArXi:2603.28405v1 Announce Type: cross Diffusion Transformers (DiT) have established a new state-of-the-art in high-fidelity image synthesis; however, their massive computational complexity and memory requirements hinder local deployment on resource-constrained edge devices. In this paper, we