“MobileDiffusion: Subsecond Text-To-Image Generation on Mobile Devices”, Yang Zhao, Yanwu Xu, Zhisheng Xiao, Tingbo Hou2023-11-28 (diffusion model, GAN)⁠:

The deployment of large-scale text-to-image diffusion models on mobile devices is impeded by their substantial model size and slow inference speed. In this paper, we propose MobileDiffusion, a highly efficient text-to-image diffusion model obtained through extensive optimizations in both architecture and sampling techniques.

We conduct a comprehensive examination of model architecture design to reduce redundancy, enhance computational efficiency, and minimize model’s parameter count, while preserving image generation quality. Additionally, we employ distillation and diffusion-GAN finetuning techniques on MobileDiffusion to achieve 8-step and 1-step inference respectively.

Empirical studies, conducted both quantitatively and qualitatively, demonstrate the effectiveness of our proposed techniques. MobileDiffusion achieves a remarkable sub-second inference speed for generating a 512×512 image on mobile devices, establishing a new state-of-the-art.