Recent advances in diffusion transformers (DiTs) have set new standards in image generation, yet remain impractical for on-device deployment due to their high computational and memory costs. In this work, we present an efficient DiT framework tailored for mobile and edge devices that achieves transformer-level generation quality under strict resource constraints. Our design combines three key components. First, we propose a compact DiT architecture with an adaptive global-local sparse attention mechanism that balances global context modeling and local detail preservation. Second, we propose an elastic training framework that jointly optimizes sub-DiTs of varying capacities within a unified supernetwork, allowing a single model to dynamically adjust for efficient inference across different hardware. Finally, we develop Knowledge-Guided Distribution Matching Distillation, a step-distillation pipeline that integrates the DMD objective with knowledge transfer from few-step teacher models, producing high-fidelity and low-latency generation (e.g., 4-step) suitable for real-time on-device use. Together, these contributions enable scalable, efficient, and high-quality diffusion models for deployment on diverse hardware.

翻译：近年来，扩散Transformer（DiTs）在图像生成领域取得了突破性进展，但其高昂的计算和内存成本使其难以在设备端实际部署。本研究提出一种专为移动和边缘设备设计的高效DiT框架，能够在严格资源约束下实现Transformer级别的生成质量。我们的设计包含三个核心组件：首先，提出一种紧凑的DiT架构，采用自适应全局-局部稀疏注意力机制，平衡全局上下文建模与局部细节保持；其次，设计弹性训练框架，在统一超网络内联合优化不同容量的子DiT，使单个模型能够动态调整以适应不同硬件的高效推理；最后，开发知识引导分布匹配蒸馏技术，将DMD目标与少步数教师模型的知识迁移相结合，构建步数蒸馏流程，生成适用于实时设备端使用的高保真低延迟图像（例如4步生成）。这些贡献共同实现了可扩展、高效且高质量的扩散模型，能够适配多样化硬件部署场景。