RayFlow: Instance-Aware Diffusion Acceleration via Adaptive Flow Trajectories
This addresses the critical challenge of slow diffusion model generation for AI practitioners, offering an incremental improvement over existing acceleration methods.
The paper tackles the slow generation speed of diffusion models by proposing RayFlow, which guides samples along unique paths to reduce steps while preserving quality and diversity, achieving improved speed and control in experiments.
Diffusion models have achieved remarkable success across various domains. However, their slow generation speed remains a critical challenge. Existing acceleration methods, while aiming to reduce steps, often compromise sample quality, controllability, or introduce training complexities. Therefore, we propose RayFlow, a novel diffusion framework that addresses these limitations. Unlike previous methods, RayFlow guides each sample along a unique path towards an instance-specific target distribution. This method minimizes sampling steps while preserving generation diversity and stability. Furthermore, we introduce Time Sampler, an importance sampling technique to enhance training efficiency by focusing on crucial timesteps. Extensive experiments demonstrate RayFlow's superiority in generating high-quality images with improved speed, control, and training efficiency compared to existing acceleration techniques.