PathRelax: Parallel-Path Relaxed Speculative Jacobi Decoding for Accelerating Auto-Regressive Text-to-Image Generation
Researchers have developed PathRelax, a novel framework designed to significantly accelerate auto-regressive text-to-image generation. This method employs a parallel-path speculative decoding approach, expanding the token search space and utilizing semantic similarities across sequences to increase token acceptance rates. Evaluated on several datasets, PathRelax achieved speedup ratios between 3.95x and 4.18x, outperforming existing methods and offering an efficient solution for real-time image generation. AI
IMPACT Accelerates text-to-image generation, potentially enabling real-time applications and faster iteration for creative workflows.