Artificial Intelligence #region-adaptive sampling#diffusion transformers
Region-Adaptive Sampling Cuts Diffusion Transformer Inference Time by Up to 2.5x With Negligible Quality Loss
Researchers introduce RAS, a training-free sampling method for Diffusion Transformers that selectively updates only the regions of focus at each step, caching others. Achieves up to 2.51x speedup on Lumina-Next-T2I and 2.36x on Stable Diffusion 3 with minimal quality drop, as reported in a new arxiv paper. A user study found comparable quality at 1.6x speedup.
Jun 17, 2026 1 source