SparkDiffusion from PKU/Tsinghua/Alibaba hits 265x video generation speedup on a single RTX 5090

机器之心 · wechat · 2026-09-28

Researchers from Peking University, Tsinghua, and Alibaba released SparkDiffusion — the first unified open-source framework combining sparse attention, few-step distillation, and FP8 quantization to accelerate DiT video generation, with weights and full training code released.

Original post →

More from Multimodal

Multimodal channel →