MPEG-Diffusion: Mixed-Resolution Video Generation

Media reports Hugging Face Papers Source language: Chinese

论文摘要(作者报告,未经本站复测):Video diffusion transformers (DiTs) generate realistic videos, but their heavy computational cost limits broader real-world applications.

Full text

MPEG-Diffusion reduces the computational cost of video diffusion transformers by generating only a self-selected high-resolution region with dual-resolution attention and a mixed-resolution decoder, achieving faster denoising without quality loss.

Sources

← Back to Daily AI Report