Rehy At Video Diffusion Attention

Merge softmax and linear attention for video diffusion models using chunk-wise recurrent reformulation with constant memory usage. Enable efficient distillation from existing softmax models, reducing training cost two orders of magnitude to ~160 GPU hours.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit 06214a6d30

Frequently asked questions

npx get-skill add adu2021/rehy-at-video-diffusion-attention