Freelong Plus Plus Long Video Generation

Extend video diffusion models to generate 4-8× longer sequences without retraining. Uses frequency-aware attention to blend local detail preservation with global consistency, identifying and fixing high-frequency distortion in extended videos.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit 36c1ff28ce

Frequently asked questions

npx get-skill add adu2021/freelong-plus-plus-long-video-generation