Worldcache Video Model Caching

Replace zero-order hold assumptions with perception-constrained approximation via four-module caching system: motion-aware skip thresholds, saliency-weighted drift, least-squares blending, and adaptive scheduling. Achieves 2.1–2.3× speedup at 2B scale with 99.4–99.6% quality retention on Cosmos-Predict video generation; apply when optimizing diffusion world model inference under real-time constraints.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit a1a23a4291

Frequently asked questions

npx get-skill add adu2021/worldcache-video-model-caching