Flowblending Video Inference

Accelerate video generation by allocating smaller models to intermediate diffusion timesteps and larger models to capacity-critical early and late stages. Achieves 1.65x speedup and 57% FLOP reduction while maintaining visual quality. Use when video generation latency or computational cost is critical and you have multiple model sizes available.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit fb14e6419c

Frequently asked questions

npx get-skill add adu2021/flowblending-video-inference