FADE: Frequency-Aware Diffusion Model Factorization for Video Editing (CVPR 2025)

Yixuan Zhu , Haolin Wang , Shilin Ma, Wenliang Zhao, Yansong Tang, Lei Chen $\dagger$, Jie Zhou

[Paper]

The repository contains the official implementation for the paper "FADE: Frequency-Aware Diffusion Model Factorization for Video Editing" (CVPR 2025).

We introduce FADE—a training-free yet highly effective video editing approach that fully leverages the inherent priors from pre-trained video diffusion models via frequency-aware factorization.

📋 To-Do List

• Release model and inference code.

💡 Pipeline

The code and demo will be coming soon!