MMODELYST
Papers/Φ-Noise: Training-Free Temporal Video Conditioning via Phase-Based Noise Manipulation
PAP

Φ-Noise: Training-Free Temporal Video Conditioning via Phase-Based Noise Manipulation

May 23, 2026

arXiv
Abstract

Latent video diffusion models generate videos by progressively transforming Gaussian noise into realistic samples conditioned on text or visual inputs. However, existing conditioning methods often require additional training and computational overhead. Motivated by recent findings on the importance of frequency components in generative models, we propose a simple, training-free approach for motion-conditioned video generation by injecting low-frequency phase information from a reference video directly into the diffusion noise latents. Our method transfers motion cues without modifying the model architecture or inference pipeline. Using several applications, we demonstrate effective control over both appearance and dynamics in generated videos, while achieving competitive or superior results compared to more complex conditioning approaches.

Select text to highlight · click a highlight to remove · saved in this browser only
Authors
Ofir Abramovich, Nadav Z. Cohen, Adi Rosenthal, Ariel Shamir
Your notes (browser-local)
saved
arXiv:2605.24509