Good Noise Makes Good Edits: A Training-Free Diffusion-Based Video Editing with Image and Text Prompts

TL;DR

VINO is a novel zero-shot, training-free video editing method that uses structured noise maps and controllable prompts to produce coherent edits guided by image and text inputs.

Contribution

It introduces $ ho$-start sampling, dilated dual masking, and zero image guidance for effective, training-free video editing conditioned on image and text prompts.

Findings

Achieves faithful incorporation of reference images into video edits.

Outperforms state-of-the-art baselines in quality and coherence.

Operates without test-time or instance-specific training.

Abstract

We propose VINO, the first zero-shot, training-free video editing method conditioned on both image and text. Our approach introduces $\rho$-start sampling and dilated dual masking to construct structured noise maps that enable coherent and accurate edits. To further enhance visual fidelity, we present zero image guidance, a controllable negative prompt strategy. Extensive experiments demonstrate that VINO faithfully incorporates the reference image into video edits, achieving strong performance compared to state-of-the-art baselines, all without any test-time or instance-specific training.