Skip to yearly menu bar Skip to main content


TokenFlow: Consistent Diffusion Features for Consistent Video Editing

Michal Geyer · Omer Bar Tal · Shai Bagon · Tali Dekel

Halle B #312
[ ] [ Project Page ]
Wed 8 May 1:45 a.m. PDT — 3:45 a.m. PDT


The generative AI revolution has recently expanded to videos. Nevertheless, current state-of-the-art video models are still lagging behind image models in terms of visual quality and user control over the generated content. In this work, we present a framework that harnesses the power of a text-to-image diffusion model for the task of text-driven video editing. Specifically, given a source video and a target text-prompt, our method generates a high-quality video that adheres to the target text, while preserving the spatial layout and motion of the input video. Our method is based on a key observation that consistency in the edited video can be obtained by enforcing consistency in the diffusion feature space. We achieve this by explicitly propagating diffusion features based on inter-frame correspondences, readily available in the model. Thus, our framework does not require any training or fine-tuning, and can work in conjunction with any off-the-shelf text-to-image editing method. We demonstrate state-of-the-art editing results on a variety of real-world videos.

Chat is not available.