TokenFlow: Consistent Diffusion Features for Consistent Video Editing |
TokenFlow: Consistent Diffusion Features for Consistent Video Editing
paper page: https://huggingface.co/papers/2307.10373
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.
Sur cette page du site, vous pouvez voir la vidéo en ligne TokenFlow: Consistent Diffusion Features for Consistent Video Editing | durée heure minute seconde en bonne qualité , qui a été Téléchargé par l'utilisateur AI Odyssey 23 juillet 2023, Partagez le lien avec vos amis et connaissances, sur youtube cette vidéo a déjà été regardée 511 fois et il a aimé 7 téléspectateurs. Bon visionnage!
