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.
Auf dieser Seite können Sie das Online-Video TokenFlow: Consistent Diffusion Features for Consistent Video Editing | mit der Dauer stunde minuten sekunde in guter Qualität ansehen, das der Benutzer AI Odyssey 23 Juli 2023 hochgeladen hat, den Link mit Freunden und Bekannten teilen, dieses Video wurde auf Youtube bereits 511 Mal angesehen und es wurde von 7 den Zuschauern gefallen. Viel Spaß beim Betrachtenden Zuschauern gefallen!
