CCEdit: Creative and Controllable Video Editing via Diffusion Models

arXiv:2309.16496v3 Announce Type: replace
Abstract: In this paper, we present CCEdit, a versatile generative video editing framework based on diffusion models. Our approach employs a novel trident network structure that separates structure and appearance control, ensuring precise and creative editing capabilities. Utilizing the foundational ControlNet architecture, we maintain the structural integrity of the video during editing. The incorporation of an additional appearance branch enables users to exert fine-grained control over the edited key frame. These two side branches seamlessly integrate …

abstract architecture arxiv capabilities control controlnet creative cs.cv diffusion diffusion models editing foundational framework generative generative video integrity network novel paper type via video