InteractiveVideo: User-Centric Controllable Video Generation with Synergistic Multimodal Instructions

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Yiyuan, Kang, Yuhao, Zhang, Zhixin, Ding, Xiaohan, Zhao, Sanyuan, Yue, Xiangyu
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909093605670912
author Zhang, Yiyuan
Kang, Yuhao
Zhang, Zhixin
Ding, Xiaohan
Zhao, Sanyuan
Yue, Xiangyu
author_facet Zhang, Yiyuan
Kang, Yuhao
Zhang, Zhixin
Ding, Xiaohan
Zhao, Sanyuan
Yue, Xiangyu
contents We introduce $\textit{InteractiveVideo}$, a user-centric framework for video generation. Different from traditional generative approaches that operate based on user-provided images or text, our framework is designed for dynamic interaction, allowing users to instruct the generative model through various intuitive mechanisms during the whole generation process, e.g. text and image prompts, painting, drag-and-drop, etc. We propose a Synergistic Multimodal Instruction mechanism, designed to seamlessly integrate users' multimodal instructions into generative models, thus facilitating a cooperative and responsive interaction between user inputs and the generative process. This approach enables iterative and fine-grained refinement of the generation result through precise and effective user instructions. With $\textit{InteractiveVideo}$, users are given the flexibility to meticulously tailor key aspects of a video. They can paint the reference image, edit semantics, and adjust video motions until their requirements are fully met. Code, models, and demo are available at https://github.com/invictus717/InteractiveVideo
format Preprint
id arxiv_https___arxiv_org_abs_2402_03040
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle InteractiveVideo: User-Centric Controllable Video Generation with Synergistic Multimodal Instructions
Zhang, Yiyuan
Kang, Yuhao
Zhang, Zhixin
Ding, Xiaohan
Zhao, Sanyuan
Yue, Xiangyu
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Multimedia
We introduce $\textit{InteractiveVideo}$, a user-centric framework for video generation. Different from traditional generative approaches that operate based on user-provided images or text, our framework is designed for dynamic interaction, allowing users to instruct the generative model through various intuitive mechanisms during the whole generation process, e.g. text and image prompts, painting, drag-and-drop, etc. We propose a Synergistic Multimodal Instruction mechanism, designed to seamlessly integrate users' multimodal instructions into generative models, thus facilitating a cooperative and responsive interaction between user inputs and the generative process. This approach enables iterative and fine-grained refinement of the generation result through precise and effective user instructions. With $\textit{InteractiveVideo}$, users are given the flexibility to meticulously tailor key aspects of a video. They can paint the reference image, edit semantics, and adjust video motions until their requirements are fully met. Code, models, and demo are available at https://github.com/invictus717/InteractiveVideo
title InteractiveVideo: User-Centric Controllable Video Generation with Synergistic Multimodal Instructions
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Multimedia
url https://arxiv.org/abs/2402.03040