Filmmaking and animation production often require sophisticated techniques for coordinating camera transitions and object movements, typically involving labor-intensive real-world capturing. Despite advancements in generative AI for video creation, achieving precise control over motion for interactive video asset generation remains challenging. To this end, we propose Image Conductor, a method for precise control of camera transitions and object movements to generate video assets from a single image. An well-cultivated training strategy is proposed to separate distinct camera and object motion by camera LoRA weights and object LoRA weights. To further address cinematographic variations from ill-posed trajectories, we introduce a camera-free guidance technique during inference, enhancing object movements while eliminating camera transitions. Additionally, we develop a trajectory-oriented video motion data curation pipeline for training. Quantitative and qualitative experiments demonstrate our method's precision and fine-grained control in generating motion-controllable videos from images, advancing the practical application of interactive video synthesis. Project webpage available at https://liyaowei-stu.github.io/project/ImageConductor/
@article{arxiv.2406.15339,
title = {Image Conductor: Precision Control for Interactive Video Synthesis},
author = {Yaowei Li and Xintao Wang and Zhaoyang Zhang and Zhouxia Wang and Ziyang Yuan and Liangbin Xie and Yuexian Zou and Ying Shan},
journal= {arXiv preprint arXiv:2406.15339},
year = {2024}
}
Comments
Project webpage available at https://liyaowei-stu.github.io/project/ImageConductor/