HunyuanVideo is an open-source video foundation model that demonstrates performance in video generation comparable to, or even surpassing, leading closed-source models. It encompasses a comprehensive framework integrating data curation, advanced architectural design, progressive model scaling and training, and efficient infrastructure tailored for large-scale model training and inference. HunyuanVideo aims to bridge the gap between closed-source and open-source communities, empowering individuals to experiment with their ideas and fostering a more dynamic video generation ecosystem.