This repository compiles research on video diffusion models, a class of generative AI systems that produce video content from text descriptions or other inputs. It organizes papers and resources across areas including text-to-video generation, video editing, unconditional video synthesis, and model architectures like latent diffusion and transformer-based approaches. The survey covers foundational work from NVIDIA, Meta, and academic institutions, serving as a reference for researchers and practitioners in generative video AI.