TY - JOUR AU - Salimans, Tim AB - Abstract: We present Imagen Video, a text-conditional video generation system based on a cascade of video diffusion models. Given a text prompt, Imagen Video generates high definition videos using a base video generation model and a sequence of interleaved spatial and temporal video super-resolution models. We describe how we scale up the system as a high definition text-to-video model including design decisions such as the choice of fully-convolutional temporal and spatial super-resolution models at certain resolutions, and the choice of the v-parameterization of diffusion models. In addition, we confirm and transfer findings from previous work on diffusion-based image generation to the video generation setting. Finally, we apply progressive distillation to our video models with classifier-free guidance for fast, high quality sampling. We find Imagen Video not only capable of generating videos of high fidelity, but also having a high degree of controllability and world knowledge, including the ability to generate diverse videos and text animations in various artistic styles and with 3D object understanding. See https://imagen.research.google/video/ for samples. TI - Imagen Video: High Definition Video Generation with Diffusion Models JF - Computing Research Repository DO - 10.48550/arxiv.2210.02303 DA - 2022-10-05 UR - https://www.deepdyve.com/lp/arxiv-cornell-university/imagen-video-high-definition-video-generation-with-diffusion-models-6ax2bwDPOO VL - 2023 IS - 2210 DP - DeepDyve ER -