Imagen Video: High Definition Video Generation with Diffusion Models
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.
- Publication:
-
arXiv e-prints
- Pub Date:
- October 2022
- DOI:
- arXiv:
- arXiv:2210.02303
- Bibcode:
- 2022arXiv221002303H
- Keywords:
-
- Computer Science - Computer Vision and Pattern Recognition;
- Computer Science - Machine Learning
- E-Print:
- See accompanying website: https://imagen.research.google/video/