DynamiCrafter can animate open-domain still images based on text prompt by leveraging the pre-trained video diffusion priors. Please check our project page and paper for more information. We will continue to improve the model's performance.
Comparisons with Stable Video Diffusion and PikaLabs can be found at https://www.youtube.com/watch?v=0NfmIsNAg-g
Online demo: https://huggingface.co/spaces/Doubiiu/DynamiCrafter
Our project page: https://doubiiu.github.io/projects/DynamiCrafter/
Arxiv link: https://arxiv.org/abs/2310.12190