We proposed a new text-to-video generation approach, VideoGen, which can generate high-definition video with high frame fidelity and strong temporal consistency using reference-guided latent diffusion. Learn more: https://t.co/HS5ALQv3GK pic.twitter.com/aEoUls78eS
— Baidu Research (@BaiduResearch) 7 septembre 2023
We proposed a new text-to-video generation approach, VideoGen, which can generate high-definition video with high frame fidelity and strong temporal consistency using reference-guided latent diffusion. Learn more: https://
videogen.github.io/VideoGen/