VLOGGER

Google recently published a blog post on its GitHub page, introducing the VLOGGER AI model. Users only need to input a portrait photo and an audio content, and the model can make these characters "animate" and read the audio content with facial expressions. VLOGGER AI is a multimodal diffusion model suitable for virtual portraits. It is trained using the MENTOR database, which contains more than 800,000 portraits and more than 2,200 hours of videos, allowing VLOGGER to generate different...