A new AI model developed by researchers at Stanford University demonstrates the ability to generate highly realistic and coherent video from simple text prompts. The system, named VideoGen, uses a novel diffusion architecture that builds upon recent advances in image generation. Early tests show it can create short clips depicting complex scenes with consistent objects and motion. The researchers acknowledge current limitations, including video length and resolution, but highlight the model’s potential for creative and educational applications. The team has released a paper detailing their methodology but has not made the full model publicly available, citing concerns over potential misuse for generating deepfakes. Read the full article at https://technologyreview.com/2024/05/15/videogen-ai-model-text-to-video.