Meta Debuts AI Video Tool

Meta Platforms unveiled a GenAI solution capable of rendering high-quality videos based on text and image prompts. Named Movie Gen, the company said the system can generate videos up to 16 seconds long based on written and photo inputs.

The company added that the product outperforms similar models in the industry, and can also edit existing videos. It has not been made available commercially to app users. Meta referred to Movie Gen as its third wave of GenAI work, combining images, videos, audio, and 3D animation models. The company explained it used a mix of licensed and publicly available datasets to train the system.

Movie Gen can remove, add, and replace certain visual elements or make a more dramatic alteration such as background or style modifications, setting it apart from traditional tools that require specialized skills or generative ones that lack precision. The company said it hopes that one day, everyone will have the opportunity to bring their artistic visions to life and create high-definition videos and audio using Movie Gen, noting it does not aim to replace artists and animators but to help people express themselves in new ways.