Midjourney, the generative image creation tool, has announced plans to introduce a “text to video” model in the coming months. The company, which is best known for running inside a Discord server, will begin training its video models starting in January. Midjourney aims to build upon its mature image model and enter the competitive generative video industry. It is known for emphasizing quality and user experience over raw speed. The move represents a natural progression for the platform, and the company expects to release a final product in a few months.
The recent v6 update from Midjourney included improvements to prompt following and more realistic images. The company aims to stay relevant and competitive in the industry. Midjourney’s venture into video creation comes at a time when other companies, such as Stability AI and Meta, have also announced releases in the video generation space. The creative and media industries are on the verge of a transformative era with the development of AI technologies that can generate, manipulate, and interact with video content. Midjourney’s entry into the video creation market will contribute to the competition and potentially reshape how we perceive reality.