Midjourney Unveils V1: A Revolutionary AI Model for Video Generation

The startup Midjourney has announced the launch of its new large language model for video generation, called V1.

«As you may know, we have been focusing on [image] generation for the past few years. What you might not realize is that we believe the ultimate purpose of this technology lies in models capable of real-time open-world simulations. […] From a technical standpoint, this model is just a stepping stone, but for now, we need to determine what exactly to provide you with,» reads the company’s press release.

V1 is an AI-driven model designed to transform images into videos. Users can upload an image, and the AI will generate a set of four five-second video clips based on it. Users can extend the clips they find appealing.

The neural network features two settings:

The model also comes with «low» and «high» modes. The former is better suited for scenes with a stationary camera and a moving subject, while the latter is intended for dynamic video content.

Currently, the model is in limited access for basic subscribers. Creating a video requires eight times more internal «energy» from Midjourney than generating an image.

The startup team has promised to further enhance the performance and quality, as well as introduce additional features.

It’s worth noting that in June, Disney and Universal accused the AI startup of theft and copying characters owned by the film companies.