Startup Midjourney has announced the launch of a new large language model for video generation—V1.
Introducing our V1 Video Model. It’s fun, easy, and beautiful. Available at 10$/month, it’s the first video model for *everyone* and it’s available now. pic.twitter.com/iBm0KAN8uy
— Midjourney (@midjourney) June 18, 2025
“As you know, for the past few years we have focused on [image generation]. What you may not know is that we believe the inevitable purpose of this technology is models capable of real-time open-world simulations. […] From a technical standpoint, this model is a stepping stone, but for now, we need to figure out what exactly to provide you,” the company’s press release states.
V1 is an AI-based model for transforming images into videos. Users can upload an image, and the AI will create a set of four five-second video clips based on it. The preferred clip can be extended.
The neural network offers two settings:
- an automatic setting that “just makes things move”;
- a “manual” setting using user prompts for animation.
The model also features “low” and “high” modes. The former is better suited for scenes with a static camera and moving object, while the latter is for dynamic clips.
midjourney / nijijourney video test pic.twitter.com/DRnF0uRUQz
— 852話(hakoniwa) (@8co28) June 19, 2025
Currently, the model is in limited access for basic subscribers. Creating a video requires eight times more of Midjourney’s internal “energy” than an image.
The startup team has promised to improve performance and quality further, as well as to add new features.
Back in June, Disney and Universal accused the AI startup of stealing and copying characters owned by the film companies.