Midjourney Unveils V1, Its First AI Video Model
Midjourney, known for its artistic AI image tools, has launched its first video generation model, called V1. This new model allows users to upload an image or use one generated through Midjourney’s existing tools and transform it into four five-second videos. Currently, V1 is only accessible via Discord and through the web.
With this release, Midjourney joins a competitive space that includes OpenAI’s Sora, Runway’s Gen 4, Adobe’s Firefly, and Google’s Veo 3. However, Midjourney continues to set itself apart by focusing on artistic and creative expression over commercial use. While other companies aim to provide solutions for ads or film B-roll, Midjourney’s goals lie elsewhere.
In a blog post, CEO David Holz explained that V1 is part of the company’s broader mission. According to Holz, the team is working toward “real-time open-world simulations,” and V1 is a major step in that direction. The roadmap doesn’t end there. Midjourney also plans to build models for 3D rendering and real-time video generation, which may expand creative possibilities further.
Pricing, Features, and Custom Controls
To use V1, users must be Midjourney subscribers. The most affordable option is the $10-per-month Basic plan. Yet, it’s worth noting that video generations are significantly more expensive eight times more than image generations. As a result, subscribers may find their monthly generation limits depleted faster. Those on the $60 Pro or $120 Mega plans can enjoy unlimited generations, but only in the slower “Relax” mode. Midjourney has stated it will reevaluate this pricing within the next month.
V1 includes both automatic and manual animation controls. Users can either let the model animate an image randomly or specify a desired motion using text prompts. Additionally, motion settings allow users to select between “low motion” and “high motion,” offering some control over camera and subject movement. While the base videos are five seconds long, users can extend them by four seconds up to four times resulting in clips as long as 21 seconds.
Although early demos don’t aim for realism, the generated content has drawn praise for its dreamlike quality. Still, questions remain about how V1 compares to other, more mature AI video tools.
Legal Pressure and Industry Challenges
Midjourney’s latest move comes amid legal tension. Just a week before V1’s release, the startup was sued by Disney and Universal. The lawsuit alleges that its image models created pictures resembling copyrighted characters, including Darth Vader and Homer Simpson.
Major studios are increasingly concerned about AI’s influence in creative industries. They argue these tools, trained on existing media, could undercut human creativity and infringe on intellectual property rights. Despite Midjourney’s emphasis on art and innovation, it hasn’t escaped such scrutiny.
As the legal landscape evolves, Midjourney must navigate both growing demand and increasing pressure. For now, V1 represents a bold step into the future of creative AI but it’s a path lined with both opportunity and risk.
