Midjourney has officially launched V1, its long-awaited AI video generation model, allowing users to turn images into short animated clips.
Unveiled on Wednesday, V1 generates four five-second videos from a single image, and like other Midjourney tools, it is currently only accessible via Discord on the web.
The new release places Midjourney in direct competition with leading video-generation platforms like OpenAI’s Sora, Runway Gen-4, Adobe Firefly, and Google’s Veo 3. However, Midjourney CEO David Holz emphasized a different vision, stating that the company’s ultimate goal is to build real-time open-world simulations, not just commercial B-roll.
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
V1 videos can be customized with either automatic or text-directed animations, and users can control motion intensity and extend videos to a maximum length of 21 seconds. Early previews show surreal, artistic outputs—consistent with Midjourney’s signature visual style.
The launch comes at a tense moment for the company, which was recently sued by Disney and Universal over alleged copyright infringement tied to its AI-generated images. While Midjourney positions itself as a creativity-first platform, it faces increasing pressure from copyright holders concerned about AI’s impact on the entertainment industry.
V1 video generation is also significantly more expensive than image generation. Midjourney’s $10/month Basic plan offers limited video credits, while $60 Pro and $120 Mega subscribers get unlimited generations in Relax mode. The company plans to revisit its pricing model in the coming weeks.





