Midjourney just launched its AI video generation model, V1. It turns images into four 5-second videos. Users upload an image or an AI-generated one, and V1 creates short video clips. It’s available now on Discord, via web only.
The subscription starts at $10/month. Video generations cost 8 times more than image generations, meaning faster use of monthly limits for video users. Pro and Mega plan subscribers get unlimited video output but in a slower mode. Pricing will be reviewed in a month.
V1 offers automatic or manual animation controls. You can adjust camera and subject motion, from low to high. Videos max out at 21 seconds if extended. Early samples look surreal, not photorealistic. 
The move puts Midjourney in direct competition with OpenAI’s Sora, Runway’s Gen 4, Adobe’s Firefly, and Google’s Veo 3. Unlike rivals chasing commercial use cases, Midjourney is focused on creative, artistic results and future real-time open-world simulations.
CEO David Holz said this video tool is a step toward AI models that handle live 3D worlds. After video, the company plans 3D rendering and real-time AI models.
The launch comes a week after Midjourney was sued by Disney and Universal. The studios claim Midjourney’s AI images include their copyrighted characters like Homer Simpson and Darth Vader. Hollywood is scrambling to control AI image and video tools, fearing they devalue creative work.
Midjourney insists it’s different from other AI firms. It aims to empower creatives, not just churn ad content. Still, these legal challenges are looming.
Midjourney on Twitter:
Introducing our V1 Video Model. It’s fun, easy, and beautiful. Available at 10$/month, it’s the first video model for everyone and it’s available now.
— Midjourney (@midjourney) June 18, 2025
