Midjourney Expands into AI Video Generation with V1 Model Launch

Midjourney has entered the AI video generation space with its inaugural V1 model, transitioning from static image creation to dynamic multimedia content. The platform's 20 million users can now animate both uploaded and AI-generated images directly through its website.

CEO David Holz positions V1 as a stepping stone toward developing AI models capable of real-time open-world simulations. The company aims beyond conventional applications like Hollywood B-roll or advertising content, signaling ambitions in broader interactive media.

Creative Director Nick St. Pierre highlights V1's technical specifications: image-to-video conversion at 480p/24fps, four free generations per clip, and compatibility with all aspect ratios. At approximately $0.20 per clip, the model undercuts competitors like Google's Veo while delivering faster processing speeds.

The system offers both automated random animations and manual text-guided motion control. Though limited to 5-second initial outputs, users can extend clips through four 4-second increments, achieving maximum durations of 21 seconds.