Midjourney Enters the Video Arena with V1 AI Model

Midjourney, the popular AI image generation platform, has officially launched its first AI video generation model, V1, marking a significant expansion into the video domain. Announced on June 18, 2025, this new model allows users to create short, AI-generated video clips, pitting it against competitors like RunwayML and Pika Labs. The launch signifies Midjourney’s ambition to become a comprehensive creative AI suite.

According to the official announcement, Midjourney’s V1 model is capable of generating videos up to 5 seconds long at 60 frames per second. Users can create these videos through text prompts, image prompts, or a combination of both. The company emphasizes that the model is still in its early stages, encouraging users to experiment and provide feedback to improve its capabilities.

The initial reactions from early testers have been mixed. While some users are impressed with the model’s ability to create surreal and imaginative scenes, others have pointed out limitations in its ability to maintain consistent visual elements and coherent narratives across the entire video. Common issues include flickering artifacts and inconsistent character appearances.

One area where Midjourney V1 seems to excel is in generating abstract and artistic visuals. Users have successfully created visually stunning clips of swirling colors, morphing landscapes, and fantastical creatures. However, generating realistic scenes with consistent character actions remains a challenge.

To access the video generation feature, users need an active Midjourney subscription. The company has rolled out access in phases, starting with users who have generated a high number of images in the past. New users will gain access gradually over the coming weeks. The video generation process is similar to image generation: users submit a prompt via the Midjourney Discord server and receive their generated video within a few minutes.

The release of V1 raises questions about the future of AI-generated video content and its potential impact on the creative industry. While the technology is still nascent, the rapid advancements in this field suggest that AI video generation will become an increasingly important tool for artists, filmmakers, and content creators. As Midjourney continues to refine its model based on user feedback, it is poised to play a key role in shaping the future of AI video creation.

Midjourney’s move into video generation is a bold step that could redefine the landscape of creative AI. By offering a user-friendly platform for generating both images and videos, Midjourney aims to empower creators with new tools for expressing their vision. As the technology evolves, it will be interesting to see how artists and storytellers leverage these capabilities to create new forms of art and entertainment.