Midjourney Enters AI Video Arena with Launch of V1 Model
Midjourney has officially expanded into the AI video generation space with the launch of its first-ever video model, V1. Known for its wildly popular image generation tools, the company unveiled V1 on Wednesday, marking a significant step beyond still imagery. The new model allows users to transform a single image—whether uploaded manually or generated using other Midjourney models—into four short, five-second video clips.
V1 operates as an image-to-video model and, staying true to Midjourney’s community-centric approach, is accessible exclusively via Discord. Unlike other platforms that offer native apps or broad integrations, Midjourney continues to focus on Discord-based access, at least during the model’s initial web-only phase. The setup encourages experimentation while preserving the collaborative and visually driven culture that has fueled Midjourney’s popularity among digital artists and creators.
With this release, Midjourney now enters the increasingly competitive AI video generation market, going head-to-head with major players such as OpenAI’s Sora, Runway’s Gen 4, Adobe’s Firefly, and Google’s Veo 3. While these rivals are largely targeting enterprise and commercial use cases, Midjourney remains oriented toward creatives, leveraging its reputation for producing stylized, visually unique content. Whether V1 will carry that same creative edge into the video realm remains to be seen, but it clearly signals the company’s ambition to be more than just an image-generation powerhouse.
