Midjourney, a leading name in the realm of AI image generation, made headlines on Wednesday with the launch of its highly anticipated AI video generation model, V1. This innovative image-to-video model allows users to upload an image, or select one generated by Midjourney’s existing models, to produce a series of four five-second videos. This groundbreaking feature positions Midjourney at the forefront of AI video technology, setting it apart from its competitors.
Currently, V1 is exclusively accessible through Discord and is available only on the web at launch. This aligns with Midjourney’s established method of delivering its services, emphasizing a community-driven approach. The introduction of V1 intensifies competition in the AI video generation space, where companies like OpenAI’s Sora, Runway’s Gen 4, Adobe’s Firefly, and Google’s Veo 3 are already making significant strides.
While many firms focus on creating controllable AI video models tailored for commercial applications, Midjourney differentiates itself through its commitment to creativity. According to CEO David Holz, the launch of V1 is just the beginning. The company has broader ambitions for its AI video models, aiming to develop systems capable of real-time open-world simulations. Following the V1 model, Midjourney plans to explore the development of AI models for 3D renderings and real-time applications.
The launch of Midjourney’s V1 comes amidst legal challenges, as the startup is facing a lawsuit from renowned Hollywood studios, including Disney and Universal. The lawsuit claims that images produced by Midjourney’s AI models infringe upon copyright by depicting iconic characters like Homer Simpson and Darth Vader. This situation highlights the growing tension between Hollywood and the rising popularity of AI image and video generation technologies, with concerns that these tools may undermine the value of creative work.
In an effort to manage expectations and usage, Midjourney has introduced a pricing structure that charges users significantly more for video generations than for image creations—specifically, an eightfold increase. This means that subscribers will utilize their monthly generation allotments much faster when producing videos. The most affordable way to access V1 is through Midjourney’s $10-per-month Basic plan. Higher-tier plans, including the $60-a-month Pro plan and $120-a-month Mega plan, offer unlimited video generations in the slower “Relax” mode.
V1 offers a range of custom settings to enhance user control over video outputs. Users can choose an automatic animation setting for random movement or a manual option that allows them to describe specific animations in text. Furthermore, users can adjust the degree of camera and subject movement by selecting either “low motion” or “high motion” settings. Although the generated videos are primarily five seconds long, users have the option to extend them by four seconds, up to four times, potentially resulting in videos that last up to 21 seconds.
The early response to V1 has been largely positive, with users appreciating its unique aesthetic, which leans toward the otherworldly rather than hyperrealistic. While it remains to be seen how V1 compares against established AI video models that have been in the market for longer periods, Midjourney’s commitment to creativity and innovation continues to position it as a formidable player in the evolving landscape of AI technologies.
