- Midjourney has launched its first AI video generation model, V1, which turns images into four five-second video clips and is available exclusively through Discord on the web.
- V1 enters a competitive field alongside OpenAI’s Sora, Runway’s Gen-4, Adobe Firefly, and Google Veo 3, but Midjourney focuses on artistic creativity rather than commercial use.
- The company plans to expand into AI-generated 3D models and real-time simulation tools, aiming to build fully interactive, AI-powered environments.
- The launch follows a lawsuit from Disney and Universal over alleged copyright infringement, while V1 video generation costs eight times more than image generation and is available through tiered subscription plans.
Midjourney, a leader in AI-generated imagery, has officially launched its first video generation model, V1. This move expands the company’s creative offerings beyond still images and marks a significant step toward its long-term vision of immersive, real-time AI experiences.
Turning Images into Video
The V1 model is an image-to-video tool that allows users to upload an image and receive four short video clips in return. Each video is five seconds long and is generated based on the visual content of the input image. Users can either upload their own images or use images generated by Midjourney’s existing models.
Access to V1 is limited to Midjourney’s Discord-based interface and is currently available only through web browsers. There is no standalone app or mobile functionality at this time.
Competing in a Crowded Market
With V1, Midjourney enters a growing and competitive field of AI video generation. Other major players include OpenAI’s Sora, Runway’s Gen-4, Adobe’s Firefly, and Google’s Veo 3.
While many of these companies focus on professional and commercial use cases, such as marketing and film production, Midjourney continues to center its tools around creative expression.
Midjourney CEO David Holz stated in a blog post that V1 is part of a larger strategy to develop AI models capable of real-time, open-world simulations. The company is aiming to go far beyond generating stock footage or promotional videos.
Future Plans Include 3D and Real-Time Tools
According to Midjourney, the release of V1 is only the beginning. The company plans to follow up with AI tools for generating 3D models and eventually real-time simulations.
These future tools are intended to provide artists and creators with the ability to build immersive digital worlds, powered entirely by artificial intelligence.
This expansion aligns with the company’s goal of building technology that not only creates content but also simulates complex environments and interactions in real time.
Legal Challenges from Hollywood Studios
Midjourney’s video debut comes at a turbulent time. Just one week before the V1 launch, the company was sued by Disney and Universal, two of the most powerful studios in Hollywood.
The lawsuit alleges that Midjourney’s image models have produced content that closely resembles copyrighted characters such as Homer Simpson and Darth Vader.
This legal action highlights a broader concern among entertainment companies regarding the use of copyrighted material in AI training datasets. There is growing fear that AI-generated content could undermine creative industries and violate intellectual property rights.
Pricing and Subscription Details
Video generation with V1 comes at a higher cost than image generation. Midjourney has stated that each video generation costs about eight times more than a single image. This pricing model means that users on limited subscription plans will use up their monthly credits more quickly when creating video content.
Midjourney’s Basic plan, priced at 10 dollars per month, offers limited access to V1. The Pro plan costs 60 dollars per month and the Mega plan is available for 120 dollars per month. Both of the higher-tier plans allow for unlimited video generations in “Relax” mode, which delivers content at a slower pace.
The company has said it will review and possibly adjust video pricing over the next month based on user feedback.
Customization and Control Features
The V1 model includes several features to help users personalize their video output. There are two animation modes: an automatic setting that introduces random motion and a manual option where users can input specific animation instructions using text.
Users can also control the movement level within the video by choosing between “low motion” and “high motion” options. This allows creators to fine-tune the animation’s intensity to match their creative goals.
Each video starts at five seconds in length. However, users have the option to extend their videos by four seconds at a time, up to four times. This means that a single video can be lengthened to a maximum duration of 21 seconds.
Early Reactions and Creative Potential
Early feedback on V1 has been largely positive. Much like Midjourney’s previous image models, the videos created with V1 lean toward surreal, dreamlike visuals rather than photorealistic output.
This artistic style has resonated well with Midjourney’s existing user base, which tends to prioritize creativity over commercial precision.
Although it remains to be seen how V1 compares in quality and functionality to other video models that have been available longer, the launch is being seen as a major milestone for Midjourney.
With plans for 3D rendering and real-time experiences already in motion, the company appears determined to shape the future of AI-powered creative tools.
Follow TechBSB For More Updates
