Midjourney has officially announced the launch of its first artificial intelligence model for video creation called V1, which allows users to generate four five-second video clips based on a single image.
This is reported by Бізнес • Медіа
Features of the V1 Model and Functionality
The new tool operates exclusively through Discord, like the company’s other services. Users can upload their own photos or use images created by other AIs on the same platform. As a result, the system generates four short video segments that can be viewed and downloaded.
The cost of a basic subscription for access to V1 is $10 per month. At the same time, creating one video clip is eight times more expensive than generating a static image. For users with Pro ($60) and Mega ($120) plans, an unlimited number of generations are available in slow mode. The length of the video can be increased to 21 seconds, and users can choose between automatic animation, text animation, and various levels of movement.
Market Competition and Company Ambitions
The launch of V1 positions Midjourney in the generative AI video market, where players like OpenAI (Sora), Runway (Gen-4), Adobe (Firefly), and Google (Veo 3) are already operating. At the same time, the company traditionally focuses on the creative audience rather than corporate or advertising orders.
According to the company’s CEO David Holz, Midjourney aims to develop AI models that can simulate open worlds in real time, with the next steps being the creation of 3D rendering and the development of models for real-time operation.
The launch of the new video model comes amid lawsuits from Disney and Universal, which accuse Midjourney of copyright infringement due to the creation of images using AI. Despite the company’s position as a platform for the creative community, legal disputes surrounding copyright continue.
It was previously reported that a scientist developed AI technology that restores damaged paintings in just a few hours.