Midjourney launches its first AI video generation model, V1

Midjourney, one of the most popular startups of AI images, announced the launch From his long-awaited AI-Videopeld model, V1.

V1 is an image-to-video model, in which users can upload or make an image or create an image that is generated by one of the other models of Midjourney and V1 will produce a set of four videos of five seconds based on that. Just like the image models of Midjourney, V1 is only available through Discord, and it is only available on the web at the launch.

The launch of V1 brings Midjourney into competition with AI -Video generation models from other companies, such as OpenAI’s Sora, Runway’s Gen 4, Adobe’s Firefly and Google’s VEO 3. Although many companies are focused on developing verifiable AI video models for a -dedicated image of the AI, Middjey, Middekellen has always had Middjey’s image -in -house.

The company says that it has larger goals for its AI video models than generating B-Roll for Hollywood films or commercials for the advertising industry. In one blog Post, Midjourney CEO David Holz says that his AI video model is the next step of the company in the direction of its ultimate destination, creating AI models “capable of real-time open-world simulations”.

After AI video models, Midjourney says that it is planning to develop AI models for producing 3D renders, as well as real-time AI models.

The launch of the V1 model of Midjourney only comes a week after the startup was sued by two of Hollywood’s most notorious film studios: Disney and Universal. The suit claims that images made by the AI ​​image models of Midjourney display the copyright characters of the studio, such as Homer Simpson and Darth Vader.

Hollywood Studios have difficulty confronting the rising popularity of AI image and video generating models, as develops Midjourney. There is a growing fear that these AI tools can replace or devalue the work of creatives in their respective areas, and various media companies have claimed that these products have been trained on their copyrighted works.

Although Midjourney has tried to pitch itself as otherwise than other AI image and video startups – more focused on creativity than immediate commercial applications – the startup cannot escape these allegations.

To begin with, Midjourney says that it will charge 8x more for a video count than a typical image generation, which means that subscribers will contain their monthly assigned generations considerably faster when making videos than images.

With the launch is the cheapest way to try V1 by subscribing to the $ 10 base plan of Midjourney. Subscribers of Midjourney’s $ 60 a month Pro Plan and $ 120 mega plan will have unlimited video drawings in the slower, “relax” mode of the company. In the following month, Midjourney says that it will re -assess its prices for video models.

V1 comes with a few custom settings with which users can arrange the output of the video model.

Users can select an automatic animation setting to make an image move randomly, or they can select a manual setting with which users in text can describe a specific animation they want to add to their video. Users can also switch the amount of camera and subject movement by selecting “low movement” or “high movement” in settings.

Although the videos generated with V1 are only five seconds, users can choose to expand them up to four times by four seconds, which means that V1 videos can be up to 21 seconds.

Just like the AI ​​image models from Midjourney, early demos of the V1 videos look somewhat alien, instead of hyper -realistic. The first reaction to V1 has been positive, although it is still unclear how well it matches other leading AI video models, which have been on the market for months or even years.