Midjourney now offers a service to generate videos based on images provided by users. To bring this capability, the Video Model V1 artificial intelligence (AI) model has been developed. The V1 model is now available to customers and comes with several generative generation modes.
Users can generate 5-second video clips at a cost of 8x higher than the cost of generating 1 image on Midjourney. Videos can be generated from images generated in Midjourney or uploaded by users themselves. Users then only need to enter a command prompt for it to be processed.
There is a built-in feature that maintains the camera position and more dynamic camera movement settings. The generated video can be extended by 4 seconds 4 times if it is felt to be too short. However, unlike Google Veo 3 and Meta Movie Gen, Video Model V1 cannot generate videos with matching audio.