Midjourney has entered the AI video generation space with the launch of its first video model, the V1. The new tool illustrates the transition from image creation to video animation, as the San Francisco-based company will allow users to turn still images into short video clips. This feature is currently only accessible via the web and is free to all users on the platform. However, you will need a monthly subscription of at least $10 to access high-speed video generation.
Midjourney V1: How it works
Midjourney V1 allows users to upload their own images or choose from AI generated images generated by Midjourney's own AI system. First, users must select the “Animation” option. This allows you to generate four 5-second video clips from a single image. Each clip can be extended up to 4 seconds with up to 20 seconds. However, it remains unclear whether these videos will include sound features at this stage.
Read again: India's digital job scene expands in 2025 with AI rise and data-driven roles
Animation mode and camera settings
There are two modes, two available modes for animation. Automatic and manual. Auto mode provides motion suggestions and guides you how to move images. Meanwhile, the manual mode allows the user to control movement through detailed prompts, allowing them to influence how the scene develops over time.
Read again: India's digital job scene expands in 2025 with AI rise and data-driven roles
Users can also choose between two camera movement styles. The low-motion style puts the camera almost stationary and limited movement. In contrast, the high-motion style introduces more dynamic movement. Here, both the camera and the subject are displayed throughout the clip.
Midjourney has made this tool available to all account tiers, including free users. However, video generation is significantly more resource-intensive. According to the company, creating video clips uses eight times the GPU time than generating still images. Midjourney CEO David Holz noted that the method is more affordable than its previous market offerings, and that it is expected to see continuous improvements in the performance and cost-effectiveness of the tool.
Read again: Samsung Galaxy S25 Review: Flagship Features in a Handful of Packages
Users can create videos in two operating modes: fast mode and relax mode. Fast mode uses fixed GPU time allocations provided each month. Here, one minute of GPU time generates images, and the video requires eight minutes. Once users run out of GPU time, they cannot create additional content until quotas are reset.
Meanwhile, “Relax Mode” is currently only available to Pro-Tier subscribers and above, allowing for unlimited video generation. However, the wait can take up to 10 minutes for the video prompt to complete.
