11 hours ago
Midjourney lets you generate AI video from still images with V1 for free: Here's how
Midjourney has entered the AI video generation space with the launch of its first video model, V1. This new tool marks a shift from image creation to video animation, as the San Francisco-based company now allows users to turn still images into short video clips. The feature is currently only accessible via the web and is free for all users on the platform. However, a monthly subscription of at least $10 is required to access fast video generation.
With Midjourney V1, users can upload either their own images or select from AI-generated images produced by Midjourney's own AI system. To begin, users need to select the 'Animate' option, which can produce four five-second video clips from a single image. Each clip can be extended by up to four seconds, for a maximum total of 20 seconds. However, it remains uncertain if these videos will include sound features at this stage.
Also read: India's digital job scene to expand in 2025 with rise in AI and data-driven roles
There are two available modes for animation: Automatic and Manual. The Automatic mode offers motion suggestions, which guide how the image could move. Meanwhile, Manual mode gives users the ability to control movement through detailed prompts, which allows them to influence how the scene develops over time.
Also read: India's digital job scene to expand in 2025 with rise in AI and data-driven roles
Users can also choose between two camera movement styles. The low-motion style keeps the camera mostly stationary, with limited movement. In contrast, the high-motion style introduces more dynamic movement, where both the camera and the subject display motion throughout the clip.
A post shared by HT Tech (@hindustantimestech)
Midjourney has made this tool available to all account tiers, including free users. However, video generation consumes significantly more resources. According to the company, creating a video clip uses eight times more GPU time than generating a still image. Midjourney CEO David Holz noted that this method is more affordable than previous market offerings and expects continued improvement in the tool's performance and cost-efficiency.
Also read: Samsung Galaxy S25 review: Flagship features in a handful package
Users can create videos in two operational modes: fast mode and relax mode. Fast mode uses a fixed GPU time allotment provided each month, where one minute of GPU time generates an image, and eight minutes are required for a video. Once users exhaust their GPU time, they cannot create additional content until the quota resets.
On the other hand, 'Relax Mode' is currently only available to Pro-tier subscribers and above and allows for unlimited video generation. However, there are longer wait times, with video prompts potentially taking up to 10 minutes to complete.
