The popular AI image generation tool, Midjourney, has recently made its video generator available to the general public. This addition represents a significant step forward in the company’s ambitious project.
Following the release of its seventh version of the image generation model in the spring of 2025, Midjourney introduced an AI-powered video generator to the general audience. This tool, which is both affordable and showcases promising capabilities, allows a broad user base to experiment with video creation. However, this project is just one piece of a much larger puzzle.
Midjourney Unveils Its AI Video Generator
Midjourney recently launched the first version of its video generator, which works differently from other similar tools as it does not create videos from scratch. Instead, it follows an Image-to-video model that begins with a reference image marking the start of the sequence. In simple terms, the tool animates an image that has been previously uploaded or created on Midjourney. While only a few examples have been showcased by the California-based startup, the tool’s accessibility is one of its primary strengths.
Introducing our V1 Video Model. It’s fun, easy, and beautiful. Available at 10$/month, it’s the first video model for *everyone* and it’s available now. pic.twitter.com/iBm0KAN8uy
— Midjourney (@midjourney) June 18, 2025
To display this content from social networks, you need to accept cookies and advertising trackers.
These cookies and trackers help our partners to offer you personalized ads and content based on your navigation, profile, and interests.More info.
Our goal: to provide an experience that’s fun, simple, beautiful, and affordable, allowing everyone to explore. We believe we’ve struck a good balance.
Midjourney has priced access to its video generator at $10 per month (approximately 12 euros in France), making it one of the most cost-effective video models on the market. Despite the lower cost, the performance remains distinctly Midjourney, especially since the videos, whether created by the startup or its early users, are based on images generated by the tool. The somewhat blurred slow motion seen in other video generators is less prevalent here, though some inconsistencies may still occur.
Midjourney provides several options for video generation: users can choose the intensity of camera movement and animations (low or high), and either let the AI animate the image or associate it with a prompt containing specific motion instructions.
How to Access Midjourney’s Video Generator
The video generator can be accessed through Midjourney’s usual web interface. By logging into the online platform and navigating to the Create tab, where your images are stored, you’ll notice an Animate button when you hover over an image. Clicking on this will automatically start the process of generating four 5-second videos.
If you click on an image to enlarge it, an options panel will appear on the right, offering the various choices mentioned earlier, according to Midjourney:
- « Low Movement: suited for atmosphere scenes, where the camera remains mostly stationary and the subject moves slowly or precisely. Sometimes, this can result in a static outcome.
- High Movement: ideal when you want everything to move, including the subject and camera. However, this can sometimes lead to visual errors. »
To generate a video from an imported image, click on the icon for uploading a file in the prompt bar, upload your image, and set it as the starting frame by clicking on Starting Frame.
The videos generated are displayed in your Create tab, following your previous creations. Once a video is created, it is possible to extend it up to four times, adding 4 to 5 seconds with each extension.
The Vision for a Real-Time Generator
This video generator is merely the latest milestone in a more ambitious project for Midjourney. In a post announcing the deployment of this v1 video, the startup elaborated on its roadmap, which aims to lead to « an AI system that generates images in real time ».
As you know, our focus over the past few years has been on imagery. What you might not realize is that we are convinced this technology will inevitably lead us to models capable of generating real-time simulations in open worlds.
Midjourney envisions these real-time simulations as follows: « You can ask the AI to move through a 3D space, and the environments and characters also move, allowing you to interact with everything around you. » To achieve this goal, Midjourney needs basic building blocks: visuals, the ability to animate them, then to allow movement through space, and finally to make the whole system fluid and fast. Thus, this video generator is a crucial second step in their project.
The business model is not fixed, and it is very likely that the cost of using this service will increase in the coming weeks. « The real cost of producing these models and the prices charged are hard to predict. We are giving you access now, and we will adjust things over the next month based on usage (or if we run out of servers) to ensure a viable economic model », the startup cautions.
Similar Posts
- Google Unveils Veo 3, Imagen 4, Flow: Explore AI Innovations in Image and Video Tech!
- Exciting AI Breakthroughs: 5 Underrated Tools You Need to Watch!
- Figma’s Latest Features: AI-Powered Code Generator, Vector Drawing, Website Creation Unveiled!
- AI-Generated Photos in Journalism: Legal or Not?
- Apple Halts Development on Camera-Equipped Apple Watch: What’s Next for Tech Giant?

Jordan Park writes in-depth reviews and editorial opinion pieces for Touch Reviews. With a background in UI/UX design, Jordan offers a unique perspective on device usability and user experience across smartphones, tablets, and mobile software.