- Midjourney launched its first AI video model V1.
- This model allows users to animate images into 5-second motion clips.
- The tool is relatively affordable and is a rival to SORA of Google Veo or Openai.
Midjourney has long been a popular AI image wizard, but now the company is making movements and films under the name V1, the first video model in history.
This image-to-video tool is now available to Midjourney's powerful community of 20 million people. They wanted to see a 5-second clip based on the image, of which up to 20 seconds was extended in 5-second increments.
Despite being a new venture from Midjourney, the V1 model is well ongoing to at least compare it to rival models such as Openai's Sora and Google's VEO 3, especially when considering price.
For now, Midjourney V1 is in web beta and you can use your credits to create and upload them on the platform.
To create a video, generate the image in MidJourney as usual, press “Animation” and select Motion Settings to get the AI to work.
The same applies to uploading images. Simply mark it as the starting frame and enter a custom motion prompt.
You can have the AI decide how to move it, or take the reins and explain how you want to move. You can choose between low or high movements depending on whether each requires gentle movement or each requires more enthusiastic scenes.
The results I've seen certainly fit into the present moment of AI video production, both on the good and the bad. Uncanny Valley is always waiting to invite users, but there are some amazingly good examples from both Midjourney and early users.
AI Video Battle
Midjourney videos are really fun from R/Midjourney
Midjourney is not trying to compete head-on with Sora or Veo in terms of technical horsepower. These models render movie-quality 4K footage with photorealistic lighting and long form of narrative based on text alone. They are trained on terabytes of data, highlighting the consistency and temporal stability of frames that the mid-journey does not claim to provide.
Midjourney's video tools are not pretending to be Hollywood's next CGI pipeline. Pitch is easy and fun for independent artists and Tinkerters in AI media.
And it really comes out pretty cheap. According to Midjourney, one video job would be roughly the same as upscaling, or costing the cost of a second image per second.
According to a rough study of Midjourney and other alternatives, this is 25 times cheaper than most AI video services in the market.
It's probably the best as many Hollywood goes after the mid-journey in court. The company is currently facing high-stakes lawsuits from several Disney, Universal and other studios, claiming it has trained its models with copyrighted content.
For now, Midjourney's AI generator for images and videos is still active, and the company has plans to expand its video production capabilities. Midjourney bullies long-term plans for full 3D rendering, scene control and even immersive world exploration. This first version is just a stepping stone.
Sora and Veo supporters probably don't need to panic yet, but while busy building an AI version of Studio Camera Crew, Midjourney handed out a magic flipbook to someone who had a bit of cash for credits, so maybe they should look to Midjourney's plans.
