Midjourney, the platform recognized for its innovative image generation through artificial intelligence, has taken a decisive step by presenting V1, its first model aimed at video creation.
This new functionality allows you to transform any static image into an animated sequence, expanding the creative possibilities of both professionals and amateurs.
However, the arrival of V1 coincides with litigation filed by entertainment giants (Disney and Universal) that raise legal questions about the use of copyright-protected content.
What can the Midjourney V1 model do?
The heart of V1 lies in its ability to convert images into five-second clips. The user can use either an illustration generated by Midjourney or their own photograph.
Once sent, the AI automatically produces four different videos, each with an initial five seconds. If you wish to extend the duration, you can add fragments of four seconds up to a maximum of twenty-one seconds.
This flexibility adapts to projects of varying sizes, from presentations and advertisements to artistic experiments.
Simplified workflow
The process begins with the selection or loading of the image, followed by the adjustment of basic parameters. V1 then generates the animated versions and presents them for review.
Thanks to this mechanic, even newcomers to the platform can obtain impressive visual results without a steep learning curve.
Customization and animation options
One of the strong points of V1 is the combination between automation and manual control. In automatic mode, the AI decides movement patterns that bring the scene to life with unpredictable and organic results.
Those looking for greater precision can opt for manual mode, defining the type of movements and effects desired through text.
The user can also choose between low or high movement levels. The first alternative offers subtle transitions and an almost hypnotic feel, ideal for calm environments or elegant presentations.
The second amplifies the dynamics, recommended for action scenes or content that requires greater visual energy.
How much does V1 cost and where is it available?
V1 is currently powered by Discord and the official Midjourney website. This choice responds to the company’s desire to control access and ensure a consistent experience with its ecosystem.
Subscription plans
The cost of using V1 varies by plan. The basic level, with a monthly fee of €10, includes a limited number of video generations.
Going up the scale, the Pro plan, at €60 per month, and the Mega plan, at €120, offer unrestricted content in “Relax” mode, which eliminates time and credit limits.
Each second of video is equivalent to the cost of one image, although generating a full clip requires up to eight times more resources.
Legal controversy
The release of V1 comes just a week after Disney and Universal filed a lawsuit against Midjourney.
According to these companies, the AI would have reproduced characters and scenes protected by copyright, such as emblematic figures of popular culture.
This litigation places Midjourney at a crossroads: on the one hand, it has the support of a creative community eager to explore new frontiers; On the other hand, it must face the risk of setting precedents that condition the development of similar AI technologies.
Future implications
The outcome of this case could redefine the way AI-based content generators handle other people’s works.
Depending on the ruling, companies in the sector could be forced to implement stricter filters or licensing mechanisms to ensure legal compliance.
Community reactions
Since its announcement, V1 has sparked mixed reactions. On social network
Other users, such as @dreamingtulpa, point out that the quality still shows ups and downs, equating the evolution of V1 to that of the platform’s first image models.
Although some criticize that the sound and resolution still need improvement, most agree that V1 lays a promising foundation.
How does Midjourney V1 compare to other models?
The video AI sector has notable competitors. OpenAI has presented Sora, a system focused on generation from text, while Runway Gen‑4 stands out for its advanced editing tools.
Adobe Firefly, for its part, integrates generation into its creative suite, and Google Veo3 is aimed at content optimized for social networks.
In contrast to them, Midjourney’s V1 is committed to maintaining aesthetic coherence with the platform’s images. Although its availability is more limited and its cost can be high, its unique style and ease of use are an advantage for those already working with Midjourney.
In conclusion: it has potential
With V1, Midjourney expands its horizon beyond static images, offering a simple and versatile animation experience. It still must resolve technical challenges (such as improving resolution and audio) and navigate litigation that could shape the future of creative AI.
However, the community’s reception and its focus on aesthetics suggest that V1 has the potential to become a valuable resource for artists, designers and content creators.
Only time will tell how this first video model will evolve, but the truth is that it has opened a new chapter in the history of Midjourney and in the use of artificial intelligence for multimedia creation.
This post is also available in: