© MKBHD/YouTube
Its first presentation surprised everyone. Sora, OpenAI's artificial intelligence capable of creating videos from simple text, is now available to the general public. The first lucky ones to have tested the tool testified to the power of AI. And to worry about the future of video creation.
Early feedback, including that of the famous YouTuber MKBHD (who was able to use the final version a week before everyone else) reveals impressive capabilities. The tool is particularly good at creating abstract animations, simulating fluid effects like water or fire, and generating cartoon-style sequences.
Subscribe to Presse-citron
Sora, how does it work ?
The interface is intended to be minimalist and accessible: a simple text box allows the user to describe the desired video.Customization options include the choice of definition (from 360p to 1080p) and duration (up to 10 seconds). Generation time varies depending on the complexity of the project, ranging from a few seconds to several minutes.
One of Sora's major innovations is its integrated storyboard system. This feature allows you to chain several prompts together to create more elaborate sequences. This allows you to bypass the tool's limitation of handling complex scenarios in a single request.
200% Deposit Bonus up to €3,000 180% First Deposit Bonus up to $20,000A particularly interesting feature allows you to remix existing videos. Users can edit them by adding or changing specific elements while preserving the overall feel of the original sequence.
Some Improvements to Expect
Despite its technical prowess, Sora is not without its flaws. Movements, especially those of human characters, can sometimes seem unnatural. Object permanence also needs improvement: some elements tend to disappear or transform incoherently over the course of sequences.
On the ethical level, OpenAI has integrated many protections. The tool categorically refuses to generate content featuring minors, public figures or registered trademarks. Each video is also marked with a watermark, but this protection can be easily bypassed by a simple crop.
There is also the painful question of the data used to “train” Sora. OpenAI mentions the use of “publicly accessible media”, but no precise details on the nature of this data and the possibilities of withdrawal for the original creators have been given.
Available to all … or almost
Like many artificial intelligences unveiled recently, Sora is available today in the United States. European users will have to wait a little longer. OpenAI has not provided an official explanation for the delayed launch.
To use Sora, it is possible to try to use a VPN to locate yourself in the United States. But there is nothing to say that OpenAI has not developed protection against this practice. We'll know more in the coming hours.
- OpenAI officially launches Sora, its video generation AI capable of creating realistic sequences from text descriptions
- The tool offers a variety of options (resolution up to 1080p, durations up to 10 seconds) and excels in abstract animations and special effects
- The launch is delayed in Europe
📍 To not miss any Presse-citron news, follow us on Google News and WhatsApp.