OpenAI, a leading company in the field of artificial intelligence, has introduced a new AI model called Sora, which is capable of creating “realistic” and “imaginative” 60-second videos starting from simple and quick text prompts (commands) .
The company said Sora is capable of generating videos up to 60 seconds in length from text instructions, with the ability to display scenes with multiple characters, specific types of movement and detailed backgrounds. The model includes not only what the user asked for in the prompt, “but also how these things exist and coexist in the physical world,” the blog post reads.
While “multi-modal models” are nothing new and text-to-video models already exist, what seems to set Sora apart is the length and accuracy that OpenAI claims to have achieved.
After all, it is possible to realize this by observing the incredible videos released by OpenAI itself.
https://www.youtube.com/watch?v=jk7iG2H-GI8
At the moment, however, OpenAI prefers to focus on security, Sora has in fact been entrusted for various tests to a team of experts in order to carefully examine various areas including disinformation, hateful content, prejudices and deep fakes also with reference to what recently happened to Taylor Swift.
https://www.youtube.com/watch?v=1WXMJHYono8
Sora will initially be made available to cybersecurity professors, called “red teamers”, who can evaluate the product for any harm or risk, while pre-access has also been granted to visual artists, designers and filmmakers to gather feedback and further suggestions.
#Sora #OpenAI #Transforming #text #realistic #creative #videos
