Oliver Haslam·

OpenAI’s Latest Release Is Sora, A Text-To-Video Model

OpenAI is the company that brought the terms chatbot and large language model to the mainstream by launching ChatGPT and taking the world by storm.

Now it’s back to do it again after announcing Sora, a new model that can create videos based on test-based instructions. It can also create a video based on a still image and even fill in the missing frames of an existing video should there be a need to do so.

In a blog post announcing the addition of Sora, OpenAI detailed what it can do and how it does it, adding that it is capable of figuring out how things exist in the real world and using that to create a realistic video.

Sora is able to generate complex scenes with multiple characters, specific types of motion, and accurate details of the subject and background. The model understands not only what the user has asked for in the prompt, but also how those things exist in the physical world.

That doesn’t mean that the model is perfect, however. OpenAI notes that it “may struggle with accurately simulating the physics of a complex scene, and may not understand specific instances of cause and effect.”

The example given is that “a person might take a bite out of a cookie, but afterward, the cookie may not have a bite mark.”

It’s still early days for Sora and it’s only available to “red teamers” who are working out what risks the technology might post. OpenAI will also give access to filmmakers so as to get their feedback, too.

You may also like to check out:

You can follow us on Twitter, or Instagram, and even like our Facebook page to keep yourself updated on all the latest from Microsoft, Google, Apple, and the Web.