Introducing Sora by OpenAI
On February 15, 2024, OpenAI introduced their new model, Sora. I, Pınar Sinem Gülten, am here to introduce Sora to you in just a couple minutes.
What’s Sora
Sora is the newest model OpenAI has ever invented. Sora is a text-to-video model. Sora can generate videos up to a minute long while maintaining visual quality and adherence to the user’s prompt.
Is Sora out?
Sora is not currently open to the public: only red teamers and a number of visual artists, designers, and filmmakers to gain feedback.
What are the abilities of Sora?
The OpenAI team’s respond the this question:
“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.
The current model has weaknesses. It may struggle with accurately simulating the physics of a complex scene, and may not understand specific instances of cause and effect. For example, a person might take a bite out of a cookie, but afterward, the cookie may not have a bite mark.
The model may also confuse spatial details of a prompt, for example, mixing up left and right, and may struggle with precise descriptions of events that take place over time, like following a specific camera trajectory.”
Safety concerns
As usual, as AI becomes more powerful, the society’s concerns also become powerful. Therefore, one of the OpenAI team’s priorities is “Safety”.
The reason why it’s not out yet is because the red team is still taking care of the safety issues, making it less dangerous.
The company adds:
“We’re also building tools to help detect misleading content such as a detection classifier that can tell when a video was generated by Sora. We plan to include C2PA metadata in the future if we deploy the model in an OpenAI product.
In addition to us developing new techniques to prepare for deployment, we’re leveraging the existing safety methods that we built for our products that use DALL·E 3, which are applicable to Sora as well.
For example, once in an OpenAI product, our text classifier will check and reject text input prompts that are in violation of our usage policies, like those that request extreme violence, sexual content, hateful imagery, celebrity likeness, or the IP of others. We’ve also developed robust image classifiers that are used to review the frames of every video generated to help ensure that it adheres to our usage policies, before it’s shown to the user.
We’ll be engaging policymakers, educators and artists around the world to understand their concerns and to identify positive use cases for this new technology. Despite extensive research and testing, we cannot predict all of the beneficial ways people will use our technology, nor all the ways people will abuse it. That’s why we believe that learning from real-world use is a critical component of creating and releasing increasingly safe AI systems over time.”
Conclusion
As an active ChatGPT user, I’m willing to pay this new model while I did not pay for GPT-4 and DALL-E (don’t come at me; I live in a place where the inflation is 64.9%).
However, I must state that even though I believe that OpenAI has a great red team, the more powerful AI becomes, the more powerful the team should be. This applies the same on other companies, too.
Now, February 17, 2024, I’m waiting for this new amazing feature to come out as soon as possible after the team is done with their amazing work. Additionally, you can find the sample videos AI has generated on the OpenAI’s page by clicking on this link.
