Naxii

OpenAI Introduces Sora, A Visually Striking Text-to-Video Converter

Posted on by Marqus Bobesich
OpenAI-sora

The creators of ChatGPT, OpenAI, have revealed a new AI model that uses only text cues to produce realistic-looking one-minute videos.

 

OpenAI Introduces Sora

A new AI model from OpenAI, appears to be incredible. The model, known as Sora, can record a whole minute of video using only text commands. The OpenAI Sora blog states, “We’re teaching AI to understand and simulate the physical world in motion, with the goal of training models that help people solve problems that require real-world interaction.”

 

 

In an amazing blog post, OpenAI provided a minute-long demonstration of the tool’s functionality. Even the actors, who had nothing to do with creating the clip, could shudder at the outcome. On the basis of user descriptions, the AI system generates videos through training on millions of documented video images.

 

The New York Times was informed by OpenAI that watermarks are added to videos produced by Sora, although the watermarks are removable. An approach to cryptographically incorporate provenance information into the code of AI-generated material is being developed by a standards consortium called C2PA, which is supported by Microsoft and OpenAI.

 

Sam Altman also showcased the tool through posts on his X account. “Please respond with captions for videos you’d like to see, and we’ll start making some. We’d like to show you what sora can do.” As stated in Altman’s post. He received a lot of prompts from users on the network, and the outcomes he gave seem extremely accurate.

 

 

 

According to the company, they will be putting in place a number of vital safety precautions before deploying Sora in OpenAI’s products. This involves collaborating with red teamers, specialists in fields like bias, hate speech, and disinformation, who will thoroughly test the model to find any potential weaknesses. Furthermore, OpenAI will be creating tools to identify deceptive content, such a detection classifier that can recognize videos produced by Sora.

 

Additionally, OpenAI claims to be actively addressing concerns and exploring beneficial applications of this new technology by collaborating with educators, artists, and governments throughout the world. “We’ll be interacting with global governments, educators, and artists to learn about their concerns and find beneficial applications for this new technology. We cannot predict every constructive or harmful method that people may use our technology, even after conducting a great deal of research and testing. Because of this, OpenAI states, “We think that developing and releasing increasingly safe AI systems over time requires learning from real-world use.”

 

As of right now, Sora can only be used by red team members to scan key locations for possible problems or threats.