Find us here
ChatGPT Creator Releases Sora, an AI Model That Can Generate Videos from Text Prompts
The creator of ChatGPT, OpenAI, has launched a new AI model capable of turning text prompts into videos. The model is called Sora.
OpenAI states that Sora can generate realistic and imaginative scenes directly from written instructions. This text-to-video model enables users to create photorealistic videos up to one minute long, all based on simple text prompts.
According to The Verge (Friday, February 16, 2024), OpenAI wrote on its blog:
“Sora can create complex scenes with multiple characters, specific types of motion, and accurate details for subjects and backgrounds.”
The company also noted that the model understands how objects exist and interact in the physical world and can accurately interpret properties while generating characters that express emotions.
The AI model is also capable of producing videos from still images. Sora can fill missing frames in existing videos or extend them further.
OpenAI’s blog post includes several demos created by Sora, such as aerial views of California and a scene resembling footage taken from inside a Tokyo train.