Liputan6.com, Jakarta – ChatGPT developer, OpenAI, launched an AI model capable of converting text commands into video. The AI model is named Sora.
OpenAI said that Sora can create realistic and imaginative scenes from text commands. The text-to-video model allows users to create photorealistic videos up to a minute long, all based on written commands.
Collect The VergeFriday (16/2/2024), the OpenAI blog said, “Sora can create, complex scenes with many characters, certain types of movement, and accurate subject and background details.”
In fact, the creators of ChatGPT also noted that the AI model can understand how objects exist in the physical world, interpret properties accurately and produce characters that express emotions.
The AI model is also claimed to be able to produce videos based on still images or still image. Sora is also said to be able to fill in missing frames in existing videos or expand them.
A demo made by Sora was also included in the OpenAI blog post, including an aerial view of California. The video seems to have been taken from a Tokyo car.
2024-02-16 07:00:03
#ChatGPT #Developer #Releases #Sora #Model #Create #Videos #Text #Commands