OpenAI has unveiled a groundbreaking new AI model called Sora, designed to generate realistic videos from text prompts. This tool allows us...
OpenAI has unveiled a groundbreaking new AI model called Sora, designed to generate realistic videos from text prompts. This tool allows users to input simple written descriptions, and in return, it produces high-quality video content that aligns with the prompt. Some of the impressive examples shared by OpenAI include a jungle scene featuring an elephant made of leaves, a kitten pirate riding a robot vacuum, and a surreal vision of Niagara Falls with colorful paint instead of water.
Currently, Sora is still in development, but it's expected to be available to the public in the near future. The tool is poised to be accessible at a cost similar to OpenAI's previous models, like DALL-E. Additionally, Sora will likely include audio functionalities and real-time editing features, further enhancing its capabilities.
While Sora is not yet available for general use, OpenAI has already demonstrated its potential with these eye-catching, realistic video examples, which you can find on their official Instagram account
OpenAI's new AI model, Sora, represents a significant leap in video generation technology. With the ability to create high-quality, realistic videos from simple text prompts, Sora showcases a future where anyone can generate complex visual content with ease. Examples shared by OpenAI include whimsical scenarios such as a leaf-elephant running through the jungle and a kitten pirate riding a robot vacuum, proving the potential of the tool for creative industries and beyond
Currently, Sora is in development and is expected to be released to the public soon. It will come with additional features, including audio and real-time editing tools. While it won't be free, OpenAI plans to price it similarly to their previous models like DALL-E
. Keep an eye on updates from OpenAI as this revolutionary tool becomes more widely available.
Aucun commentaire