OpenAI has introduced a groundbreaking text-to-video model, named Sora, capable of creating realistic videos from text prompts, garnering astonishment online.
The model, with a profound understanding of language, generates scenes with multiple characters, specific motion, and accurate details.
OpenAI CEO Sam Altman invited users to suggest prompts, resulting in hyper-realistic videos that left social media users awestruck, describing them as “out of this world” and a “game changer.”
Despite the excitement, concerns about potential risks, particularly during important events like elections, have prompted OpenAI to prioritize safety measures before releasing Sora to the public.
The company is collaborating with domain experts and developing tools to address potential issues like misinformation and bias in generated content.
Sora, however, has acknowledged weaknesses, such as challenges in continuity and distinguishing left from right.
