FlagThis AI

OpenAI’s Sora, a text-to-video AI generator, has launched, showcasing impressive capabilities in depicting realistic-looking content including news anchors and news-style cutaways. While capable of generating highly realistic visuals, the AI-generated videos still exhibit telltale signs that distinguish them from real footage. Early reviews highlight the model’s proficiency in creating landscapes, people, and stylistic content; however, it has difficulties with basic physics such as object permanence.

OpenAI has officially released Sora, its AI video generation model, making it available to ChatGPT Plus and Pro subscribers with the new ‘Sora Turbo’ version. This launch marks a significant advancement in AI-powered video creation, allowing users to generate videos from text, images, and video inputs, albeit with some limitations such as restrictions in the UK and EU. Sora offers a novel way for content creators to produce high-quality video content, enhancing creative capabilities. The model aims to serve as a foundation for AI that can understand and simulate the real world, positioning OpenAI as a leader in AI development and video generation technology.