OpenAI, the company responsible for the development of ChatGPT, has unveiled a groundbreaking text-to-video program called Sora. This new tool has the ability to transform text prompts into computer-generated videos, promising a range of applications and creative possibilities.
According to OpenAI, Sora is capable of generating intricate scenes featuring multiple characters, specific types of motion, and accurate details of the subject and background. Users can provide prompts to Sora, which will then use these inputs to produce videos. Additionally, Sora can create videos based on user-submitted images or extend existing video footage with new material.
To showcase the capabilities of Sora, OpenAI shared several videos created by the program. One video was generated from the prompt of a beautiful snowy Tokyo city bustling with activity. The camera followed people enjoying the snow and shopping at nearby stalls, with sakura petals and snowflakes gently floating in the wind. OpenAI founder Sam Altman also demonstrated Sora’s versatility by posting videos suggested by followers, including one featuring two golden retrievers podcasting on top of a mountain and another showcasing a lifelike cooking session for homemade gnocchi hosted by a grandmother social media influencer.
OpenAI has not disclosed the release date for Sora to the public. However, the company announced that the program will first undergo thorough censorship measures. OpenAI’s ‘Red Team’ will review and ensure that Sora cannot be used to create content featuring extreme violence, sexual content, hateful imagery, celebrity likeness, or the intellectual property of others.
While Sora represents an incredible advancement in AI technology, OpenAI acknowledges that the program still has its limitations. It can sometimes struggle to accurately simulate the physics of a complex scene and may not fully understand cause and effect. For example, a person taking a bite out of a cookie may not result in a visible bite mark on the cookie in the generated video.
OpenAI’s GPT language model has made significant strides over the past two years, with its performance surpassing expectations. From powering a chatbot program in late 2022, GPT can now perform at the 93rd percentile on a SAT reading exam and at the 89th percentile on a SAT math test.
Despite concerns about the potential risks associated with their technology, OpenAI has partnered with the US military on various artificial intelligence projects. The company recently lifted its prior prohibition on the use of its technologies for military and warfare purposes, stating that it is now collaborating with the Pentagon.
OpenAI’s introduction of the Sora text-to-video program demonstrates their commitment to advancing AI capabilities and pushing the boundaries of technology. With proper censorship measures in place, Sora could revolutionize the way videos are created and utilized in various industries. However, further refinement and improvement are still needed to address existing glitches and enhance its understanding of complex scenes.
In conclusion, Sora has the potential to be a game-changer in the field of video generation, enabling users to bring their text prompts to life in the form of computer-generated videos. OpenAI’s dedication to incorporating censorship features ensures responsible and ethical use of this powerful technology. As AI continues to advance, it is essential for companies like OpenAI to strike a balance between innovation and addressing potential risks.
