Artificial Intelligence company, OpenAI, has recently launched Sora, an AI model that is designed to generate videos from text prompts.
This new tool is an addition to OpenAI’s repertoire of AI models, such as ChatGPT and DALL-E, which are great for generating text and images.
Sora is a text-to-video model that can create realistic videos up to 60 seconds in length with the help of descriptive text prompts. According to OpenAI, the tool can create videos while maintaining visual quality and accuracy to the user’s prompt. It can generate multiple characters, specific types of motion, and accurate details of the subject and background. The Sora website showcases various examples of videos created by the tool.
OpenAI CEO Sam Altman has also requested text prompts from his X followers and later replied to the users with AI-generated videos created by Sora based on their requests.
While Sora has promising capabilities, OpenAI acknowledges that the current model has weaknesses and may struggle to generate a few prompts. Therefore, the company will be working with experts to create strict guidelines for misinformation, hateful content, and bias. They are also working on developing safety measures before Sora is available to other OpenAI products. Sora will be made available to red teamers, visual artists, designers, and filmmakers to assess risk and provide feedback on improving or advancing the AI model.
