OpenAI Unveils Text-To-Video AI Model

Microsoft-backed OpenAI has announced the development of software that converts text into short videos.

The software, known as ‘Sora,’ is currently accessible for red teaming, assists in identifying AI system flaws, and aids visual artists, designers, and filmmakers in receiving model feedback.

Sora can craft intricate scenes with multiple characters, specific motions, and precise details; it generates multiple shots in a single video. Additionally, it animates still images.

This software follows OpenAI’s ChatGPT chatbot, renowned for its email composition, code writing, and poetry skills.

Also Read: OpenAI develops task automation software

Meta Platforms enhanced its image generation model, Emu, to include two AI-driven features for editing and generating videos from text prompts, aiming to rival tech giants like Microsoft, Google, and Amazon in the generative AI field.

However, Sora remains a work-in-progress, as it may struggle with spatial details and following specific camera paths.

OpenAI is also developing tools to identify videos generated by Sora.