OpenAI, backed by Microsoft, has introduced new software designed to transform text into concise videos. Named ‘Sora,’ this software is presently utilized for red team exercises, assisting in the detection of flaws in AI systems, and offering valuable feedback to visual artists, designers, and filmmakers.
Sora has the capability to construct detailed scenes featuring multiple characters, precise movements, and intricate elements, generating numerous shots within a single video. Moreover, it can animate static images.
Also Read: What is Google Gemini AI ? How to use it?
This development follows OpenAI’s renowned ChatGPT chatbot, which is celebrated for its proficiency in tasks such as composing emails, writing code, and crafting poetry.
In a parallel move, Meta Platforms has upgraded its image generation model, Emu, incorporating two AI-driven functionalities for editing and generating videos based on textual prompts. This move positions Meta Platforms to compete with major players in the generative AI domain like Microsoft, Google, and Amazon.
However, Sora is still a work in progress and may encounter challenges in rendering spatial details and adhering to specific camera paths.
Additionally, OpenAI is actively working on tools to identify videos generated by Sora.
