OpenAI Unveils Sora, a Powerful Text-to-Video AI Tool
OpenAI introduces Sora, a new artificial intelligence tool that generates high-definition videos up to a minute long from simple text or image prompts. The tool remains restricted to select researchers and creators while the company addresses remaining bugs and implements safety measures.
OpenAI announces Sora, a new generative artificial intelligence tool that creates high-definition videos up to a minute long from simple text or image prompts. The AI model understands physical world dynamics and generates complex scenes featuring multiple characters with accurate details. Examples show impressive results, such as a beautifully rendered video of a woman walking through neon-lit, rain-slicked Tokyo streets.
Despite the amazing visual output, OpenAI admits that bugs remain in the current version of Sora. Some generated clips look noticeably artificial or resemble video game graphics rather than real footage. Because of these lingering issues and the potential for misuse, Sora is not yet available to the general public.
Access is currently restricted to a select group of researchers, artists, and visual professionals who are testing the tool's capabilities. OpenAI uses this limited release phase to refine the technology and implement crucial safety measures. These guardrails aim to prevent the creation of misinformation, hateful content, and other harmful material before a wider public rollout occurs.