In another breakthrough into generative artificial intelligence, the maker of ChatGPT has unveiled a new tool that can instantly make short videos in response to written commands. Microsoft-backed OpenAI's new text-to-video generator is called Sora. While big tech giants like Google and Meta have demonstrated similar technology in the past, OpenAI has gone way ahead in terms of quality.
Following the announcement about Sora software, a social media user told OpenAI CEO Sam Altman “Sam please don’t make me homeless", he replied, “will generate you a video, what would you like?". The user recommended, “Hmmm, a monkey playing chess in a park". Immediately, Altman shared a high-quality video by Sora on the X platform
Sora is not publicly available yet and OpenAI has revealed limited information about how it was built.
It is currently available for red teaming, which helps identify flaws in the AI system, as well as for use by visual artists, designers, and filmmakers to gain feedback on the model, the company said in a statement. According to the OpenAI, Sora may confuse the spatial details of a prompt and have difficulty in following a specific camera trajectory.
ChatGPT can now remember your conversation: Here's how it works
"Sora is able to generate complex scenes with multiple characters, specific types of motion, and accurate details of the subject and background," the statement said, adding that it can create multiple shots within a single video.
Apart from generating videos from text prompts, Sora can animate a still image, the company said in a blogpost.
OpenAI hits landmark $2 billion revenue as growth zooms
OpenAI said it was also developing tools that can discern if a video was generated by Sora.
Last year, Meta Platforms beefed up its image generation model Emu to add two AI-based features that can edit and generate videos from text prompts.
