In another breakthrough in generative AI, the maker of ChatGPT has unveiled a new tool that can instantly create short videos in response to written commands. Microsoft-backed OpenAI’s new text-to-video generator is called Sora. While Google and Meta have demonstrated similar technology in the past, OpenAI has gone above and beyond 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 yet publicly available, and OpenAI has revealed limited information about its construction.
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. OpenAI suggests that Sora may be confused by the spatial details of a prompt and have trouble 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 has announced that it is developing tools that can determine if a video was created by Sora.
Last year, Meta Platforms enhanced its Emu image generation model by adding two AI-based features that enable editing and generating videos from text prompts.
