OpenAI's artificially intelligent video model, Sora, continues to demonstrate its amazing ability to capture the real world using only text prompts

According to the company, it will be available to the public at some point this year, but until then, its capabilities can only be experienced through Sora Sunday posts on social media

The release comes amid growing pressure on OpenAI to disclose the source of the data used to train Sora This was prompted by CTO Mira Murati's refusal in an interview with the Wall Street Journal to confirm whether public videos from YouTube creators were included in the data set

On the other hand, one can enjoy Sora's creations, such as its uncanny ability to composite different videos, follow simple prompts, and generate multiple scenes from a single text prompt

This week we saw a video of an elephant covered in green leaves in honor of St Patrick's Day, a rainbow waterfall, and a bumblebee waltz

OpenAI adds to all the videos it shares: "We are sharing our research progress early on to learn from feedback and to give the public a sense of what AI capabilities are on the horizon