OpenAI has introduced Sora, an AI model that can create photorealistic videos “featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions” up to a minute long using detailed instructions provided by a user in text format.
For example, you can provide Sora with this prompt: Beautiful, snowy Tokyo city is bustling. The camera moves through the bustling city street, following several people enjoying the beautiful snowy weather and shopping at nearby stalls. Gorgeous Sakura petals are flying through the wind along with snowflakes. The AI model will then process those instructions and create the video that you see in this post on X/Twitter.
When you look at the video closely, you will come across a few things that don’t look real (artifacts) which will give away that it is not a real video but an AI-generated one. From a distance, however, the video looks quite real, and that’s very impressive. It has been only a day since OpenAI announced Sora and people are already being very creative with it by making videos that we never thought AI was capable of coming up with.
At the moment, OpenAI is making Sora available to “red teamers” to “assess critical areas for harms and risks” and to “a number of visual artists, designers, and filmmakers to gain feedback on how to advance the model to be most helpful for creative professionals.” Currently, there’s no info about when it will make Sora available to the public.
