OpenAI’s highly-anticipated AI text-to-video generator, Sora, will become available to everyone today. In a video posted on Monday, Marques Brownlee confirmed its imminent release and detailed his experience using Sora over the past few weeks, calling the results “horrifying and inspiring at the same time.”
OpenAI first revealed Sora in February but only made the tool available to a select number of visual artists, designers, and filmmakers to start.
Brownlee shows how Sora can convert your text prompt into a video, which you can then customize with additional text prompts as part of its “remix” tool. You can also use Sora to transform a photo into a video, as well as use its storyboard feature to “string together” several text prompts that Sora will attempt to blend into cohesive scenes.
During his video, Brownlee points out that Sora currently struggles with generating realistic physics and often shows objects that disappear or pass through each other. He also found that Sora often rejects prompts that include public figures and copyrighted characters.
Sora will launch today, and will most likely be announced during the 12 days of “ship-mas” video OpenAI plans on releasing at 1PM ET. Last Thursday, OpenAI announced a $200 / month ChatGPT Pro subscription and the full release of its o1 reasoning model.
