Sora can also seamless transition between two completely unrelated videos ( the middle videos) ... man, Ima need a cold shower

So it turns out that OpenAI's Sora is even more insane than I thought. Here are some of the absolutely nutty things it can do ⬇️

It can take any image and create a video based off it, here is an example they showed using Dall-E generated images

Here is another example of Sora's image to video capabilities

This one is really show stopping, because it's diffusion based, it seems you can essentially edit a video sequence by prompt ... I ... I just can't believe what Im seeing

Oh and how about the ability to extend video both forwards and backwards in time!? What is this sorcery

🚨 New Open AI Sora video just dropped by @billpeeb It took me until the end to realise that it may have been AI generated The prompt he used was: "a giant cathedral is completely filled with cats. there are cats everywhere you look. a man enters the cathedral and bows before the giant cat king sitting on a throne."

Another OpenAI Sora video posted by @_tim_brooks "a walking figure made out of water tours an art gallery with many beautiful works of art in different styles"

The bottom right one perplexes me. I have carefully examined it and can't find one single thing wrong with it. Am I stupid?