Inside Sora: OpenAI's Jaw-Dropping Text-to-Video Breakthrough

#openai #aivideoart #aitools
OpenAI announced Sora, it's brand new video model that provides unbelievable outputs from textual prompts, images, and existing videos. Here's the initial reactions to the new model, reviewing the outputs, and what this means for the future of media consumption.

Important links:

[notanemoprog]

Also the spoon appearing out of nowhere in the Gnocchi Lady's hand opens up new possibilities for horror lol, and those puppies materializing out of thin air and the basketball exploding, I can see that as the future of special effects

[notanemoprog]

It was really wild seeing Altman on X create videos on demand, and to me especially the only one so far AFAIK where we got to see two different versions "A half duck half dragon flies through a beautiful sunset with a hamster dressed in adventure gear on its back" when he later posted "here is a better one", I wonder whether variations have the same sort of seed/prompt/pixel dimensions uniqueness and can be re-generated exactly the same like in Comfy