Introducing Sora, our text-to-video model.
— OpenAI (@OpenAI) February 15, 2024
Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions. https://t.co/7j2JN27M3W
Prompt: “Beautiful, snowy… pic.twitter.com/ruTEWn87vf
Lots of seethe on Twitter. Discuss the societal implications, and what degenerate thing you're going to make when stable diffusion released their copy in a year!
Also, what will it take for Yann LeCum to admit he is wrong? We'll have AIs that simulate the future and he will still be arguing they aren't intelligent and his model (which is essentially the same thing) is better
Jump in the discussion.
No email address required.
https://twitter.com/Croc_Block/status/1758214024066691125
https://twitter.com/EasbyGames/status/1758210947154657542
https://twitter.com/_VioMarks_/status/1758269803049931191
https://twitter.com/EverikReal/status/1758234102942011857
Jump in the discussion.
No email address required.
The blanket corner moves by itself in the last part. These videos are admittedly really impressive, but you can still tell theyre fake if youre looking for it
Jump in the discussion.
No email address required.
Mega r-slurs can't tell it's fake.
Jump in the discussion.
No email address required.
More options
Context
That would be easy enough to circumvent for the time being by using less complex objects in your scenes.
Jump in the discussion.
No email address required.
More options
Context
I'm not going to be looking for it
Jump in the discussion.
No email address required.
More options
Context
also the cat has three front legs lol
Jump in the discussion.
No email address required.
https://twitter.com/samsheffer/status/1758205467682357732
It'll be fixed in future iterations. This was the state of text to video a year ago.
Jump in the discussion.
No email address required.
More options
Context
More options
Context
More options
Context
More options
Context