J
Sora can be a bit of an eyesore.
It’s impressive, but we’re not the only ones who found the results from OpenAI’s new AI video model tend to be a bit weird. It struggles with natural movement, often includes additional appendages or other visual distortions, and sometimes ignores half your prompt directions entirely.
Follow topics and authors from this story to see more like this in your personalized homepage feed and to receive email updates.
Loading comments
Getting the conversation ready...
