“do 500 forward pass or a thousand forward passes of the…” — Practical AI at 26:23
“do 500 forward pass or a thousand forward passes of the model. In a video generation model, like every pixel is kind of generated at once. So each forward pass produces all of the pixels that you see in your video across space and time. And we do multiple de-noising steps. You start with a kind of a pure noise sample…”
0:00
45:09