People act like text is the only input. Nah: these are denoisers. They fill in gaps. Current models aren’t tuned specifically to finish sketches or tween animatics, but that’s right there waiting to happen.
I wanna know what Sora does if you drop in unfinished parts of The Thief & The Cobbler. It’s not gonna spit out some completely different cartoon.
I’m sure if there’s one thing animators are excited about, it’s the possibility of having AI generate the animation for them.
Did he draw every frame of his other works?
People act like text is the only input. Nah: these are denoisers. They fill in gaps. Current models aren’t tuned specifically to finish sketches or tween animatics, but that’s right there waiting to happen.
I wanna know what Sora does if you drop in unfinished parts of The Thief & The Cobbler. It’s not gonna spit out some completely different cartoon.