Idk, seems like it would be an easy fix to tell the AI to generate more in-betweens to make the animation smoother. Not like you’d normally put that much work into hand-made animation that is not specifically made to showcase what animation CAN look like.
Also, the video might profit from actually comparing the sequences, at least by having the AI one and the hand-animated ones run side by side.
Edit: I’m saying the video is bad because it doesn’t actually do any comparing and just lets the viewer guess what it wants to convey.
Not like you’d normally put that much work into hand-made animation that is not specifically made to showcase what animation CAN look like.
Have you never watched an animated film? And I don’t mean those Saturday morning cartoon things. I mean actual long-form film made for adults.
Animators put insane amount of work into details and subtleties when animating to sell the immersion.
Idk, seems like it would be an easy fix to tell the AI to generate more in-betweens to make the animation smoother.
Then you’d just get more random in-betweens. The issue is that the degenerative AI has literally no idea what it’s making. It doesn’t know about legs or arms or eyes or noses or whatever. It has no internal model guiding it in any way, so asking it to generate more frames is just going to get you more frames of arms and legs jerking around in disturbing, incoherent ways.
Idk, seems like it would be an easy fix to tell the AI to generate more in-betweens to make the animation smoother.
Adding more frames would not fix the issues with the AI animation as it entirely lacks purpose, meaning that it is only jiggling around the place. Just look at the arms in the AI animation and compare that to the real animations. The AI also does nothing with the character’s face in sharp contrast to the real animation, if you look at the real animations again pay close attention to all the small details the animator includes.
I do not think the purpose of the animation was to compare the framerate, instead I think it was to compare the overall quality and to showcase the lack of intent AI ‘art’ in general has.
Not like you’d normally put that much work into hand-made animation that is not specifically made to showcase what animation CAN look like.
Those are animations that they did for fun and practice.
but recently, I started animating him doing different dance moves—partly to practice animation, partly to keep myself drawing.
-Video description
I watched a video talking about smoothing is actually not always better in animation.
Easy example, in an action scene smoothly and consistently animation of impossible action is just a blur. An animator is deciding to punctuate the scene by letting certain frames linger, or just generally reducing the frames for a certain type of scene.
Not saying anything about AI assisting in authoring that, but “smooth” is not always better.
Sure but since the video doesn’t say and gives no further context, I have to conclude that smoothness of animation is what it’s comparing.
Well, it’s more than just smoothness. The AI segment looks like kind of random jiggling of the limbs. If anything attempting to inject smoothing probably would have made it look worse, like a jello man wobbling around more than dancing. The AI one seems pretty devoid of intent…
Now if an animator had created more keyframes to create the intent and delegated an AI model to animate smoothness more? Sure, though the animator I saw highlighted non-AI tools that could do the same, but generally at a greater quality, at least for cartoonish content.
Of course, the AI tools may lower the bar of effort for people that wouldn’t otherwise have the skill or effort to try, but at least in the animation of 2D content, it may lag a bit.
