I opened this with an open mind, but it felt dead and AI immediately to me. Neural Viz, however, had succeeded in making things I find watchable all by himself[0] by working around some of the current weaknesses and by having stellar human writing. Perhaps unsurprisingly, it seems he got burnt out from doing it all alone so it's been a while since the last upload. The Remo Green one is my favorite[1].

[0]https://www.wired.com/story/the-future-of-ai-media-parody-of...

[1]https://www.youtube.com/watch?v=5bYA2Rv2CQ8

> about as good as Disney Animation

I’ve never seen a Disney animation where they focus on the character’s shoes so they can magically tie a shoelace that is already tied, then put on a jacket through the sleeve, then walk a boring long time with bad cuts and choppy frames so the character can put on another jacket from the front which morphs into a onesie.

I disagree it gets much better after episode 3, as you claim in other comments. Gave episode 4 a shot and it’s still full of stiff movement, bad faces, bad pacing, bad dialogue.

That anyone thinks this looks like professional animation is the reason professionals are struggling. Let’s stop devaluing the craft and start paying attention to what goes into it. Details make the piece.

Seeing comments here arguing about the quality of this. To me it shows how much loss of love there is for the details in arts. Episode 1 for example immediately starts with jank when the camera shifts to the closeup of the guy packing the bag. Suddenly the woman in the background is in a position that should be impossible relative to where he was in the first shot. In any normal film it would be jarring. A 1st semester film student with a smartphone would know to setup the scene better than that.

Saw folks saying it improves in each episode. Skipped to chapter 6. First shot shows a disjointed stairway. And then a boy coming skating into view in a different spot and picking up the board which flips in an impossible way.

There's interesting stuff being experimented on in the AI video space that I keep an eye on. The Naruto "live action" is an interesting experiment that pushes the boundary on character + scene control. It's obvious copyright to me and probably gets far purely because of the source material it can reference. Which means artists have done a lot of the visual hard work already. But it's still a good example of where the frontier could be if piloted carefully. This kono express however, is in fact, slop.

Interesting, had never heard of Kono Express. It definitely looks a little ‘Unreal’, has video game vibes. The quality is pretty good at a glance, especially the environments and effects, but it doesn’t feel all the way there under scrutiny. This reminds me of all AI generated stuff (so far) - looks great from a distance but from up close you see glaring problems. The lipsync feels automated and robotic all the way through well past ep3, for example. Very little action in the whole series.

TBH I think it’s a big mistake to compare this to hand-animated Disney material. They are just very different things, and the debatable comparison will just cause people to focus on what’s wrong with Kono. If you think it’s good, just talk about the good qualities and share it. Also don’t forget the AI is trained on Disney material, and with heavy AI, it’s highly questionable whether you can credit one person for “cranking out stuff”.

What is the ink & paint comment about? The article doesn’t mention ink & paint…

> he's cranking out stuff about as good as Disney Animation all by himself

https://www.youtube.com/watch?v=ikm5lP0zsi0

Yeah... no. Not at all. It's just classic AI slop.

This has nothing to do with animation, it's pure AI slop. Everything is bland, characters, story etc. I've seen far better AI videos.