Comment on People keep saying Lain protocol 7 is made but with AI, but this video shows it isn't?
mindbleach@sh.itjust.works 1 week ago
Tool used to do thing it’s for.
Oh no, apparently.
The constant hand-wringing about killing art is especially rich here, since this art presumably could not exist without it. It’s an unauthorized fan work. (Or as unauthorized as Japan’s tightass copyright law permits.) Yet even this video prattles on about how carefully they’ve triple-checked the output… like the haters give a shit. They have a one-drop rule.
All that ultimately matters is, does it look good? And if you’re starting from a decent storyboard - it ought to. I dunno if AI’s gonna raise the ceiling for any creative work, but it should absolutely raise the floor for low-budget productions. If your style is not extreme camera angles and visible keyframes, this is the tech that will do a thousand hours of busywork in a couple minutes.
The trailer at the end of this blatantly has that AI vibe. Which is fine. CGI took ages to become invisible, and mostly got there by hiding what you’re not looking at.
For Lain specifically - I think they’d hew closer to the premise if they went all-in on generated video. Specifically, so they could produce unreasonable quantities of animation, and somehow deliver different versions to different viewers. Change the reason for common events. Change the outcome of things concluded offscreen. Change what really happened, behind a white lie someone tells later. Illustrate the modern problem of the Wired: a loss of shared reality. An epistemic crisis. We’re not disappearing into the network; the real world itself is trapped in hyperreality.
I don’t get it either, personally I don’t care. It will become funny though once AI can’t even be detected by the human eye anymore. They’ll be chasing ghosts, well at least until everybody is as used to AI as they are to regular CGI.
Like you said, AI is just a tool, who cares.
mindbleach@sh.itjust.works 1 week ago
If I had the right GPU, I’d be tempted to go back and use 2023-ass video generators to adapt an original story, just to demonstrate - no tool is immune to human expression. Of fucking course you can convey complex feelings despite visible constraints. Anyone going ‘well why didn’t you just animate it?’ is incorrect, in the same way as if they’d told an animator, ‘well why didn’t you just film it?’
I’ve worked cgi professionally since 1994 and unlike other artists I don’t feel treathened by AI, I embrace it, and I’ve been using AI myself too for years now. What people don’t realize is how much more productive artists can be using this tool. Thats all it is, a tool.
mindbleach@sh.itjust.works 1 week ago
Corridor Digital seems to get it. They’ve dorked with it to fill in for missing frames. They’re using it to relight flat greenscreen shots for their D&D… podcast? Anyway those relit shots look like PS3 cinematics, but they’re putting real dudes in real costumes inside a video game, basically in real time. Nitpicking the quality is missing the point. Getting all the shots they’re doing, but “properly,” would take ten times as long and cost a hundred times as much. It’s the same dudes putting in just as much work as the previous season. Anyone shouting ‘not art!’ doesn’t mean things when they say words.
The same dudes also used neural networks to fix greenscreen. They rendered a bunch of scenes with complex alpha blending, and built a neural network on that synthetic data. Unsurprisingly, the example-based universal approximator is pretty good at approximating from similar examples.