cross-posted from: https://beehaw.org/post/28095114
Vapor World: Over The Mind is a Soulslike Metroidvania with an evocative, painterly art style reminiscent of Lies of P and the narrative platformers of Playdead. According to Korean studio Alive Inc, the game had 100,000 wishlists just before its early access launch on August 19, mostly on the strength of a demo available since January 2025.
But what should have been a triumphant early access launch went pear shaped very quickly. At launch, few talked about the quite distinctive worldbuilding or the parry-heavy combat. Instead, all focus was trained entirely on something absent from the popular demo: very obvious AI use.
The problem is that there is no way of knowing (at first sight) if there was an earnest attempt. AI has a certain look to it, and that look has been associated with slop and shortcuts because of unbridled use of an imperfect technology. It makes sense that it would illicit a sense of revulsion. Also, people who lack the skills or time necessary to create a certain type of art are more likely to lack the ability or patience to properly judge the quality of that art. “Good enough” is rarely good enough.
I think this is a dangerous misconception.
I could feed locally run Minimax H3 a set of reference art, like the painted stills from this game, and it would exactly match the style. I could use start/end frames, motion masks, pose control, character sheets, voice and music samples, reference videos; I can get it to do whatever I want with extreme precision, and as long as I checked the output it would be indistinguishable from CGI.
The point I’m making is that a lot of people percieve diffusion as mashing a Stable Diffusion keyword prompt into a text box, and getting a sloppy result. Maybe thats still how shit corporate services like ChatGPT work.
But a LOT has changed over two years.
Theres no way people can definitively detect generative output anymore. We can IF its done lazily, but its quite possibly indistinguishable now, too.
Even two years ago, I remember someone telling me they saw a YouTube video that said you could always tell an AI generated image because their noise map would be the same in R, G, and B. And I tried to explain to this person that that depends entirely on how the image was generated, on what platform, by what model and method, what post-processing was done, etc.
And I was told I was ignoring their evidence. 🙄
Also… you could just add grain via post processing?
Its actually a reasonable technique, as it softens diffusion blocking artifacts the same way it softens video codec blocking artifacts.
The YouTuber sorta kinda has a point, depending on the context. Spammers tend to use the absolute laziest lowest common denomenator, so its quite possible theyre largely using the same model, with the same artifacts, and not bothering to edit output. So maybe they did have a common noise pattern? Though the way thats presented still sounds fishy to me.
I think the idea was that within an image the noise in red would match the noise in green and the noise in blue, because whatever system they were looking at picked a single noise map per image? Something like that. And yeah, it was reasonable because it was absolutely true of the laziest stuff out there (which is most AI stuff, which is why we use the word “slop”). But my counter-argument wasn’t that the method couldn’t work, it was that it couldn’t always work. Because image generation is done in thousands of different ways and post-processing exists.
The thing that I wish was better understood is that “slop” = “low effort.” Artists can make some pretty amazing stuff when AI is merely a part of their toolset and they still put effort into their work. But that means that not all AI is slop, and thus if you really want to detect AI, you can’t rely on it always being slop.
That is called luma noise, yes. Heh. Its nothing new.
Yes! I would wear this on my forehead on Lemmy, if I could.