![](/static/253f0d9b/assets/icons/icon-96x96.png)
![](https://fry.gs/pictrs/image/c6832070-8625-4688-b9e5-5d519541e092.png)
Same. Guess I won’t bother looking into it if it’s impossible 🤷♀️
Same. Guess I won’t bother looking into it if it’s impossible 🤷♀️
R
i
s
e
A
n
d
S
h
i
n
e
,
M
r
.
F
r
e
e
m
a
n
Ooooh I thought the ratio in question was upvote to downvote lol. The part about mods went over my head.
I don’t get it
Sort of, but no. They’re transparent because of the frame blending. Since moving objects/characters occupy different parts of the foreground across multiple frames, the background ends up getting blended into them. They call that “ghosting” because it effectively makes them transparent.
So they do lose opacity, but it’s not like they’re lowering an opacity value or anything.
It’s an anti-seizure measure. Which makes sense for TV where kids might come across it by accident, but it doesn’t make sense for streaming services where we could easily opt in/out of those versions.
Edit: This is what it looks like, compared to Blu-ray. They dim the whole screen and blend multiple frames together, which makes it hard to decipher what’s going on and mutes the colors. (Another):
My story but with anime. Japan has some really annoying laws requiring their shows to be blurred and dimmed during fast-paced scenes and it absolutely butchers the height of good animations.
The Blu-ray releases don’t have this issue, but guess what releases aren’t available for purchase/streaming for English audiences. 🫠 I want to give them money so bad, but 🤷♀️
Qe1#
I use premium and even I cringed at this. The first two thirds of this are written like an AI generated ad.
I get the sentiment but I don’t think anything here addresses anything I haven’t already mentioned. The labor is certainly being used and it’s certainly for profit, but not in any way that humans don’t already do.
I really am sympathetic towards artists, though. Like I get that a lot of demand for their work could one day be taken by what generative AI is working towards. I just don’t understand how we can reasonably call it theft/crime when a computer figures out how to make an image by looking at other images but not when humans do it. The whole thing seems like an appeal to emotion.
Rizz
The lack of neurotoxin is disturbing
Honestly I still don’t understand the “stealing” argument. Does the stealing occur during training? From everything I’ve learned about the technology, the training, in terms of the data given and the end result, isn’t any different than me scrolling through Google images to get a concept of how to draw something. It’s not like they have a copy of the whole Internet on their servers to make it work.
Does it occur during the image generation? Because try as I might, I’ve never been able to get it to output copyrighted material. I know over fitting used to be an issue, but we figured out how to solve that issue a long time ago. “But the signatures!!” yeah, it’s never outputted a recognizable/legible signature, it just associates signatures with art.
Shouldn’t art theft be judged like any other copyright matter? It doesn’t matter how it was created, it matters if it violates fair use. I really don’t think training crosses that line, and I’ve yet to see these models output a copy of another image outside of image-to-image models.
Where I live, the taste has that sort of La Croix thing going on where it tastes like the bottle sat open adjacent to a sewer. Smells alright, but when I taste it it makes me ಠ_ಠ
That’s it, you’re going in the dungeon
You when billion dollar companies want to literally shove more ads in your face:
It’s when you suck oligarch cock
Wouldn’t that be long term memory loss