I’d add that “requirement” is relative. My city’s bus system has stops near enough to cover my home and work, so you could say a car is not required for the route. However, using the bus system would turn my 20 minute (10 minutes one way) daily commute into 3 hours. That’s just too impractical to consider.
Yeah, it’s actually been kind of a relief to have fewer new games to look forward to every year. I have a backlog of something like 700 unplayed games already in my library. I know I’m not going to play them all as much as they deserve before I die, but being able to make a much bigger dent in them is nice.
Mostly agreed. For me the actual biggest problem here is Nvidia presenting this as the assumed default experience everyone obviously wants and using a heavily genericized face as a win. The tech needs to be much more energy efficient and configurable on both the developer and end-user side before I’ll give it any serious attention.
Regarding future versions of this tech, I think “death of the author” still applies to video games, so changing artistic intent isn’t always bad, especially for games that get frequently replayed. I certainly don’t play stock Skyrim or Minecraft anymore. To use your example, yes, a photorealistic (attempt of) Ocarina of Time would probably be too off-putting, but give me style options like BotW, Spiderverse, Pixar, anime, etc.? I’d be down to try those.
So, I actually like generative AI (disclaimer I feel I have to include every time: local open models only), and my main problem with that image is how genericized the new face is. If you’ve seen a lot of AI images, it’s immediately recognizable as the default mixed Asian/Caucasian face you get when not prompting something more specific than “woman” due to the datasets dominating the training data. It heavily implies all faces will be similarly genericized.
I don’t think this tech will be viable unless creators can give the AI a reference image of what a character should look like when photorealistic, and that’s just going to increase the workload of running this in realtime.
I’m not OP, but thanks for spelling that out. I guess I must have seen a bunch of tech stuff from that instance starting out. I was under the impression it was started by Machine Learning enthusiasts. Lol.