You kill way too many birds with such a stone. Of course you could never do any kind of photorealistic game in real time if you had to pre-screen everything with an actually effective censor.
Indeed, what they're already doing is already hobbling the models.
Emad is right that we learn new things from the creativity unleashed by accessible models that can be run (and even fine tuned) or consumer hardware.
But judging from what people post, one thing we learn is that it seems models fine tuned on porn (such as the notorious f222 and its derivative Hassan's blend) can be quite a bit better at non-porn generation of diverse, photorealistic faces and hands too.
> Of course you could never do any kind of photorealistic game in real time if you had to pre-screen everything with an actually effective censor.
I'm not sure I understand this. A possible implementation could be a neural net that blanked the screen with a frown face any time it detected something it thinks was "bad". What purpose/need would pre-screening serve?
That you describe IS pre-screening. And it's not workable, because it would take a ton of dedicated resources to make it work in real time, and even then it would be disastrous for latency, unworkable for most games and even desktop applications.
I think this is making the assumption that all frames are blocked.
> then it would be disastrous for latency
We're talking about the future here. I'm not sure it makes sense to use current tech to say it's not going to happen, or come up with latency numbers. But, "real time" inference is definitely a possibility, and is in active use for video moderation (Youtube, etc) and object detection (Tesla, etc). Nobody will notice a system running at 2000fps.
