Earlier quoted context omitted.
> Politics will be influenced. You can't trust anything you see anymore I've been wondering for a while now if this will lead to an unexpected boon: perhaps people will be forced to pay attention to a speaker's content instead of simply who is speaking.
The problem with this is that you will never know who is actually speaking. Deep fakes are already a thing, but as they get better and more accessible we will approach a world where anyone can make anyone say anything and make it hyper believable. In that world, it will be very difficult to tell what is real.
Stable Diffusion Public Release
131–140 of 437 posts
Re: Stable Diffusion Public Release
#132Re: Stable Diffusion Public Release
#133> You can join our dedicated community for Stable Diffusion here: [ https://discord.gg/stablediffusion ] Oh, discord... I've had so many problems trying to log into discord in the last couple of years that I've given up on it.
Re: Stable Diffusion Public Release
#134This release changes society forever. Free and open access to generate a hyper-realistic image via just a text prompt is more powerful than I think we can imagine currently. Art, media, politics, conspiracy theories; all of it changes with this.
Eh... if I was making conspiracy theories, it's not like Photoshop hasn't existed for decades already, with far more predictable results.
Everyone just got their own KGB art department.
Re: Stable Diffusion Public Release
#135Earlier quoted context omitted.
Human works are needed to create the initial datasets, but an increasing amount of models use generative feedback loops to create more training data. This layer can easily introduce novel styles and concepts without further human input. The time is coming where we will need to, as patrons, reevaluate our relationships with art. I fear art is returning to a patronage model, at least for now, as certainly an industry w…
Why would people want to consume art that says nothing and means nothing? While this technology is fascinating, it produces the visual equivalent of muzak, and will continue to do so in perpetuity without the ability to reason.
Re: Stable Diffusion Public Release
#136Earlier quoted context omitted.
If I’m willing to buy a computer, any pointers on what I would have to buy? I’m asking for specific models from a company like Dell, Apple, or Lenovo?
You'll need a GPU. One with a LOT of RAM, like an RTX 3090, which has 24 GB.
Re: Stable Diffusion Public Release
#137DALL-E 2 just got smoked. Anyone with a graphics card isn't going to pay to generate images, or have their prompts blocked because of the overly aggressive anti-abuse filter, or have to put up with the DALL-E 2 "signature" in the corner. It makes me wonder how OpenAI is going to work around this because this makes DALL-E 2 a very uncompetitive proposition. Except, of course, for people without graphics cards, but it'…
Even though DALL-E tends to be better at following prompt details, you're inhibited from being able to explore the space freely because of how prohibitively expensive it can become.
Re: Stable Diffusion Public Release
#138If you want to try it out this seems to be the best tool for doing so: https://beta.dreamstudio.ai/
I just tried it via this link. I'm not sure what I'm looking at here but the results were extremely underwhelming. I've used Dall E 2 and Midjourney extensively so I know what they're capable of. Maybe I'm missing something?
Re: Stable Diffusion Public Release
#139Earlier quoted context omitted.
Why would people want to consume art that says nothing and means nothing? While this technology is fascinating, it produces the visual equivalent of muzak, and will continue to do so in perpetuity without the ability to reason.
Marvel Studios makes billions of dollars every year
Re: Stable Diffusion Public Release
#140Just tried it, the results seem pretty poor, about on par with Craiyon/DALL-E Mini. I don't think OpenAI should be worried quite yet.
There's plenty of cases it's worse than Dall-E and there's plenty of cases where it's better. Overall it seems to show less semantic understanding but it handles many stylistic suggestions much better. It's definitely in the right ballpark.
In fact I'm still using a wide range of models - many of which aren't regarded as "state of the art" any more - but they have qualities that are unique and often desireable.