The game was in a pretty rough state when they relaunched it, but they have been slowly improving it a bit at a time (it often feels like 2 steps forward, 1 step back). I feel like the game is in a pretty good spot though. I enjoy it and am looking forward to season 4.
Headline talks about AI, article talks about algorithms. Chasing that click bait I see.
Well, hopefully this will at least force stability’s hand in some way and get them to at least make an official statement instead of just remaining silent.
Per the software website (which the article links to), I don’t see any mention of generative AI. Their “ai image intelligence” only makes mention of tagging images for SEO. https://www.pixometry.com/en/publishing/ai-image-intelligence/
It would be great if the model could produce this beautifully disfigured stuff when the user asked it to. But if it can’t follow the user’s prompts reasonably, then it’s pretty useless as a tool
It’s been a wait, but glad to see it finally out. Looking forward to playing with it later.
I’m addition to the other comment, I’ll add that just because you train the AI on good and correct sources of information, it still doesn’t necessarily mean that it will give you a correct answer all the time. It’s more likely, but not ensured.
I have no problem with developers continuing to create new content and give customers the option to buy it or not.
Loot boxes and gambling stuff and types of micro transactions where you are basically paying a fee to avoid artificial annoyance/grinding are a cancer on the industry.
Wtf, they just released stable cascade like a week ago. All they are doing is just confusing the users and model trainers. From the blog post it’s not even clear why I would want to use this one over the other one that they just released.
Looks interesting, but also somewhat complicated. Now generation has to run through 3 models? I thought it was bad enough having a separate refiner model for sdxl.
“AMD decided this year to discontinue funding the effort and not release it as any software product”.
So AMD decided that it wasn’t worthwhile and so the developer released it on his own. AMDs decisions are just baffling. You still can’t even install Pytorch for rocm on Windows.
I mean, they would have started appearing in there from the first moment that someone created one and hosted it somewhere, no? So it’s already been a thing for a couple years now, I believe.
Wow, this looks amazing!
I’m kind of mixed on this, because I think AI art is pretty cool, but I also hate our current copyright system. I kind of agree with the copyright office that images generated by a prompt should not be covered by copyright. What if I just type in “cat” and set the seed to 1, and try to copyright that? What if I copyright the image for EVERY seed with that prompt? Literally anyone else could easily generate the exact same image, and are they going to be in violation of my copyright now?
It gets really complicated though. What if I draw a sketch and then feed it into stable diffusion to flesh it out further? Then I do extensive inpainting across the whole thing, then I take it to Photoshop and do further edits. At this point, I think it’s fair to say this is an original image of my own creation, which should be eligible for copyright protection.
But according to the article, it wasn’t generated in minutes. The artist went through over 600 iterations of tweaking the prompt to get what he wanted. Sounds like days or even weeks of work probably. And then made additional tweaks via Photoshop.
Not too say that makes it any more impressive, but it wasn’t something that was without effort.
You can usually get past a lot of that stuff by just using the reader mode (button in the address bar)
Wow, L4sBot reposts the same story it already posted but from a different link.
This video is a really good explanation of why this is a horrible thing for the web.
Based on the post title, I was expecting some new revelation here, but it basically just explains everything that we already knew.
Is a diamagnetic semiconductor still a useful discovery, or do we already have those?
Looks like an exciting model. I am curious to see how it will be with finetunes and controlnets. Could potentially be better than sdxl. It does unfortunately appear to be a non commercial license though, which might limit interest.