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.
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.
It’s been a wait, but glad to see it finally out. Looking forward to playing with it later.
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.
Wow, this looks amazing!
So is this just a new stable diffusion gui? Any notable features, or does it just work the same as all the other ones?
Saw a clip of someone working with it on an rtx 3090. Image was updating multiple times per second, and looked pretty good quality.
Well shit, they finally released the thing he was talking about a year ago.
Always have to take what he says with a grain of salt. I remember last year when he said they were a few weeks away from releasing a model that was like 30x faster.
Been trying this with my local comfy installation. It’s a lot of fun! For some reason it tells me I don’t have control net installed, even though I installed the stuff listed on the GitHub page.
Now I need to try to learn to paint in krita a little better
What do you mean? I run the normal SDXL on 12gb vram.
I see the problem as, most people on Lemmy are already signed up to an instance that they are happy with. If the instance offers something to really differentiate itself, such as a focus on certain types of communities, or different types of rules or moderation than most other instances, then it might have a chance at catching on. But otherwise, I feel like it would be very hard to promote an instance if its 95% the same as all the other instances.
Yeah, this seems like such an odd claim, because all one has to do is go to Kbin.social and the downvote buttons are right there.
I’m not sure what you are referring to about a “bootleg”. The message seems to be saying that they have seen some really amazing new versions of the model in the past few days, and they need some more time to evaluate them, so they can make sure that 1.0 is the best model they can put forward.
I’m no stranger to node based workflows, but I have struggled to see how nodes are beneficial for stable diffusion. It just seems like a ton of extra steps to have to lay down like 10 nodes just to make a simple image, where other interfaces let me do the same thing a lot easier.
When you say it’s faster, are you referring to the workflow, or the actual generation? Do you see any other benefits from comfy?
Then for the next week your internal clock is messed up and you can’t actually fall asleep when you want to.
Learn some alphabets of foreign languages. Russian is fun because some of the characters looks like English letters but have completely different sounds. Korean is also cool because it looks crazy complex but it’s actually extremely simple.
Use it for a grilled cheese sandwich. Or just about any kind of sandwich.
This is the thing that most companies seem to obsess over these days: https://en.m.wikipedia.org/wiki/Net_promoter_score
I think it’s just a fad.
So there used to be this cartoon called Silverhawks, which was about these dudes who are partially made of metal and they can fly.
First dream I can remember, I was at the doctor and they wanted to give me a shot in my leg. I was really afraid of needles at the time, but suddenly I became a Silverhawk. The nurse was trying to stick the needle in my thigh, but my thigh was metal, so her plan was foiled.
You’re never going to get all Democrats to be satisfied with any candidate, ever. People are going to complain because they love complaining. That said, I think most people are probably fine with her.