How long is the generation taking on say a 2021 MacBook M1 Pro?
And another datapoint, my M1 Max (24 core gpu) with 64GB RAM takes:
~36s for 50 steps
~19s for 25 steps
Diffusion Bee: Stable Diffusion GUI App for M1 Mac
51–60 of 199 posts
Re: Diffusion Bee: Stable Diffusion GUI App for M1 Mac
#52Re: Diffusion Bee: Stable Diffusion GUI App for M1 Mac
#53For those of you following the lstein fork (especially the development branch), it has been making great progress. I'm not getting black images anymore and the speed has gone up significantly.
Not one click install by a long shot, but the documentation is pretty clear to follow. Anyone with a bit of CLI experience can do it and if you don't have that, this is a great way to kind of stumble your way towards something working and learn in the process...
https://github.com/lstein/stable-diffusion/tree/development/...
Re: Diffusion Bee: Stable Diffusion GUI App for M1 Mac
#54I can confirm that this works great on the M1 Max. It has been taking less than a minute to run the model and generate the images. So far I have been really satisfied with the output. Let's please make one-click installers the norm for future technology. I love nerding out, but wading through dependency hell is not worth it most of the time.
You're right. On top of that, python dependency / package management is a joke.
Normally it's fine, but Apple have decided to force everyone into installing a conda python alongside normal python, which makes everything way more complicated than it needs to be.
Re: Diffusion Bee: Stable Diffusion GUI App for M1 Mac
#55Nice one. Too bad "image to image" is not available, as that's the one I'd like to experiment with the most.
Re: Diffusion Bee: Stable Diffusion GUI App for M1 Mac
#56Does anyone have something for the Intel Macs?
Re: Diffusion Bee: Stable Diffusion GUI App for M1 Mac
#57Earlier quoted context omitted.
And the real questions come out. Seriously though, I imagine this is less a case of whether this specific implementation permits pornography, but whether any porn was included in the dataset it was trained on. No matter how good AI is, it only knows what it knows.
I mean I don't know why we have to talk around this point: yes, you can definitely generate pornography with SD. Be prepared to see a lot of weird things, because that super-realism really means it just drives right into the uncanny/body horror valley at full speed. But the second point here is also wrong: the whole reason these models are interesting is because they can generate things they haven't seen before - the…
>it can generate porn
It's not good at penises or vaginas, just breasts and butts. I can find what I like pornographically without ai. But the ducking and dodging around nudity and sexuality is childish and tiresome and we ought to discuss this topic as disinterestedly and nonchalantly as we do the other things it excels or struggles at. Penises and vaginas are not somehow more vile than other things.
Sure enough, sexual content ought to be age-gated and there is potential for abuse (slapping a person's face onto explicit imagery without their consent isn't cool yall). But are we working toward AGI or not? Because at some point it's gonna have to know about the birds and the bees.
Re: Diffusion Bee: Stable Diffusion GUI App for M1 Mac
#58Has anyone looked at the code and verified the statements in the readme?
Ran it with Little Snitch installed (why bother looking at the code when a malicious actor can just upload a modified binary anyway?) and the claims seem to be legit so far.
Re: Diffusion Bee: Stable Diffusion GUI App for M1 Mac
#59Earlier quoted context omitted.
And the real questions come out. Seriously though, I imagine this is less a case of whether this specific implementation permits pornography, but whether any porn was included in the dataset it was trained on. No matter how good AI is, it only knows what it knows.
I mean I don't know why we have to talk around this point: yes, you can definitely generate pornography with SD. Be prepared to see a lot of weird things, because that super-realism really means it just drives right into the uncanny/body horror valley at full speed. But the second point here is also wrong: the whole reason these models are interesting is because they can generate things they haven't seen before - the…
> But the second point here is also wrong: the whole reason these models are interesting is because they can generate things they haven't seen before
No, it's essentially generating mashups of its training data, which can be very interesting.
So a model that hasn't been trained on a lot of porn will of course do a very bad job at generating porn.