Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Diffusion Bee: Stable Diffusion GUI App for M1 Mac

github.com

Post reply on HN
Print view View original

61–70 of 199 posts

Re: Diffusion Bee: Stable Diffusion GUI App for M1 Mac

#61

Post by Gigachad »

nextaccountic wrote: post #42
gpm wrote: post #27

Earlier quoted context omitted.

"Stable Diffusion" is referring to one specific set of models, which were trained on a dataset including some porn. The official implementation has a second model that detects pornography, and replaces outputs including it with a picture of this dude https://www.youtube.com/watch?v=dQw4w9WgXcQ (Not kidding). Removing that is a really simple a one line change in the official script.

I guess the question is whether this toggle is available in the GUI, or if someone has to edit source code

For the CLI version, there was no UI, you have to open the python file and stub out the NSFW check. (trivial though)

Re: Diffusion Bee: Stable Diffusion GUI App for M1 Mac

#63

Post by Gigachad »

firecall wrote: post #60
ShamelessC wrote: post #32

Earlier quoted context omitted.

Oh wow! Didn’t realize.

RAM might hold it back? Still, probably not too hard to build for iPad or iOS.

The ipad pro has a 16gb option. It's essentially the same hardware as the macbook.

Re: Diffusion Bee: Stable Diffusion GUI App for M1 Mac

#64

Post by wlesieutre »

ShamelessC wrote: post #32
wlesieutre wrote: post #13

Earlier quoted context omitted.

The Pro and Air models have M1 chips, roughly on par with a MacBook Air

Oh wow! Didn’t realize.

iPad Pro got it in spring 2021, so an M2 refresh seems likely too. October event along with an M2 MacBook Pro refresh? Or maybe not until spring 2023.

Another comment mentions RAM capabilities. Unfortunately that’s tied to the storage tiers instead of being something you can pick separately, so if you want 16 GB of RAM you have to buy the 1 TB or 2 TB models. Meaning for a 12.9” iPad Pro, if you want 16 GB you’re looking at an $1800 tablet. Not ideal.

Re: Diffusion Bee: Stable Diffusion GUI App for M1 Mac

#65

Post by hot_gril »

anothernewdude wrote: post #54
Mystery-Machine wrote: post #43

Earlier quoted context omitted.

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.

It's bad either way. Should be easy like npm.

Re: Diffusion Bee: Stable Diffusion GUI App for M1 Mac

#66

Post by chipotle_coyote »

anothernewdude wrote: post #54
Mystery-Machine wrote: post #43

Earlier quoted context omitted.

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.

I feel like I'm maybe missing some context here, because I've never had to install "conda Python" on any Mac ever. I had the system Python and a Homebrew-installed Python happily co-existing, and at various points have had "virtualized" Pythons installed via virtualenv or pipx. On Apple Silicon Macs there's no Python installed by default at all.

Now, I've seen an awful lot of programs written in Python that decide to force you to install them with virtualenv or pipx, but that's not Apple's doing.

Re: Diffusion Bee: Stable Diffusion GUI App for M1 Mac

#67

Post by aivoyeur »

chipotle_coyote wrote: post #66
anothernewdude wrote: post #54

Earlier quoted context omitted.

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.

I feel like I'm maybe missing some context here, because I've never had to install "conda Python" on any Mac ever. I had the system Python and a Homebrew-installed Python happily co-existing, and at various points have had "virtualized" Pythons installed via virtualenv or pipx. On Apple Silicon Macs there's no Python installed by default at all. Now, I've seen an awful lot of programs written in Python that decide to…

> On Apple Silicon Macs there's no Python installed by default at all.

Not true. There's no python2 anymore, but there is a python3. You can find it at /usr/bin/python3 (most likely your homebrew install preceeds it in your PATH)

Re: Diffusion Bee: Stable Diffusion GUI App for M1 Mac

#68

Post by ihateolives »

aivoyeur wrote: post #45

This really is a one-click installer, which is excellent. As far as I know it's the first and only one for M1. It's quite a polished UI, but there are a lot of features missing. The first ones that come to mind are: - No way to specify a seed. This is an important part of SD workflows, letting you redo an image with a slightly tweaked a prompt. - No way to specify a custom model. Alternative models (such as Waifu Dif…

> This really is a one-click installer, which is excellent. As far as I know it's the first and only one for M1.

There's https://www.charl-e.com/

Re: Diffusion Bee: Stable Diffusion GUI App for M1 Mac

#69

Post by aryamaan »

wfme wrote: post #51
indigodaddy wrote: post #19

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

Looking to buy a laptop (preferrably mac) to run such models now and for the upcoming years.

I should max out on the Mac gpus?

Re: Diffusion Bee: Stable Diffusion GUI App for M1 Mac

#70

Post by fragmede »

KaoruAoiShiho wrote: post #40
fragmede wrote: post #9

Earlier quoted context omitted.

Yes: https://nmkd.itch.io/t2i-gui No idea if it supports AMD GPUs though.

Do you have any info on perf compared to this: https://news.ycombinator.com/item?id=32805174

More optimization work has and is going into Nvidia support, so those are currently faster. Pytorch support for MPS devices is relatively new, so there's a ton of optimization that hasn't been done yet, so it's not clear which underlying hardware is actually faster for this specific task, but it looks like the top end Apple Silicon is in the same bracket as a consumer-grade Nvidia GPU.
Post reply on HN