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

Run Stable Diffusion on Your M1 Mac’s GPU

replicate.com

Post reply on HN
Print view View original

111–120 of 415 posts

Re: Run Stable Diffusion on Your M1 Mac’s GPU

#111

Post by valley_guy_12 »

gzer0 wrote: post #103

The difference between an M2 air (8gb/512gb) versus an M1 pro (16gb/1tb) is much more than I expected. * M1 pro (16gb/1tb) can run the model in around 3 minutes. * M2 air (8gb/512gb) takes ~60 minutes for the same model. I knew there would be some throttling due to the m2 air's fanless model, but I had no idea it would be a 20x difference (albeit, the m1 pro does have double the RAM. I don't have any other macbooks t…

That's probably due to swapping due to the 8GB of RAM. People who have run Stable Diffusion on M2 airs with 16 GB of RAM seem to get performance that is in line with their GPU core count.

Re: Run Stable Diffusion on Your M1 Mac’s GPU

#112

Post by pwinnski »

hbn wrote: post #84
antihero wrote: post #75

Earlier quoted context omitted.

On an M1 Pro 16GB it is taking a couple minutes for each image.

Is that the difference in graphics performance between the M1 and M1 Pro or did the other person do something wrong? 70-90 minutes seems nuts

I have the M1 8GB I mentioned in my first comment, and the M1 Pro 16GB I mentioned in my second component, side-by-side. However, the first one was running a Stable Diffusion branch from earlier in the week, so I replaced using the same instructions. The only difference now is the physical hardware.

The thing to understand is that the 8GB M1 has 8GB. When I run txt2img.py, my Activity Monitor shows a Python process with 9.42GB of memory, and the "Memory Pressure" graph spends time in the red zone as the machine is swapping. While the 16GB M1 Pro immediately shows PLMS Sampler progress, and consistently spends around 3 seconds per iteration (e.g. "3.29s/it" and "2.97s/it"), the 8GB M1 takes several minutes before it jumps from 0% to 2% progress, and it accurately reports "326.24s/it"

So yes, whether it's M1 vs M1 Pro, or 8GB vs 16GB, it really is that stark a difference.

Update: after the second iteration it is 208.44s/it, so it is speeding up. It should drop to less than 120s/it before it finishes, if it runs as quickly as my previous install. And yes, 186.04s/it after the third iteration, and 159.22s/it after the fourth.

Re: Run Stable Diffusion on Your M1 Mac’s GPU

#113

Post by neurostimulant »

dougmwne wrote: post #34
scoopertrooper wrote: post #27

Earlier quoted context omitted.

They've got death robots that can fly now. Why is nobody impressed by the future?

I believe those are human controlled, no? Robotics gets really interesting when the robots can start driving and building the roads as well.

Not necessarily. Some just require human to turn it on and it'll loiter and attack enemy autonomously (loitering munition [1]).

[1] https://en.wikipedia.org/wiki/Loitering_munition

Re: Run Stable Diffusion on Your M1 Mac’s GPU

#114

Post by squeaky-clean »

r3trohack3r wrote: post #30

I've been playing with Stable Diffusion a lot the past few days on a Dell R620 CPU (24 cores, 96 GB of RAM). With a little fiddling (not knowing any python or anything about machine learning) I was able to get img2img.py working by simply comparing that script to the txt2img.py CPU patch. Was only a few lines of tweaking. img2img takes ~2 minutes to generate an image with 1 sample and 50 iterations, txt2img takes abo…

> You wouldn't know that steps 10 and steps 15 came from the same seed/sample they change so much.

I don't think this is CPU specific, this happens at these very low number of samples, even on the GPU. Most guides recommend starting with 45 steps as a useful minimum for quickly trialing prompt and setting changes, and then increasing that number once you've found values you like for your prompt and other parameters.

I've also noticed another big change sometimes happens between 70-90 steps. It's not all the time and it doesn't drastically change your image, but orientations may get rotated, colors will change, the background may change completely.

> img2img takes ~2 minutes to generate an image with 1 sample and 50 iterations

If you check the console logs you'll notice img2img doesn't actually run the real number of steps. It's number of steps multiplied by the Denoising Strength factor. So with a denoising strength of 0.5 and 50 steps, you're actually running 25 steps.

Later edit: Oh and if you do end up liking an image from step 10 or whatever, but iterating further completely changes the image, one thing you can do is save your output at 10 steps, and use that as your base image for the img2img script to do further work.

Re: Run Stable Diffusion on Your M1 Mac’s GPU

#115

Post by JimmyAustin »

gzer0 wrote: post #103

The difference between an M2 air (8gb/512gb) versus an M1 pro (16gb/1tb) is much more than I expected. * M1 pro (16gb/1tb) can run the model in around 3 minutes. * M2 air (8gb/512gb) takes ~60 minutes for the same model. I knew there would be some throttling due to the m2 air's fanless model, but I had no idea it would be a 20x difference (albeit, the m1 pro does have double the RAM. I don't have any other macbooks t…

I suspect that the M2 air is thrashing the disk pretty aggressively. Diffusion models rerun the same model once per step, so for a generation with 50 steps, you copy the entire model in and out of memory 50 times. That's going to kill performance.

Re: Run Stable Diffusion on Your M1 Mac’s GPU

#116

Post by valley_guy_12 »

dgreensp wrote: post #80

I'm working on getting this running. Instead of "venv/bin/activate" I had to run "source venv/bin/activate". And I got an error installing the requirements, fixed by running "pip install pyyaml" as a separate command.

Having to use "source" means you have an older version of conda. Python package management is kind of a mess.

Re: Run Stable Diffusion on Your M1 Mac’s GPU

#117

Post by bm-rf »

gzer0 wrote: post #103

The difference between an M2 air (8gb/512gb) versus an M1 pro (16gb/1tb) is much more than I expected. * M1 pro (16gb/1tb) can run the model in around 3 minutes. * M2 air (8gb/512gb) takes ~60 minutes for the same model. I knew there would be some throttling due to the m2 air's fanless model, but I had no idea it would be a 20x difference (albeit, the m1 pro does have double the RAM. I don't have any other macbooks t…

just water cool it! https://www.youtube.com/watch?v=9DyUitTVWlw

Re: Run Stable Diffusion on Your M1 Mac’s GPU

#119

Post by moneycantbuy »

Anyone know the largest possible image size > 512x512? I'm getting the following error when trying 1024x1024 with 64 GB RAM on M1 MAX:

/opt/homebrew/Cellar/python@3.10/3.10.6_2/Frameworks/Python.framework/Versions/3.10/lib/python3.10/multiprocessing/resource_tracker.py:224: UserWarning: resource_tracker: There appear to be 1 leaked semaphore objects to clean up at shutdown warnings.warn('resource_tracker: There appear to be %d '

Re: Run Stable Diffusion on Your M1 Mac’s GPU

#120

Post by fassssst »

andybak wrote: post #110
gzer0 wrote: post #103

The difference between an M2 air (8gb/512gb) versus an M1 pro (16gb/1tb) is much more than I expected. * M1 pro (16gb/1tb) can run the model in around 3 minutes. * M2 air (8gb/512gb) takes ~60 minutes for the same model. I knew there would be some throttling due to the m2 air's fanless model, but I had no idea it would be a 20x difference (albeit, the m1 pro does have double the RAM. I don't have any other macbooks t…

Unscientifically that puts the M1 Pro GPU at about 25% of the performance of a RTX 3080. Not too shabby... EDIT - this comment implies it's much faster: https://news.ycombinator.com/item?id=32679518 If that's correct then it's close to matching my 3080 (mobile).

img2img runs in 6 seconds on my GeForce 3080 12 GB. 6+ it\s depending on how much GPU memory is available. If I have any electron apps running it slows down dramatically.
Post reply on HN