I run it locally. I prefer having the most control I can over the install, what extensions I want to use, etc.
The most important thing to run it in my opinion is VRAM. The more the better, as much as you can get.
this post was submitted on 23 Jul 2023
11 points (100.0% liked)
Stable Diffusion
1487 readers
1 users here now
Welcome to the Stable Diffusion community, dedicated to the exploration and discussion of the open source deep learning model known as Stable Diffusion.
Introduced in 2022, Stable Diffusion uses a latent diffusion model to generate detailed images based on text descriptions and can also be applied to other tasks such as inpainting, outpainting, and generating image-to-image translations guided by text prompts. The model was developed by the startup Stability AI, in collaboration with a number of academic researchers and non-profit organizations, marking a significant shift from previous proprietary models that were accessible only via cloud services.
founded 1 year ago
MODERATORS
I run locally too. I have a 10gb 3080.
I haven’t had vram issues could you elaborate on your statement?
I know on local llama I have been limited to 13b models
Stable Diffusion loves VRAM. The larger and more complex the images you're trying to produce, the more it'll eat.
My line of thinking is that if you have a slower GPU it'll generate slower, sure, but if you run out of VRAM it'll straight up fail and shout at you.
I'm not an expert in this field though, so grain of salt, YMMV, all that.
I know on local llama I have been limited to 13b models
You can run llama.cpp on the CPU with reasonable speeds making full use of normal RAM to run much larger models.
As for 10GB in SD, I run into lack of VRAM quite constantly when overdoing it, e.g. 1024x768 with multiple ControlNets and some other stuff is pretty much guaranteed to overflow it. I have to reduce the resolution when making use of ControlNet. Dreambooth training didn't even work at all for me due to lack of VRAM (might be possible to work around, but at least the defaults weren't usable).
10GB is still very much usable with SD, but one has to be aware of the limitations. The new SDXL will also increase the VRAM requirements a good bit.
Runs fine with 1660, but that is about 20 sec for 512x512 and upscaling takes upwards of a minute.
If you want to run it online I suggest paperspace paid tier, not too big of a hassle to set up but you might have to wait a couple mins spamming refresh to get a better GPU, the instance can run for 6 hours, then it will be autoshutdown. Generally 2-4sec for 512 and 10-20 for 1024. Also, you will have to either download models every time, settle for only two or three models at a time or fork up a couple extra bucks for the permanent storage as base paid is only 15GB.
Locally with automatic1111, I'd say 10GB VRAM as a starting point to have a good experience (can do up to 1024x768 in a single go or a little less when ControlNet is involved). Though one can never have enough VRAM, when buying a new card I'd aim for 16GB VRAM to have some spare room for future models. Image generation takes about ~30sec. Upscaling is possible, but can take quite a while and results can be a bit hit and miss.
The plain StableDiffusion model is largely useless these days, go over to https://civitai.com/ and download something custom trained, they give far better results. ControlNet is another absolute must have and gives a lot of control over the resulting image (pose, 3d shape, sketch), along with a far superior inpainting, compared to img2img.
I have been playing around with SD for about half a year and it still blows my mind what kind of results you can get with rather minuscule effort. Though worth mentioning that the results are largely dictated by the AI, trying to get very specific results can be an absolute nightmare.
locally, always.
I even got it to run without GPU on a pure old i5 CPU with 8GB system RAM (not VRAM) paired with 32GB swap. SD1.5 takes 4-10 minutes per image, SDXL about 2 hours. But it works. With GPU its between 7 and 90 seconds per image, depending on model and settings.
What were your settings for the CPU usage? I have an older laptop it would be fun to get it running on.
Just install ComfyUI and start it with the --cpu flag. Ensure you have enough system RAM and a swap partition (preferably on nvme/ssd).
How did you get to use regular ram?
I run it locally with an 11gb 1080 TI. It's just exposed on the local network, so I still use the main SD website if I'm out and about somewhere.
I have it running on my M2 MacBook Air (16gb RAM)
I run it locally. I have a CPU from 2009. All you need is a good GPU.
I am running it locally with a 3060 TI and it works decently well.