91–100 of 141 posts
Earlier quoted context omitted.
It's not possible to halve the precision further. The precision was already dropped from float32 to float16 in the OP. I now used parameters to drop the resolution to 256x256, and now it's running, but it's somehow broken. Every output image it produces is literally a green square.
You need to be in full precision mode in that case. Running on my AMD card this was necessary.
Earlier quoted context omitted.
> I feel like I'm going insane. That's the world of running machine learning models for you. Why would anything ever work the first time right? Or at least the 10th time...
Which is so silly since ML models should be the most portable thing in the world. It's just a series of math operations, not a bunch of OS/hardware specific API calls or something like that. We should be at a stage where each ML model is boiled down to a simple executable with zero dependencies at this point.
But one of the tricky parts with stable diffusion is that people are trying to get it to run on lighter hardware, which is basically another engineering problem where simple apis typically won't expose the kind of internals people want to mess around with.
I started out using my old GTX 1080 on Thursday, could generate 512x512 just fine. That's in 8G of VRAM. It worked well on the hlky branch using webui (built using gradio). Seeing that training etc. is much more memory intensive, and wanting to get faster results, I bought an RTX 3090, which has 24G of VRAM. However it maxes out at about 1024x512, only twice as many pixels. Observing the card with GPUZ, it never actu…
Earlier quoted context omitted.
Recommendations: - Linux w/ Display drivers on CPU (and just...ditch miniconda please) - Use lower FP precision mode if available to use the tensor cores (also to double "effective" memory) - Batch things! - I don't know what the max resolution of the diffusion network is, you may have to just simply tile it past a certain point (with overlap please! ;P Hope that helps somewhat. A 3090 should be more than enough for…
I ordered an NVIDIA Tesla K80 off eBay (and the power adapter... and the blower fan shroud, etc.) and intend to install it when it arrives around Thursday or Friday. I'm hoping that after I install the NVIDIA Linux datacenter drivers I'll be able to use the card with SD. My only worry is that because the K80 is two GPUs on one board, that it might only utilize one of them, with only 12 GB of VRAM instead of both chip…
Craft Computing on Youtube has the best information from what I have seen so far. I don't like watching Youtube videos for information like this, but I understand why creators have moved to this medium in general. Linux should be much easier to configure for using the K80 to capacity.
I started out using my old GTX 1080 on Thursday, could generate 512x512 just fine. That's in 8G of VRAM. It worked well on the hlky branch using webui (built using gradio). Seeing that training etc. is much more memory intensive, and wanting to get faster results, I bought an RTX 3090, which has 24G of VRAM. However it maxes out at about 1024x512, only twice as many pixels. Observing the card with GPUZ, it never actu…
Recommendations: - Linux w/ Display drivers on CPU (and just...ditch miniconda please) - Use lower FP precision mode if available to use the tensor cores (also to double "effective" memory) - Batch things! - I don't know what the max resolution of the diffusion network is, you may have to just simply tile it past a certain point (with overlap please! ;P Hope that helps somewhat. A 3090 should be more than enough for…
The issues with f*ng console commands is that they fail, too often. After installing CUDA 11.7 and reinstalling torch I'm still facing: > AssertionError: Torch not compiled with CUDA enabled
Earlier quoted context omitted.
Google is paying, and yes, you can, but they will disconnect you after a while. And if you abuse it too much, you won't be able to use it until the following day... You can also buy Colab Pro and Colab Pro+, which have fewer limitations and faster GPUs.
How fast is the Colab stuff? Is Colab Pro/Pro+ a lot faster too? I run it locally and can generate images with 50 steps in about 6 seconds per image, would it be faster for me to use Colab Free/Pro/Pro+?
I don't use anaconda so I created a new venv with python 3.10, installed the requirements as proposed, registered with hugging face and create the api key and run the provided source code.
Any way to improve the quality of the faces? Also how could I tune the parameters a bit ? (I'm not familiar with this AI stuff at all, I'm just a humble python programmer)