cooperdk

Results 108 comments of cooperdk

Well once again, SD is based on torch (and similar modules) which is a CUDA module. Therefore, you're only guaranteed for this to work with a CUDA-enabled GPU (nVidia). It...

What os do you use? Also, why do you use Docker for something like this? I guarantee that will give you issues due to indirect access to the GPU. If...

> @cooperdk There are lots of reasons to run in docker because of SDW dependencies. At least on Linux, getting them passed through to docker isn't bad. From what I...

> I'm not disagreeing with your feature request here, it's a good idea, but it's not relevant to the issue of mine that you linked. In some ways it is,...

I doubt that you're able to train much with a 6 GB card. One of the reasons why I just bought a 3060 OC 12 GB.

> I did a lot TI with my 1070 but on sd1 U rly dont need more than 4-5 pics, so training is fast even on 1xxx cards According to...

Using this software on an ARM-based mac is going to give you trouble, guaranteed. Not only is the newer Macs ARM-based (RISC which is most often used in network attached...

It is: trouble with the available compiled modules for Python. AI specific modules that are made to work on nVidia hardware which Apple no longer uses af they were thrown...

> then why didn't I have this issue with this software before it integrated support for SD 2.0? > > why don't I have this problem with any other implementation...

I have read that's how it is on Mac. You need a lot of ram. Probably twice is good. It loads everything in ram and swaps nothing to the gpu....