derRaab
RRunPod
•Created by derRaab on 1/4/2024 in #⚡｜serverless
qt.qpa.plugin error with sd-scripts/sdxl_gen_img.py
I implemented SDXL LoRa training similar to https://github.com/runpod-workers/worker-lora_trainer using https://github.com/kohya-ss/sd-scripts which seems to work fine now. So I figured it would be very simple to also use the provided https://github.com/kohya-ss/sd-scripts/blob/main/sdxl_gen_img.py script for image generation, but even a very basic call always results in this error and kills my worker:
qt.qpa.plugin: Could not load the Qt platform plugin "xcb" in "/usr/local/lib/python3.8/..." even though it was found.
qt.qpa.xcb: could not connect to display
I'm a total noob regarding these kind of issues, but I think that is related to the runpod environment itself? (because there is of course no display?)
Maybe one of you pros ran into this issue before and there is a obvious mistake I made. Or maybe you can smack the back of my head with an research idea? Many thanks in advance!
4 replies
RRunPod
•Created by derRaab on 12/22/2023 in #⚡｜serverless
accelerate launch best --num_cpu_threads_per_process value ?
Hi guys, I try to do some lora training on a serverless endpoint and I wonder how many cpu cores are available with the different GPU types? Is there a specification on that somewhere? And / or what do you use? My first tests ran on a single thread but would love to maximize performance. 🙂
6 replies