Config for running Automatic1111 Stable Diffusion WebUI on an AWS SageMaker Notebook

StableDiffusionUI_SageMaker.ipynb

I am also getting an error this one
Saving ngrok auth token to ~/.ngrok_token
/home/studio-lab-user/SageMaker/stable-diffusion-webui
fatal: No names found, cannot describe anything.
Python 3.9.0 | packaged by conda-forge | (default, Oct 14 2020, 22:59:50)
[GCC 7.5.0]
Version: 1.6.1
Commit hash: 4afaaf8a020c1df457bcf7250cb1c7f609699fa7
Cloning Stable Diffusion into /home/studio-lab-user/SageMaker/stable-diffusion-webui/repositories/stable-diffusion-stability-ai...
Cloning into '/home/studio-lab-user/SageMaker/stable-diffusion-webui/repositories/stable-diffusion-stability-ai'...
remote: Enumerating objects: 580, done.
remote: Counting objects: 100% (580/580), done.
remote: Compressing objects: 100% (284/284), done.
remote: Total 580 (delta 281), reused 492 (delta 275), pack-reused 0
Receiving objects: 100% (580/580), 73.43 MiB | 49.15 MiB/s, done.
Resolving deltas: 100% (281/281), done.
Cloning Stable Diffusion XL into /home/studio-lab-user/SageMaker/stable-diffusion-webui/repositories/generative-models...
Cloning into '/home/studio-lab-user/SageMaker/stable-diffusion-webui/repositories/generative-models'...
remote: Enumerating objects: 740, done.
remote: Counting objects: 100% (383/383), done.
remote: Compressing objects: 100% (145/145), done.
remote: Total 740 (delta 301), reused 238 (delta 238), pack-reused 357
Receiving objects: 100% (740/740), 22.31 MiB | 27.46 MiB/s, done.
Resolving deltas: 100% (377/377), done.
Cloning K-diffusion into /home/studio-lab-user/SageMaker/stable-diffusion-webui/repositories/k-diffusion...
Cloning into '/home/studio-lab-user/SageMaker/stable-diffusion-webui/repositories/k-diffusion'...
remote: Enumerating objects: 1323, done.
remote: Counting objects: 100% (605/605), done.
remote: Compressing objects: 100% (76/76), done.
remote: Total 1323 (delta 565), reused 535 (delta 529), pack-reused 718
Receiving objects: 100% (1323/1323), 237.11 KiB | 3.34 MiB/s, done.
Resolving deltas: 100% (928/928), done.
Cloning CodeFormer into /home/studio-lab-user/SageMaker/stable-diffusion-webui/repositories/CodeFormer...
Cloning into '/home/studio-lab-user/SageMaker/stable-diffusion-webui/repositories/CodeFormer'...
remote: Enumerating objects: 594, done.
remote: Counting objects: 100% (245/245), done.
remote: Compressing objects: 100% (90/90), done.
remote: Total 594 (delta 176), reused 170 (delta 155), pack-reused 349
Receiving objects: 100% (594/594), 17.30 MiB | 62.83 MiB/s, done.
Resolving deltas: 100% (287/287), done.
Cloning BLIP into /home/studio-lab-user/SageMaker/stable-diffusion-webui/repositories/BLIP...
Cloning into '/home/studio-lab-user/SageMaker/stable-diffusion-webui/repositories/BLIP'...
remote: Enumerating objects: 277, done.
remote: Counting objects: 100% (165/165), done.
remote: Compressing objects: 100% (30/30), done.
remote: Total 277 (delta 137), reused 136 (delta 135), pack-reused 112
Receiving objects: 100% (277/277), 7.03 MiB | 45.59 MiB/s, done.
Resolving deltas: 100% (153/153), done.
Launching Web UI with arguments: --skip-torch-cuda-test --disable-console-progressbars --gradio-debug --gradio-auth NullEqualsZero:0 --ngrok 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
Traceback (most recent call last):
File "/home/studio-lab-user/SageMaker/stable-diffusion-webui/launch.py", line 48, in
main()
File "/home/studio-lab-user/SageMaker/stable-diffusion-webui/launch.py", line 44, in main
start()
File "/home/studio-lab-user/SageMaker/stable-diffusion-webui/modules/launch_utils.py", line 432, in start
import webui
File "/home/studio-lab-user/SageMaker/stable-diffusion-webui/webui.py", line 13, in
initialize.imports()
File "/home/studio-lab-user/SageMaker/stable-diffusion-webui/modules/initialize.py", line 14, in imports
import torch # noqa: F401
File "/home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages/torch/init.py", line 26, in
from ._utils import _import_dotted_name, classproperty
ModuleNotFoundError: No module named 'torch._utils'

Is there a way to not use ngrok? Running SD hits the consumption limit of a free ngrok account in like two days.