CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching in backup paths... The following directories listed in your path were found to be non-existent: {WindowsPath('/usr/local/cuda/lib64')}

[wh213]

I keep getting this and cannot solve it no matter what i do, please help (RTX 3060):

venv "C:\Users\sf4bm\A1111\stable-diffusion-webui\venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: v1.6.0
Commit hash: 5ef669d
Installing requirements
Installing requirements for easyphoto-webui
Installing requirements for tensorflow
Installing requirements for easyphoto-webui
Installing requirements for modelscope
Installing requirements for easyphoto-webui
Installing requirements for diffusers
Installing requirements for easyphoto-webui
Installing requirements for fsspec
Checking ReActor requirements... Ok
If submitting an issue on github, please provide the full startup log for debugging purposes.

Initializing Dreambooth
Dreambooth revision: 1a1d1621086a4725fda1200256f319c845dc7a8a
Successfully installed accelerate-0.23.0 bitsandbytes-0.41.2.post2 diffusers-0.21.4 fastapi-0.94.1 tensorboard-2.13.0 transformers-4.32.1

Installing bitsandbytes
Bitsandbytes 0.41.1 installation failed.
Some features such as 8bit optimizers will be unavailable
Please install manually with
'python -m pip install bitsandbytes==0.41.1 --extra-index-url=https://jllllll.github.io/bitsandbytes-windows-webui --prefer-binary --force-install'
[!] xformers version 0.0.20 installed.
[+] torch version 2.0.1+cu118 installed.
[+] torchvision version 0.15.2+cu118 installed.
[+] accelerate version 0.23.0 installed.
[+] diffusers version 0.21.4 installed.
[+] transformers version 4.32.1 installed.
[+] bitsandbytes version 0.41.2.post2 installed.
Launching Web UI with arguments: --xformers --autolaunch --precision full --no-half --skip-torch-cuda-test
2023-11-09 12:37:44,189 - modelscope - INFO - PyTorch version 2.0.1+cu118 Found.
2023-11-09 12:37:44,192 - modelscope - INFO - TensorFlow version 2.14.0 Found.
2023-11-09 12:37:44,192 - modelscope - INFO - Loading ast index from C:\Users\sf4bm.cache\modelscope\ast_indexer
2023-11-09 12:37:44,320 - modelscope - INFO - Loading done! Current index file version is 1.9.3, with md5 c52ba39bb9555d343cfb372c176bc862 and a total number of 943 components indexed
2023-11-09 12:37:53,392 - ControlNet - INFO - ControlNet v1.1.411
ControlNet preprocessor location: C:\Users\sf4bm\A1111\stable-diffusion-webui\extensions\sd-webui-controlnet\annotator\downloads
2023-11-09 12:37:53,532 - ControlNet - INFO - ControlNet v1.1.411
12:38:05 - ReActor - STATUS - Running v0.4.3
Loading weights [40c6475ecb] from C:\Users\sf4bm\A1111\stable-diffusion-webui\models\Stable-diffusion\purepornplusMerge_purepornplus10.ckpt
False

===================================BUG REPORT===================================

The following directories listed in your path were found to be non-existent: {WindowsPath('AQAAANCMnd8BFdERjHoAwE/Cl+sBAAAAq0ma6YshEES2r+cxWHTOdgQAAAACAAAAAAAQZgAAAAEAACAAAADWpIABZZfb50lICSmbA7O4v1Llzh00IEULpif5LbIPmgAAAAAOgAAAAAIAACAAAAD+VIRCO9j2jQe1VXxO+FZTyqxGVCrUEHAeaB5kTXeboGAAAABhoTEYBoyPYxGw5nJCfmmgMSwnecYhwdCu+VjdPbmeSgeHSYkFkIWg359idS/3wO3112L26qtw62JwsqGfs7eXxU8hRpgywgYtm7TDbjcT82i6xKL1MEmPGg+OgU+TARtAAAAAJBknwHEtTIB/y45Orc3b6C1pL0xXLIWKcrgszGSvNfP5yxen3GxtfCTz5OajMn8MfEYOYvRJ0DyEVtlsecxz6w==')}
The following directories listed in your path were found to be non-existent: {WindowsPath('tmp/restart')}
CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching in backup paths...
The following directories listed in your path were found to be non-existent: {WindowsPath('/usr/local/cuda/lib64')}
DEBUG: Possible options found for libcudart.so: set()
CUDA SETUP: PyTorch settings found: CUDA_VERSION=118, Highest Compute Capability: 8.6.
CUDA SETUP: To manually override the PyTorch CUDA version please see:https://github.com/TimDettmers/bitsandbytes/blob/main/how_to_use_nonpytorch_cuda.md
CUDA SETUP: Loading binary C:\Users\sf4bm\A1111\stable-diffusion-webui\venv\lib\site-packages\bitsandbytes\libbitsandbytes_cuda118.so...
argument of type 'WindowsPath' is not iterable
CUDA SETUP: Problem: The main issue seems to be that the main CUDA runtime library was not detected.
CUDA SETUP: Solution 1: To solve the issue the libcudart.so location needs to be added to the LD_LIBRARY_PATH variable
CUDA SETUP: Solution 1a): Find the cuda runtime library via: find / -name libcudart.so 2>/dev/null
CUDA SETUP: Solution 1b): Once the library is found add it to the LD_LIBRARY_PATH: export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:FOUND_PATH_FROM_1a
CUDA SETUP: Solution 1c): For a permanent solution add the export from 1b into your .bashrc file, located at ~/.bashrc
CUDA SETUP: Solution 2: If no library was found in step 1a) you need to install CUDA.
CUDA SETUP: Solution 2a): Download CUDA install script: wget https://github.com/TimDettmers/bitsandbytes/blob/main/cuda_install.sh
CUDA SETUP: Solution 2b): Install desired CUDA version to desired location. The syntax is bash cuda_install.sh CUDA_VERSION PATH_TO_INSTALL_INTO.
CUDA SETUP: Solution 2b): For example, "bash cuda_install.sh 113 ~/local/" will download CUDA 11.3 and install into the folder ~/local

===================================BUG REPORT===================================

The following directories listed in your path were found to be non-existent: {WindowsPath('AQAAANCMnd8BFdERjHoAwE/Cl+sBAAAAq0ma6YshEES2r+cxWHTOdgQAAAACAAAAAAAQZgAAAAEAACAAAADWpIABZZfb50lICSmbA7O4v1Llzh00IEULpif5LbIPmgAAAAAOgAAAAAIAACAAAAD+VIRCO9j2jQe1VXxO+FZTyqxGVCrUEHAeaB5kTXeboGAAAABhoTEYBoyPYxGw5nJCfmmgMSwnecYhwdCu+VjdPbmeSgeHSYkFkIWg359idS/3wO3112L26qtw62JwsqGfs7eXxU8hRpgywgYtm7TDbjcT82i6xKL1MEmPGg+OgU+TARtAAAAAJBknwHEtTIB/y45Orc3b6C1pL0xXLIWKcrgszGSvNfP5yxen3GxtfCTz5OajMn8MfEYOYvRJ0DyEVtlsecxz6w==')}
The following directories listed in your path were found to be non-existent: {WindowsPath('tmp/restart')}
CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching in backup paths...
The following directories listed in your path were found to be non-existent: {WindowsPath('/usr/local/cuda/lib64')}
DEBUG: Possible options found for libcudart.so: set()
CUDA SETUP: PyTorch settings found: CUDA_VERSION=118, Highest Compute Capability: 8.6.
CUDA SETUP: To manually override the PyTorch CUDA version please see:https://github.com/TimDettmers/bitsandbytes/blob/main/how_to_use_nonpytorch_cuda.md
CUDA SETUP: Loading binary C:\Users\sf4bm\A1111\stable-diffusion-webui\venv\lib\site-packages\bitsandbytes\libbitsandbytes_cuda118.so...
argument of type 'WindowsPath' is not iterable
CUDA SETUP: Problem: The main issue seems to be that the main CUDA runtime library was not detected.
CUDA SETUP: Solution 1: To solve the issue the libcudart.so location needs to be added to the LD_LIBRARY_PATH variable
CUDA SETUP: Solution 1a): Find the cuda runtime library via: find / -name libcudart.so 2>/dev/null
CUDA SETUP: Solution 1b): Once the library is found add it to the LD_LIBRARY_PATH: export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:FOUND_PATH_FROM_1a
CUDA SETUP: Solution 1c): For a permanent solution add the export from 1b into your .bashrc file, located at ~/.bashrc
CUDA SETUP: Solution 2: If no library was found in step 1a) you need to install CUDA.
CUDA SETUP: Solution 2a): Download CUDA install script: wget https://github.com/TimDettmers/bitsandbytes/blob/main/cuda_install.sh
CUDA SETUP: Solution 2b): Install desired CUDA version to desired location. The syntax is bash cuda_install.sh CUDA_VERSION PATH_TO_INSTALL_INTO.
CUDA SETUP: Solution 2b): For example, "bash cuda_install.sh 113 ~/local/" will download CUDA 11.3 and install into the folder ~/local

===================================BUG REPORT===================================

The following directories listed in your path were found to be non-existent: {WindowsPath('AQAAANCMnd8BFdERjHoAwE/Cl+sBAAAAq0ma6YshEES2r+cxWHTOdgQAAAACAAAAAAAQZgAAAAEAACAAAADWpIABZZfb50lICSmbA7O4v1Llzh00IEULpif5LbIPmgAAAAAOgAAAAAIAACAAAAD+VIRCO9j2jQe1VXxO+FZTyqxGVCrUEHAeaB5kTXeboGAAAABhoTEYBoyPYxGw5nJCfmmgMSwnecYhwdCu+VjdPbmeSgeHSYkFkIWg359idS/3wO3112L26qtw62JwsqGfs7eXxU8hRpgywgYtm7TDbjcT82i6xKL1MEmPGg+OgU+TARtAAAAAJBknwHEtTIB/y45Orc3b6C1pL0xXLIWKcrgszGSvNfP5yxen3GxtfCTz5OajMn8MfEYOYvRJ0DyEVtlsecxz6w==')}
The following directories listed in your path were found to be non-existent: {WindowsPath('tmp/restart')}
CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching in backup paths...
The following directories listed in your path were found to be non-existent: {WindowsPath('/usr/local/cuda/lib64')}
DEBUG: Possible options found for libcudart.so: set()
CUDA SETUP: PyTorch settings found: CUDA_VERSION=118, Highest Compute Capability: 8.6.
CUDA SETUP: To manually override the PyTorch CUDA version please see:https://github.com/TimDettmers/bitsandbytes/blob/main/how_to_use_nonpytorch_cuda.md
CUDA SETUP: Loading binary C:\Users\sf4bm\A1111\stable-diffusion-webui\venv\lib\site-packages\bitsandbytes\libbitsandbytes_cuda118.so...
argument of type 'WindowsPath' is not iterable
CUDA SETUP: Problem: The main issue seems to be that the main CUDA runtime library was not detected.
CUDA SETUP: Solution 1: To solve the issue the libcudart.so location needs to be added to the LD_LIBRARY_PATH variable
CUDA SETUP: Solution 1a): Find the cuda runtime library via: find / -name libcudart.so 2>/dev/null
CUDA SETUP: Solution 1b): Once the library is found add it to the LD_LIBRARY_PATH: export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:FOUND_PATH_FROM_1a
CUDA SETUP: Solution 1c): For a permanent solution add the export from 1b into your .bashrc file, located at ~/.bashrc
CUDA SETUP: Solution 2: If no library was found in step 1a) you need to install CUDA.
CUDA SETUP: Solution 2a): Download CUDA install script: wget https://github.com/TimDettmers/bitsandbytes/blob/main/cuda_install.sh
CUDA SETUP: Solution 2b): Install desired CUDA version to desired location. The syntax is bash cuda_install.sh CUDA_VERSION PATH_TO_INSTALL_INTO.
CUDA SETUP: Solution 2b): For example, "bash cuda_install.sh 113 ~/local/" will download CUDA 11.3 and install into the folder ~/local

===================================BUG REPORT===================================

The following directories listed in your path were found to be non-existent: {WindowsPath('AQAAANCMnd8BFdERjHoAwE/Cl+sBAAAAq0ma6YshEES2r+cxWHTOdgQAAAACAAAAAAAQZgAAAAEAACAAAADWpIABZZfb50lICSmbA7O4v1Llzh00IEULpif5LbIPmgAAAAAOgAAAAAIAACAAAAD+VIRCO9j2jQe1VXxO+FZTyqxGVCrUEHAeaB5kTXeboGAAAABhoTEYBoyPYxGw5nJCfmmgMSwnecYhwdCu+VjdPbmeSgeHSYkFkIWg359idS/3wO3112L26qtw62JwsqGfs7eXxU8hRpgywgYtm7TDbjcT82i6xKL1MEmPGg+OgU+TARtAAAAAJBknwHEtTIB/y45Orc3b6C1pL0xXLIWKcrgszGSvNfP5yxen3GxtfCTz5OajMn8MfEYOYvRJ0DyEVtlsecxz6w==')}
The following directories listed in your path were found to be non-existent: {WindowsPath('tmp/restart')}
CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching in backup paths...
The following directories listed in your path were found to be non-existent: {WindowsPath('/usr/local/cuda/lib64')}
DEBUG: Possible options found for libcudart.so: set()
CUDA SETUP: PyTorch settings found: CUDA_VERSION=118, Highest Compute Capability: 8.6.
CUDA SETUP: To manually override the PyTorch CUDA version please see:https://github.com/TimDettmers/bitsandbytes/blob/main/how_to_use_nonpytorch_cuda.md
CUDA SETUP: Loading binary C:\Users\sf4bm\A1111\stable-diffusion-webui\venv\lib\site-packages\bitsandbytes\libbitsandbytes_cuda118.so...
argument of type 'WindowsPath' is not iterable
CUDA SETUP: Problem: The main issue seems to be that the main CUDA runtime library was not detected.
CUDA SETUP: Solution 1: To solve the issue the libcudart.so location needs to be added to the LD_LIBRARY_PATH variable
CUDA SETUP: Solution 1a): Find the cuda runtime library via: find / -name libcudart.so 2>/dev/null
CUDA SETUP: Solution 1b): Once the library is found add it to the LD_LIBRARY_PATH: export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:FOUND_PATH_FROM_1a
CUDA SETUP: Solution 1c): For a permanent solution add the export from 1b into your .bashrc file, located at ~/.bashrc
CUDA SETUP: Solution 2: If no library was found in step 1a) you need to install CUDA.
CUDA SETUP: Solution 2a): Download CUDA install script: wget https://github.com/TimDettmers/bitsandbytes/blob/main/cuda_install.sh
CUDA SETUP: Solution 2b): Install desired CUDA version to desired location. The syntax is bash cuda_install.sh CUDA_VERSION PATH_TO_INSTALL_INTO.
CUDA SETUP: Solution 2b): For example, "bash cuda_install.sh 113 ~/local/" will download CUDA 11.3 and install into the folder ~/local
Running on local URL: http://127.0.0.1:7860

To create a public link, set share=True in launch().
[sd-webui-comfyui] Could not find ComfyUI under directory "C:\Users\sf4bm\A1111\stable-diffusion-webui\extensions\sd-webui-comfyui\ComfyUI". The server will NOT be started.
Startup time: 176.3s (prepare environment: 134.9s, import torch: 2.9s, import gradio: 0.8s, setup paths: 0.7s, initialize shared: 0.2s, other imports: 12.7s, setup codeformer: 0.2s, load scripts: 22.6s, create ui: 0.9s, gradio launch: 0.3s).
Creating model from config: C:\Users\sf4bm\A1111\stable-diffusion-webui\configs\v1-inference.yaml
Applying attention optimization: xformers... done.
Model loaded in 6.3s (load weights from disk: 4.5s, create model: 0.3s, apply weights to model: 0.9s, apply float(): 0.1s, calculate empty prompt: 0.3s).

[wfjsw]

Delete dreambooth extension and uninstall bitsandbytes

[wh213]

but im trying to use dreambooth

[wfjsw]

You are better off using some separated tool, for example kohya-ss, rather than trying to use it with stable-diffusion-webui. It's simply unstable.

[syboot]

hi
activate venv Python

1. python -m pip install numpy torch==2.1.0 torchvision torchaudio --force-reinstall --index-url https://download.pytorch.org/whl/cu118
2. python -m pip install -U xformers --index-url https://download.pytorch.org/whl/cu118
3. python -m pip install bitsandbytes-windows
4. Launching Web UI with arguments: --listen ,don't add "--xformers",add "--xformers" when it's working properly.
5. run webui-user.bat ,observe failed in the log.

[wh213]

venv "C:\Users\sf4bm\A1111\stable-diffusion-webui\venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: v1.6.0
Commit hash: 5ef669d
Installing requirements
Installing requirements for easyphoto-webui
Installing requirements for tensorflow
Installing requirements for easyphoto-webui
Installing requirements for modelscope
Installing requirements for easyphoto-webui
Installing requirements for diffusers
Installing requirements for easyphoto-webui
Installing requirements for fsspec
Checking ReActor requirements... Ok
False

===================================BUG REPORT===================================

The following directories listed in your path were found to be non-existent: {WindowsPath('AQAAANCMnd8BFdERjHoAwE/Cl+sBAAAAq0ma6YshEES2r+cxWHTOdgQAAAACAAAAAAAQZgAAAAEAACAAAADWpIABZZfb50lICSmbA7O4v1Llzh00IEULpif5LbIPmgAAAAAOgAAAAAIAACAAAAD+VIRCO9j2jQe1VXxO+FZTyqxGVCrUEHAeaB5kTXeboGAAAABhoTEYBoyPYxGw5nJCfmmgMSwnecYhwdCu+VjdPbmeSgeHSYkFkIWg359idS/3wO3112L26qtw62JwsqGfs7eXxU8hRpgywgYtm7TDbjcT82i6xKL1MEmPGg+OgU+TARtAAAAAJBknwHEtTIB/y45Orc3b6C1pL0xXLIWKcrgszGSvNfP5yxen3GxtfCTz5OajMn8MfEYOYvRJ0DyEVtlsecxz6w==')}
The following directories listed in your path were found to be non-existent: {WindowsPath('tmp/restart')}
CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching in backup paths...
The following directories listed in your path were found to be non-existent: {WindowsPath('/usr/local/cuda/lib64')}
DEBUG: Possible options found for libcudart.so: set()
CUDA SETUP: PyTorch settings found: CUDA_VERSION=118, Highest Compute Capability: 8.6.
CUDA SETUP: To manually override the PyTorch CUDA version please see:https://github.com/TimDettmers/bitsandbytes/blob/main/how_to_use_nonpytorch_cuda.md
CUDA SETUP: Loading binary C:\Users\sf4bm\A1111\stable-diffusion-webui\venv\lib\site-packages\bitsandbytes\libbitsandbytes_cuda118.so...
argument of type 'WindowsPath' is not iterable
CUDA SETUP: Problem: The main issue seems to be that the main CUDA runtime library was not detected.
CUDA SETUP: Solution 1: To solve the issue the libcudart.so location needs to be added to the LD_LIBRARY_PATH variable
CUDA SETUP: Solution 1a): Find the cuda runtime library via: find / -name libcudart.so 2>/dev/null
CUDA SETUP: Solution 1b): Once the library is found add it to the LD_LIBRARY_PATH: export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:FOUND_PATH_FROM_1a
CUDA SETUP: Solution 1c): For a permanent solution add the export from 1b into your .bashrc file, located at ~/.bashrc
CUDA SETUP: Solution 2: If no library was found in step 1a) you need to install CUDA.
CUDA SETUP: Solution 2a): Download CUDA install script: wget https://github.com/TimDettmers/bitsandbytes/blob/main/cuda_install.sh
CUDA SETUP: Solution 2b): Install desired CUDA version to desired location. The syntax is bash cuda_install.sh CUDA_VERSION PATH_TO_INSTALL_INTO.
CUDA SETUP: Solution 2b): For example, "bash cuda_install.sh 113 ~/local/" will download CUDA 11.3 and install into the folder ~/local

===================================BUG REPORT===================================

The following directories listed in your path were found to be non-existent: {WindowsPath('AQAAANCMnd8BFdERjHoAwE/Cl+sBAAAAq0ma6YshEES2r+cxWHTOdgQAAAACAAAAAAAQZgAAAAEAACAAAADWpIABZZfb50lICSmbA7O4v1Llzh00IEULpif5LbIPmgAAAAAOgAAAAAIAACAAAAD+VIRCO9j2jQe1VXxO+FZTyqxGVCrUEHAeaB5kTXeboGAAAABhoTEYBoyPYxGw5nJCfmmgMSwnecYhwdCu+VjdPbmeSgeHSYkFkIWg359idS/3wO3112L26qtw62JwsqGfs7eXxU8hRpgywgYtm7TDbjcT82i6xKL1MEmPGg+OgU+TARtAAAAAJBknwHEtTIB/y45Orc3b6C1pL0xXLIWKcrgszGSvNfP5yxen3GxtfCTz5OajMn8MfEYOYvRJ0DyEVtlsecxz6w==')}
The following directories listed in your path were found to be non-existent: {WindowsPath('tmp/restart')}
CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching in backup paths...
The following directories listed in your path were found to be non-existent: {WindowsPath('/usr/local/cuda/lib64')}
DEBUG: Possible options found for libcudart.so: set()
CUDA SETUP: PyTorch settings found: CUDA_VERSION=118, Highest Compute Capability: 8.6.
CUDA SETUP: To manually override the PyTorch CUDA version please see:https://github.com/TimDettmers/bitsandbytes/blob/main/how_to_use_nonpytorch_cuda.md
CUDA SETUP: Loading binary C:\Users\sf4bm\A1111\stable-diffusion-webui\venv\lib\site-packages\bitsandbytes\libbitsandbytes_cuda118.so...
argument of type 'WindowsPath' is not iterable
CUDA SETUP: Problem: The main issue seems to be that the main CUDA runtime library was not detected.
CUDA SETUP: Solution 1: To solve the issue the libcudart.so location needs to be added to the LD_LIBRARY_PATH variable
CUDA SETUP: Solution 1a): Find the cuda runtime library via: find / -name libcudart.so 2>/dev/null
CUDA SETUP: Solution 1b): Once the library is found add it to the LD_LIBRARY_PATH: export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:FOUND_PATH_FROM_1a
CUDA SETUP: Solution 1c): For a permanent solution add the export from 1b into your .bashrc file, located at ~/.bashrc
CUDA SETUP: Solution 2: If no library was found in step 1a) you need to install CUDA.
CUDA SETUP: Solution 2a): Download CUDA install script: wget https://github.com/TimDettmers/bitsandbytes/blob/main/cuda_install.sh
CUDA SETUP: Solution 2b): Install desired CUDA version to desired location. The syntax is bash cuda_install.sh CUDA_VERSION PATH_TO_INSTALL_INTO.
CUDA SETUP: Solution 2b): For example, "bash cuda_install.sh 113 ~/local/" will download CUDA 11.3 and install into the folder ~/local

===================================BUG REPORT===================================

The following directories listed in your path were found to be non-existent: {WindowsPath('AQAAANCMnd8BFdERjHoAwE/Cl+sBAAAAq0ma6YshEES2r+cxWHTOdgQAAAACAAAAAAAQZgAAAAEAACAAAADWpIABZZfb50lICSmbA7O4v1Llzh00IEULpif5LbIPmgAAAAAOgAAAAAIAACAAAAD+VIRCO9j2jQe1VXxO+FZTyqxGVCrUEHAeaB5kTXeboGAAAABhoTEYBoyPYxGw5nJCfmmgMSwnecYhwdCu+VjdPbmeSgeHSYkFkIWg359idS/3wO3112L26qtw62JwsqGfs7eXxU8hRpgywgYtm7TDbjcT82i6xKL1MEmPGg+OgU+TARtAAAAAJBknwHEtTIB/y45Orc3b6C1pL0xXLIWKcrgszGSvNfP5yxen3GxtfCTz5OajMn8MfEYOYvRJ0DyEVtlsecxz6w==')}
The following directories listed in your path were found to be non-existent: {WindowsPath('tmp/restart')}
CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching in backup paths...
The following directories listed in your path were found to be non-existent: {WindowsPath('/usr/local/cuda/lib64')}
DEBUG: Possible options found for libcudart.so: set()
CUDA SETUP: PyTorch settings found: CUDA_VERSION=118, Highest Compute Capability: 8.6.
CUDA SETUP: To manually override the PyTorch CUDA version please see:https://github.com/TimDettmers/bitsandbytes/blob/main/how_to_use_nonpytorch_cuda.md
CUDA SETUP: Loading binary C:\Users\sf4bm\A1111\stable-diffusion-webui\venv\lib\site-packages\bitsandbytes\libbitsandbytes_cuda118.so...
argument of type 'WindowsPath' is not iterable
CUDA SETUP: Problem: The main issue seems to be that the main CUDA runtime library was not detected.
CUDA SETUP: Solution 1: To solve the issue the libcudart.so location needs to be added to the LD_LIBRARY_PATH variable
CUDA SETUP: Solution 1a): Find the cuda runtime library via: find / -name libcudart.so 2>/dev/null
CUDA SETUP: Solution 1b): Once the library is found add it to the LD_LIBRARY_PATH: export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:FOUND_PATH_FROM_1a
CUDA SETUP: Solution 1c): For a permanent solution add the export from 1b into your .bashrc file, located at ~/.bashrc
CUDA SETUP: Solution 2: If no library was found in step 1a) you need to install CUDA.
CUDA SETUP: Solution 2a): Download CUDA install script: wget https://github.com/TimDettmers/bitsandbytes/blob/main/cuda_install.sh
CUDA SETUP: Solution 2b): Install desired CUDA version to desired location. The syntax is bash cuda_install.sh CUDA_VERSION PATH_TO_INSTALL_INTO.
CUDA SETUP: Solution 2b): For example, "bash cuda_install.sh 113 ~/local/" will download CUDA 11.3 and install into the folder ~/local

===================================BUG REPORT===================================

The following directories listed in your path were found to be non-existent: {WindowsPath('AQAAANCMnd8BFdERjHoAwE/Cl+sBAAAAq0ma6YshEES2r+cxWHTOdgQAAAACAAAAAAAQZgAAAAEAACAAAADWpIABZZfb50lICSmbA7O4v1Llzh00IEULpif5LbIPmgAAAAAOgAAAAAIAACAAAAD+VIRCO9j2jQe1VXxO+FZTyqxGVCrUEHAeaB5kTXeboGAAAABhoTEYBoyPYxGw5nJCfmmgMSwnecYhwdCu+VjdPbmeSgeHSYkFkIWg359idS/3wO3112L26qtw62JwsqGfs7eXxU8hRpgywgYtm7TDbjcT82i6xKL1MEmPGg+OgU+TARtAAAAAJBknwHEtTIB/y45Orc3b6C1pL0xXLIWKcrgszGSvNfP5yxen3GxtfCTz5OajMn8MfEYOYvRJ0DyEVtlsecxz6w==')}
The following directories listed in your path were found to be non-existent: {WindowsPath('tmp/restart')}
CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching in backup paths...
The following directories listed in your path were found to be non-existent: {WindowsPath('/usr/local/cuda/lib64')}
DEBUG: Possible options found for libcudart.so: set()
CUDA SETUP: PyTorch settings found: CUDA_VERSION=118, Highest Compute Capability: 8.6.
CUDA SETUP: To manually override the PyTorch CUDA version please see:https://github.com/TimDettmers/bitsandbytes/blob/main/how_to_use_nonpytorch_cuda.md
CUDA SETUP: Loading binary C:\Users\sf4bm\A1111\stable-diffusion-webui\venv\lib\site-packages\bitsandbytes\libbitsandbytes_cuda118.so...
argument of type 'WindowsPath' is not iterable
CUDA SETUP: Problem: The main issue seems to be that the main CUDA runtime library was not detected.
CUDA SETUP: Solution 1: To solve the issue the libcudart.so location needs to be added to the LD_LIBRARY_PATH variable
CUDA SETUP: Solution 1a): Find the cuda runtime library via: find / -name libcudart.so 2>/dev/null
CUDA SETUP: Solution 1b): Once the library is found add it to the LD_LIBRARY_PATH: export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:FOUND_PATH_FROM_1a
CUDA SETUP: Solution 1c): For a permanent solution add the export from 1b into your .bashrc file, located at ~/.bashrc
CUDA SETUP: Solution 2: If no library was found in step 1a) you need to install CUDA.
CUDA SETUP: Solution 2a): Download CUDA install script: wget https://github.com/TimDettmers/bitsandbytes/blob/main/cuda_install.sh
CUDA SETUP: Solution 2b): Install desired CUDA version to desired location. The syntax is bash cuda_install.sh CUDA_VERSION PATH_TO_INSTALL_INTO.
CUDA SETUP: Solution 2b): For example, "bash cuda_install.sh 113 ~/local/" will download CUDA 11.3 and install into the folder ~/local
If submitting an issue on github, please provide the full startup log for debugging purposes.

Initializing Dreambooth
Dreambooth revision: 1a1d1621086a4725fda1200256f319c845dc7a8a
Successfully installed accelerate-0.23.0 diffusers-0.21.4 fastapi-0.94.1 tensorboard-2.13.0 transformers-4.32.1

Installing bitsandbytes
Bitsandbytes 0.41.1 installation failed.
Some features such as 8bit optimizers will be unavailable
Please install manually with
'python -m pip install bitsandbytes==0.41.1 --extra-index-url=https://jllllll.github.io/bitsandbytes-windows-webui --prefer-binary --force-install'
[!] xformers version 0.0.20 installed.
[+] torch version 2.0.1+cu118 installed.
[+] torchvision version 0.15.2+cu118 installed.
[+] accelerate version 0.23.0 installed.
[+] diffusers version 0.21.4 installed.
[+] transformers version 4.32.1 installed.
[+] bitsandbytes version 0.41.2.post2 installed.
Launching Web UI with arguments: --listen ,dont add "--xformers",add "--xformers" when its working properly.
2023-11-11 23:03:24,801 - modelscope - INFO - PyTorch version 2.0.1+cu118 Found.
2023-11-11 23:03:24,804 - modelscope - INFO - TensorFlow version 2.14.0 Found.
2023-11-11 23:03:24,805 - modelscope - INFO - Loading ast index from C:\Users\sf4bm.cache\modelscope\ast_indexer
2023-11-11 23:03:24,929 - modelscope - INFO - Loading done! Current index file version is 1.9.3, with md5 c52ba39bb9555d343cfb372c176bc862 and a total number of 943 components indexed
2023-11-11 23:03:27,241 - ControlNet - INFO - ControlNet v1.1.411
ControlNet preprocessor location: C:\Users\sf4bm\A1111\stable-diffusion-webui\extensions\sd-webui-controlnet\annotator\downloads
2023-11-11 23:03:27,417 - ControlNet - INFO - ControlNet v1.1.411
23:03:28 - ReActor - STATUS - Running v0.4.3
Loading weights [ee6ef0295b] from C:\Users\sf4bm\A1111\stable-diffusion-webui\models\Stable-diffusion\realNotRealNSFW_v10.safetensors
Creating model from config: C:\Users\sf4bm\A1111\stable-diffusion-webui\configs\v1-inference.yaml
False

===================================BUG REPORT===================================

The following directories listed in your path were found to be non-existent: {WindowsPath('AQAAANCMnd8BFdERjHoAwE/Cl+sBAAAAq0ma6YshEES2r+cxWHTOdgQAAAACAAAAAAAQZgAAAAEAACAAAADWpIABZZfb50lICSmbA7O4v1Llzh00IEULpif5LbIPmgAAAAAOgAAAAAIAACAAAAD+VIRCO9j2jQe1VXxO+FZTyqxGVCrUEHAeaB5kTXeboGAAAABhoTEYBoyPYxGw5nJCfmmgMSwnecYhwdCu+VjdPbmeSgeHSYkFkIWg359idS/3wO3112L26qtw62JwsqGfs7eXxU8hRpgywgYtm7TDbjcT82i6xKL1MEmPGg+OgU+TARtAAAAAJBknwHEtTIB/y45Orc3b6C1pL0xXLIWKcrgszGSvNfP5yxen3GxtfCTz5OajMn8MfEYOYvRJ0DyEVtlsecxz6w==')}
The following directories listed in your path were found to be non-existent: {WindowsPath('tmp/restart')}
CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching in backup paths...
The following directories listed in your path were found to be non-existent: {WindowsPath('/usr/local/cuda/lib64')}
DEBUG: Possible options found for libcudart.so: set()
CUDA SETUP: PyTorch settings found: CUDA_VERSION=118, Highest Compute Capability: 8.6.
CUDA SETUP: To manually override the PyTorch CUDA version please see:https://github.com/TimDettmers/bitsandbytes/blob/main/how_to_use_nonpytorch_cuda.md
CUDA SETUP: Loading binary C:\Users\sf4bm\A1111\stable-diffusion-webui\venv\lib\site-packages\bitsandbytes\libbitsandbytes_cuda118.so...
argument of type 'WindowsPath' is not iterable
CUDA SETUP: Problem: The main issue seems to be that the main CUDA runtime library was not detected.
CUDA SETUP: Solution 1: To solve the issue the libcudart.so location needs to be added to the LD_LIBRARY_PATH variable
CUDA SETUP: Solution 1a): Find the cuda runtime library via: find / -name libcudart.so 2>/dev/null
CUDA SETUP: Solution 1b): Once the library is found add it to the LD_LIBRARY_PATH: export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:FOUND_PATH_FROM_1a
CUDA SETUP: Solution 1c): For a permanent solution add the export from 1b into your .bashrc file, located at ~/.bashrc
CUDA SETUP: Solution 2: If no library was found in step 1a) you need to install CUDA.
CUDA SETUP: Solution 2a): Download CUDA install script: wget https://github.com/TimDettmers/bitsandbytes/blob/main/cuda_install.sh
CUDA SETUP: Solution 2b): Install desired CUDA version to desired location. The syntax is bash cuda_install.sh CUDA_VERSION PATH_TO_INSTALL_INTO.
CUDA SETUP: Solution 2b): For example, "bash cuda_install.sh 113 ~/local/" will download CUDA 11.3 and install into the folder ~/local

===================================BUG REPORT===================================

The following directories listed in your path were found to be non-existent: {WindowsPath('AQAAANCMnd8BFdERjHoAwE/Cl+sBAAAAq0ma6YshEES2r+cxWHTOdgQAAAACAAAAAAAQZgAAAAEAACAAAADWpIABZZfb50lICSmbA7O4v1Llzh00IEULpif5LbIPmgAAAAAOgAAAAAIAACAAAAD+VIRCO9j2jQe1VXxO+FZTyqxGVCrUEHAeaB5kTXeboGAAAABhoTEYBoyPYxGw5nJCfmmgMSwnecYhwdCu+VjdPbmeSgeHSYkFkIWg359idS/3wO3112L26qtw62JwsqGfs7eXxU8hRpgywgYtm7TDbjcT82i6xKL1MEmPGg+OgU+TARtAAAAAJBknwHEtTIB/y45Orc3b6C1pL0xXLIWKcrgszGSvNfP5yxen3GxtfCTz5OajMn8MfEYOYvRJ0DyEVtlsecxz6w==')}
The following directories listed in your path were found to be non-existent: {WindowsPath('tmp/restart')}
CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching in backup paths...
The following directories listed in your path were found to be non-existent: {WindowsPath('/usr/local/cuda/lib64')}
DEBUG: Possible options found for libcudart.so: set()
CUDA SETUP: PyTorch settings found: CUDA_VERSION=118, Highest Compute Capability: 8.6.
CUDA SETUP: To manually override the PyTorch CUDA version please see:https://github.com/TimDettmers/bitsandbytes/blob/main/how_to_use_nonpytorch_cuda.md
CUDA SETUP: Loading binary C:\Users\sf4bm\A1111\stable-diffusion-webui\venv\lib\site-packages\bitsandbytes\libbitsandbytes_cuda118.so...
argument of type 'WindowsPath' is not iterable
CUDA SETUP: Problem: The main issue seems to be that the main CUDA runtime library was not detected.
CUDA SETUP: Solution 1: To solve the issue the libcudart.so location needs to be added to the LD_LIBRARY_PATH variable
CUDA SETUP: Solution 1a): Find the cuda runtime library via: find / -name libcudart.so 2>/dev/null
CUDA SETUP: Solution 1b): Once the library is found add it to the LD_LIBRARY_PATH: export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:FOUND_PATH_FROM_1a
CUDA SETUP: Solution 1c): For a permanent solution add the export from 1b into your .bashrc file, located at ~/.bashrc
CUDA SETUP: Solution 2: If no library was found in step 1a) you need to install CUDA.
CUDA SETUP: Solution 2a): Download CUDA install script: wget https://github.com/TimDettmers/bitsandbytes/blob/main/cuda_install.sh
CUDA SETUP: Solution 2b): Install desired CUDA version to desired location. The syntax is bash cuda_install.sh CUDA_VERSION PATH_TO_INSTALL_INTO.
CUDA SETUP: Solution 2b): For example, "bash cuda_install.sh 113 ~/local/" will download CUDA 11.3 and install into the folder ~/local

===================================BUG REPORT===================================

The following directories listed in your path were found to be non-existent: {WindowsPath('AQAAANCMnd8BFdERjHoAwE/Cl+sBAAAAq0ma6YshEES2r+cxWHTOdgQAAAACAAAAAAAQZgAAAAEAACAAAADWpIABZZfb50lICSmbA7O4v1Llzh00IEULpif5LbIPmgAAAAAOgAAAAAIAACAAAAD+VIRCO9j2jQe1VXxO+FZTyqxGVCrUEHAeaB5kTXeboGAAAABhoTEYBoyPYxGw5nJCfmmgMSwnecYhwdCu+VjdPbmeSgeHSYkFkIWg359idS/3wO3112L26qtw62JwsqGfs7eXxU8hRpgywgYtm7TDbjcT82i6xKL1MEmPGg+OgU+TARtAAAAAJBknwHEtTIB/y45Orc3b6C1pL0xXLIWKcrgszGSvNfP5yxen3GxtfCTz5OajMn8MfEYOYvRJ0DyEVtlsecxz6w==')}
The following directories listed in your path were found to be non-existent: {WindowsPath('tmp/restart')}
CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching in backup paths...
The following directories listed in your path were found to be non-existent: {WindowsPath('/usr/local/cuda/lib64')}
DEBUG: Possible options found for libcudart.so: set()
CUDA SETUP: PyTorch settings found: CUDA_VERSION=118, Highest Compute Capability: 8.6.
CUDA SETUP: To manually override the PyTorch CUDA version please see:https://github.com/TimDettmers/bitsandbytes/blob/main/how_to_use_nonpytorch_cuda.md
CUDA SETUP: Loading binary C:\Users\sf4bm\A1111\stable-diffusion-webui\venv\lib\site-packages\bitsandbytes\libbitsandbytes_cuda118.so...
argument of type 'WindowsPath' is not iterable
CUDA SETUP: Problem: The main issue seems to be that the main CUDA runtime library was not detected.
CUDA SETUP: Solution 1: To solve the issue the libcudart.so location needs to be added to the LD_LIBRARY_PATH variable
CUDA SETUP: Solution 1a): Find the cuda runtime library via: find / -name libcudart.so 2>/dev/null
CUDA SETUP: Solution 1b): Once the library is found add it to the LD_LIBRARY_PATH: export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:FOUND_PATH_FROM_1a
CUDA SETUP: Solution 1c): For a permanent solution add the export from 1b into your .bashrc file, located at ~/.bashrc
CUDA SETUP: Solution 2: If no library was found in step 1a) you need to install CUDA.
CUDA SETUP: Solution 2a): Download CUDA install script: wget https://github.com/TimDettmers/bitsandbytes/blob/main/cuda_install.sh
CUDA SETUP: Solution 2b): Install desired CUDA version to desired location. The syntax is bash cuda_install.sh CUDA_VERSION PATH_TO_INSTALL_INTO.
CUDA SETUP: Solution 2b): For example, "bash cuda_install.sh 113 ~/local/" will download CUDA 11.3 and install into the folder ~/local

===================================BUG REPORT===================================

The following directories listed in your path were found to be non-existent: {WindowsPath('AQAAANCMnd8BFdERjHoAwE/Cl+sBAAAAq0ma6YshEES2r+cxWHTOdgQAAAACAAAAAAAQZgAAAAEAACAAAADWpIABZZfb50lICSmbA7O4v1Llzh00IEULpif5LbIPmgAAAAAOgAAAAAIAACAAAAD+VIRCO9j2jQe1VXxO+FZTyqxGVCrUEHAeaB5kTXeboGAAAABhoTEYBoyPYxGw5nJCfmmgMSwnecYhwdCu+VjdPbmeSgeHSYkFkIWg359idS/3wO3112L26qtw62JwsqGfs7eXxU8hRpgywgYtm7TDbjcT82i6xKL1MEmPGg+OgU+TARtAAAAAJBknwHEtTIB/y45Orc3b6C1pL0xXLIWKcrgszGSvNfP5yxen3GxtfCTz5OajMn8MfEYOYvRJ0DyEVtlsecxz6w==')}
The following directories listed in your path were found to be non-existent: {WindowsPath('tmp/restart')}
CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching in backup paths...
The following directories listed in your path were found to be non-existent: {WindowsPath('/usr/local/cuda/lib64')}
DEBUG: Possible options found for libcudart.so: set()
CUDA SETUP: PyTorch settings found: CUDA_VERSION=118, Highest Compute Capability: 8.6.
CUDA SETUP: To manually override the PyTorch CUDA version please see:https://github.com/TimDettmers/bitsandbytes/blob/main/how_to_use_nonpytorch_cuda.md
CUDA SETUP: Loading binary C:\Users\sf4bm\A1111\stable-diffusion-webui\venv\lib\site-packages\bitsandbytes\libbitsandbytes_cuda118.so...
argument of type 'WindowsPath' is not iterable
CUDA SETUP: Problem: The main issue seems to be that the main CUDA runtime library was not detected.
CUDA SETUP: Solution 1: To solve the issue the libcudart.so location needs to be added to the LD_LIBRARY_PATH variable
CUDA SETUP: Solution 1a): Find the cuda runtime library via: find / -name libcudart.so 2>/dev/null
CUDA SETUP: Solution 1b): Once the library is found add it to the LD_LIBRARY_PATH: export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:FOUND_PATH_FROM_1a
CUDA SETUP: Solution 1c): For a permanent solution add the export from 1b into your .bashrc file, located at ~/.bashrc
CUDA SETUP: Solution 2: If no library was found in step 1a) you need to install CUDA.
CUDA SETUP: Solution 2a): Download CUDA install script: wget https://github.com/TimDettmers/bitsandbytes/blob/main/cuda_install.sh
CUDA SETUP: Solution 2b): Install desired CUDA version to desired location. The syntax is bash cuda_install.sh CUDA_VERSION PATH_TO_INSTALL_INTO.
CUDA SETUP: Solution 2b): For example, "bash cuda_install.sh 113 ~/local/" will download CUDA 11.3 and install into the folder ~/local
Running on local URL: http://0.0.0.0:7860

To create a public link, set share=True in launch().
[sd-webui-comfyui] Could not find ComfyUI under directory "C:\Users\sf4bm\A1111\stable-diffusion-webui\extensions\sd-webui-comfyui\ComfyUI". The server will NOT be started.
Startup time: 90.3s (prepare environment: 65.8s, import torch: 3.3s, import gradio: 0.8s, setup paths: 2.1s, initialize shared: 0.2s, other imports: 6.5s, setup codeformer: 0.2s, list SD models: 0.1s, load scripts: 5.7s, create ui: 1.2s, gradio launch: 4.2s).
Applying attention optimization: Doggettx... done.
Model loaded in 27.6s (load weights from disk: 0.7s, create model: 0.6s, apply weights to model: 25.2s, apply half(): 0.1s, load VAE: 0.3s, calculate empty prompt: 0.5s).

got basically the same thing

[wh213]

now it just wont open

[syboot]

"[!] xformers version 0.0.20 installed. 2
[+] torch version 2.0.1+cu118 installed. 1
[+] torchvision version 0.15.2+cu118 installed.
[+] accelerate version 0.23.0 installed.
[+] diffusers version 0.21.4 installed.
[+] transformers version 4.32.1 installed.
[+] bitsandbytes version 0.41.2.post2 installed. 3
Launching Web UI with arguments: --listen ,dont add "--xformers",add "--xformers" when its working properly." 4

Judging from the log,The torch version is still the old version.

Activate Venv
1.python -m pip install numpy torch==2.1.0 torchvision torchaudio --force-reinstall --index-url https://download.pytorch.org/whl/cu118
2.python -m pip install -U xformers --index-url https://download.pytorch.org/whl/cu118
3.python -m pip install bitsandbytes-windows
4.set COMMANDLINE_ARGS=--listen