is there a tutorial for that part?
is there a tutorial for that part?
Fwell that above video explains all actually
Fyou can also watch this python tutorial
Fto understand venv
FYouTubeSECourses
How to install Python, have multiple Python installations, set system wide default Python version. How to compose venv for any Python installation, change Python default path, and install SD web UI properly. Discord: https://bit.ly/SECoursesDiscord.
If I have been of assistance to you and you would like to show your support for my work, please...
If I have been of assistance to you and you would like to show your support for my work, please...
I" activate venv and type pip install xformers==0.0.18" is this all i have to do?
Iin which folder do i have to run that?
Fvenv of automatic111
IERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
torchvision 0.14.1+cu117 requires torch==1.13.1, but you have torch 2.0.0 which is incompatible.
open-clip-torch 2.7.0 requires protobuf==3.20.0, but you have protobuf 4.22.3 which is incompatible.
clean-fid 0.1.29 requires requests==2.25.1, but you have requests 2.29.0 which is incompatible.
torchvision 0.14.1+cu117 requires torch==1.13.1, but you have torch 2.0.0 which is incompatible.
open-clip-torch 2.7.0 requires protobuf==3.20.0, but you have protobuf 4.22.3 which is incompatible.
clean-fid 0.1.29 requires requests==2.25.1, but you have requests 2.29.0 which is incompatible.
Ilooks like this also changed my torch
Inow my webUI wont open
Traceback (most recent call last):
File "C:\Users\Brandon\stable-diffusion-webui\launch.py", line 355, in <module>
prepare_environment()
File "C:\Users\Brandon\stable-diffusion-webui\launch.py", line 260, in prepare_environment
run_python("import torch; assert torch.cuda.is_available(), 'Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check'")
File "C:\Users\Brandon\stable-diffusion-webui\launch.py", line 121, in run_python
return run(f'"{python}" -c "{code}"', desc, errdesc)
File "C:\Users\Brandon\stable-diffusion-webui\launch.py", line 97, in run
raise RuntimeError(message)
RuntimeError: Error running command.
Command: "C:\Users\Brandon\stable-diffusion-webui\venv\Scripts\python.exe" -c "import torch; assert torch.cuda.is_available(), 'Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check'"
Error code: 1
stdout: <empty>
stderr: Traceback (most recent call last):
File "<string>", line 1, in <module>
AssertionError: Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check
Press any key to continue . . .
Traceback (most recent call last):
File "C:\Users\Brandon\stable-diffusion-webui\launch.py", line 355, in <module>
prepare_environment()
File "C:\Users\Brandon\stable-diffusion-webui\launch.py", line 260, in prepare_environment
run_python("import torch; assert torch.cuda.is_available(), 'Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check'")
File "C:\Users\Brandon\stable-diffusion-webui\launch.py", line 121, in run_python
return run(f'"{python}" -c "{code}"', desc, errdesc)
File "C:\Users\Brandon\stable-diffusion-webui\launch.py", line 97, in run
raise RuntimeError(message)
RuntimeError: Error running command.
Command: "C:\Users\Brandon\stable-diffusion-webui\venv\Scripts\python.exe" -c "import torch; assert torch.cuda.is_available(), 'Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check'"
Error code: 1
stdout: <empty>
stderr: Traceback (most recent call last):
File "<string>", line 1, in <module>
AssertionError: Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check
Press any key to continue . . .
Fyes you should install torch 2
Fyou have a new card
Iyes but now Web UI gives me that error when i try to start it
Ior do i have to delete venv again now?
Fno activate venv install torch 2
Fyou are not following tutorial?
Iyes the error says i have torch 2 thats whats causing the problem
Iit installed torch 2 when it updated xformers
Fok i see now
Fdo this
Factivate venv
Fpip uninstall torch
Fpip uninstall torchvision
Fpip uninstall torchaudio
Fthen this below
FIactivate venv only works in scripts?
Iwhen i run activate in venv nothing happens
Fyes only in scripts
Iok thank you its installing the last line now
Iit gave me this error at the end, is it important?
ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
open-clip-torch 2.7.0 requires protobuf==3.20.0, but you have protobuf 4.22.3 which is incompatible.
clean-fid 0.1.29 requires requests==2.25.1, but you have requests 2.29.0 which is incompatible.
ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
open-clip-torch 2.7.0 requires protobuf==3.20.0, but you have protobuf 4.22.3 which is incompatible.
clean-fid 0.1.29 requires requests==2.25.1, but you have requests 2.29.0 which is incompatible.
Iweb ui works now! proper version of everything on the bottom. ty!
ZLearn pip tools and pip compile. Thank me later
Fyou can ignore it
Imy TI actually training now lol i ran like 3 trainings at 1200 steps and just got noise
Iwaste of compute
Fwhat you think about this thumb?
Fye it was xformers version error
Fi just did a mini finetuning today 
Fwith file captions
ZClassy
HWhenever I need change a model ， it takes almost 2 minutes
H@Furkan Gözükara SECourses
Issd or hdd?
Mhugging face may need to queue.
KHi thank you very much. I found out that part of my classification images are not 512x512 so I fix it and it works now. It's weird that last time I use the same classification images but everything was fine.
KI think it looks great, very professional and realistic. But the thumbnails of your videos are different from each other. I believe that if we could find a way to make them easily recognizable as being from your SECourses Youtube channel, it would be even better.
Aall of a sudden I can't train anything.. I get : Loss is NaN, your model is dead. Cancelling training. I have no idea what's the cause, I cant remember changeiing anything.. any thoughts?
Cdeforum is madness