Thanks so much! I'm not new to SD, I even built myself a very good PC to run it but I was completely stumped, every other tutorial I've followed lead to errors and I couldn't figure out for the life of me how to make it work. Your instructions worked for some reason, even though the resources were exactly the same! Keep it up!
thanks for sharing your wisdom to me! i have a question. sorry for my rusty english i tried to install stable diffusion following your instructions, everything went well before 8:08 of this video. the screen of stable diffusion didn't pop up in my computer screen. when i try to launch the file, webui- user, i see black window and text me some messages, and press any key message. when i do that, the window just closes. can you help me with this? ++ i installed 1.5 version from web ui site. maybe this is because of that. how can i uninstall 1.5 version and install the latest version? +++ i see some messages saying: not a git repository from the screen.
@@MunKaw-ui i saw 'fatal: not a git repository' message first. after i searched around othe youtube videos, i could type in 'git init' through git bash. after that, i saw message saying 'nothing added to commit but untracked files present (use "git add" to track)'. i use window 11. thanks for your reply.
In this case, try uninstalling any other version of Python and git already installed, restart your PC and reinstall with the correct version. Make sure all other version are uninstalled If you follow the process correctly, everything should work fine without using an environment variable. But if it still doesn't work, try using Easy diffusion : it will do all the work
What is the latest and most useful version of Stable Diffusion that I can use locally? I keep coming across versions like SD XL, SD 3, etc. I would like to know which of these is the most widely used and the best quality in terms of production.
Can you please do a install video for A1111 on Linux? I recently moved to Linux Mint and somehow after installing everything, the start file doesn't work :( ...I searched for solutions but coudln't get any good advice so far. Please help me out.
Great video, very good explanation. I see only one problem " fatal: not a git repository (or any of the parent directories): .git" Any advices for it? Thank you
when adding command line args first press space bar then type in --autolaunch "press space bar" then --xformers ,so stable diffusion opens the browser automatically..
Thank you! I have one problem, I can get the webui open, but cant generate any images. Heres the error: FileNotFoundError: No checkpoints found. When searching for checkpoints, looked at: - file C:\Users\Kaarel\Downloads\Stable Diffusion\stable-diffusion-webui-1.10.0\model.ckpt - directory C:\Users\Kaarel\Downloads\Stable Diffusion\stable-diffusion-webui-1.10.0\models\Stable-diffusionCan't run without a checkpoint. Find and place a .ckpt or .safetensors file into any of those locations.
Everytime i ran webui-user.bat. I always get an error when installing torch and torchvision. With an error code "ERROR: Could not find a version that satisfies the requirement torch==2.1.2 (from versions: none) ERROR: No matching distribution found for torch==2.1.2 Any way on how to fix this?
I am very new, so please advice me I wish to use Kohya to train LORAs (not using Civitai for this one) but it seems to require plython 3.10.9 or above, not 3.10.6. If I use the former instead of 3.10.6, stable diffusion won't work. Is there any other software/programme that allows me to train LORA offline and on local PC or how to reconcile the different plython requirement? Thank you.
But what if i want to use it over and over again? will it reinstall the file on command line every time? If that is the case then its a long process since it will download and install all the files in command line.
Also getting this error, and I tried your solution you mentioned below; could it be because I have an AMD GPU? RuntimeError: Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check
Edit webui-user.bat, where it says: COMMANDLINE_ARGS= and change it to: COMMANDLINE_ARGS= --lowvram --precision full --no-half --skip-torch-cuda-test Edit: The above assumes windows, if linux then add the line to webui-user.sh, and use quotes, may also need to delete the /venv folder based on others' comments: COMMANDLINE_ARGS="--lowvram --precision full --no-half --skip-torch-cuda-test"
i am getting this error: fatal: not a git repository (or any of the parent directories): .git fatal: not a git repository (or any of the parent directories): .git
You are in the wrong working directory. You run the command but not to the project folder where the git folder is located, make sure you typed the correct path.
@@MunKaw-ui i am really confused. I had followed exactly you did. Created desktop folder too. and ran the bat file after editing it as you did. earlier i had copied the main files on another drive. But now as i have done exact same and on desktop. Still i am getting issue. I am really confused....
i figure out during git installation, the autoselection didn't allowed to run cmd anywhere, so after i reinstalled git with this change, it is installing. hope it works. Thanks
Hi. Thanks for the video. i followed all the instruction. Upon running user.bat file I get the following error message. can you please help? ERROR: Could not find a version that satisfies the requirement torch==2.1.2 (from versions: 2.2.0, 2.2.0+cu121, 2.2.1, 2.2.1+cu121, 2.2.2, 2.2.2+cu121) ERROR: No matching distribution found for torch==2.1.2
You can copy those folders that have your assets, Loras and checkpoints to another folder in the Hard Drive. Then try what you want to do. You can always uninstall SD and reinstall . I don't know about your extensions but you won't lose your Loras and checkpoints.
So I will start by giving credit where it's due... thank you, this tutorial was a big help. I have come from NKMD side of things not knowing code at all, python is like Greek... ??? That said, I got A1111 up and running on my desktop, but I am getting hung up with an error on my laptop, (NVidia)GPU is 12, CPU graphics is 4, but it gives me this error: RuntimeError: 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 . . . How... Where do I modify code? Please... Thank you... ::D
Edit webui-user.bat where it says: set COMMANDLINE_ARGS= You can open it with a block Note You can fiind webui-user.bat in your : stable diffusion folder\webui I hope this helps !
@MunKaw-ui thank you greatly :) Can you help with the next hang up? I have it installed, but every time I try and run it it tells me "lowvram". The UI runs fine, but click generate and i get error. I don't think it is using my GPU, Is there a setting or code to force it to my GPU (Nvidia GTX 1650/Max-Q, 12GB). It makes no sense I have lowvram. Lol. Oh 'AttributeError: 'NoneType' object has no attribute 'lowvram' Your help has been great and thanks again.
Thank you for this wonderful explanation But I have a problem. When all the files are downloaded, even the 3.97 GB file, the installation doesnt progress after that. I even left it for 8 hours, but it didnt progress.
@@MunKaw-ui Thank you for this, but it didnt serve the purpose either, because the installation process freezes after downloading the file of this size 3.97 G
It doesn't work, it can't download torch: ERROR: Could not find a version that satisfies the requirement torch==2.1.2 (from versions: 2.2.0, 2.2.0+cu121, 2.2.1, 2.2.1+cu121, 2.2.2, 2.2.2+cu121, 2.3.0, 2.3.0+cu121, 2.3.1, 2.3.1+cu121) ERROR: No matching distribution found for torch==2.1.2
Good morning! I am trying to install Automatic1111 and I can't get it to work at all. I'm getting the error "exit code 1." Is there any way you can help me? Maybe a Zoom call or something like that? I've tried everything and I can't make it work... Thank you!
hello, i have some trouble that when i start generating images, it took my CPU to do it instead my GPU (im using RX6600 btw), is there a way to switch them so that my GPU can do the work? thank you
File "D:\automatic1111\stable-diffusion-webui-1.0. 0-pre\venv\lib\site-packages\httpx\_transports\default.py", line 275 in ___ init_ self. _ pool = httpcore. AsyncConnectionPool( TypeError: AsyncConnectionPool. __ init __ () got an unexpected keyword argument 'socket_options' Press any key to continue this error is showing up
![Stable Diffusion 1.5 - Windows Installation Guide [Tutorial]](/img/n.gif)
Thanks so much! I'm not new to SD, I even built myself a very good PC to run it but I was completely stumped, every other tutorial I've followed lead to errors and I couldn't figure out for the life of me how to make it work. Your instructions worked for some reason, even though the resources were exactly the same! Keep it up!
nice video, i used stable dif way before but it was too outdated so i needed a clean install and this video actually really helped me thank you !
Welcom
thanks for sharing your wisdom to me! i have a question. sorry for my rusty english
i tried to install stable diffusion following your instructions, everything went well before 8:08 of this video. the screen of stable diffusion didn't pop up in my computer screen. when i try to launch the file, webui- user, i see black window and text me some messages, and press any key message. when i do that, the window just closes. can you help me with this?
++ i installed 1.5 version from web ui site. maybe this is because of that. how can i uninstall 1.5 version and install the latest version?
+++ i see some messages saying: not a git repository from the screen.
Hi Can you share the msg plz
@@MunKaw-ui i saw 'fatal: not a git repository' message first. after i searched around othe youtube videos, i could type in 'git init' through git bash. after that, i saw message saying 'nothing added to commit but untracked files present (use "git add" to track)'.
i use window 11. thanks for your reply.
In this case, try uninstalling any other version of Python and git already installed, restart your PC and reinstall with the correct version. Make sure all other version are uninstalled
If you follow the process correctly, everything should work fine without using an environment variable.
But if it still doesn't work, try using Easy diffusion : it will do all the work
Its working but using only CPU, I have a RTX 4060 GPU but it's not being used at all.
Thank you for the initial success that I had today.
What is the latest and most useful version of Stable Diffusion that I can use locally? I keep coming across versions like SD XL, SD 3, etc. I would like to know which of these is the most widely used and the best quality in terms of production.
thx a lot, finally , wtih your guidance i make it :)😍
Can you please do a install video for A1111 on Linux? I recently moved to Linux Mint and somehow after installing everything, the start file doesn't work :( ...I searched for solutions but coudln't get any good advice so far. Please help me out.
thanks bro. you helped me out of the tunnel.
Great video, very good explanation. I see only one problem " fatal: not a git repository (or any of the parent directories): .git" Any advices for it? Thank you
You are in the wrong directory or in the wrong path to the repository
Initialize your repository with git init if you didn’t.
@@MunKaw-ui Thank you. Will try
Would this also work on a Intel HD graphics card? Or is this strictly for Nvidia? :(
when adding command line args first press space bar then type in --autolaunch "press space bar" then --xformers ,so stable diffusion opens the browser automatically..
can u elaborate more on this because i am not getting automatic popup
Is it work with portable stable diffusion, i have Git error with 1111, but on portable i can start
Yes it work if you Make sure the required dependencies are met
Thank you! I have one problem, I can get the webui open, but cant generate any images. Heres the error: FileNotFoundError: No checkpoints found. When searching for checkpoints, looked at:
- file C:\Users\Kaarel\Downloads\Stable Diffusion\stable-diffusion-webui-1.10.0\model.ckpt
- directory C:\Users\Kaarel\Downloads\Stable Diffusion\stable-diffusion-webui-1.10.0\models\Stable-diffusionCan't run without a checkpoint. Find and place a .ckpt or .safetensors file into any of those locations.
did you fix the issue?
When i try to generate, it didn't work it and it always say "Connection errored out", how can i fix this?
Reload program and let cmd window open.
Good explanation bro thanku
Everytime i ran webui-user.bat. I always get an error when installing torch and torchvision. With an error code "ERROR: Could not find a version that satisfies the requirement torch==2.1.2 (from versions: none)
ERROR: No matching distribution found for torch==2.1.2
Any way on how to fix this?
Try Python 3.10.6 in with a new environment variable
@@MunKaw-ui Thank You for the reply, i found the solution was to install python version 3.10.9, and i can now access SD, thanks again for this video
I am very new, so please advice me
I wish to use Kohya to train LORAs (not using Civitai for this one) but it seems to require plython 3.10.9 or above, not 3.10.6. If I use the former instead of 3.10.6, stable diffusion won't work.
Is there any other software/programme that allows me to train LORA offline and on local PC or how to reconcile the different plython requirement?
Thank you.
Hi
Try to install a different Python Version in a new virtual environment.
But what if i want to use it over and over again? will it reinstall the file on command line every time? If that is the case then its a long process since it will download and install all the files in command line.
hi
No, this is not the case
if you want to reuse it, just restart it by clicking on webui.bat
And dont forget to subscribe 🫶😁
Also getting this error, and I tried your solution you mentioned below; could it be because I have an AMD GPU?
RuntimeError: Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check
Edit webui-user.bat, where it says:
COMMANDLINE_ARGS=
and change it to:
COMMANDLINE_ARGS= --lowvram --precision full --no-half --skip-torch-cuda-test
Edit: The above assumes windows, if linux then add the line to webui-user.sh, and use quotes, may also need to delete the /venv folder based on others' comments:
COMMANDLINE_ARGS="--lowvram --precision full --no-half --skip-torch-cuda-test"
i am getting this error:
fatal: not a git repository (or any of the parent directories): .git
fatal: not a git repository (or any of the parent directories): .git
You are in the wrong working directory.
You run the command but not to the project folder where the git folder is located, make sure you typed the correct path.
@@MunKaw-ui i am really confused. I had followed exactly you did. Created desktop folder too. and ran the bat file after editing it as you did.
earlier i had copied the main files on another drive. But now as i have done exact same and on desktop. Still i am getting issue. I am really confused....
i figure out during git installation, the autoselection didn't allowed to run cmd anywhere, so after i reinstalled git with this change, it is installing. hope it works. Thanks
Hi. Thanks for the video. i followed all the instruction. Upon running user.bat file I get the following error message. can you please help?
ERROR: Could not find a version that satisfies the requirement torch==2.1.2 (from versions: 2.2.0, 2.2.0+cu121, 2.2.1, 2.2.1+cu121, 2.2.2, 2.2.2+cu121)
ERROR: No matching distribution found for torch==2.1.2
The instructions specifically state to use 3.10.6
Newer Python is not compatible with torch.
Torch is not able to use GPU....what to do know?
Delete the "VENV" folder
re-install
type CMD to open command window on VENV folder > scripts
type: pip install fastapi==0.90.1
type: python.exe -m pip install --upgrade pip
Reinstall the whole stable diffusion?
You can copy those folders that have your assets, Loras and checkpoints to another folder in the Hard Drive.
Then try what you want to do.
You can always uninstall SD and reinstall .
I don't know about your extensions but you won't lose your Loras and checkpoints.
So I will start by giving credit where it's due... thank you, this tutorial was a big help. I have come from NKMD side of things not knowing code at all, python is like Greek... ??? That said, I got A1111 up and running on my desktop, but I am getting hung up with an error on my laptop, (NVidia)GPU is 12, CPU graphics is 4, but it gives me this error:
RuntimeError: 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 . . .
How... Where do I modify code? Please... Thank you... ::D
Edit webui-user.bat where it says: set COMMANDLINE_ARGS=
You can open it with a block Note
You can fiind webui-user.bat in your : stable diffusion folder\webui
I hope this helps !
@MunKaw-ui thank you greatly :)
Can you help with the next hang up? I have it installed, but every time I try and run it it tells me "lowvram". The UI runs fine, but click generate and i get error. I don't think it is using my GPU, Is there a setting or code to force it to my GPU (Nvidia GTX 1650/Max-Q, 12GB). It makes no sense I have lowvram. Lol.
Oh 'AttributeError: 'NoneType' object has no attribute 'lowvram'
Your help has been great and thanks again.
Hi@@jrtcloud9 try : --xformers --upcast-sampling --precision full --medvram --no-half-vae
Automatic 11 can only run with an NVidia GPU This is completely false.
Thank you for this wonderful explanation
But I have a problem. When all the files are downloaded, even the 3.97 GB file, the installation doesnt progress after that. I even left it for 8 hours, but it didnt progress.
github.com/AUTOMATIC1111/stable-diffusion-webui/releases/tag/v1.0.0-pre
@@MunKaw-ui Thank you for this, but it didnt serve the purpose either, because the installation process freezes after downloading the file of this size 3.97 G
hey can i put sd3 model in it bro?
Hi
You have to install StableSwarmUI or ComfyUI for that
It doesn't work, it can't download torch: ERROR: Could not find a version that satisfies the requirement torch==2.1.2 (from versions: 2.2.0, 2.2.0+cu121, 2.2.1, 2.2.1+cu121, 2.2.2, 2.2.2+cu121, 2.3.0, 2.3.0+cu121, 2.3.1, 2.3.1+cu121)
ERROR: No matching distribution found for torch==2.1.2
the python version is too recent
if you go back to install an older version, this kind of problem arises
You have to reinstall in a clean venv
"Stable diffusion model failed to load" any solution for this? Thank you!
windowsreport.com/stable-diffusion-model-failed-to-load-exiting/
Hell yeah batman
not getting the bat file
I downloaded microsoft 64-bit but, it didn't open a file, it was just a zip file
github.com/AUTOMATIC1111/stable-diffusion-webui/releases/tag/v1.0.0-pre
thank you
Post more content
Good morning! I am trying to install Automatic1111 and I can't get it to work at all. I'm getting the error "exit code 1."
Is there any way you can help me? Maybe a Zoom call or something like that?
I've tried everything and I can't make it work... Thank you!
Yes of course there is a solution that I will share soon !
But you also need the minimum configuration.
i have error code 9009
I only have 2gb dedicated gpu and 9.9gb shared gpu
Try stable diffusion forge
jimmy voice from Mrbeast?
you're almost there.
hello, i have some trouble that when i start generating images, it took my CPU to do it instead my GPU (im using RX6600 btw), is there a way to switch them so that my GPU can do the work?
thank you
Hi,
Try this installation :github.com/lshqqytiger/stable-diffusion-webui-amdgpu/
File "D:\automatic1111\stable-diffusion-webui-1.0. 0-pre\venv\lib\site-packages\httpx\_transports\default.py", line 275
in ___ init_
self. _ pool = httpcore. AsyncConnectionPool(
TypeError: AsyncConnectionPool. __ init __ () got an unexpected keyword argument 'socket_options'
Press any key to continue this error is showing up
model.diffusion_model.input_blocks.0.0.weight
error
You have to update !