Installing Stable Diffusion Locally
ฝัง
- เผยแพร่เมื่อ 19 ต.ค. 2022
- HOW TO SUPPORT MY CHANNEL
-Support me by joining my Patreon: / enigmatic_e
_________________________________________________________________________
SOCIAL MEDIA
-Join my discord: / discord
-Instagram: / enigmatic_e
-Tik Tok: / enigmatic_e
-Twitter: / 8bit_e
_________________________________________________________________________
Links
Python
www.python.org/downloads/rele...
Git
git-scm.com/download/win
Automatic1111
github.com/AUTOMATIC1111/stab...
sd-v1-4.ckpt
huggingface.co/CompVis/stable...
GFPGAN v1.4 checkpoints
github.com/TencentARC/GFPGAN
![Stable Diffusion 1.5 - Windows Installation Guide [Tutorial]](http://i.ytimg.com/vi/ycQJDJ-qNI8/mqdefault.jpg)
thanks man! subscribed :) I am looking forward to see how your channel evolves.
brooo i've searched everwhere a tutorial like thisss, thank u so much♥
Thanks for this. Really appreciate it.
thanks for all of the info in your videos - keep it up!
if you don't mind sharing - what is your PC setup?
There it is... great job...
THE MOST STRAIGHTFORWARD tutorial ever. Appreciate you man!!
amazing stuff bro.. downloaded the 1.5 version and its game changer
Need your help !!
Torch are not installing
Tried doing it manually but still couldn't
You just have to install Git... you probably didn't install it correctly or you didn't install it at all, by the way... reboot the PC if you still have the same problem after installing Git.
Hi I've installed locally successfully. When I tried to use simple wordings for txt2img, and waited for few minutes, but the result turned out blank/black only. Any thoughts why this happened?
I've already choose the model.ckpt checkpoint before generating the image.
Maybe you can help me out.. If I want to add more stable diffusion models for inpainting/outpainting, what do I do? Just download the ckpt and stick it in the model folder?
I'm kinda lost on this. I've got SD v 1.5 :)
thnk you so much
thanks 🙏🙏
thanks a lot 😀
very good
Hi! congratulations for your channel!!! look, stable diffusion V2 has been released... do you think this model can be used with the new version of SD? thanks a lot in general
Hey thanks! Not sure, I haven‘t tried V2 yet. But i dont see how it would be different.
@@enigmatic_e well, I am going to get rid of the interface I had and try the one you suggest in the video. I guess I will try V1 first, since I want to be sure everything works and see if later -once everything works- can try to do the same with V2. I don't have the knowlege to try myself directly 🤕 Maybe I should wait till someone more experienced does it. Let's see. Cheers and keep on testing! thank you very much!
@@manimartinez1232 i will try to make an update video asap.
@@enigmatic_e That's very kind. I heard V" doesn't have UI made yet... but you are more into it. I did install your model and it works great!
Hey bro can you help me out ?
The last installation step is not working for me, its showing an error
Type Error: 'NonType' object is not subsrciptable
I have an Intel Mac. Am I correct in assuming that I’m going to need a different machine (one with an NVIDIA GPU)? Also, what’s the cheapest one / earliest model of the GPU that I could get away with (for Stable Diffusion)? Say for instance the wait time for a 720p image should not be greater than 30 seconds. So roughly which ones should I be looking into? Any help would be greatly appreciated. Thanks so much.
Hello! At the 01:00 mark I go over system requirements. Unfortunately you can’t use mac from what I understand.
@@enigmatic_e automatic1111 is supposedly Mac compatible but I am a mac user and can’t get it to install 😬
@@enigmatic_e Sorry I missed that part. Thanks so much for replying. I’m trying the ‘openvino’ version right now. Let’s see if it works. Will let you know if it works.
@@HopsinThaGoat The automatic1111 is said to be Apple Silicon compatible (M1 chip).
@@enigmatic_e Got it to work on my Intel Mac. Speed - 6s/iteration. This is using OpenVino SD version.
Python was not found; run without arguments to install from the Microsoft Store, or disable this shortcut from Settings > Manage App Execution Aliases. how could i fix that > thanks you
Hi, thank you for the job, i install and follow all steps succesfully.
👍🏽
do i need to run the BAT everytime or can I go to the link?
Hi so, when it comes to download torch and torchvision, my computer stops responding, as in, i cant do anything and it doesn't download it. Any ideas what might b causing this?
same, any update on how to fix?
hello for those who are stuck at sd-v1-4.ckpt. it is very simple just create account. click the link again then ABOVE THE FILE LOCATION U NEED TO ACCEPT TERMS! only then it will let you download
can i download this on my mac book pro?
hi, i installed stable defusion (fairly easily thanks to your video) and it worked fine. but when I closed the command prompt window it stopped working and I could not get it back when I closed the browser. is there something I missed ?
Mmm sure what that could be. Are you still having that issue?
@@enigmatic_e yes
Do you mean you closed the window where you got your link from? If so, you shouldn‘t close while using browser.
@@enigmatic_e no, i close the cmd prompt window and it stalled. i then closed the browser but could not find where to restart it. like i bookmarked the browser but it wasn't threr. i looked thruough my programs and apps and couldnot find how to restart it. there was some desktop shortcuts but i could't figure out hoe to start it. it could just me being stupid ofc
"webui-user" bat file does not open when I double click it.
i got Error verifying pickled file from ..... , AttributeError: 'NoneType' object has no attribute 'keys'
What should I do if the last step keeps showing an error during the installation? Error message: ERROR: Could not find a version that satisfies the requirement numpy (from torchvision) (from versions: none)
ERROR: No matching distribution found for numpy
Not sure but this is an older video. Maybe if you follow my newer one you can fix the issue th-cam.com/video/qmnXBx3PcuM/w-d-xo.html
Excelente mil grx, no sabia x dnd instalar
@enigmatic_e
Can you do a video tutorial of Stable diffusion installation on Windows 11 but with an Intel Arc A770 16 GB GPU?
I've tried to find clear sound videos but some say with OpenVino Script and instead of making the tutorial step by
step all the way till working; they just stop and say go here and there and the installation doesn't work or it works
and it doesn't allow OpenVino Script usage. Or it works and some models like Loras or Checkpoints do not work.
Thanks for your help. Or if you come across a video where it explains step by step like you did without skipping
any part for Intel Arc GPU's I will sincerely appreciated it. All the best and God bless you Sir.
Hey enigmatic,
followed everything to the T ...when double-clicking on the BAT file, it shows:
Couldn't launch python
exit code: 9009
stderr:
Python was not found; run without arguments to install from the Microsoft Store, or disable this shortcut from Settings > Manage App Execution Aliases.
much appreciate the help.
UPDATE: found out that i needed to edit the bat file and put in the location of python.
Thanks for making this guide bro 🙏
So you were about to get it going?
@@enigmatic_e yes got it! thanks for the follow up. 🙌
@@NathanHoang can you explain how you fixed this cause i have this issue :(
@@itshuskai oh man.. completely missed your comment, i hope you found the solution. But if you didnt...
It was in the webui-user.bat file that i have to edit and put in the location of the python.exe
Easy Peasy thanks
I cannot get past git installation
It freezes at "running post-initial script.
Can anyone help me with that?
bro the ckpt site is not working, can u please upload the ckpt file to a google drive
probably cause its an old tut. heres a newer one studio.th-cam.com/users/videoqmnXBx3PcuM/edit
@@enigmatic_e huggingface site is down
Help! How do I turn mine to dark mode?
Probably a total noob question. I downloaded and installed this a couple of weeks ago after following similar instructions on another video and both his one AND your one defaulted automatically to dark mode however mine doesn't and I have no idea where to change it and googling hasn't helped. Anyone able to school me? Is it a python thing you have to switch???
-thanks!
Hey, I was able to change the colors in my browser settings under appearance. I‘m not sure how you would do it on other browsers but I would guess it‘s something similar.
@@enigmatic_e Found it! It's a Windows dark setting not a Chrome one. Thanks!
will this work with version 2.1?
I may need to upload an updated video. Might do that today.
i get exit code: 9009 when starting the bat
Hello Sir, I tried almost 7 times, in came out with
“self.weight = Parameter(torch. empty((out_features, in_features), **factory_kwargs))
RuntimeError: [enforce fail at .. \c10\core\impl\alloc_cu.cpp:72] data. DefaultCPUAllocator: not enough memory: you trie d to allocate 6553600 bytes
Stable diffusion model failed to load, exiting
Press any key to continue
What I need to do? Pls help me
@@logendransubramaniam9913 try to see this newer video helps th-cam.com/video/qmnXBx3PcuM/w-d-xo.html
What type of graphic card model is required for use?
Brother!! I clicked on it (the SD-v1-4.ckpt), but it asked me for username and password. What should I do??? Please add helps for that..
You have to create an account.
Its free
@@enigmatic_e I tried to sign up for joining Huggingface, but when I put my email address, added password, and clicked next,,, it just turned back for me to refill again (what was wrong with that??) 😓😓 My first time to sign up with something happening like this. I tried to apply two of my emails, however; didn’t work at all. Any kind of emails they need I don’t know, please help..
@@thivtsab9968 same over here
@@hezhahama2306 yeah same
top respect спасибо из России бро
Hey, i just got this error message right after it show me the local url. It says : " Interrupted with signal 2 in
Didn't work for me.
Even though GFPGN was not in the directory, running webui-user.bat still leads to a "Installing gfpgan" prompt which fails.
Why is it trying to install something that it does not know exists?
Even if I put it in the directory it still will not process and just leads to a long message.
I Have A Problem When Running Webuiuser.bat - "OSError: Can't load tokenizer for 'openai/clip-vit-large-patch14'. If you were trying to load it from 'huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'openai/clip-vit-large-patch14' is the correct path to a directory containing all relevant files for a CLIPTokenizer tokenizer"
I am unable to find any solution for this
please let me know If Anyone Finds Solution for this Problem
sd-v1-4.ckpt wants login and password
Yea just create an account. Should be free
Nevermind, I had to accept the terms and conditions or something first.
Traceback (most recent call last):
File "D:\SD UI\stable-diffusion-webui-master\launch.py", line 294, in
prepare_environment()
File "D:\SD UI\stable-diffusion-webui-master\launch.py", line 212, in prepare_environment
run_pip(f"install {gfpgan_package}", "gfpgan")
File "D:\SD UI\stable-diffusion-webui-master\launch.py", line 78, in run_pip
return run(f'"{python}" -m pip {args} --prefer-binary{index_url_line}', desc=f"Installing {desc}", errdesc=f"Couldn't install {desc}")
File "D:\SD UI\stable-diffusion-webui-master\launch.py", line 49, in run
raise RuntimeError(message)
RuntimeError: Couldn't install gfpgan.
Command: "D:\SD UI\stable-diffusion-webui-master\venv\Scripts\python.exe" -m pip install git+github.com/TencentARC/GFPGAN.git@8d2447a2d918f8eba5a4a01463fd48e45126a379 --prefer-binary
Error code: 1
stdout: Collecting git+github.com/TencentARC/GFPGAN.git@8d2447a2d918f8eba5a4a01463fd48e45126a379
Cloning github.com/TencentARC/GFPGAN.git (to revision 8d2447a2d918f8eba5a4a01463fd48e45126a379) to c:\users\kin777\appdata\local\temp\pip-req-build-xjt_92m2
stderr: ERROR: Error [WinError 2] ϵͳҲָļ while executing command git version
ERROR: Cannot find command 'git' - do you have 'git' installed and in your PATH?
[notice] A new release of pip available: 22.2.1 -> 22.3.1
[notice] To update, run: D:\SD UI\stable-diffusion-webui-master\venv\Scripts\python.exe -m pip install --upgrade pip
How to solve it Thank you
There are problems with gfpgan.
1, There are actually multiple versions of 1.4, and you need the exact right one. How to find it? Who knows.
2. If you failed for whatever reason to install it once, and then tried re-installing it with a different version it will still fail until you uninstall everything (manually delete all leftover folders including the python ones in user/appdata) and try again. Even then it still may fail.
I just get errors Installing torch and torchvision
Traceback (most recent call last):
File "D:\StableDiffusion\stable-diffusion-webui-master\launch.py", line 255, in
prepare_enviroment()
File "D:\StableDiffusion\stable-diffusion-webui-master\launch.py", line 173, in prepare_enviroment
run(f'"{python}" -m {torch_command}', "Installing torch and torchvision", "Couldn't install torch")
File "D:\StableDiffusion\stable-diffusion-webui-master\launch.py", line 34, in run
raise RuntimeError(message)
RuntimeError: Couldn't install torch.
Command: "D:\StableDiffusion\stable-diffusion-webui-master\venv\Scripts\python.exe" -m pip install torch==1.12.1+cu113 torchvision==0.13.1+cu113 --extra-index-url download.pytorch.org/whl/cu113
Error code: 1
stdout: Looking in indexes: pypi.org/simple, download.pytorch.org/whl/cu113
stderr: ERROR: Could not find a version that satisfies the requirement torch==1.12.1+cu113 (from versions: none)
ERROR: No matching distribution found for torch==1.12.1+cu113
[notice] A new release of pip available: 22.3 -> 22.3.1
[notice] To update, run: D:\StableDiffusion\stable-diffusion-webui-master\venv\Scripts\python.exe -m pip install --upgrade pip
You just have to install Git... you probably didn't install it correctly or you didn't install it at all, by the way... reboot the PC if you still have the same problem after installing Git.