| AI Image Creation Offline on Windows using NVIDIA GPU | |
| About installing Diffusers in a virtual environment: | |
| https://huggingface.co/docs/diffusers/installation | |
| But I include the instructions on what you need to do below. | |
| --- | |
| I am still working on this. (note added December 7th, 2023) I am very new to | |
| this, so I'm sure there are many ways this could be done better. | |
| --- | |
| You must have a NVIDIA graphics card with Cuda installed. I already had Cuda | |
| installed. If you need Cuda, it's in a step below. This script is written to | |
| be used on my Windows computer using the GPU. This script will not work | |
| using a CPU. While there is code in the script for CPU usage, it doesn't | |
| work on a Windows computer. It might be related to the Triton module not | |
| being available in Windows. There seem to be something that might work, but | |
| it would have meant installing something from elsewhere that I was not | |
| willing to try. | |
| The version of CUDA might matter. If you have one that doesn't work, you | |
| might have to install a different version of CUDA. | |
| If you have installed Automatic1111, you don't need to do step 1 and 2 as | |
| that program required Python and Git. You don't need Automatic1111 installed | |
| to use this program. | |
| About Automatic1111: | |
| https://github.com/AUTOMATIC1111/stable-diffusion-webui#installation-and-running | |
| Your Antivirus/Firewall software will need to be set to allow the command | |
| prompt to download and install these programs. What you allow or don't allow | |
| is up to you. You may need to reinstall some of it if you don't allow it | |
| through the first time and it doesn't work for you. I don't know what the | |
| minimum you need to allow would be, or if some or all of it can operate in a | |
| sandboxed environment. | |
| --- | |
| Step 1 (if you haven't done already): | |
| Install Python 3.10.6: | |
| https://www.python.org/ftp/python/3.10.6/python-3.10.6-amd64.exe | |
| Make sure to check "Add Python to PATH" | |
| --- | |
| Step 2 (if you haven't done already): | |
| Install git | |
| https://git-scm.com/download/win | |
| --- | |
| Step 3: | |
| Create directory manually: | |
| C:/Diffusers | |
| This can be anywhere, but if you change it here you need to change it in all | |
| the other places in these instructions and in some of the files you | |
| download. | |
| --- | |
| Step 4: | |
| You need to open a regular Command Prompt. You can press Win key + R to get | |
| "Run" window. In that, enter: | |
| cmd | |
| In Command Prompt, copy this line and press Enter: | |
| cd C:\Diffusers && py -m venv .venv && .venv\Scripts\activate.bat | |
| This will change the directory of the command prompt to the directory you | |
| created. Next, it creates a virtual environment for Python as described | |
| here: | |
| https://packaging.python.org/en/latest/guides/installing-using-pip-and-virtual-environments/ | |
| Finally, it activates that virtual environment as also described there. | |
| The command prompt will now look like this: | |
| (.venv) C:\Diffusers> | |
| You don't need to reopen the Command Prompt each time. Wait until a task | |
| finishes and then you will be able to enter the next command. It's best you | |
| do not close it. | |
| If you do close it, you will need to go to the directory again each time and | |
| activate the virtual environment like this, by copying this and pressing | |
| Enter: | |
| cd C:\Diffusers && .venv\Scripts\activate.bat | |
| You do not want to install Python packages outside of the virtual | |
| environment as it would replace the packages in your main installation. That | |
| could cause conflicts in other programs. | |
| Always make sure you have: | |
| (.venv) C:\Diffusers> | |
| In future steps. (though I have added the code to activate it every time as | |
| a precaution) | |
| --- | |
| Step 5 (optional): | |
| pip is the package installer for Python. | |
| If you want to make sure pip is up-to-date, in Command Prompt (that is doing | |
| things in your virtual environment), copy this line and press Enter: | |
| cd C:\Diffusers && .venv\Scripts\activate.bat && py -m pip install --upgrade pip | |
| If you want to then verify it updated, you could optionally do this, in | |
| Command Prompt, copy this line and press Enter: | |
| cd C:\Diffusers && .venv\Scripts\activate.bat && py -m pip --version | |
| Since you are using a virtual environment, packages that are installed will | |
| be installed into this folder rather than into Python's main program: | |
| C:/Diffusers/.venv/Lib/site-packages | |
| That way you don't cause issues updating things you may not want to have | |
| updated. | |
| --- | |
| Step 6 (if needed; unsure of this step, I didn't do it): | |
| If you don't have Cuda and need to get it, it's here: | |
| https://developer.nvidia.com/cuda-toolkit-archive | |
| I have 12.2 installed. Some things mention needing 12.1. In Step 8, as of | |
| writing this, it specifically mentions Cuda 12.1. You may want to check the | |
| PyTorch website first in Step 8 if you need to install Cuda to see what | |
| version it is compatible with or you will not get past that step. | |
| That link above has a list of prior versions. As packages update, you might | |
| need something even newer. | |
| To see what version of Cuda you have, in Command Prompt, copy this | |
| line and press Enter: | |
| nvidia-smi | |
| In the top right corner of the text output that is displayed, your Cuda | |
| version will be displayed. | |
| An older page on this command is here: | |
| https://developer.nvidia.com/nvidia-system-management-interface | |
| The text output now looks different. | |
| --- | |
| Step 7: | |
| You need to install PyTorch. | |
| You should visit their website and see what version they recommend based on | |
| the version of Cuda you have. | |
| https://pytorch.org/ | |
| As of writing this, in the "INSTALL PYTORCH" section I selected the Stable | |
| PyTorch build, Windows, Pip, Python and Cuda 12.1. | |
| That generated in the "Run this Command" section the command you see below. | |
| (with the added code to do this in the virtual environment) | |
| To install PyTorch in Command Prompt (that is doing things in your virtual | |
| environment), copy this line and press Enter: | |
| cd C:\Diffusers && .venv\Scripts\activate.bat && pip3 install -U xformers --index-url https://download.pytorch.org/whl/cu121 | |
| A lot of things will download and install, including any packages needed to | |
| run this. When complete, move on to the next step. (when the command prompt | |
| returns to where you can paste into it again) | |
| The torch file alone is over 2 gigabytes. | |
| --- | |
| Step 8: | |
| This step installs the rest of what you need. | |
| You can read about them if you want: | |
| https://huggingface.co/docs/diffusers/index | |
| https://huggingface.co/docs/transformers/index | |
| https://huggingface.co/docs/accelerate/index | |
| https://pypi.org/project/ftfy/ | |
| https://github.com/modin-project/modin | |
| https://pypi.org/project/invisible-watermark/ | |
| https://github.com/gradio-app/gradio | |
| To install these, in Command Prompt (that is doing things in your virtual | |
| environment), all you need to do is copy this line and press Enter: | |
| cd C:\Diffusers && .venv\Scripts\activate.bat && pip install diffusers transformers accelerate ftfy modin[all] invisible_watermark | |
| A whole bunch of things, what might be 100 packages or more, will download | |
| and install, including any packages needed to run these. | |
| When complete, you might need to install a later version of Gradio. A later | |
| version fixes a bug that is needed for the menus to work properly. This | |
| worked for me: | |
| cd C:\Diffusers && .venv\Scripts\activate.bat && pip install https://gradio-builds.s3.amazonaws.com/6b1401c514c2ec012b0a50c72a6ec81cb673bf1d/gradio-4.8.0-py3-none-any.whl | |
| That was found here: | |
| https://www.gradio.app/docs/blocks | |
| After selecting "main" from the version number dropdown in the left column. | |
| The link changes. If you don't want to doit that way, just do this instead | |
| to see if the dropdown menus work: | |
| cd C:\Diffusers && .venv\Scripts\activate.bat && pip install gradio | |
| The gallery feature doesn't allow images to be downloaded using the download | |
| button in the current version above. Hopefully that will work in a later | |
| version. (so eventually you will need to try another Gradio version) | |
| When a later version is eventually called, "gradio" will eventually be added | |
| to the original command rather than having to specify it separately. | |
| When complete, move on to the next step. | |
| --- | |
| Step 9: | |
| Download the following file: | |
| https://huggingface.co/spaces/magicfixeseverything/ai_image_creation/raw/main/app.py | |
| Add it into a folder you create here: | |
| C:/Diffusers/.venv/ | |
| Like this: | |
| C:/Diffusers/.venv/ai_image_creation/ | |
| Add then add the file here: | |
| C:/Diffusers/.venv/ai_image_creation/app.py | |
| There are some things you will need to change in that file, most notably the | |
| directory specified in "main_dir" | |
| --- | |
| Step 10: | |
| You're ready to run the script that runs the web interface. | |
| The first time the models download it will take time as it's gigabytes of | |
| data that you need to download. An individual model file isn't downloaded | |
| until you actually try creating an image for that model. For all four | |
| models, the total size might be about 20 gigabytes if running on a GPU. It | |
| could be twice that size if on a CPU. | |
| In Command Prompt (that is doing things in your virtual environment), copy | |
| this line and press Enter: | |
| cd C:\Diffusers && .venv\Scripts\activate.bat && py .venv\ai_image_creation\app.py | |
| That will launch the web interface. | |
| Model files are downloaded to: | |
| C:\Diffusers\model_data | |
| You should know that this folder can grow considerably. You need to manually | |
| clean it out when you need to get rid of old models. Occasionally, new | |
| versions will be downloaded when you create an image. When that happens, you | |
| may want to remove the old version if the new version works. Otherwise, you | |
| could have 10 to 20 gigabytes of space added each time. | |
| You should also know that temporary images created are likely stored here: | |
| %USERPROFILE%/AppData/Local/Temp/gradio | |
| Those however are likely cleaned out automatically by your computer. | |
| A package called Triton apparently can't be installed on Windows so you will | |
| see an error in the Command Prompt go by about that every time you launch | |
| the web interface. It doesn't seem to impact anything when using a GPU on | |
| Windows. | |
| https://github.com/openai/triton/issues/1057 | |
| https://github.com/openai/triton/issues/1640 | |
| Someone offers something there that might work, but I didn't want to install | |
| something from someone randomly. Again, it seems to work without it when | |
| using a GPU. If trying to use a CPU using Windows, then it might mean you | |
| can't use this script. | |
| When done, you will get a message like this: | |
| Running on local URL: http://127.0.0.1:7860 | |
| If your browser did not open a web browser, visit the link that was in the | |
| command prompt. If it was not the one above, note it. However, if you have | |
| something like Automatic1111 open already, it will use a different port, | |
| like "7861". | |
| It might be this: | |
| http://127.0.0.1:7860 | |
| --- | |
| Step 11: | |
| When you open the link, you'll see the display to create the imagery. You | |
| must leave the command prompt open. When you process an image, the command | |
| prompt will tell you the progress of what you are creating and approximately | |
| how long it will take for the step it is on. It will take longer as there | |
| will be things that happen for which there is no progress indicator. | |
| --- | |
| Step 12: | |
| To create a shortcut to the command prompt that needs to be launched every | |
| time, download the following file: | |
| https://huggingface.co/spaces/magicfixeseverything/ai_image_creation/raw/main/ai_image_creation.bat | |
| Add it into the folder you created: | |
| C:/Diffusers/.venv/ai_image_creation/ai_image_creation.bat | |
| The content of that file is the following: | |
| @echo off | |
| cd C:\Diffusers | |
| call .venv\Scripts\activate.bat | |
| timeout /t 0 >nul | |
| py .venv\ai_image_creation\app.py | |
| cmd /k | |
| For whatever reason, sometimes a shortcut from the desktop doesn't execute. | |
| I am seeing if a timeout for zero seconds works. (>nul makes the delay | |
| message not appear) | |
| Next, we will create a shortcut to that, which you could do on the desktop. | |
| You can follow the instructions below or download this file instead: | |
| https://huggingface.co/spaces/magicfixeseverything/ai_image_creation/resolve/main/AI%20Image%20Creation.lnk | |
| Right click on your desktop and then click on "New > Shortcut". | |
| For "Type the location of the item", enter: | |
| cmd | |
| Then click "Next". You can name the shortcut whatever you want, like | |
| "AI Image Creation". | |
| Then click "Finish". | |
| Then right click on the shortcut you created and click "Properties". | |
| In "Target", replace what is there with the following: | |
| C:\Windows\System32\cmd.exe /k C:/Diffusers/.venv/ai_image_creation/ai_image_creation.bat | |
| That will execute that file each time you click on it. | |
| If for some reason that doesn't work sometimes, and rather than get the | |
| program to launch it simply opens the command prompt, then you must enter | |
| this each time in the command prompt: | |
| cd C:\Diffusers && .venv\Scripts\activate.bat && py .venv\ai_image_creation\app.py | |
| You might also not be able to use a shortcut. If so, just copy | |
| "ai_image_creation.bat" and put it on your desktop and name it what you | |
| want. | |
| --- | |
| Step 13 (Important): | |
| I feel this is a very important step. After you have created model data for | |
| each base model, as well as have used the refiner and upscaler, data will | |
| then have been downloaded. This could be 30 gigabytes or more of data. I | |
| strongly recommend that you then disable the script from downloading updates | |
| to the model data. It will not automatically delete old data. If you didn't | |
| manually go through and delete the older data, eventually the model data | |
| would use all of the space on your computer. | |
| There is something that is very important to note however. If you do this, | |
| other installations that use Hugging Face for example, like Automatic1111, | |
| will not be able to download data and will not work properly. | |
| Once you have downloaded the model data for each model, you can disable | |
| updating by doing the following in a command prompt: | |
| setx HF_HUB_OFFLINE "1" | |
| It doesn't matter if it is in your virtual environment or not as it will be | |
| stored with all your environment variables. | |
| To view where this variable goes, in the search bar in Windows you can look | |
| for: | |
| edit environment variables | |
| And it will be listed. | |
| If you need to once again download model data, you can delete it there or | |
| enter the following in the command prompt: | |
| setx HF_HUB_OFFLINE "0" && REG DELETE HKEY_CURRENT_USER\Environment /v HF_HUB_OFFLINE /f | |
| In my testing, setting it to 0 and then deleting it made it immediately take | |
| effect, once you restart the script, to be able to download model data | |
| again. | |
| You can read about environment variables here at Hugging Face: | |
| https://huggingface.co/docs/huggingface_hub/package_reference/environment_variables#hfhuboffline | |
| In regard to Hugging Face caching things, you can learn more on this page: | |
| https://huggingface.co/docs/huggingface_hub/how-to-cachehttps://huggingface.co/docs/huggingface_hub/how-to-cache#limitations | |
| This is just my preferred way of handling it. | |
| Optionally, you can disable telemetry by entering this in the command | |
| prompt: | |
| setx HF_HUB_DISABLE_TELEMETRY "1" | |
| And to turn it back on: | |
| setx HF_HUB_DISABLE_TELEMETRY "0" && REG DELETE HKEY_CURRENT_USER\Environment /v HF_HUB_DISABLE_TELEMETRY /f | |