tutorial Archives - Austin's Nerdy Things

Like most other internet-connected people, I have seen the increase in AI-generated content in recent months. ChatGPT is fun to use and I’m sure there are plenty of useful use cases for it but I’m not sure I have the imagination required to use it to it’s full potential. The AI art fad of a couple months ago was cool too. In the back of my mind, I kept thinking “where will AI take us in the next couple years”. I still don’t know the answer to that. The only “art” I am good at is pottery (thanks to high-school pottery class – I took 4 semesters of it and had a great time doing so, whole different story). But now I’m able to generate my own AI art thanks to a guide I found the other day on /g/. I am re-writing it here with screenshots and a bit more detail to try and make it more accessible to general users.

NOTE: You need a decent/recent Nvidia GPU to follow this guide. I have a RTX 2080 Super with 8GB of VRAM. There are low-memory workarounds but I haven’t tested them yet. An absolute limit is 2GB VRAM, and a GTX 7xx (Maxwell architecture) or newer GPU.

Stable Diffusion Tutorial Contents

Installing Python 3.10
Installing Git (the source control system)
Clone the Automatic1111 web UI (this is the front-end for using the various models)
Download models
Adjust memory limits & enable listening outside of localhost
First run
Launching the web UI
Generating Stable Diffusion images

Video version of this install guide

Coming soon. I always do the written guide first, then record based off the written guide. Hopefully by end of day (mountain time) Feb 24.

1 – Installing Python 3.10

This is relatively straight-forward. To check your Python version, go to a command line and enter

python --version

If you already have Python 3.10.x installed (as seen in the screenshot below), you’re good to go (minor version doesn’t matter).

Python 3.10 installed for Stable Diffusion

If not, go to the Python 3 download page and select the most recent 3.10 version. As of writing, the most recent is 3.10.10. Download the x64 installer and install. Ensure the “add python.exe to PATH” checkbox is checked. Adding python.exe to PATH means it can be called with only python at a command prompt instead of the full path, which is something like c:/users/whatever/somedirectory/moredirectories/3.10.10/python.exe.

Installing python and adding python.exe to PATH

2 – Installing Git (the source control system)

This is easier than Python – just install it – https://git-scm.com/downloads. Check for presence and version with git –version:

git installed and ready to go for Stable Diffusion

3 – Clone the Automatic1111 web UI (this is the front-end for using the various models)

With Git, clone means to download a copy of the code repository. When you clone a repo, a new directory is created in whatever directory the command is run in. Meaning that if you navigate to your desktop, and run git clone xyz, you will have a new folder on your desktop named xyz with the contents of the repository. To keep things simple, I am going to create a folder for all my Stable Diffusion stuff in the C:/ root named sd and then clone into that folder.

Open a command prompt and enter

cd c:\

Next create the sd folder and enter it:

mkdir sd
cd sd

Now clone the repository while in your sd folder:

git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui

After the git clone completes, there will be a new directory called ‘stable-diffusion-webui’:

stable-diffusion-webui cloned and ready to download models

4 – Download models

“Models” are what actually generate the content based on provided prompts. Generally, you will want to use pre-trained models. Luckily, there are many ready to use. Training your own model is far beyond the scope of this basic installation tutorial. Training your own models generally also requires huge amounts of time crunching numbers on very powerful GPUs.

As of writing, Stable Diffusion 1.5 (SD 1.5) is the recommended model. It can be downloaded (note: this is a 7.5GB file) from huggingface here.

Take the downloaded file, and place it in the stable-diffusion-webui/models/Stable-diffusion directory and rename it to model.ckpt (it can be named anything you want but the web UI automatically attempts to load a model named ‘model.ckpt’ upon start). If you’re following along with the same directory structure as me, this file will end up at C:\sd\stable-diffusion-webui\models\Stable-diffusion\model.ckpt.

Another popular model is Deliberate. It can be downloaded (4.2GB) here. Put it in the same folder as the other model. No need to rename the 2nd (and other) models.

After downloading both models, the directory should look like this:

Stable Diffusion 1.5 (SD 1.5) and Deliberate_v11 models ready for use

5 – Adjust memory limits & enable listening outside of localhost (command line arguments)

Inside the main stable-diffusion-webui directory live a number of launcher files and helper files. Find webui-user.bat and edit it (.bat files can be right-clicked -> edit).

Add –medvram (two dashes) after the equals sign of COMMANDLINE_ARGS. If you also want the UI to listen on all IP addresses instead of just localhost (don’t do this unless you know what that means), also add –listen.

webui-user.bat after edits

@echo off

set PYTHON=
set GIT=
set VENV_DIR=
set COMMANDLINE_ARGS=--listen --medvram

call webui.bat

6 – First run

The UI tool (developed by automatic1111) will automatically download a variety of requirements upon first launch. It will take a few minutes to complete. Double-click the webui-user.bat file we just edited. It calls a few .bat files and eventually launches a Python file. The .bat files are essentially glue to stick a bunch of stuff together for the main file.

The very first thing it does is creates a Python venv (virtual environment) to keep the Stable Diffusion packages separate from your other Python packages. Then it pip installs a bunch of packages related to cuda/pytorch/numpy/etc so Python can interact with your GPU.

webui-user.bat using pip to install necessary python packages like cuda

After everything is installed and ready to go, you will see a line that says: Running on local URL: http://127.0.0.1:7860. That means the Python web server UI is running on your own computer on port 7860 (if you added –listen to the launch args, it will show 0.0.0.0:7860, which means it is listening on all IP addresses and can be accessed by external machinse).

stable-diffusion-webui launched and ready to load

7 – Launching the web UI

With the web UI server running, it can be accessed via browser on the same computer running the Python at http://127.0.0.1:7860. That link should work for you if you click it.

Note that if the Python process closes for whatever reason (you close the command window, your computer reboots, etc), you need to double-click webui-user.bat to relaunch it and it needs to be running any time you want to access the web UI.

Automatic1111 stable diffusion web UI up and running

As seen in the screenshot, there are a ton of parameters/settings. I’ll highlight a few in the next section

8 – Generating Stable Diffusion images

This is the tricky part. The prompts make or break your generation. I am still learning. The prompt is where you enter what you want to see. Negative prompt is where you enter what you don’t want to see.

Let’s start simple, with cat in the prompt. Then click generate. A very reasonable-looking cat should soon appear (typically takes a couple seconds per image):

AI-generated cat with stable diffusion 1.5 with default settings

To highlight a few of the settings/sliders:

Stable diffusion checkpoint – model selector. Note that it’ll take a bit to load a new model (the multi-GB files need to be read in their entirety and ingested).
Prompt – what you want to see
Negative prompt – what you don’t want to see
Sampling method – various methods to sample new points
Sampling steps – how many iterations to use for image generation for a single image
Width – width of image to generate (in pixels). NOTE, you need a very powerful GPU with a ton of VRAM to go much higher than the default 512
Height – height of image to generate (in pixels). Same warning applies as width
Batch count – how many images to include in a batch generation
Batch size – haven’t used yet, presumably used to specify how many batches to generate
CFG Scale – this slider tells the models how specific they need to be for the prompt. Higher is more specific. Really high values (>12ish) start to get a bit abstract. Probably want to be in the range of 3-10 for this slider.
Seed – random number generator seed. -1 means use a new seed for every image.

Some thoughts on prompt/negative prompt

From my ~24 hours using this tool, it is very clear that prompt/negative prompts are what make or break your generation. I think that your ability as a pre-AI artist would come in handy here. I am no artist so I have a hard time putting what I want to see into words. Take example prompt: valley, fairytale treehouse village covered, matte painting, highly detailed, dynamic lighting, cinematic, realism, realistic, photo real, sunset, detailed, high contrast, denoised, centered. I would’ve said “fairytale treehouse” and stopped at that. Compare the two prompts below with the more detailed prompt directly below and the basic “fairytale treehouse” prompt after that:

AI-generated “fairytale treehouse” via stable diffusion. Prompt: valley, fairytale treehouse village covered, matte painting, highly detailed, dynamic lighting, cinematic, realism, realistic, photo real, sunset, detailed, high contrast, denoised, centered

AI-generated “fairytale treehouse” via stable diffusion. Prompt: fairytale treehouse

One of these looks perfectly in place for a fantasy story. The other you could very possibly see in person in a nearby forest.

Both positive and negative can get very long very quickly. Many of the AI-generated artifacts present over the last month or two can be eliminated with negative prompt entries.

Example negative prompt: ugly, deformed, malformed, lowres, mutant, mutated, disfigured, compressed, noise, artifacts, dithering, simple, watermark, text, font, signage, collage, pixel

I will not pretend to know what works well vs not. Google is your friend here. I believe that “prompt engineering” will be very important in AI’s future. Google is your friend here.

Conclusion

AI-generated content is here. It will not be going away. Even if it is outlawed, the code is out there. AI will be a huge part of our future, regardless of if you want it or not. As the saying goes – pandora’s box is now open.

I figured it was worth trying. The guide this is based off made it relatively easy for me (but I do have above-average computer skill), and I wanted to make it even easier. Hopefully you found this ‘how to set up stable diffusion’ guide easy to use as well. Please let me know in the comments section if you have any questions/comments/feedback – I check at least daily!

Resources

Huge shout out to whoever wrote the guide (“all anons”) at https://rentry.org/voldy. That is essentially where this entire guide came from.

Introduction – what is SDR?

SDR stands for software defined radio. It is a term used to describe devices that can receive radio frequency signals over a wide range of frequencies. These devices most commonly interface with USB drives of computers / Raspberry Pi / similar. There are standalone-devices but they often cost quite a bit more than the USB devices. The best part about the base-level SDRs? They’re less than $50. I have a couple that I paid $18 for.

Video link to follow along – https://youtu.be/HUkaIJhoYUs

So you’re here on the “Getting Started with SDR” post. In this SDR tutorial post we’ll get a SDR plugged into your Windows computer, install drivers, and start sniffing for signals. We’ll try FM radio first since they have very powerful transmitters and there is almost certainly one you can receive at your hose, followed by checking for those wireless temperature sensors, and then some aircraft position signals.

What does a SDR look like? Below is a image with 3 I have around the house that I snagged for a picture (USB plug for size reference). Below the picture is the table of contents for the post.

picture showing 3 SDR devices - NooElec NESDR Nano 2, FlightAware ProStick, RTL-SDR Blog R820T2 RTL2832U V# — Example of a couple SDRs (all Realtek chipset-based, hence the RTL abbreviation)

SDR Tutorial Contents

Purchasing a suitable SDR
Plugging it into a Windows computer and installing drivers
Installing SDR# (a program to monitor any and all frequencies)
Listening to a FM radio station
Installing rtl_433 and listening for wireless temperature sensors
Installing dump1090 and listening for aircraft position signals

1 – Purchasing a suitable SDR

To get started, you’ll obviously need a RTL-SDR. I recommend the NooElec devices, specifically the NooElec NESDR Smart v5 bundle. NooElec devices have lasted the longest out of the 8 SDRs I’ve purchased and have been very useful for me. It includes 3 different antenna (433 MHz for sensors, 1090 MHz for ADS-B aircraft signals, and an adjustable antenna) which are useful for the rest of the tutorial:

With a SDR in hand, let’s get started!

2 – Installing drivers and plugging in the RTL-SDR

I use Windows 10 for this SDR tutorial, but I use Linux for the long-term monitoring I have in place around the house. Linux doesn’t ever automatically reboot for updates, and is generally much more stable (and doesn’t need a license). Windows is easy to get started so we’ll use it.

The instructions for installation are a bit long so I’ll just leave a link to the official source where they will always have the most up to date drivers and such – https://www.rtl-sdr.com/rtl-sdr-quick-start-guide/. I will re-write these at some point (and also make a video) but I’ll just leave the link for now.

3 – SDRSharp installation

If you followed the instructions in the link above, you should have a file called SDRSharp.exe in the folder you used:

SDRSharp.exe present in working directory

This means it is already “installed” since it is just a simple executable file. No need to click next, next, next finish to install.

4 – Listening to a FM radio station with your RTL-SDR

Go ahead and double-click on SDRSharp.exe and launch it! First thing you need to do is select the RTL-SDR USB option from the sources drop down menu:

Selecting the RTL-SDR USB source in SDRSharp

Next up, we need to crank the gain to get useful signal out of the SDR. Click the gear icon, make sure the RTL2832U device is selected, then set the RF gain slider to around 40dB, then click close:

Now we are ready to listen to FM radio!

Ensure the WFM radio button is selected in the signal type, set the zoom slider all the way down, set the step to 100 kHz, then click the frequency numbers up/down to pick a known FM station. This should get everything ready to go:

Setting SDRSharp for FM radio station reception

With all that setup out of the way, click the play button and watch the signals start streaming in! Assuming your speakers are set to a decent volume, you’ll hear the radio from your computer! From my 2nd story bedroom near Broomfield, CO, I can easily get 98.5 MHz and 99.5 MHz (and many others). You can also check the “FM Stereo” checkbox on the left side if you know you’ll be receiving FM stereo. Make sure you uncheck it if you start looking at other things:

SDRSharp FM radio reception for 98.5 Mhz (KYGO) and 99.5 MHz (KQMT)

Here is a picture showing my setup for writing this blog – a simple NooElec Nano SDR I bought in 2016, a little bit of cable, and a 1090 MHz antenna (which is clearly not ideal for FM radio frequencies, but radio is so powerful it doesn’t really matter). Also say hi to Fluffy the cat:

RTL-SDR set up for writing this blog post, with an appearance from Fluffy the black cat

5 – Installing rtl_433 and listening for wireless temperature/humidity sensors

Ok so now that we know radio works, let’s see what other radio frequency signals are traveling through the air. We will start by downloading the rtl_433 Windows release from GitHub. The latest version as of this post is here (https://github.com/winterrace/rtl_433_win/releases/download/v19.8.19/rtl_433_win_2019-08-19.zip). Unzip the .zip file. There should be two files inside, rtl_433.exe and rtlsdr.dll. I put these files on my desktop in a folder called rtl_433:

rtl_433.exe in a folder called rtl_433 on my desktop

Now open a command window, and change directory (cd) to Desktop/rtl_433.

C:\Users\Austin>cd Desktop\rtl_433

C:\Users\Austin\Desktop\rtl_433>

Ok now we’re in the rtl_433 directory so we can run commands now. The most basic command for this program is to run it and only specify the gain. We used 40 dB for the FM radio so let’s use 40 again by specifying it with the -g option (you can view all commands by running rtl_433 -h):

rtl_433 -g 40

The output will show the following (ending in “Tuned to 433.92 MHz”) if all went well:

Let it run for a couple minutes. You might see some thermometers and other such devices! Here is what my output looks like after about 60 seconds:

If you look closely, you can see there are three separate devices broadcasting on 433 MHz that I can pick up with my (still not desirable) 1090 MHz antenna! One is sitting in my garage, another is next to me in the bedroom, and I don’t actually know where the 3rd is or who owns it.

With the same, tiny USB RTL-SDR, we have picked up FM radio as well as temperature/humidity readings from three separate sensors!

6 – Installing dump1090 and listening for aircraft position (ADS-B) signals

Last up for this RTL-SDR tutorial is installing dump1090 and checking to see if we can pick up any aircraft signals.

Dump1090 is a utility written many years ago that decodes aircraft ADS-B position signals. Some brave souls ported it for use in Windows a while ago. Using the directions and links from https://sonicgoose.com/using-dump1090-in-windows/ I have distilled it down for you. Download the dump1090 windows package that I’ve rehosted here –

dump1090-win.1.09.0608.14 Download

And then extract it to your desktop in a folder called dump1090.

There is a .bat file (batch file) in the folder, double-click it to run it:

dump1090 folder in Windows showing dump1090.bat highlighted

You will be presented with a screen that updates in realtime as signals come in. You are now receiving ADS-B signals with the same device that could listen to FM radio, and also temperature/humidity sensors around the house!

Windows dump1090 showing ADS-B data streaming in from the RTL-SDR

All this from a 1090 MHz antenna (which is actually finally the right frequency for the application at hand). Fluffy is still supervising:

1090 MHz antenna attached to RTL-SDR to pick up aircraft ADS-B signals. Cat is helping (and has not moved in 3 hours).

Conclusion

In this SDR tutorial, we have purchased a RTL-SDR, installed the drivers, plugged it in, listened to FM radio, checked for wireless temperature/humidity sensors and found 3, and listened for aircraft ADS-B signals (and found 15 aircraft broadcasting in the last screenshot). This is an addictive hobby. With the right antenna, you can hear people speaking and morse code coding from across the world. In my next post I’ll show how to implement some of these into automated programs to take the data and input it into Home Assistant and other databases.

One last thing – receiving RF signals is 98% about the antenna and 2% about what you’re receiving the signals with! The base antennas that come with RTL-SDRs are good for the basics but if you really want to get into receiving interesting/distant signals, be prepared to spend 2-3x the cost of a SDR on a single antenna.

Hope you learned something and enjoyed this tutorial!