Stable Diffusion SDXL LoRA Training Tutorial

🎁#stablediffusion #sdxl #stablediffusiontutorial

Stable Diffusion SDXL Lora Training Tutorial

📚 Commands to install sd-scripts 📝

📚 Training config files for Stable Diffusion SDXL Lora Training Tutorial 🚀📝

🏋️‍♀️ System RAM 💾, Graphic card VRAM 🎮, time taken ⏱️ for different training 🏋️‍♀️

☕️ Please consider supporting me in Patreon 🍻

👩‍👧LoRA model 😊

Mastering stable diffusion SDXL Lora training can be a daunting challenge, especially for those passionate about AI art and stable diffusion.

But fear not! If you're eager to unlock the full creative potential of Lora in AI art, we have the perfect tutorial for you.

In this YouTube video, we'll take you step-by-step through the stable diffusion SDXL Lora training process, empowering you to create mesmerizing AI art like never before.

So, if you're ready to dive into the world of stable diffusion and elevate your AI art with Lora, stay tuned and let's embark on this exciting journey together!

Today we will go through the steps to train the S D X L Lora model on Windows

It’s the same on Linux Ubuntu

[OZM]

what exactly do you gain from blurring the times in the chart?

[SussyBacca]

Im so glad he blurred his times and ram and such... i was like "OH MY GOD MY KIDS ARE WATCHING THIS!!!" But luckily he blured the times and my kids remain unscathed to this day. Great job mate! We appreciate the quick thinking and extra effort! 🙏

[jason]

This is great thank you very much for this video. I'm using a 3070ti and it all worked perfectly. The majority of the pictures that I have made came out okay but none at the level from SD1.5. I tried to run the refiner however that resulted in a error.

[PeteStueve]

Just curious why are you using cuda 116 I have a 4090 would it be better for me to install torch with 118 or 12.1??

[resxd]

Thank you for your tutorial, ill try it today see how it goes.
How much vram do i need ? I have nvidia rtx 3060 with 12gigabites of memory will that be enough ?

[jamesclow]

Thanks :-) What version of python are you using? I want to make sure my conda environment is set to use the correct version. Thanks

[muratgokturk]

I get an error like this when starting the tutorial:

PS C:\SDLora\sd-scripts> accelerate launch "sdxl_train_network.py"
The following values were not passed to `accelerate launch` and had defaults used instead:
`--num_processes` was set to a value of `1`
`--num_machines` was set to a value of `1`
`--mixed_precision` was set to a value of `'no'`
`--dynamo_backend` was set to a value of `'no'`
To avoid this warning pass in values for each of the problematic parameters or run `accelerate config`.
Loading settings from
Traceback (most recent call last):
File "C:\Users\murat\AppData\Local\Programs\Python\Python310\lib\site-packages\toml\decoder.py", line 511, in loads
ret = decoder.load_line(line, currentlevel, multikey,
File "C:\Users\murat\AppData\Local\Programs\Python\Python310\lib\site-packages\toml\decoder.py", line 778, in load_line
value, vtype = self.load_value(pair[1], strictly_valid)
File "C:\Users\murat\AppData\Local\Programs\Python\Python310\lib\site-packages\toml\decoder.py", line 866, in load_value
raise ValueError("Reserved escape sequence used")
ValueError: Reserved escape sequence used

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "C:\SDLora\sd-scripts\sdxl_train_network.py", line 173, in <module>
args = train_util.read_config_from_file(args, parser)
File "C:\SDLora\sd-scripts\library\train_util.py", line 3274, in read_config_from_file
config_dict = toml.load(f)
File "C:\Users\murat\AppData\Local\Programs\Python\Python310\lib\site-packages\toml\decoder.py", line 156, in load
return loads(f.read(), _dict, decoder)
File "C:\Users\murat\AppData\Local\Programs\Python\Python310\lib\site-packages\toml\decoder.py", line 514, in loads
raise TomlDecodeError(str(err), original, pos)
toml.decoder.TomlDecodeError: Reserved escape sequence used (line 1 column 1 char 0)
Traceback (most recent call last):
File "C:\Users\murat\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "C:\Users\murat\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 86, in _run_code
exec(code, run_globals)
File "C:\Users\murat\AppData\Local\Programs\Python\Python310\Scripts\accelerate.exe\__main__.py", line 7, in <module>
File "C:\Users\murat\AppData\Local\Programs\Python\Python310\lib\site-packages\accelerate\commands\accelerate_cli.py", line 45, in main
args.func(args)
File "C:\Users\murat\AppData\Local\Programs\Python\Python310\lib\site-packages\accelerate\commands\launch.py", line 918, in launch_command
simple_launcher(args)
File "C:\Users\murat\AppData\Local\Programs\Python\Python310\lib\site-packages\accelerate\commands\launch.py", line 580, in simple_launcher
raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd)
Command '['C:\\Users\\murat\\AppData\\Local\\Programs\\Python\\Python310\\python.exe', 'sdxl_train_network.py', returned non-zero exit status 1.

[makulVR]

I appreciate your tutorial and I would love to support you but the LoRA you have created is far from perfection. It looks more like an early 1.5 LoRA with a lot of artefacts. I am looking for a tutorial with a superior outcome like the latest 1.5 realism-models but with more depth and details

[abdallahalswaiti]

i think it will be amazing if you find a way to transforms sd 1.5 loras to sdxl one

[AgustinCaniglia]

Do I need to install and use the visual basic? or can I do it in a simple terminal?

[TheKuzmann]

I'm getting error when trying to use reg images (Invalid user config). extra keys not allowed @ Help pls :)

[zdnmite]

thanks! But where can I download the Lora folder like your demonstration?

[ORGANICMINDART]

How about running in M1 Mac .. can u provide the tutorial or the setting ?

[Endangereds]

which graphics card are you using? VRAM?

[Bakobiibizo]

you need to slow down the speed the text to speech is read back, took me a sec to pick it up tho

[silvermushroom-gamifyevery]

I'll bait, what's up with the downvote ratio?

[simplymanneh]

SDXL is currently unusable due to censorship -> uninstalled