SDXL LORA Training locally with Kohya - FULL TUTORIAL // stable diffusion

Let me show you how to train LORA SDXL locally with the help of Kohya ss GUI. This is the ultimate LORA step-by-step training guide, and I have to say this because this video took me two weeks to make /rip/.
To know how to train a LORA the easy way, you gotta set up all the boring stuff first. You only do this once and then can train many awesome character and style LORAs easily for Stable Diffusion XL 1.0 and SD 1.5.

scale_parameter=False relative_step=False warmup_init=False

\\__ Articles __//

\\__ LINKS __//

\\__ TIMESTAMPS __//
00:00 - Intro
00:38 - Installing Kohya ss GUI
03:28 - Download 2 SDXL models
03:13 - Preparing Images for Training
06:25 - Captioning Images with Kohya
9:20 - Preparing Training Folders
11:34 - Kohya LORA settings
16:28 - Testing for the BEST LORA

[swannschilling]

Thank you so much for this one!! Very structured and easy to follow! Also your voice is very pleasant to listen to! 😊

[ukie_power]

Amazing explanation!!! Best one I found so far. ❤

[MarkKhoury]

Thank you so much for your time making this!

[cptsermorgan]

You rock! Thank you for being concise.

[_onzqi]

This tutorial... PERFECT! no explanation needed

[kqgymdv]

The English was so easy to understand that even a Japanese person like me could understand it. You have a very nice voice.❤

[MrStetsonator]

LFG -- I just trained my first LoRA thanks to you

[HanSolocambo]

well explained and very well video composited thanks.

[switterbeet]

Thanks a lot! Nice straight to the point tutorial. Btw you can export your parameter settings as a json file at the top and share it along with the video or just reuse it every time :)

[JDRos]

epiCRealism is based on SD1.5, so if I were to use that as pretrain model, should I check v2, v_parameterization or SDXL Model?

[wanderingmoon]

I really wish I had a machine that had vram. The one I have now does not. 😭😭😭

I need to watch more of your videos to see if you discuss the other settings and what they mean. I love that you told us what epoch (sp?) means.

[grahamulax]

HEY! This is THE BEST tutorial I have seen to date! I just wanted to let you know and that I did it right first try! Funny thing is.. I'm only at 15gb of gpu memory out of 24 on my 4090! What numbers could I pump up to test this beast out and get even more quality out of training? Again, this is by far THE BEST TUTORIAL on training with SDXL. Just fun, good pace, perfectly instructed and awesome.

[DhikaPraditya]

Hi, I would like to ask. I have a character sheet with different poses and perspectives. I would like to make a LoRA out of it. When making a LoRA we need to chose a model right. My question is that, is there any model that is neutral which can retain the style of the character sheet when I generate images with stable diffusion? Is there any way I can do that? Thank you

[JasonTheOneAndOnly]

Holy shitz the f2 shortcut changing my life

[luisfhurtadop]

¡Gracias por el video! Me encantó.Tu video fue muy informativo y útil.

[sikliztailbunch]

Is this tutorial adaptable to for example training on s specific animal? I really think SDXL is lacking good scorpions and I am currently creating a dataset of about 200 images. Do you have any suggestions for the settings when using that much images? I have 24 GB VRAM. Any suggestions on how to push the card to the limit in order to get the best results possible?

[metanulski]

Hi. I did start a training just fine using my 12GB 3060 just by reducing the resolution to 768, 768. But the card is a bit too slow. So here is my tip for low vram cards. Use 16 pics max. Resize all pictures to 768, 768 using birme. Don't use buckets and only 8 Epochs. That should get you a Lora Training in 2 hours.

[MrStetsonator]

One note I'd add is to be sure to fill in caption extension with .txt! Assuming that we want captions and they work well. Otherwise, you get an error that no caption file was found

[touchdownchef]

The videos have been very helpful. Thank you. While there are many tutorials on creating LoRa, it seems there is no tutorial on creating checkpoint models anywhere on YouTube. Do you have any plans to produce a tutorial on creating checkpoint models?

[jepperisum]

Great tutorial. Thanks! However, my training times keep growing to 250 hours'ish. Adjusting in accordance to your advice, but apparently I do something wrong. (I have around 50 portrait images of a person). Saw some other comments advicing you to add a link to a json settings file. Is that something you consider?