Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

YouTube

How to Do SDXL Training with Kohya LoRA - Kaggle - No GPU Required

Software Engineering Courses - SE Courses via YouTube

Overview

Learn how to perform Stable Diffusion XL training for free using Kaggle and Kohya LoRA in this comprehensive 49-minute tutorial. Master the process of setting up a Kaggle account, utilizing free GPU resources, and implementing Kohya SS GUI for SDXL LoRA training. Discover techniques for preparing datasets, configuring training parameters, and optimizing results. Explore methods for downloading and using trained LoRA checkpoints in Automatic1111 Web UI, including tips for achieving realistic images and implementing useful extensions like after detailer. Gain insights into advanced topics such as calculating training steps, managing resources, and finding the best checkpoints among generated images.

Syllabus

Introduction to how to do amazing FREE training of Stable Diffusion XL without owning a GPU
How to register Kaggle to get a free account to do free training
How to verify your phone number in Kaggle to be able to use cloud GPUs for free
How to generate a Kaggle notebook and start Stable Diffusion XL free Kohya SS LoRA training
How to download and import SDXL LoRA training notebook
How to properly with correct config start session on Kaggle to begin training
How to enable GPU on Kaggle
How to see how much GPU time you have used and how much you have left on Kaggle
How to look at used resources in your Kaggle session such as disk space, GPU, CPU, RAM
How to clone Kohya SS GUI and install it on a free Kaggle notebook
How to understand and use pathing structure of Kaggle
Where is our root / working directory in Kaggle
How to know when the installation of Kohya SS GUI has been completed
How to download ground truth regularization / classification images
How to upload your regularization / classification images and use them
How to use your previously uploaded images / datasets in your Kaggle training sessions
How to start Kohya SS GUI on Kaggle notebook
How to access started Kohya SS GUI instance via publicly given Gradio link
Starting to setup Kohya SDXL LoRA training parameters and settings
Which source model we need to use for SDXL training a free Kaggle notebook
How to prepare training dataset easily with dataset preparation feature of Kohya SS GUI
How to upload your training images and prepare them for SDXL training
How get and set folder path of training and regularization / classification images
Where to and how to save training results and how to generate training folders
How to copy info to folders tab
Setting up all training parameters
Network Rank Dimension trade-off
Continuing to setting up all training parameters
How to start training after everything is set
What is the formula of calculating number of training total steps
How to execute training command
How to calculate necessary number of classification / regularization images that you need
Training started
Why it shows total number of epochs double of the number we did set
Where is our SDXL LoRA training checkpoints are saved and how to download them
Why generated safetensor files, checkpoints are 228 MBs
How to enable allow multiple files download in your browser to download generated LoRA checkpoints
How to download all of the checkpoints as a single file - zip them all
How to download LoRA safetensors folder entirely
How to extract and open downloaded as zip LoRA checkpoints
How to save your LoRA checkpoints on your Kaggle account to use later
How to use your trained LoRA checkpoints in your Automatic1111 Web UI on your PC
How to download and use 750 styles containing styles.csv file
How to find best checkpoint of your Kohya SDXL LoRA training
How to see used prompts and settings of generated images via png info tab of Automatic1111 Web UI
How did I decide to use the certain checkpoint via x/y/z script of Automatic1111 Web UI
How to use your LoRAs in Automatic1111 Web UI
How to select your LoRA from the interface
How to generate same batch with correct seed, how batch seed is determined
How to install after detailer adetailer extension to improve faces in your generations automatically
After detailer extension enabled comparison results
How to get amazing likeness - realism having images of your trained subject,
How to find best amazing among thousands of generated images by using DeepFace AI similarity script

Taught by

Software Engineering Courses - SE Courses

Reviews

Start your review of How to Do SDXL Training with Kohya LoRA - Kaggle - No GPU Required

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.