SDXL Training With Kohya LoRA - Stable Diffusion XL Training Will Replace Older Models
Software Engineering Courses - SE Courses via YouTube
Overview
Syllabus
Introduction to SDXL LoRA training tutorial
How to install Kohya GUI trainer
How to start Kohya GUI trainer after the installation
Beginning to show all SDXL LoRA training setup and parameters on Kohya trainer
How to download SDXL model to use as a base training model
How to prepare training data with Kohya GUI
What is repeating parameter of Kohya training
How to set classification images and use which images as regularization images
How to prepare training dataset folders for Kohya LoRA / DreamBooth training
What are ohwx rare token and man class token
Why I am using real images as classification images for realism
Don't forget copy folders info
Best parameters for SDXL Kohya LoRA training
Explanation of Network Rank Dimension for LoRA
What is Network Alpha for LoRA training
How to save settings / configuration in Kohya GUI trainer
The importance and usage of print training command button
Why did I get out of VRAM error OOM
What does it / second means you see in Kohya trainer or on SD web UIs
Where to see number of steps it will take
Where I shared my training command and how you can use it
How you can do training with my settings
How to use trained SDXL LoRA models with ComfyUI
How to do checkpoint comparison with Kohya LoRA SDXL in ComfyUI
How to generate amazing images after finding best training checkpoint
How to utilize AI to find best generated images very easily
How to find best images in certain looking direction / pose
How to inpaint generated image to improve quality and similarity
How to do SDXL LoRA training if you don't have a strong GPU
How to get stylized images such as GTA5 style images of yourself
Please help me. Thank you so much
Taught by
Software Engineering Courses - SE Courses