This course aims to teach learners how to train LoRA for style diffusion. By the end of the course, students will be able to understand the significance of LoRA, prepare datasets, write captions, use GUI tools for training, and test the trained models. The course covers skills such as dataset preparation, batch renaming, cropping, captioning, and testing models in different scenarios. The teaching method includes a combination of theoretical explanations, practical demonstrations, and hands-on exercises. This course is intended for digital artists, concept artists, character designers, and individuals interested in exploring machine learning applications in digital art.
Stable Diffusion - How to Train LoRA for Style - LoRA Part 1
Overview
Syllabus
Intro
Why is LoRA a new standard?
Required resources
Overview of video parts 1. local GUI and 2. Google Colab Notebook
Part 1. local GUI training
PC hardware specs
Dataset preparation
Batch renaming filetypes to a new filetype
Batch renaming attempt #2
BIRME cropping
BLIP captioning
How to write good captions
Captioning example #2
Creating project folder structure using kohya_ss GUI
Training parameters
Why the training steps in the console are different from max train steps
Console output after training commences
What you get after training finishes
Testing the style LoRA in AUTOMATIC1111 webui
Using x/y/z plot in scripts to vary parameters
Checking x/y/z plot in photoshop
Testing the final epoch LoRA
Verifying LoRA's flexibility with prompting
Part 2. Anime style LoRA
Dataset preparation on redjuice/shiru artwork
Using AUTOMATIC1111 webui extension tagger
Modifying Danbooru style tags
Using the kohya LoRA DreamBooth colab notebook
Fixing the error that occurred
Preliminary testing of redjuice style LoRA
Checking x/y/z plot in photoshop
Combining character and style LoRAs
Taught by
kasukanra
Related Courses
-
Perfect Style Lora Training for SDXL - Amazing Results
-
How to Do Stable Diffusion LORA Training by Using Web UI on Different Models
-
Stable Diffusion- LyCORIS for Style - LoRA Part 2
-
Stable Diffusion - Create a PNGtuber with Character LoRA
-
Generate Studio Quality Realistic Photos With Kohya LoRA Stable Diffusion Training - Full Tutorial
-
How to Do SDXL Training with Kohya LoRA - Kaggle - No GPU Required
Related articles
Reviews
4.0 rating, based on 1 Class Central review
-
Stable Diffusion: How to train LoRA for Style | LoRA Part 1 is a video tutorial by Kasucast that teaches you how to train a LoRA model for style. LoRA is a type of diffusion model that can be used to generate images with a specific style. In this tutorial, Kasucast walks you through the process of training a LoRA model using the Dreambooth software. He also provides tips on how to improve the quality of your generated images.
The tutorial is well-organized and easy to follow. Kasucast explains the concepts clearly and provides plenty of visuals to help you understand what he is talking about. He also includes a link to the Dreambooth software so that you can follow along at home.
