Completed
How to set destination directory and model output into temp disk space
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Stable Diffusion XL DreamBooth Training on Kaggle - Free Tutorial
Automatically move to the next video in the Classroom when playback concludes
- 1 Introduction To The Kaggle Free SDXL DreamBooth Training Tutorial
- 2 How to register Kaggle account and login
- 3 Where to and how to download Kaggle training notebook for Kohya GUI
- 4 How to import / load downloaded Kaggle Kohya GUI training notebook
- 5 How to enable GPUs and Internet on your Kaggle session
- 6 How to start your Kaggle session / cloud machine
- 7 How to see your Kaggle given free hardware features
- 8 How to install Kohya GUI on a Kaggle notebook
- 9 How to know when the Kohya GUI installation has been completed on a Kaggle notebook
- 10 How to download regularization images before starting training
- 11 Introduction to the classification dataset that I prepared
- 12 How to setup and enter your token to use Kohya Web UI on Kaggle
- 13 How to load pre-prepared configuration json file on Kohya GUI
- 14 How to do Dataset Preparation after configuration loaded
- 15 How to upload your training dataset to your Kaggle session
- 16 Properties of my training images dataset
- 17 What kind of training dataset is good and why
- 18 How to upload any data to Kaggle and use it on your notebook
- 19 How to use previously composed Kaggle dataset in your new Kaggle session
- 20 How to get path of session included dataset
- 21 Why do I train with 100 repeating and 1 epoch
- 22 Explanation of 1 epoch and how to calculate epochs
- 23 How to set path of regularization images
- 24 How to set instance prompt and why we set it to a rare token
- 25 How to set destination directory and model output into temp disk space
- 26 How to set Kaggle temporary models folder path
- 27 How many GB temporary space do Kaggle provides us for free
- 28 Which parameters you need to set on Kohya GUI before starting training
- 29 How to calculate the N number of save every N steps parameter to save checkpoints
- 30 How to calculate total number of steps that your Kohya Stable Diffusion going to take
- 31 If I want to take 5 checkpoints what number of steps I need calculation
- 32 How to download saved configuration json file
- 33 Click start training and training starts
- 34 Can we combine both GPU VRAM and use as a single VRAM
- 35 How we are setting the base model that it will do training
- 36 The SDXL full DreamBooth training speed we get on a free Kaggle notebook
- 37 Can you close your browser or computer during training
- 38 Can we download models during training
- 39 Training has been completed
- 40 How to prevent last checkpoint to be saved 2 times
- 41 How to download generated checkpoints / model files
- 42 How you will know the download status when downloading from Kaggle working directory
- 43 How to upload generated checkpoints / model files into Hugging Face for blazing fast upload and download
- 44 Where to find Hugging Face uploaded models after upload has been completed
- 45 Explanation of why generated last 2 checkpoints are duplicate
- 46 Hugging Face upload started and the amazing speed of the upload
- 47 All uploads have been completed now how to download them
- 48 Download speed from Hugging Face repository
- 49 How to terminate your Kaggle session
- 50 Where to see how much GPU time you have left for free on Kaggle for that week
- 51 How to make a fresh installation of Automatic1111 SD Web UI
- 52 How to download Hugging Face uploaded models with wget very fast
- 53 Which settings to set on a freshly installed Automatic1111 Web UI, e.g. VAE quick selection
- 54 How to install after detailer adetailer extension to improve faces automatically
- 55 Why you should add --no-half-vae to your command line arguments
- 56 How to start / restart Automatic1111 Web UI
- 57 How switch to the development branch of Automatic1111 Web UI to use latest version
- 58 Where to download amazing prompts list for DreamBooth trained models
- 59 How to use PNG info to quickly load prompts
- 60 How to do x/y/z checkpoint comparison to find the best checkpoint of your SDXL DreamBooth training
- 61 How to make SDXL work faster on weak GPUs
- 62 How to analyze results of x/y/z checkpoint comparison to decide best checkpoint
- 63 How to obtain better images
- 64 How to install TensorRT and use it to generate images very fast with same quality
- 65 How to use amazing prompt list as a list txt file
