1 Introduction to how to do amazing FREE training of Stable Diffusion XL without owning a GPU 2:34
2 How to register Kaggle to get a free account to do free training 0:29
3 How to verify your phone number in Kaggle to be able to use cloud GPUs for free 0:49
4 How to generate a Kaggle notebook and start Stable Diffusion XL free Kohya SS LoRA training 0:24
5 How to download and import SDXL LoRA training notebook 1:25
6 How to properly with correct config start session on Kaggle to begin training 0:09
7 How to enable GPU on Kaggle 0:37
8 How to see how much GPU time you have used and how much you have left on Kaggle 0:14
9 How to look at used resources in your Kaggle session such as disk space, GPU, CPU, RAM 0:10
10 How to clone Kohya SS GUI and install it on a free Kaggle notebook 0:20
11 How to understand and use pathing structure of Kaggle 0:15
12 Where is our root / working directory in Kaggle 2:19
13 How to know when the installation of Kohya SS GUI has been completed 0:16
14 How to download ground truth regularization / classification images 3:02
15 How to upload your regularization / classification images and use them 0:55
16 How to use your previously uploaded images / datasets in your Kaggle training sessions 1:46
17 How to start Kohya SS GUI on Kaggle notebook 0:30
18 How to access started Kohya SS GUI instance via publicly given Gradio link 0:37
19 Starting to setup Kohya SDXL LoRA training parameters and settings 0:30
20 Which source model we need to use for SDXL training a free Kaggle notebook 1:14
21 How to prepare training dataset easily with dataset preparation feature of Kohya SS GUI 0:30
22 How to upload your training images and prepare them for SDXL training 0:58
23 How get and set folder path of training and regularization / classification images 0:25
24 Where to and how to save training results and how to generate training folders 0:52
25 How to copy info to folders tab 0:24
26 Setting up all training parameters 1:34
27 Network Rank Dimension trade-off 0:59
28 Continuing to setting up all training parameters 1:09
29 How to start training after everything is set 0:59
30 What is the formula of calculating number of training total steps 0:59
31 How to execute training command 1:15
32 How to calculate necessary number of classification / regularization images that you need 1:54
33 Training started 0:18
34 Why it shows total number of epochs double of the number we did set 0:45
35 Where is our SDXL LoRA training checkpoints are saved and how to download them 0:56
36 Why generated safetensor files, checkpoints are 228 MBs 0:19
37 How to enable allow multiple files download in your browser to download generated LoRA checkpoints 0:09
38 How to download all of the checkpoints as a single file - zip them all 0:49
39 How to download LoRA safetensors folder entirely 0:36
40 How to extract and open downloaded as zip LoRA checkpoints 1:43
41 How to save your LoRA checkpoints on your Kaggle account to use later 1:01
42 How to use your trained LoRA checkpoints in your Automatic1111 Web UI on your PC 0:59
43 How to download and use 750 styles containing styles.csv file 0:49
44 How to find best checkpoint of your Kohya SDXL LoRA training 0:26
45 How to see used prompts and settings of generated images via png info tab of Automatic1111 Web UI 0:18
46 How did I decide to use the certain checkpoint via x/y/z script of Automatic1111 Web UI 0:41
47 How to use your LoRAs in Automatic1111 Web UI 0:59
48 How to select your LoRA from the interface 1:55
49 How to generate same batch with correct seed, how batch seed is determined 0:33
50 How to install after detailer adetailer extension to improve faces in your generations automatically 0:28
51 After detailer extension enabled comparison results 0:53
52 How to get amazing likeness - realism having images of your trained subject, 0:25
53 How to find best amazing among thousands of generated images by using DeepFace AI similarity script