Patreon
Home / Videos / No Strong GPU? Train SDXL DreamBooth for Free on Kaggle, 30

No Strong GPU? Train SDXL DreamBooth for Free on Kaggle, 30 GPU Hours a Week (2023 Tutorial)

Timestep sampling shift explained for diffusion models: Qwen Image uses an exponential shift and FLUX a linear one, and 2.205 matches Qwen at 1664x928.

Published Nov 24, 2023 · 19,885 views · Watch on YouTube

Get the app and files

Decoding the Timestep Shift in Diffusion Training: Qwen Image & FLUX

Decoding the Timestep Shift in Diffusion Training: Qwen Image & FLUX

Timestep sampling shift explained for diffusion models: Qwen Image uses an exponential shift and FLUX a linear one, and 2.205 matches Qwen at 1664x928.

Kohya GUI Kaggle Notebook: Free SD 1.5 & SDXL Training on Dual T4 GPUs

Kohya GUI Kaggle Notebook: Free SD 1.5 & SDXL Training on Dual T4 GPUs

Kohya GUI Kaggle notebook trains Stable Diffusion 1.5 and SDXL LoRA or DreamBooth models for free on a Kaggle account, on a single T4 or dual T4 GPUs.

SD 1.5 & SDXL DreamBooth and LoRA Training: Full Newbie Workflow

SD 1.5 & SDXL DreamBooth and LoRA Training: Full Newbie Workflow

Stable Diffusion training workflow for newbies, built from 120+ SDXL and 70+ SD 1.5 trainings: Kohya, regularization images and ADetailer.

SDXL DreamBooth Training: Photos of Yourself in Cities and Fancy Suits

SDXL DreamBooth Training: Photos of Yourself in Cities and Fancy Suits

SDXL DreamBooth training on SDXL 1.0 Base lets you generate photos of yourself in different cities and fancy suits, using a config found after 120 trainings.

Chapters

  1. 0:00 Introduction To The Kaggle Free SDXL DreamBooth Training Tutorial
  2. 2:01 How to register Kaggle account and login
  3. 2:26 Where to and how to download Kaggle training notebook for Kohya GUI
  4. 2:47 How to import / load downloaded Kaggle Kohya GUI training notebook
  5. 3:08 How to enable GPUs and Internet on your Kaggle session
  6. 3:52 How to start your Kaggle session / cloud machine
  7. 4:02 How to see your Kaggle given free hardware features
  8. 4:18 How to install Kohya GUI on a Kaggle notebook
  9. 4:46 How to know when the Kohya GUI installation has been completed on a Kaggle notebook
  10. 5:00 How to download regularization images before starting training
  11. 5:22 Introduction to the classification dataset that I prepared
  12. 6:35 How to setup and enter your token to use Kohya Web UI on Kaggle
  13. 8:20 How to load pre-prepared configuration json file on Kohya GUI
  14. 8:48 How to do Dataset Preparation after configuration loaded
  15. 8:59 How to upload your training dataset to your Kaggle session
  16. 9:12 Properties of my training images dataset
  17. 9:22 What kind of training dataset is good and why
  18. 10:06 How to upload any data to Kaggle and use it on your notebook
  19. 10:20 How to use previously composed Kaggle dataset in your new Kaggle session
  20. 10:34 How to get path of session included dataset
  21. 10:44 Why do I train with 100 repeating and 1 epoch
  22. 10:54 Explanation of 1 epoch and how to calculate epochs
  23. 11:23 How to set path of regularization images
  24. 11:33 How to set instance prompt and why we set it to a rare token
  25. 11:46 How to set destination directory and model output into temp disk space
  26. 12:29 How to set Kaggle temporary models folder path
  27. 13:07 How many GB temporary space do Kaggle provides us for free
  28. 13:23 Which parameters you need to set on Kohya GUI before starting training
  29. 13:33 How to calculate the N number of save every N steps parameter to save checkpoints
  30. 13:45 How to calculate total number of steps that your Kohya Stable Diffusion going to take
  31. 14:10 If I want to take 5 checkpoints what number of steps I need calculation
  32. 14:33 How to download saved configuration json file
  33. 14:43 Click start training and training starts
  34. 14:55 Can we combine both GPU VRAM and use as a single VRAM
  35. 15:05 How we are setting the base model that it will do training
  36. 15:55 The SDXL full DreamBooth training speed we get on a free Kaggle notebook
  37. 16:51 Can you close your browser or computer during training
  38. 17:54 Can we download models during training
  39. 18:26 Training has been completed
  40. 18:57 How to prevent last checkpoint to be saved 2 times
  41. 19:30 How to download generated checkpoints / model files
  42. 21:11 How you will know the download status when downloading from Kaggle working directory
  43. 22:03 How to upload generated checkpoints / model files into Hugging Face for blazing fast upload and download
  44. 25:02 Where to find Hugging Face uploaded models after upload has been completed
  45. 26:54 Explanation of why generated last 2 checkpoints are duplicate
  46. 27:27 Hugging Face upload started and the amazing speed of the upload
  47. 27:49 All uploads have been completed now how to download them
  48. 29:02 Download speed from Hugging Face repository
  49. 29:17 How to terminate your Kaggle session
  50. 29:36 Where to see how much GPU time you have left for free on Kaggle for that week
  51. 29:46 How to make a fresh installation of Automatic1111 SD Web UI
  52. 31:05 How to download Hugging Face uploaded models with wget very fast
  53. 31:57 Which settings to set on a freshly installed Automatic1111 Web UI, e.g. VAE quick selection
  54. 32:07 How to install after detailer (adetailer) extension to improve faces automatically
  55. 32:51 Why you should add --no-half-vae to your command line arguments
  56. 33:05 How to start / restart Automatic1111 Web UI
  57. 33:37 How switch to the development branch of Automatic1111 Web UI to use latest version
  58. 34:24 Where to download amazing prompts list for DreamBooth trained models
  59. 35:07 How to use PNG info to quickly load prompts
  60. 35:52 How to do x/y/z checkpoint comparison to find the best checkpoint of your SDXL DreamBooth training
  61. 38:09 How to make SDXL work faster on weak GPUs
  62. 38:37 How to analyze results of x/y/z checkpoint comparison to decide best checkpoint
  63. 42:06 How to obtain better images
  64. 42:20 How to install TensorRT and use it to generate images very fast with same quality
  65. 44:41 How to use amazing prompt list as a list txt file

About this video

🌟 Master Stable Diffusion XL Training on Kaggle for Free! 🌟 Welcome to this comprehensive tutorial where I'll be guiding you through the exciting world of setting up and training Stable Diffusion XL (SDXL) with Kohya on a free Kaggle account. This video is your one-stop resource for learning everything from initiating a Kaggle session with dual T4 GPUs to fine-tuning your SDXL model for optimal performance.

Notebook ⤵️

https://www.patreon.com/posts/kohya-sdxl-lora-88397937

Tutorial GitHub Readme File ⤵️

https://github.com/FurkanGozukara/Stable-Diffusion/blob/main/Tutorials/Full-Stable-Diffusion-XL-SDXL-DreamBooth-Training-Tutorial-On-Kaggle.md

0:00 Introduction To The Kaggle Free SDXL DreamBooth Training Tutorial

2:01 How to register Kaggle account and login

2:26 Where to and how to download Kaggle training notebook for Kohya GUI

2:47 How to import / load downloaded Kaggle Kohya GUI training notebook

3:08 How to enable GPUs and Internet on your Kaggle session

3:52 How to start your Kaggle session / cloud machine

4:02 How to see your Kaggle given free hardware features

4:18 How to install Kohya GUI on a Kaggle notebook

4:46 How to know when the Kohya GUI installation has been completed on a Kaggle notebook

5:00 How to download regularization images before starting training

5:22 Introduction to the classification dataset that I prepared

6:35 How to setup and enter your token to use Kohya Web UI on Kaggle

8:20 How to load pre-prepared configuration json file on Kohya GUI

8:48 How to do Dataset Preparation after configuration loaded

8:59 How to upload your training dataset to your Kaggle session

9:12 Properties of my training images dataset

9:22 What kind of training dataset is good and why

10:06 How to upload any data to Kaggle and use it on your notebook

10:20 How to use previously composed Kaggle dataset in your new Kaggle session

10:34 How to get path of session included dataset

10:44 Why do I train with 100 repeating and 1 epoch

10:54 Explanation of 1 epoch and how to calculate epochs

11:23 How to set path of regularization images

11:33 How to set instance prompt and why we set it to a rare token

11:46 How to set destination directory and model output into temp disk space

12:29 How to set Kaggle temporary models folder path

13:07 How many GB temporary space do Kaggle provides us for free

13:23 Which parameters you need to set on Kohya GUI before starting training

13:33 How to calculate the N number of save every N steps parameter to save checkpoints

13:45 How to calculate total number of steps that your Kohya Stable Diffusion going to take

14:10 If I want to take 5 checkpoints what number of steps I need calculation

14:33 How to download saved configuration json file

14:43 Click start training and training starts

14:55 Can we combine both GPU VRAM and use as a single VRAM

15:05 How we are setting the base model that it will do training