Patreon
Home / Videos / How To Do Stable Diffusion LORA Training By Using Web UI On

How To Do Stable Diffusion LORA Training By Using Web UI On Different Models - Tested SD 1.5, SD 2.1

Our Discord : https://discord.gg/HbqgGaZVmr. Ultimate guide to the LoRA training. If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on 🥰 https://www.patreon.com/SECourses

Published Dec 31, 2022 · 128,085 views · Watch on YouTube

Chapters

  1. 0:00 Introduction speech
  2. 1:07 How to install the LoRA extension to the Stable Diffusion Web UI
  3. 2:36 Preparation of training set images by properly sized cropping
  4. 2:54 How to crop images using Paint .NET, an open-source image editing software
  5. 5:02 What is Low-Rank Adaptation (LoRA)
  6. 5:35 Starting preparation for training using the DreamBooth tab - LoRA
  7. 6:50 Explanation of all training parameters, settings, and options
  8. 8:27 How many training steps equal one epoch
  9. 9:09 Save checkpoints frequency
  10. 9:48 Save a preview of training images after certain steps or epochs
  11. 10:04 What is batch size in training settings
  12. 11:56 Where to set LoRA training in SD Web UI
  13. 13:45 Explanation of Concepts tab in training section of SD Web UI
  14. 14:00 How to set the path for training images
  15. 14:28 Classification Dataset Directory
  16. 15:22 Training prompt - how to set what to teach the model
  17. 15:55 What is Class and Sample Image Prompt in SD training
  18. 17:57 What is Image Generation settings and why we need classification image generation in SD training
  19. 19:40 Starting the training process
  20. 21:03 How and why to tune your Class Prompt (generating generic training images)
  21. 22:39 Why we generate regularization generic images by class prompt
  22. 23:27 Recap of the setting up process for training parameters, options, and settings
  23. 29:23 How much GPU, CPU, and RAM the class regularization image generation uses
  24. 29:57 Training process starts after class image generation completed
  25. 30:04 Displaying the generated class regularization images folder for SD 2.1
  26. 30:31 The speed of the training process - how many seconds per iteration on an RTX 3060 GPU
  27. 31:19 Where LoRA training checkpoints (weights) are saved
  28. 32:36 Where training preview images are saved and our first training preview image
  29. 33:10 When we will decide to stop training
  30. 34:09 How to resume training after training has crashed or you close it down
  31. 36:49 Lifetime vs. session training steps
  32. 37:54 After 30 epochs, resembling images start to appear in the preview folder
  33. 38:19 The command line printed messages are incorrect in some cases
  34. 39:05 Training step speed, a certain number of seconds per iteration (IT)
  35. 39:44 How I'm picking a checkpoint to generate a full model .ckpt file
  36. 40:23 How to generate a full model .ckpt file from a LoRA checkpoint .pt file
  37. 41:17 Generated/saved file name is incorrect, but it is generated from the correct selected .pt file
  38. 42:01 Doing inference (generating new images) using the text2img tab with our newly trained and generated model
  39. 42:47 The results of SD 2.1 Version 768 pixel model after training with the LoRA method and teaching a human face
  40. 44:38 Setting up the training parameters/options for SD version 1.5 this time
  41. 48:35 Re-generating class regularization images since SD 1.5 uses 512 pixel resolution
  42. 49:11 Displaying the generated class regularization images folder for SD 1.5
  43. 50:16 Training of Stable Diffusion 1.5 using the LoRA methodology and teaching a face has been completed and the results are displayed
  44. 51:09 The inference (text2img) results with SD 1.5 training
  45. 51:19 You have to do more inference with LoRA since it has less precision than DreamBooth
  46. 51:39 How to give more attention/emphasis to certain keywords in the SD Web UI
  47. 52:51 How to generate more than 100 images
  48. 54:46 How to check PNG info to see used prompts and settings
  49. 55:24 How to upscale using AI models
  50. 56:12 Fixing face image quality, especially eyes, with GFPGAN visibility
  51. 56:32 How to batch post-process
  52. 57:00 Where batch-generated images are saved

About this video

Our Discord : https://discord.gg/HbqgGaZVmr. Ultimate guide to the LoRA training. If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on 🥰 https://www.patreon.com/SECourses

Playlist of Stable Diffusion Tutorials, #Automatic1111 and Google Colab Guides, DreamBooth, Textual Inversion / Embedding, #LoRA, AI Upscaling, Pix2Pix, Img2Img:

https://www.youtube.com/playlist?list=PL_pbwdIyffsmclLl0O144nQRnezKlNdx3

Welcome to the ultimate beginner's guide to training with #StableDiffusion models using Automatic1111 Web UI. In this video, we will walk you through the entire process of setting up and training a Stable Diffusion model, from installing the LoRA extension to preparing your training set and tuning your training parameters. We'll also cover advanced training options and show you how to generate new images using your trained model. By the end of this video, you'll have a solid understanding of how to use Stable Diffusion to train your own custom models and generate high-quality images.

You should watch these two videos prior to this one if you don't have sufficient knowledge about Stable Diffusion or Automatic1111 Web UI:

1 - Easiest Way to Install & Run Stable Diffusion Web UI on PC by Using Open Source Automatic Installer - https://youtu.be/AZg6vzWHOTA

2 - How to Use SD 2.1 & Custom Models on Google Colab for Training with Dreambooth & Image Generation - https://youtu.be/AZg6vzWHOTA

0:00 Introduction speech

1:07 How to install the LoRA extension to the Stable Diffusion Web UI

2:36 Preparation of training set images by properly sized cropping

2:54 How to crop images using Paint .NET, an open-source image editing software

5:02 What is Low-Rank Adaptation (LoRA)

5:35 Starting preparation for training using the DreamBooth tab - LoRA

6:50 Explanation of all training parameters, settings, and options

8:27 How many training steps equal one epoch

9:09 Save checkpoints frequency

9:48 Save a preview of training images after certain steps or epochs

10:04 What is batch size in training settings

11:56 Where to set LoRA training in SD Web UI

13:45 Explanation of Concepts tab in training section of SD Web UI

14:00 How to set the path for training images

14:28 Classification Dataset Directory

15:22 Training prompt - how to set what to teach the model

15:55 What is Class and Sample Image Prompt in SD training

17:57 What is Image Generation settings and why we need classification image generation in SD training

19:40 Starting the training process

21:03 How and why to tune your Class Prompt (generating generic training images)

22:39 Why we generate regularization generic images by class prompt

23:27 Recap of the setting up process for training parameters, options, and settings

29:23 How much GPU, CPU, and RAM the class regularization image generation uses

29:57 Training process starts after class image generation completed

30:04 Displaying the generated class regularization images folder for SD 2.1

30:31 The speed of the training process - how many seconds per iteration on an RTX 3060 GPU

31:19 Where LoRA training checkpoints (weights) are saved

32:36 Where training preview images are saved and our first training preview image

33:10 When we will decide to stop training

34:09 How to resume training after training has crashed or you close it down

36:49 Lifetime vs. session training steps

37:54 After 30 epochs, resembling images start to appear in the preview folder

38:19 The command line printed messages are incorrect in some cases