Patreon
Home / Videos / Zero To Hero Stable Diffusion DreamBooth Tutorial By Using A

Zero To Hero Stable Diffusion DreamBooth Tutorial By Using Automatic1111 Web UI - Ultra Detailed

Stable Diffusion and SDXL video list: 75 expert-level tutorials on Automatic1111, DreamBooth, LoRA, Textual Inversion and Google Colab, with fixed subtitles.

Published Jan 09, 2023 · 149,284 views · Watch on YouTube

Get the app and files

Stable Diffusion & SDXL: 75 Expert-Level Generative AI Tutorials

Stable Diffusion & SDXL: 75 Expert-Level Generative AI Tutorials

Stable Diffusion and SDXL video list: 75 expert-level tutorials on Automatic1111, DreamBooth, LoRA, Textual Inversion and Google Colab, with fixed subtitles.

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.

60 Generative AI Tutorials: Stable Diffusion, SDXL, LoRA & DreamBooth

60 Generative AI Tutorials: Stable Diffusion, SDXL, LoRA & DreamBooth

60 generative AI video tutorials in one list, each marked local, RunPod, Kaggle or Colab, from Stable Diffusion and SDXL training to voice cloning.

Chapters

  1. 0:00 Introduction to Grand Master yet most beginner friendly Stable Diffusion Dreambooth tutorial by using Automatic1111 Web UI
  2. 3:11 How to install DreamBooth extension to the Web UI
  3. 4:09 How to update installed extensions on the Web UI
  4. 4:35 Introduction to DreamBooth extension tab
  5. 4:45 Training model generation for DreamBooth
  6. 5:34 How to download official SD model files
  7. 6:21 Training model selection and settings tab of the DreamBooth extension
  8. 7:36 What is training steps per image epochs
  9. 8:24 Checkpoint saving frequency
  10. 9:15 What is training batch size in DreamBooth training and how to set them properly
  11. 10:47 Set gradients to none when zeroing
  12. 11:24 Gradient checkpoint
  13. 12:04 Image processing and resolution
  14. 12:39 Horizontal flip and Center crop
  15. 12:50 What is Sanity sample prompt and how to utilize it to understand overtraining
  16. 13:30 Best options to set in Advanced tab of DreamBooth extension
  17. 14:22 Step Ratio of Text Encoder Training
  18. 14:49 Concepts tab of the DreamBooth extension
  19. 15:27 How to crop images from any position with Paint .NET or use Birme .NET
  20. 17:22 Setting training dataset directory
  21. 17:44 What are classification images
  22. 18:46 What is Instance prompt
  23. 19:05 How to and why to pick your instance prompt as a very rare word (very crucial)
  24. 21:52 Class of the subject
  25. 22:15 Everything about class prompt
  26. 22:55 Sample prompt
  27. 23:30 Clas images per instance
  28. 25:00 Number of samples to generate
  29. 26:27 Teach multiple concepts in 1 run
  30. 28:24 Saving tab
  31. 29:10 How to generate checkpoints during training
  32. 30:52 Generating class images before start training
  33. 33:28 What is batch size in txt2img tab
  34. 36:09 Start training
  35. 38:25 First samples/previews of training
  36. 39:13 Sanity prompt sample
  37. 39:54 How to understand overtraining with sanity samples
  38. 40:34 How to properly prepare your training dataset images
  39. 43:15 Checkpoint saving during training
  40. 44:30 What is Lr displayed in cmd during training
  41. 45:38 How to continue / resume training if an error occurs or you cancel it
  42. 46:41 We started to overtraining and how we understood it
  43. 48:24 How to start generating our subject (face) images from best trained checkpoint
  44. 50:09 What is prompt strength / attention / emphasis and how to increase it
  45. 51:17 How to increase image quality with negative prompts
  46. 51:50 How to get your taught subject with which correct prompting
  47. 52:31 What is CFG and why should we increase it
  48. 52:54 How to try multiple CFG scale values by using X/Y prompting
  49. 54:54 Analyzing CFG effect
  50. 56:03 How to test different artist styles with different CFG scales by using X/Y plot
  51. 60:47 How to use prompt matrix
  52. 62:54 Prompts from file or text box to test many different prompts
  53. 63:57 Generate thousands of images while sleeping
  54. 64:22 PNG info to learn used prompts, CFG, seed and others
  55. 67:00 Extras tab to upscale images by using AI models with awesome quality
  56. 69:54 How improve eyes and face quality by using GFPGAN
  57. 71:35 How to continue training from any saved ckpt checkpoint
  58. 72:06 How to upload your trained model to Google Colab to use
  59. 74:19 How to teach a new subject to your already trained model
  60. 75:55 How to use filewords for training
  61. 81:52 What is fine tuning and how it is done
  62. 83:10 Hybrid training
  63. 84:39 How to understand out of memory error
  64. 85:39 Lowest GPU VRAM settings
  65. 87:35 How to batch preprocess images
  66. 91:47 How to generate very correct descriptions by using GIT large model
  67. 93:19 How to inject your trained subject into any custom / new model
  68. 97:36 Where is model hash written and how to compare

About this video

Our Discord : https://discord.gg/HbqgGaZVmr. The most advanced tutorial of Stable Diffusion Dreambooth 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

I am explaining from scratch to very advanced level how to use #Automatic1111 Web UI and D8ahazard #DreamBooth extension to teach new subjects, e.g. your face into a model. Moreover, I am showing how to inject your taught face into a completely new model e.g. Protogen x3.4 to produce awesome quality images without wasting too much time on finding correct prompts.

Automatic1111

https://github.com/AUTOMATIC1111/stable-diffusion-webui

How to install Web UI: https://youtu.be/AZg6vzWHOTA

How to use #StableDiffusion different models on Web UI:

https://youtu.be/aAyvsX-EpG4

Official SD v1-5-pruned : https://bit.ly/sd15ckpt

How To Do LoRA Training: https://youtu.be/mfaqqL5yOO4

Wiki Ram memory: http://bit.ly/3IqFUeW

Rare tokens: https://bit.ly/SDRareTokens

Rare tokens list: https://bit.ly/SDRareTokensList

Basics wiki: http://bit.ly/3Yy78pn

DreamBooth paper

https://arxiv.org/pdf/2208.12242.pdf

Best caption: https://bit.ly/bestcaption2

0:00 Introduction to Grand Master yet most beginner friendly Stable Diffusion Dreambooth tutorial by using Automatic1111 Web UI

3:11 How to install DreamBooth extension to the Web UI

4:09 How to update installed extensions on the Web UI

4:35 Introduction to DreamBooth extension tab

4:45 Training model generation for DreamBooth

5:34 How to download official SD model files

6:21 Training model selection and settings tab of the DreamBooth extension

7:36 What is training steps per image epochs

8:24 Checkpoint saving frequency

9:15 What is training batch size in DreamBooth training and how to set them properly

10:47 Set gradients to none when zeroing

11:24 Gradient checkpoint

12:04 Image processing and resolution

12:39 Horizontal flip and Center crop

12:50 What is Sanity sample prompt and how to utilize it to understand overtraining

13:30 Best options to set in Advanced tab of DreamBooth extension

14:22 Step Ratio of Text Encoder Training

14:49 Concepts tab of the DreamBooth extension

15:27 How to crop images from any position with Paint .NET or use Birme .NET

17:22 Setting training dataset directory

17:44 What are classification images

18:46 What is Instance prompt