Patreon
Home / Videos / Training Midjourney Level Style And Yourself Into The SD 1.5

Training Midjourney Level Style And Yourself Into The SD 1.5 Model via DreamBooth Stable Diffusion

Midjourney level style model trained on SD 1.5 pruned ckpt by SECourses; download the safetensors file and YAML and put both into models/Stable-diffusion.

Published Mar 20, 2023 · 15,182 views · Watch on YouTube

Get the app and files

Midjourney Level Style Trained SD 1.5 Model With Video Tutorial

Midjourney Level Style Trained SD 1.5 Model With Video Tutorial

Midjourney level style model trained on SD 1.5 pruned ckpt by SECourses; download the safetensors file and YAML and put both into models/Stable-diffusion.

Chapters

  1. 0:00 Midjourney level style for free
  2. 0:35 Most important part of teaching a style into Stable Diffusion
  3. 1:23 I trained myself into the model and got amazing styled myself
  4. 1:30 First part of animation generation just like Corridor Crew did in their anime video
  5. 1:37 Used DreamBooth extension of Web UI on RunPod for training
  6. 1:57 Why training dataset is 1024x1024 pixels
  7. 2:25 Which rare token and class token are chosen why
  8. 2:54 Which dataset I have used to train myself
  9. 3:05 What kind of training dataset you need to generate consistent animation like Corridor Crew
  10. 3:27 A better way to connect your RunPod web UI instance
  11. 3:43 Which DreamBooth settings I have used to train myself into the base model
  12. 4:10 A good explanation of max resolution settings
  13. 4:31 Advanced tab settings of DreamBooth extension
  14. 5:15 Concepts tab of DreamBooth training
  15. 5:35 FileWords - image captions explanation
  16. 7:31 Where to see source checkpoint used for training
  17. 7:49 Why do seperate training instead of multiple concepts training
  18. 8:08 Style training used settings
  19. 9:20 Analysis of after style training upon myself trained model
  20. 10:25 x/y/z plot testing for Brad Pitt face to see overtraining effect
  21. 11:03 Castle in a forest test to verify not overtrained 1 more time
  22. 11:32 I had to do another training of my face
  23. 12:03 Final x/y/z plot comparison to decide best checkpoint
  24. 13:05 Analysis of final x/y/z plot
  25. 14:48 What you can do by using this methodology I explained
  26. 15:05 How to generate good quality, good face distant shots
  27. 15:10 very important parts of selecting good face training dataset
  28. 15:25 Why Stable Diffusion can't produce good face distant shots
  29. 15:33 How to do inpainting to fix your face in distant shots
  30. 15:48 What settings to use for inpainting to fix faces
  31. 16:17 How to upscale your image
  32. 16:30 GFPGAN to further improve face

About this video

RunPod: https://bit.ly/RunPodIO. Discord : https://bit.ly/SECoursesDiscord. Get your own #Midjourney level model for free via Style Teaching. 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 #StableDiffusion Tutorials, Automatic1111 and Google Colab Guides, #DreamBooth, Textual Inversion / Embedding, LoRA, AI Upscaling, Pix2Pix, Img2Img:

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

Used training dataset in the video:

https://www.patreon.com/posts/style-teaching-80233878

Style Trained model .safetensors (not includes myself - based on SD 1.5 pruned ckpt):

https://www.patreon.com/posts/midjourney-level-80356527

2400 Photo Of Man classification images:

https://drive.google.com/file/d/1qBf8VyUbmPNalKqm076yOsQjE8BrcG7R/view

0:00 Midjourney level style for free

0:35 Most important part of teaching a style into Stable Diffusion

1:23 I trained myself into the model and got amazing styled myself

1:30 First part of animation generation just like Corridor Crew did in their anime video

1:37 Used DreamBooth extension of Web UI on RunPod for training

1:57 Why training dataset is 1024x1024 pixels

2:25 Which rare token and class token are chosen why

2:54 Which dataset I have used to train myself

3:05 What kind of training dataset you need to generate consistent animation like Corridor Crew

3:27 A better way to connect your RunPod web UI instance

3:43 Which DreamBooth settings I have used to train myself into the base model

4:10 A good explanation of max resolution settings

4:31 Advanced tab settings of DreamBooth extension

5:15 Concepts tab of DreamBooth training

5:35 FileWords - image captions explanation

7:31 Where to see source checkpoint used for training

7:49 Why do seperate training instead of multiple concepts training

8:08 Style training used settings

9:20 Analysis of after style training upon myself trained model

10:25 x/y/z plot testing for Brad Pitt face to see overtraining effect

11:03 Castle in a forest test to verify not overtrained 1 more time

11:32 I had to do another training of my face

12:03 Final x/y/z plot comparison to decide best checkpoint

13:05 Analysis of final x/y/z plot

14:48 What you can do by using this methodology I explained

15:05 How to generate good quality, good face distant shots

15:10 very important parts of selecting good face training dataset

15:25 Why Stable Diffusion can't produce good face distant shots

15:33 How to do inpainting to fix your face in distant shots

15:48 What settings to use for inpainting to fix faces

16:17 How to upscale your image