Stable Diffusion - How to Train LoRA for Style - LoRA Part 1

Stable Diffusion - How to Train LoRA for Style - LoRA Part 1

kasukanra via YouTube Direct link

Intro

1 of 32

1 of 32

Intro

Class Central Classrooms beta

YouTube playlists curated by Class Central.

Classroom Contents

Stable Diffusion - How to Train LoRA for Style - LoRA Part 1

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Intro
  2. 2 Why is LoRA a new standard?
  3. 3 Required resources
  4. 4 Overview of video parts 1. local GUI and 2. Google Colab Notebook
  5. 5 Part 1. local GUI training
  6. 6 PC hardware specs
  7. 7 Dataset preparation
  8. 8 Batch renaming filetypes to a new filetype
  9. 9 Batch renaming attempt #2
  10. 10 BIRME cropping
  11. 11 BLIP captioning
  12. 12 How to write good captions
  13. 13 Captioning example #2
  14. 14 Creating project folder structure using kohya_ss GUI
  15. 15 Training parameters
  16. 16 Why the training steps in the console are different from max train steps
  17. 17 Console output after training commences
  18. 18 What you get after training finishes
  19. 19 Testing the style LoRA in AUTOMATIC1111 webui
  20. 20 Using x/y/z plot in scripts to vary parameters
  21. 21 Checking x/y/z plot in photoshop
  22. 22 Testing the final epoch LoRA
  23. 23 Verifying LoRA's flexibility with prompting
  24. 24 Part 2. Anime style LoRA
  25. 25 Dataset preparation on redjuice/shiru artwork
  26. 26 Using AUTOMATIC1111 webui extension tagger
  27. 27 Modifying Danbooru style tags
  28. 28 Using the kohya LoRA DreamBooth colab notebook
  29. 29 Fixing the error that occurred
  30. 30 Preliminary testing of redjuice style LoRA
  31. 31 Checking x/y/z plot in photoshop
  32. 32 Combining character and style LoRAs

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.