Patreon
Home / Videos / Train FLUX on Your Own Photos With Just 8GB VRAM: Kohya GUI

Train FLUX on Your Own Photos With Just 8GB VRAM: Kohya GUI LoRA Tutorial (2024, Windows)

FLUX 2 Pro compared with a trained FLUX SRPO model, plus the new Kohya trainer V35 that trains FLUX on GPUs with as little as 6 GB VRAM.

Published Aug 29, 2024 · 111,108 views · Watch on YouTube

Get the app and files

FLUX 2 vs FLUX SRPO & New Kohya SS GUI Premium FLUX Training App

FLUX 2 vs FLUX SRPO & New Kohya SS GUI Premium FLUX Training App

FLUX 2 Pro compared with a trained FLUX SRPO model, plus the new Kohya trainer V35 that trains FLUX on GPUs with as little as 6 GB VRAM.

Kohya GUI: Convert FLUX, SD 3.5 & SDXL LoRAs to FP8 to Save Space

Kohya GUI: Convert FLUX, SD 3.5 & SDXL LoRAs to FP8 to Save Space

Converting a trained LoRA to FP8 with Kohya GUI shrinks a 2.5 GB FP32 file to 634 MB with almost the best quality, as the FP8 vs FP16 vs FP32 grid shows.

FLUX Fine-Tuning vs LoRA: Example Dataset, Trained Models & Configs

FLUX Fine-Tuning vs LoRA: Example Dataset, Trained Models & Configs

FLUX fine-tuning / DreamBooth vs LoRA experiment shared in full: a 28-image dataset, Kohya configs, grids and every trained checkpoint free on Hugging Face.

FLUX LoRA vs Fine Tuning / DreamBooth Comparison: Batch Size 1 vs 7

FLUX LoRA vs Fine Tuning / DreamBooth Comparison: Batch Size 1 vs 7

FLUX LoRA and Fine Tuning / DreamBooth compared with 15 and 256 training images at batch size 1 and 7, for both realism and stylization.

Kohya GUI: Full FLUX Dev DreamBooth on 6 GB GPUs Without Quality Loss

Kohya GUI: Full FLUX Dev DreamBooth on 6 GB GPUs Without Quality Loss

Kohya GUI can now fully fine-tune FLUX Dev on 6 GB GPUs with the same quality as 48 GB GPUs, and fine-tuning gives better results than any LoRA training.

FLUX LoRA Single Block Training Research: Network Alpha & Rank Tests

FLUX LoRA Single Block Training Research: Network Alpha & Rank Tests

FLUX LoRA single block / layer training tested in Kohya GUI: one block needed over 10 times the usual learning rate and still gave sub-par results.

Chapters

  1. 0:00 Full FLUX LoRA Training Tutorial
  2. 3:37 Guide on downloading and extracting Kohya GUI
  3. 4:22 System requirements: Python, FFmpeg, CUDA, C++ tools, and Git
  4. 5:40 Verifying installations using the command prompt
  5. 6:20 Kohya GUI installation process and error-checking
  6. 6:59 Setting the Accelerate option in Kohya GUI, with a discussion of choices
  7. 7:50 Use of the bat file update to upgrade libraries and scripts
  8. 8:42 Speed differences between Torch 2.4.0 and 2.5, particularly on Windows and Linux
  9. 9:54 Starting Kohya GUI via the gui.bat or automatic starter file
  10. 10:14 Kohya GUI interface and selecting LoRA training mode
  11. 10:33 LoRA vs. DreamBooth training, with pros and cons
  12. 11:03 Emphasis on extensive research, with over 72 training sessions
  13. 11:50 Ongoing research on hyperparameters and future updates
  14. 12:30 Selecting configurations based on GPU VRAM size
  15. 13:05 Different configurations and their impact on training quality
  16. 14:22 "Better colors" configuration for improved image coloring
  17. 15:58 Setting the pre-trained model path and links for downloading models
  18. 16:42 Significance of training images and potential errors
  19. 17:08 Dataset preparation, emphasizing image captioning, cropping, and resizing
  20. 17:54 Repeating and regularization images for balanced datasets
  21. 18:25 Impact of regularization images and their optional use in FLUX training
  22. 19:00 Instance and class prompts and their importance in training
  23. 19:58 Setting the destination directory for saving training data
  24. 20:26 Preparing training data in Kohya GUI and generated folder structure
  25. 21:10 Joy Caption for batch captioning images, with key features
  26. 21:52 Joy Caption interface for batch captioning
  27. 22:39 Impact of captioning on likeness, with tips for training styles
  28. 23:26 Adding an activation token to prompts
  29. 23:54 Image caption editor for manual caption editing
  30. 24:53 Batch edit options in the caption editor
  31. 25:34 Verifying captions for activation token inclusion
  32. 26:06 Kohya GUI and copying info to respective fields
  33. 27:01 "Train images image" folder path and its relevance
  34. 28:10 Setting different repeating numbers for multiple concepts
  35. 28:45 Setting the output name for generated checkpoints
  36. 29:03 Parameters: epochs, training dataset, and VAE path
  37. 29:21 Epochs and recommended numbers based on images
  38. 30:11 Training dataset quality, including diversity
  39. 31:00 Importance of image focus, sharpness, and lighting
  40. 31:42 Saving checkpoints at specific intervals
  41. 32:11 Caption file extension option (default: TXT)
  42. 33:20 VAE path setting and selecting the appropriate VA.saveTensor file
  43. 33:59 Clip large model setting and selecting the appropriate file
  44. 34:20 T5 XXL setting and selecting the appropriate file
  45. 34:51 Saving and reloading configurations in Kohya GUI
  46. 35:36 Ongoing research on clip large training and VRAM usage
  47. 36:06 Checking VRAM usage before training and tips to reduce it
  48. 37:39 Starting training in Kohya GUI and explanation of messages
  49. 38:48 Messages during training: steps, batch size, and regularization factor
  50. 39:59 How to set virtual RAM memory to prevent errors
  51. 40:34 Checkpoint saving process and their location
  52. 41:11 Output directory setting and changing it for specific locations
  53. 42:00 Checkpoint size and saving them in FP16 format for smaller files
  54. 43:21 Swarm UI for using trained models and its features
  55. 44:02 Moving LoRA files to the Swarm UI folder
  56. 44:41 Speed up Swarm UI on RTX 4000 series GPUs
  57. 45:13 Generating images using FLUX in Swarm UI
  58. 46:12 Generating an image without a LoRA using test prompts
  59. 46:55 VRAM usage with FLUX and using multiple GPUs for faster generation
  60. 47:54 Using LoRAs in Swarm UI and selecting a LoRA
  61. 48:27 Generating an image using a LoRA
  62. 49:01 Optional in-painting face feature in Swarm UI
  63. 49:46 Overfitting in FLUX training and training image quality
  64. 51:59 Finding the best checkpoint using the Grid Generator tool
  65. 52:55 Grid Generator tool for selecting LoRAs and prompts
  66. 53:59 Generating the grid and expected results
  67. 56:57 Analyzing grid results in Swarm UI
  68. 57:56 Finding the best LoRA checkpoint based on grid results
  69. 58:56 Generating images with wildcards in Swarm UI
  70. 60:05 Save models on Hugging Face with a link to a tutorial
  71. 63:20 Using regularization images for SDXL training
  72. 65:30 Saving checkpoints during SDXL training
  73. 66:15 Extracting LoRAs from SDXL models

About this video

Ultimate Kohya GUI FLUX LoRA training tutorial. This tutorial is product of non-stop 9 days research and training. I have trained over 73 FLUX LoRA models and analyzed all to prepare this tutorial video. The research still going on and hopefully the results will be significantly improved and latest configs and findings will be shared. Please watch the tutorial without skipping any part. If you are a beginner user or an expert user, this tutorial covers all for you.

🔗 Full Instructions and Links Written Post (the one used in the tutorial) ⤵️

▶️ https://www.patreon.com/posts/click-to-open-post-used-in-tutorial-110879657

0:00 Full FLUX LoRA Training Tutorial

3:37 Guide on downloading and extracting Kohya GUI

4:22 System requirements: Python, FFmpeg, CUDA, C++ tools, and Git

5:40 Verifying installations using the command prompt

6:20 Kohya GUI installation process and error-checking

6:59 Setting the Accelerate option in Kohya GUI, with a discussion of choices

7:50 Use of the bat file update to upgrade libraries and scripts

8:42 Speed differences between Torch 2.4.0 and 2.5, particularly on Windows and Linux

9:54 Starting Kohya GUI via the gui.bat or automatic starter file

10:14 Kohya GUI interface and selecting LoRA training mode

10:33 LoRA vs. DreamBooth training, with pros and cons

11:03 Emphasis on extensive research, with over 72 training sessions

11:50 Ongoing research on hyperparameters and future updates

12:30 Selecting configurations based on GPU VRAM size

13:05 Different configurations and their impact on training quality

14:22 "Better colors" configuration for improved image coloring

15:58 Setting the pre-trained model path and links for downloading models

16:42 Significance of training images and potential errors

17:08 Dataset preparation, emphasizing image captioning, cropping, and resizing

17:54 Repeating and regularization images for balanced datasets

18:25 Impact of regularization images and their optional use in FLUX training

19:00 Instance and class prompts and their importance in training

19:58 Setting the destination directory for saving training data

20:26 Preparing training data in Kohya GUI and generated folder structure

21:10 Joy Caption for batch captioning images, with key features

21:52 Joy Caption interface for batch captioning

22:39 Impact of captioning on likeness, with tips for training styles

23:26 Adding an activation token to prompts

23:54 Image caption editor for manual caption editing

24:53 Batch edit options in the caption editor

25:34 Verifying captions for activation token inclusion

26:06 Kohya GUI and copying info to respective fields

27:01 "Train images image" folder path and its relevance

28:10 Setting different repeating numbers for multiple concepts

28:45 Setting the output name for generated checkpoints

29:03 Parameters: epochs, training dataset, and VAE path

29:21 Epochs and recommended numbers based on images