1 Full FLUX LoRA Training Tutorial 3:36
2 Guide on downloading and extracting Kohya GUI 0:44
3 System requirements: Python, FFmpeg, CUDA, C++ tools, and Git 1:17
4 Verifying installations using the command prompt 0:39
5 Kohya GUI installation process and error-checking 0:38
6 Setting the Accelerate option in Kohya GUI, with a discussion of choices 0:50
7 Use of the bat file update to upgrade libraries and scripts 0:51
8 Speed differences between Torch 2.4.0 and 2.5, particularly on Windows and Linux 1:11
9 Starting Kohya GUI via the gui.bat or automatic starter file 0:19
10 Kohya GUI interface and selecting LoRA training mode 0:18
11 LoRA vs. DreamBooth training, with pros and cons 0:29
12 Emphasis on extensive research, with over 72 training sessions 0:46
13 Ongoing research on hyperparameters and future updates 0:39
14 Selecting configurations based on GPU VRAM size 0:34
15 Different configurations and their impact on training quality 1:16
16 "Better colors" configuration for improved image coloring 1:35
17 Setting the pre-trained model path and links for downloading models 0:43
18 Significance of training images and potential errors 0:25
19 Dataset preparation, emphasizing image captioning, cropping, and resizing 0:45
20 Repeating and regularization images for balanced datasets 0:30
21 Impact of regularization images and their optional use in FLUX training 0:34
22 Instance and class prompts and their importance in training 0:57
23 Setting the destination directory for saving training data 0:27
24 Preparing training data in Kohya GUI and generated folder structure 0:43
25 Joy Caption for batch captioning images, with key features 0:41
26 Joy Caption interface for batch captioning 0:46
27 Impact of captioning on likeness, with tips for training styles 0:46
28 Adding an activation token to prompts 0:27
29 Image caption editor for manual caption editing 0:58
30 Batch edit options in the caption editor 0:40
31 Verifying captions for activation token inclusion 0:31
32 Kohya GUI and copying info to respective fields 0:54
33 "Train images image" folder path and its relevance 1:08
34 Setting different repeating numbers for multiple concepts 0:34
35 Setting the output name for generated checkpoints 0:17
36 Parameters: epochs, training dataset, and VAE path 0:17
37 Epochs and recommended numbers based on images 0:49
38 Training dataset quality, including diversity 0:48
39 Importance of image focus, sharpness, and lighting 0:41
40 Saving checkpoints at specific intervals 0:28
41 Caption file extension option default: TXT 1:08
42 VAE path setting and selecting the appropriate VA.saveTensor file 0:38
43 Clip large model setting and selecting the appropriate file 0:20
44 T5 XXL setting and selecting the appropriate file 0:30
45 Saving and reloading configurations in Kohya GUI 0:44
46 Ongoing research on clip large training and VRAM usage 0:29
47 Checking VRAM usage before training and tips to reduce it 1:32
48 Starting training in Kohya GUI and explanation of messages 1:08
49 Messages during training: steps, batch size, and regularization factor 1:10
50 How to set virtual RAM memory to prevent errors 0:34
51 Checkpoint saving process and their location 0:36
52 Output directory setting and changing it for specific locations 0:48
53 Checkpoint size and saving them in FP16 format for smaller files 1:20
54 Swarm UI for using trained models and its features 0:40
55 Moving LoRA files to the Swarm UI folder 0:38
56 Speed up Swarm UI on RTX 4000 series GPUs 0:31
57 Generating images using FLUX in Swarm UI 0:58
58 Generating an image without a LoRA using test prompts 0:42
59 VRAM usage with FLUX and using multiple GPUs for faster generation 0:58
60 Using LoRAs in Swarm UI and selecting a LoRA 0:32
61 Generating an image using a LoRA in Swarm UI 0:33
62 Optional in-painting face feature in Swarm UI 0:44
63 Overfitting in FLUX training and training image quality 2:12
64 Finding the best checkpoint using the Grid Generator tool in Swarm UI 0:55
65 Grid Generator tool for selecting LoRAs and prompts 1:03
66 Generating the grid and expected results 2:57
67 Analyzing grid results in Swarm UI 0:58
68 Finding the best LoRA checkpoint based on grid results 0:59
69 Generating images with wildcards in Swarm UI 1:08
70 Save models on Hugging Face with a link to a tutorial
71 Training SDXL and SD1.5 models using Kohya GUI
72 Using regularization images for SDXL training 2:09
73 Saving checkpoints during SDXL training 0:44
74 Extracting LoRAs from SDXL models