>#Kohya SS web GUI DreamBooth #LoRA training full tutorial. You don’t need technical knowledge to follow this tutorial. In this tutorial I have explained how to generate professional photo studio quality portrait / self images for free with Stable Diffusion training.

Our Discord server ⤵️

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 🥰 ⤵️

Technology & Science: News, Tips, Tutorials, Tricks, Best Applications, Guides, Reviews ⤵️
https://www.youtube.com/playlist?list=PL_pbwdIyffsnkay6X91BWb9rrfLATUMr3 />
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 />
Gist file used in tutorial ⤵️

How to install Python and Git tutorial ⤵️

Master DreamBooth tutorial to learn rare tokens, instance prompt, class prompt and such ⤵️

How to fix distant faces with inpainting ⤵️

How to install and use Automatic1111 Web UI for Stable Diffusion ⤵️
1 : https://youtu.be/AZg6vzWHOTA
2 : https://youtu.be/AZg6vzWHOTA

How many classification images performs best for DreamBooth training ⤵️

How LoRA training actually works tutorial ⤵️

Watch this tutorial to understand how token thing actually works ⤵️

0:00 Introduction to Kohya LoRA Training and Studio Quality Realistic AI Photo Generation
2:40 How to download and install Kohya’s GUI to do Stable Diffusion training
5:04 How to install newer cuDNN dll files to increase training speed
6:43 How to upgrade to the latest version previously installed Kohya GUI
7:02 How to start Kohya GUI via cmd
8:00 How to set DreamBooth LoRA training parameters correctly
8:10 How to use previously downloaded models to do Kohya LoRA training
8:35 How to download Realistic Vision V2 model
8:49 How to do training with Stable Diffusion 2.1 512px and 768px versions
9:44 Instance / activation and class prompt settings
10:18 What kind of training dataset you should use
11:46 Explanation of number of repeats in Kohya DreamBooth LoRA training
13:34 How to set best VAE file for better image generation quality
13:52 How to generate classification / regularization images via Automatic1111 Web UI
16:53 How to prepare captions to images and when you do need image captions
17:48 What kind of regularization images I have used
18:04 How to set training folders
18:57 Best LoRA Training settings for minimum amount of VRAM having GPUs
21:47 How to save state of training and continue later
22:44 How to save and load Kohya Training settings
23:31 How to calculate 1 epoch step count when considering repeating count
24:41 How to decide how many epochs when repeating count considered
26:00 Explanation of command line parameters displayed during training
28:19 Caption extension changing
29:24 After when we will get a checkpoint and checkpoints will be saved where
29:57 How to use generated LoRA safetensors files in SD Automatic1111 Web UI
30:45 How to activate LoRA in Stable Diffusion web UI
31:30 How to do x/y/z checkpoint comparison of LoRA checkpoints to find best model
33:29 How to improve face quality of generated images with high res fix
36:00 18 Different training parameters experiments I have made and their results comparison
36:42 How to test 18 different LoRA checkpoints with x/y/z plot
39:18 How to properly set number of epochs and save checkpoints when reducing repeating count
40:36 How to use checkpoints of Kohya DyLora, LoCon, LyCORIS/LoCon, LoHa in Automatic1111 Web UI
42:12 How to install Torch 1.13 instead of 1.12 and newer xFormers compatible with this version
43:06 How to make Kohya scripts to use your second GPU instead of your primary GPU

Dreambooth LoRA training is a method for training large language models (LLMs) to generate images from text descriptions. It is a combination of two techniques: Dreambooth and LoRA.

Dreambooth is a method for generating images from text descriptions by iteratively updating the image to match the text description. It works by first generating a random image, then using a text-to-image model to generate a new image that is closer to the text description. This process is repeated until the image is sufficiently close to the text description.

LoRA is a method for improving the performance of Dreambooth by using a latent representation of the image. LoRA works by first generating a latent representation of the image. This latent representation is then used to train a text-to-image model.

Support the Hairy Eyeball

Share this on