Completed
How to improve face quality of generated images with high res fix
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Generate Studio Quality Realistic Photos With Kohya LoRA Stable Diffusion Training - Full Tutorial
Automatically move to the next video in the Classroom when playback concludes
- 1 Introduction to Kohya LoRA Training and Studio Quality Realistic AI Photo Generation
- 2 How to download and install Kohya’s GUI to do Stable Diffusion training
- 3 How to install newer cuDNN dll files to increase training speed
- 4 How to upgrade to the latest version previously installed Kohya GUI
- 5 How to start Kohya GUI via cmd
- 6 How to set DreamBooth LoRA training parameters correctly
- 7 How to use previously downloaded models to do Kohya LoRA training
- 8 How to download Realistic Vision V2 model
- 9 How to do training with Stable Diffusion 2.1 512px and 768px versions
- 10 Instance / activation and class prompt settings
- 11 What kind of training dataset you should use
- 12 Explanation of number of repeats in Kohya DreamBooth LoRA training
- 13 How to set best VAE file for better image generation quality
- 14 How to generate classification / regularization images via Automatic1111 Web UI
- 15 How to prepare captions to images and when you do need image captions
- 16 What kind of regularization images I have used
- 17 How to set training folders
- 18 Best LoRA Training settings for minimum amount of VRAM having GPUs
- 19 How to save state of training and continue later
- 20 How to save and load Kohya Training settings
- 21 How to calculate 1 epoch step count when considering repeating count
- 22 How to decide how many epochs when repeating count considered
- 23 Explanation of command line parameters displayed during training
- 24 Caption extension changing
- 25 After when we will get a checkpoint and checkpoints will be saved where
- 26 How to use generated LoRA safetensors files in SD Automatic1111 Web UI
- 27 How to activate LoRA in Stable Diffusion web UI
- 28 How to do x/y/z checkpoint comparison of LoRA checkpoints to find best model
- 29 How to improve face quality of generated images with high res fix
- 30 18 Different training parameters experiments I have made and their results comparison
- 31 How to test 18 different LoRA checkpoints with x/y/z plot
- 32 How to properly set number of epochs and save checkpoints when reducing repeating count
- 33 How to use checkpoints of Kohya DyLora, LoCon, LyCORIS/LoCon, LoHa in Automatic1111 Web UI
- 34 How to install Torch 1.13 instead of 1.12 and newer xFormers compatible with this version
- 35 How to make Kohya scripts to use your second GPU instead of your primary GPU
