Train an SDXL LoRA in 2 Hours on a 35-Cent-per-Hour Cloud GPU: Kohya on RunPod (2023)
Timestep sampling shift explained for diffusion models: Qwen Image uses an exponential shift and FLUX a linear one, and 2.205 matches Qwen at 1664x928.
Published Aug 13, 2023 · 19,205 views · Watch on YouTube
Get the app and files

Decoding the Timestep Shift in Diffusion Training: Qwen Image & FLUX
Timestep sampling shift explained for diffusion models: Qwen Image uses an exponential shift and FLUX a linear one, and 2.205 matches Qwen at 1664x928.

Kohya FLUX LoRA & Fine Tuning Research and Early Configs (Legacy)
Kohya FLUX LoRA and fine tuning research from August 2024 with early configs, Clip-L and multi-GPU tests; the post is deprecated in favor of newer tutorials.

SDXL DreamBooth / Fine Tuning: Best Kohya Configs From 6 GB GPUs
SDXL DreamBooth / fine tuning configs for Kohya SS GUI, based on results of 100+ full trainings, train on GPUs with as low as 6 GB VRAM via block swapping.

SD 1.5 & SDXL DreamBooth and LoRA Training: Full Newbie Workflow
Stable Diffusion training workflow for newbies, built from 120+ SDXL and 70+ SD 1.5 trainings: Kohya, regularization images and ADetailer.
Chapters
- 0:00 Introduction to easy tutorial of using RunPod to do SDXL training
- 1:55 How to start your RunPod machine for Stable Diffusion XL usage and training
- 3:18 How to install Kohya on RunPod with a single click installer
- 4:22 Important things about using SDXL on RunPod
- 5:38 Step by step installation of Kohya SS GUI trainer on RunPod
- 7:08 How to terminate automatically started Automatic1111 Instance to free up VRAM
- 7:26 How to change relauncher.py file to prevent infinite auto relaunch of Automatic1111 Web UI
- 8:00 Where do you need to download and put Stable Diffusion model and VAE files on RunPod
- 8:58 How to download Stable Diffusion models into RunPod
- 9:25 How to terminate previously started Automatic1111 Web UI instance to free up VRAM before training
- 10:03 How to start Kohya GUI after installation
- 10:42 How to save and load Kohya training configuration on RunPod
- 10:54 How to upload and set your training images
- 12:01 How to install runpodctl
- 13:15 Why runpodctl is useful
- 13:51 How to configure Kohya LoRA training on RunPod for Stable Diffusion XL
- 15:58 What is the importance and effect of Network Rank (Dimension)
- 19:41 How to update Automatic1111 Web UI on RunPod
- 20:04 How to understand your Kohya training completed or not
- 21:57 How to start using your trained or downloaded SDXL LoRA models
- 22:13 Where the training checkpoint files are saved
- 22:46 How you should connect to Automatic1111 Web UI interface on RunPod for image generation
- 23:15 How to set best Stable Diffusion VAE file for best image quality
- 23:33 How to set full precision VAE on RunPod --no-half-vae
- 24:18 Where to find good Stable Diffusion prompts for SDXL and SD 1.5 models
- 25:05 How to activate your trained LoRA via appending to the prompt
- 25:47 How to improve faces / fix them via using Adetailer automatic inpainting extension
- 26:44 How to reload last used prompt and all settings with 1 click
- 26:52 How to enable and use adetailer extension
- 27:06 In which folder generated images saved and how to download them very fast on RunPod
- 29:24 How to test face quality and verify your trained LoRA or DreamBooth models / checkpoints
- 30:10 How to do prompt engineering to improve and fix faces
- 32:06 How to join our community helping Discord and where to contact to me
About this video
If you don't have a GPU, or have a strong GPU, or you are using Mac and your computer not supporting Stable Diffusion training, SDXL training, then this is the tutorial you are looking for. In this tutorial, we will use a cheap cloud GPU service provider RunPod to use both Stable Diffusion Web UI Automatic1111 and Stable Diffusion trainer Kohya SS GUI to train SDXL LoRAs. By watching this tutorial, you will be able to training and generate images as easy as your own computer by using RunPod cloud service.
1 click Auto Kohya Installer ⤵️
https://www.patreon.com/posts/84898806
Tutorial GitHub Readme File ⤵️
SECourses Discord To Get Full Support ⤵️
https://discord.com/servers/software-engineering-courses-secourses-772774097734074388
My LinkedIn ⤵️
https://www.linkedin.com/in/furkangozukara/
My Instagram ⤵️
https://www.instagram.com/gozukarafurkan/
My Medium ⤵️
@FurkanGozukara https://medium.com/@furkangozukara
My CivitAI ⤵️
https://civitai.com/user/SECourses
Hopefully I will do more research about SDXL training. Will investigate training only unet without text encoder. Moreover, I will investigate and make a workflow about celebrity name based training hopefully. Furthermore, SDXL full DreamBooth training is also on my research and workflow preparation list. Stay subscribed for all.
0:00 Introduction to easy tutorial of using RunPod to do SDXL training
1:55 How to start your RunPod machine for Stable Diffusion XL usage and training
3:18 How to install Kohya on RunPod with a single click installer
4:22 Important things about using SDXL on RunPod
5:38 Step by step installation of Kohya SS GUI trainer on RunPod
7:08 How to terminate automatically started Automatic1111 Instance to free up VRAM
7:26 How to change relauncher.py file to prevent infinite auto relaunch of Automatic1111 Web UI
8:00 Where do you need to download and put Stable Diffusion model and VAE files on RunPod
8:58 How to download Stable Diffusion models into RunPod
9:25 How to terminate previously started Automatic1111 Web UI instance to free up VRAM before training,
10:03 How to start Kohya GUI after installation
10:42 How to save and load Kohya training configuration on RunPod
10:54 How to upload and set your training images
12:01 How to install runpodctl
13:15 Why runpodctl is useful
13:51 How to configure Kohya LoRA training on RunPod for Stable Diffusion XL
15:58 What is the importance and effect of Network Rank (Dimension)
19:41 How to update Automatic1111 Web UI on RunPod
20:04 How to understand your Kohya training completed or not
21:57 How to start using your trained or downloaded SDXL LoRA models
22:13 Where the training checkpoint files are saved
22:46 How you should connect to Automatic1111 Web UI interface on RunPod for image generation
23:15 How to set best Stable Diffusion VAE file for best image quality
23:33 How to set full precision VAE on RunPod --no-half-vae