Patreon
Home / Videos / Train an AI on Your Own Photos With an 8GB GPU: Z-Image Turb

Train an AI on Your Own Photos With an 8GB GPU: Z-Image Turbo LoRA Training on Your PC

Ostris AI-Toolkit installs automatically on Windows, RunPod, SimplePod and Massed Compute and is now patched to train on custom single-file base models.

Published Dec 04, 2025 · 15,551 views · Watch on YouTube

Get the app and files

Ostris AI-Toolkit 1-Click Installers: LoRA Training on Windows & Cloud

Ostris AI-Toolkit 1-Click Installers: LoRA Training on Windows & Cloud

Ostris AI-Toolkit installs automatically on Windows, RunPod, SimplePod and Massed Compute and is now patched to train on custom single-file base models.

Z-Image Turbo Tutorial: LoRA Training, ControlNet Union & Presets

Z-Image Turbo Tutorial: LoRA Training, ControlNet Union & Presets

Z-Image Turbo step by step: generate with ready SwarmUI presets, add Fun ControlNet Union and train LoRAs with Ostris AI Toolkit on GPUs from 6 GB.

Chapters

  1. 0:00 Introduction to Z-Image Turbo Model
  2. 0:54 FP8 Scaled Version 5.7GB for Low VRAM
  3. 1:10 ControlNet Union with Z-Image Turbo
  4. 1:30 LoRA Training with Ostris AI Toolkit
  5. 2:00 Default vs Custom Training Preset Quality Comparison
  6. 3:00 RunPod Cloud Training Preview
  7. 3:40 MassedCompute Cloud Training Preview
  8. 4:16 Downloading Z-Image Models via SwarmUI
  9. 5:00 Z-Image Turbo Core Bundle & ControlNet Files
  10. 5:58 FP8 Scaled Model & Musubi Tuner Converter
  11. 7:13 Updating ComfyUI for Sage & Flash Attention
  12. 8:13 Updating SwarmUI & ControlNet Preprocessors
  13. 8:52 Updating & Importing Latest SwarmUI Presets
  14. 9:20 Generating with Quality 2 Fast Preset
  15. 10:48 Generating with Quality 1 Upscale Preset
  16. 11:35 Quality 1 vs Quality 2 Visual Comparison
  17. 12:13 Setting up ControlNet Input & Aspect Ratio
  18. 13:41 ControlNet Strength Settings & Canny Test
  19. 15:26 Using Depth Preprocessor with Z-Image
  20. 15:58 Coloring Lineart Drawings with ControlNet
  21. 16:58 Lineart Preprocessing Comparison
  22. 17:50 Ostris AI Toolkit Installation Prerequisites
  23. 19:12 Installing Ostris AI Toolkit on Windows
  24. 20:02 First Time UI Setup & Launching Interface
  25. 21:04 Loading Custom Training Configs
  26. 21:38 Creating a New Dataset Structure
  27. 22:24 Ultimate Batch Image Processing App Install
  28. 23:17 Dataset Prep Stage 1: Auto-Zooming with SAM2
  29. 26:08 Dataset Prep Stage 2: Resizing to Exact Resolution
  30. 28:12 How to Select Best Training Images
  31. 30:24 Importance of Emotions & Angles in Datasets
  32. 31:44 Z-Image Resolution & Aspect Ratio Rules
  33. 33:21 Configuring Training Parameters & Epochs
  34. 36:52 Resolution Impact on Training Speed
  35. 37:46 Starting the Training Job on Windows
  36. 38:39 Monitoring Training Progress & VRAM
  37. 39:43 Checkpoint Generation Settings
  38. 40:40 Resuming Training from Last Checkpoint
  39. 42:09 Training Speeds on RTX 5090 vs 4090 vs 3060
  40. 43:01 Training Quality: Default vs Custom Preset Comparison
  41. 44:21 Testing LoRAs with SwarmUI Grid Generator
  42. 46:04 Fixing ControlNet Error in Grid Generation
  43. 47:09 Comparing Generated LoRA Checkpoints
  44. 47:38 Using Trained LoRA with ControlNet Union
  45. 48:10 RunPod: GPU Selection & Template Setup
  46. 50:32 RunPod: Port 8675 Config & Initialization
  47. 51:36 RunPod: Uploading Installation Files
  48. 52:01 RunPod: One-Click Installation Command
  49. 54:07 RunPod: Starting AI Toolkit & Proxy Connection
  50. 54:38 RunPod: Uploading Dataset via Interface
  51. 55:32 RunPod: Starting the Training Job
  52. 56:24 RunPod: Speed & Cost Analysis
  53. 57:28 RunPod: Auto-Stop Command Setup
  54. 58:24 MassedCompute: GPU Selection & Coupon Code
  55. 60:16 MassedCompute: ThinLinc Client Setup
  56. 61:21 MassedCompute: Transferring Files to Shared Folder
  57. 62:55 MassedCompute: Installation Command
  58. 65:49 MassedCompute: Connecting via Public URL
  59. 66:54 MassedCompute: Starting Training Job
  60. 68:43 Downloading Checkpoints & Stopping Instance

About this video

Z-Image Turbo LoRA training with Ostris AI Toolkit + Z-Image Turbo Fun Controlnet Union + 1-click to download and install the very best Z-Image Turbo presets. In this tutorial, I will explain how to setup Z-Image Turbo model properly in your local PC with SwarmUI and download models and use them with highest quality via ready presets. Moreover, I will show to install Z-Image Turbo Fun Controlnet Union to generate amazing quality images with ControlNet preprocessors. Furthermore, I will show how to 1-click install AI Toolkit from Ostris and train Z-Image Turbo model LoRAs with highest quality configs made for every GPU like 8 GB GPUs, 12 GB GPUs, 24 GB GPUs and so on. I did a massive research to prepare these Z-Image Turbo model training configurations.

👇 Links & Resources Mentioned:

Download SwarmUI & Models: [ https://www.patreon.com/posts/Download-SwarmUI-Models-114517862 ]

Ostris AI Toolkit & Configs (SECourses Version): [ https://www.patreon.com/posts/Ostris-AI-Toolkit-140089077 ]

Ultimate Batch Image Processing App: [ https://www.patreon.com/posts/Ultimate-Batch-Image-Processing-App-120352012 ]

SwarmUI with ComfyUI Backend Windows Tutorial: [ https://youtu.be/c3gEoAyL2IE ]

SwarmUI with ComfyUI Backend RunPod and Massed Compute Cloud Tutorial: [ https://youtu.be/bBxgtVD3ek4 ]

⏱️ Video Chapters:

0:00 Introduction to Z-Image Turbo Model

0:54 FP8 Scaled Version 5.7GB for Low VRAM

1:10 ControlNet Union with Z-Image Turbo

1:30 LoRA Training with Ostris AI Toolkit

2:00 Default vs Custom Training Preset Quality Comparison

3:00 RunPod Cloud Training Preview

3:40 MassedCompute Cloud Training Preview

4:16 Downloading Z-Image Models via SwarmUI

5:00 Z-Image Turbo Core Bundle & ControlNet Files

5:58 FP8 Scaled Model & Musubi Tuner Converter

7:13 Updating ComfyUI for Sage & Flash Attention

8:13 Updating SwarmUI & ControlNet Preprocessors

8:52 Updating & Importing Latest SwarmUI Presets

9:20 Generating with Quality 2 Fast Preset

10:48 Generating with Quality 1 Upscale Preset

11:35 Quality 1 vs Quality 2 Visual Comparison

12:13 Setting up ControlNet Input & Aspect Ratio

13:41 ControlNet Strength Settings & Canny Test

15:26 Using Depth Preprocessor with Z-Image

15:58 Coloring Lineart Drawings with ControlNet

16:58 Lineart Preprocessing Comparison

17:50 Ostris AI Toolkit Installation Prerequisites

19:12 Installing Ostris AI Toolkit on Windows

20:02 First Time UI Setup & Launching Interface

21:04 Loading Custom Training Configs

21:38 Creating a New Dataset Structure

22:24 Ultimate Batch Image Processing App Install

23:17 Dataset Prep Stage 1: Auto-Zooming with SAM2

26:08 Dataset Prep Stage 2: Resizing to Exact Resolution

28:12 How to Select Best Training Images

30:24 Importance of Emotions & Angles in Datasets

31:44 Z-Image Resolution & Aspect Ratio Rules