Patreon
Home / Videos / Zero to Hero Stable Diffusion 3 Tutorial with Amazing SwarmU

Zero to Hero Stable Diffusion 3 Tutorial with Amazing SwarmUI SD Web UI that Utilizes ComfyUI

ComfyUI and SwarmUI on RunPod, step by step: install both with 1 click, connect ComfyUI as the SwarmUI backend and generate FLUX images and Wan 2.1 videos.

Published Jun 16, 2024 · 35,660 views · Watch on YouTube

Get the app and files

ComfyUI & SwarmUI on RunPod Tutorial: 1-Click Setup With RTX 5000 GPUs

ComfyUI & SwarmUI on RunPod Tutorial: 1-Click Setup With RTX 5000 GPUs

ComfyUI and SwarmUI on RunPod, step by step: install both with 1 click, connect ComfyUI as the SwarmUI backend and generate FLUX images and Wan 2.1 videos.

SwarmUI Master Tutorial: Stable Diffusion 3.5 Large & FLUX Models

SwarmUI Master Tutorial: Stable Diffusion 3.5 Large & FLUX Models

SwarmUI master tutorial for Stable Diffusion 3.5 Large, FLUX Dev, SD 1.5, SDXL and SD3 on your PC and in the cloud, led by a 70-chapter main Windows video.

Genmo Mochi 1 Tutorial: Free Local AI Video Generation in SwarmUI

Genmo Mochi 1 Tutorial: Free Local AI Video Generation in SwarmUI

Genmo Mochi 1, a 10B parameter open source video model, runs free on your PC with SwarmUI; the full tutorial covers setup, best settings and VAE tiling.

SD 3.5 Large vs FLUX Dev: Best Sampler, Scheduler & FP8 Comparison

SD 3.5 Large vs FLUX Dev: Best Sampler, Scheduler & FP8 Comparison

Stable Diffusion 3.5 Large tested with 62 prompts to find the best sampler and scheduler, plus an SD 3.5 Large vs FLUX Dev comparison with raw grids shared.

FLUX LoRA vs Fine Tuning / DreamBooth Comparison: Batch Size 1 vs 7

FLUX LoRA vs Fine Tuning / DreamBooth Comparison: Batch Size 1 vs 7

FLUX LoRA and Fine Tuning / DreamBooth compared with 15 and 256 training images at batch size 1 and 7, for both realism and stylization.

Kohya FLUX LoRA & Fine Tuning Research and Early Configs (Legacy)

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.

Chapters

  1. 0:00 Introduction to the Stable Diffusion 3 (SD3) and SwarmUI and what is in the tutorial
  2. 4:12 Architecture and features of SD3
  3. 5:05 What each different model files of Stable Diffusion 3 means
  4. 6:26 How to download and install SwarmUI on Windows for SD3 and all other Stable Diffusion models
  5. 8:42 What kind of folder path you should use when installing SwarmUI
  6. 10:28 If you get installation error how to notice and fix it
  7. 11:49 Installation has been completed and now how to start using SwarmUI
  8. 12:29 Which settings I change before start using SwarmUI and how to change your theme like dark, white, gray
  9. 12:56 How to make SwarmUI save generated images as PNG
  10. 13:08 How to find description of each settings and configuration
  11. 13:28 How to download SD3 model and start using on Windows
  12. 13:38 How to use model downloader utility of SwarmUI
  13. 14:17 How to set models folder paths and link your existing models folders in SwarmUI
  14. 14:35 Explanation of Root folder path in SwarmUI
  15. 14:52 VAE of SD3 do we need to download?
  16. 15:25 Generate and model section of the SwarmUI to generate images and how to select your base model
  17. 16:02 Setting up parameters and what they do to generate images
  18. 17:06 Which sampling method is best for SD3
  19. 17:22 Information about SD3 text encoders and their comparison
  20. 18:14 First time generating an image with SD3
  21. 19:36 How to regenerate same image
  22. 20:17 How to see image generation speed and step speed and more information
  23. 20:29 Stable Diffusion 3 it per second speed on RTX 3090 TI
  24. 20:39 How to see VRAM usage on Windows 10
  25. 22:08 And testing and comparing different text encoders for SD3
  26. 22:36 How to use FP16 version of T5 XXL text encoder instead of default FP8 version
  27. 25:27 The image generation speed when using best config for SD3
  28. 26:37 Why VAE of the SD3 is many times better than previous Stable Diffusion models, 4 vs 8 vs 16 vs 32 channels VAE
  29. 27:40 How to and where to download best AI upscaler models
  30. 29:10 How to use refiner and upscaler models to improve and upscale generated images
  31. 29:21 How to restart and start SwarmUI
  32. 32:01 The folders where the generated images are saved
  33. 32:13 Image history feature of SwarmUI
  34. 33:10 Upscaled image comparison
  35. 34:01 How to download all upscaler models at once
  36. 34:34 Presets feature in depth
  37. 36:55 How to generate forever / infinite times
  38. 37:13 Non-tiled upscale caused issues
  39. 38:36 How to compare tiled vs non-tiled upscale and decide best
  40. 39:05 275 SwarmUI presets (cloned from Fooocus) I prepared and the scripts I coded to prepare them and how to import those presets
  41. 42:10 Model browser feature
  42. 43:25 How to generate TensorRT engine for huge speed up
  43. 43:47 How to update SwarmUI
  44. 44:27 Prompt syntax and advanced features
  45. 45:35 How to use Wildcards (random prompts) feature
  46. 46:47 How to see full details / metadata of generated images
  47. 47:13 Full guide for extremely powerful grid image generation (like X/Y/Z plot)
  48. 47:35 How to put all downloaded upscalers from zip file
  49. 51:37 How to see what is happening at the server logs
  50. 53:04 How to continue grid generation process after interruption
  51. 54:32 How to open grid generation after it has been completed and how to use it
  52. 56:13 Example of tiled upscaling seaming problem
  53. 60:30 Full guide for image history
  54. 62:22 How to directly delete images and star them
  55. 63:20 How to use SD 1.5 and SDXL models and LoRAs
  56. 66:24 Which sampler method is best
  57. 66:43 How to use image to image
  58. 68:43 How to use edit image / inpainting
  59. 70:38 How to use amazing segmentation feature to automatically inpaint any part of images
  60. 75:55 How to use segmentation on existing images for inpainting and get perfect results with different seeds
  61. 78:19 More detailed information regarding upscaling and tiling and SD3
  62. 80:08 Seams perfect explanation and example and how to fix it
  63. 81:09 How to use queue system
  64. 81:23 How to use multiple GPUs with adding more backends
  65. 84:38 Loading model in low VRAM mode
  66. 85:10 How to fix colors over saturation
  67. 87:00 Best image generation configuration for SD3
  68. 87:44 How to apply upscale to your older generated images quickly via preset
  69. 88:39 Other amazing features of SwarmUI
  70. 88:49 Clip tokenization and rare token OHWX

About this video

Do not skip any part of this tutorial to master how to use Stable Diffusion 3 (SD3) with the most advanced generative AI open source APP SwarmUI. Automatic1111 SD Web UI or Fooocus are not supporting the #SD3 yet. Therefore, I am starting to make tutorials for SwarmUI as well. #StableSwarmUI is officially developed by the StabilityAI and your mind will be blown after you watch this tutorial and learn its amazing features. StableSwarmUI uses #ComfyUI as the back end thus it has all the good features of ComfyUI and it brings you easy to use features of Automatic1111 #StableDiffusion Web UI with them. I really liked SwarmUI and planning to do more tutorials for it.

🔗 The Public Post (no login or account required) Shown In The Video With The Links ➡️ https://www.patreon.com/posts/stableswarmui-3-106135985

0:00 Introduction to the Stable Diffusion 3 (SD3) and SwarmUI and what is in the tutorial

4:12 Architecture and features of SD3

5:05 What each different model files of Stable Diffusion 3 means

6:26 How to download and install SwarmUI on Windows for SD3 and all other Stable Diffusion models

8:42 What kind of folder path you should use when installing SwarmUI

10:28 If you get installation error how to notice and fix it

11:49 Installation has been completed and now how to start using SwarmUI

12:29 Which settings I change before start using SwarmUI and how to change your theme like dark, white, gray

12:56 How to make SwarmUI save generated images as PNG

13:08 How to find description of each settings and configuration

13:28 How to download SD3 model and start using on Windows

13:38 How to use model downloader utility of SwarmUI

14:17 How to set models folder paths and link your existing models folders in SwarmUI

14:35 Explanation of Root folder path in SwarmUI

14:52 VAE of SD3 do we need to download?

15:25 Generate and model section of the SwarmUI to generate images and how to select your base model

16:02 Setting up parameters and what they do to generate images

17:06 Which sampling method is best for SD3

17:22 Information about SD3 text encoders and their comparison

18:14 First time generating an image with SD3

19:36 How to regenerate same image

20:17 How to see image generation speed and step speed and more information

20:29 Stable Diffusion 3 it per second speed on RTX 3090 TI

20:39 How to see VRAM usage on Windows 10

22:08 And testing and comparing different text encoders for SD3

22:36 How to use FP16 version of T5 XXL text encoder instead of default FP8 version

25:27 The image generation speed when using best config for SD3

26:37 Why VAE of the SD3 is many times better than previous Stable Diffusion models, 4 vs 8 vs 16 vs 32 channels VAE

27:40 How to and where to download best AI upscaler models

29:10 How to use refiner and upscaler models to improve and upscale generated images

29:21 How to restart and start SwarmUI

32:01 The folders where the generated images are saved

32:13 Image history feature of SwarmUI

33:10 Upscaled image comparison

34:01 How to download all upscaler models at once

34:34 Presets feature in depth

36:55 How to generate forever / infinite times

37:13 Non-tiled upscale caused issues