Patreon
Home / Videos / No GPU? Run Stable Diffusion 3 in SwarmUI on a Cloud GPU or

No GPU? Run Stable Diffusion 3 in SwarmUI on a Cloud GPU or a Free Kaggle Account (2024)

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.

Published Jun 25, 2024 · 7,953 views · Watch on YouTube

Get the app and files

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 Local & Cloud Tutorial With SwarmUI: Open Source Text to Image

FLUX Local & Cloud Tutorial With SwarmUI: Open Source Text to Image

FLUX, the pioneering open source txt2img model, outperforms Midjourney and others; this tutorial runs it in SwarmUI locally and in the cloud.

Chapters

  1. 0:00 Introduction to SwarmUI on cloud services tutorial (Massed Compute, RunPod & Kaggle)
  2. 3:18 How to install (pre-installed we just 1-click update) and use SwarmUI on Massed Compute virtual Ubuntu machines like in your local PC
  3. 4:52 How to install and setup synchronization folder of ThinLinc client to access and use Massed Compute virtual machine
  4. 6:34 How to connect and start using Massed Compute virtual machine after it is initialized and status is running
  5. 7:05 How to 1-click update SwarmUI on Massed Compute before start using it
  6. 7:46 How to setup multiple GPUs on SwarmUI backend to generate images on each GPU at the same time with amazing queue system
  7. 7:57 How to see status of all GPUs with nvitop command
  8. 8:43 Which pre installed Stable Diffusion models we have on Massed Compute
  9. 9:53 New model downloading speed of Massed Compute
  10. 10:44 How do I notice GPU backend setup error of 4 GPU setup
  11. 11:42 How to monitor status of all running 4 GPUs
  12. 12:22 Image generation speed, step speed on RTX A6000 on Massed Compute for SD3
  13. 12:50 How to setup and use CivitAI API key to be able to download gated (behind a login) models from CivitAI
  14. 13:55 How to quickly download all of the generated images from Massed Compute
  15. 15:22 How to install latest SwarmUI on RunPod with accurate template selection
  16. 16:50 Port setup to be able to connect SwarmUI after installation
  17. 17:50 How to download and run installer sh file for RunPod to install SwarmUI
  18. 19:47 How to restart Pod 1 time to fix backends loading forever error
  19. 20:22 How to start SwarmUI again on RunPod
  20. 21:14 How to download and use Stable Diffusion 3 (SD3) on RunPod
  21. 22:01 How to setup multiple GPU backends system on RunPod
  22. 23:22 Generation speed on RTX 4090 (step speed for SD3)
  23. 24:04 How to quickly download all generated images on RunPod to your computer / device
  24. 24:50 How to install and use SwarmUI and Stable Diffusion 3 on a free Kaggle account
  25. 28:39 How to change model root folder path on SwarmUI on Kaggle to use temporary disk space
  26. 29:21 Add another backend to utilize second T4 GPU on Kaggle
  27. 29:32 How to cancel run and start SwarmUI again (restarting)
  28. 31:39 How to use Stable Diffusion 3 model on Kaggle and generate images
  29. 33:06 Why we did get out of RAM error and how we fixed it on Kaggle
  30. 33:45 How to disable one of the back ends to prevent RAM error when using T5 XXL text encoder twice
  31. 34:04 Stable Diffusion 3 image generation speed on T4 GPU on Kaggle
  32. 34:35 How to download all of the generated images on Kaggle at once to your computer / device

About this video

In this video, I demonstrate how to install and use #SwarmUI on cloud services. If you lack a powerful GPU or wish to harness more GPU power, this video is essential. You'll learn how to install and utilize SwarmUI, one of the most powerful Generative AI interfaces, on Massed Compute, RunPod, and Kaggle (which offers free dual T4 GPU access for 30 hours weekly). This tutorial will enable you to use SwarmUI on cloud GPU providers as easily and efficiently as on your local PC. Moreover, I will show how to use Stable Diffusion 3 (#SD3) on cloud. SwarmUI uses #ComfyUI backend.

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

🔗 Windows Tutorial for Learn How to Use SwarmUI ➡️ https://youtu.be/HKX8_F1Er_w

🔗 How to download models very fast to Massed Compute, RunPod and Kaggle and how to upload models or files to Hugging Face very fast tutorial ➡️ https://youtu.be/X5WVZ0NMaTg

🔗 SECourses Discord ➡️ https://discord.com/servers/software-engineering-courses-secourses-772774097734074388

🔗 Stable Diffusion GitHub Repo (Please Star, Fork and Watch) ➡️ https://github.com/FurkanGozukara/Stable-Diffusion

Coupon Code for Massed Compute : SECourses

Coupon works on Alt Config RTX A6000 and also RTX A6000 GPUs

0:00 Introduction to SwarmUI on cloud services tutorial (Massed Compute, RunPod & Kaggle)

3:18 How to install (pre-installed we just 1-click update) and use SwarmUI on Massed Compute virtual Ubuntu machines like in your local PC

4:52 How to install and setup synchronization folder of ThinLinc client to access and use Massed Compute virtual machine

6:34 How to connect and start using Massed Compute virtual machine after it is initialized and status is running

7:05 How to 1-click update SwarmUI on Massed Compute before start using it

7:46 How to setup multiple GPUs on SwarmUI backend to generate images on each GPU at the same time with amazing queue system

7:57 How to see status of all GPUs with nvitop command

8:43 Which pre installed Stable Diffusion models we have on Massed Compute

9:53 New model downloading speed of Massed Compute

10:44 How do I notice GPU backend setup error of 4 GPU setup

11:42 How to monitor status of all running 4 GPUs

12:22 Image generation speed, step speed on RTX A6000 on Massed Compute for SD3

12:50 How to setup and use CivitAI API key to be able to download gated (behind a login) models from CivitAI

13:55 How to quickly download all of the generated images from Massed Compute

15:22 How to install latest SwarmUI on RunPod with accurate template selection

16:50 Port setup to be able to connect SwarmUI after installation

17:50 How to download and run installer sh file for RunPod to install SwarmUI

19:47 How to restart Pod 1 time to fix backends loading forever error

20:22 How to start SwarmUI again on RunPod

21:14 How to download and use Stable Diffusion 3 (SD3) on RunPod

22:01 How to setup multiple GPU backends system on RunPod

23:22 Generation speed on RTX 4090 (step speed for SD3)

24:04 How to quickly download all generated images on RunPod to your computer / device

24:50 How to install and use SwarmUI and Stable Diffusion 3 on a free Kaggle account

28:39 How to change model root folder path on SwarmUI on Kaggle to use temporary disk space

29:21 Add another backend to utilize second T4 GPU on Kaggle

29:32 How to cancel run and start SwarmUI again (restarting)

31:39 How to use Stable Diffusion 3 model on Kaggle and generate images

33:06 Why we did get out of RAM error and how we fixed it on Kaggle

33:45 How to disable one of the back ends to prevent RAM error when using T5 XXL text encoder twice

34:04 Stable Diffusion 3 image generation speed on T4 GPU on Kaggle

34:35 How to download all of the generated images on Kaggle at once to your computer / device