Patreon
Home / Videos / No GPU? Run FLUX and SDXL Free on Kaggle With SwarmUI (30 GP

No GPU? Run FLUX and SDXL Free on Kaggle With SwarmUI (30 GPU Hours a Week)

SwarmUI notebook for a free Kaggle account that runs FLUX Dev Q8 GGUF on both T4 GPUs at once, generating 2 images at the same time, with a video tutorial.

Published Feb 22, 2025 · 2,652 views · Watch on YouTube

Get the app and files

SwarmUI Free Kaggle Notebook: FLUX, SDXL and SD 3.5 on Dual T4 GPUs

SwarmUI Free Kaggle Notebook: FLUX, SDXL and SD 3.5 on Dual T4 GPUs

SwarmUI notebook for a free Kaggle account that runs FLUX Dev Q8 GGUF on both T4 GPUs at once, generating 2 images at the same time, with a video tutorial.

Chapters

  1. 0:00 Introduction to the tutorial
  2. 0:16 How to download Kaggle notebook and load it into Kaggle and start installation
  3. 1:06 Kaggle configuration before starting the notebook
  4. 1:24 How to start Kaggle session and start installation of SwarmUI on a free Kaggle account
  5. 2:50 How to understand Kaggle cell execution / installation has been completed
  6. 3:11 How to clear cell execution outputs / logs
  7. 3:42 How to disable of downloading certain models in given cell / preventing that line execution
  8. 3:53 How to check how much disk space you have on Kaggle and how much left to use
  9. 4:11 Some of the models we preset put into Kaggle
  10. 5:10 How to learn more information about SwarmUI and how to use it
  11. 5:42 How much model download speed we are reaching with specially crafted downloader for Kaggle
  12. 6:01 How to install and start SwarmUI after download of models have been completed
  13. 7:03 When do we click visit site to access SwarmUI
  14. 7:28 Which options you need to select when installing SwarmUI on Kaggle
  15. 8:19 How to set backends of SwarmUI and change root folder path on Kaggle
  16. 9:08 How to see detailed logs of what is happening in debug menu of SwarmUI
  17. 9:18 How to set root folder path to Kaggle temp path we are using - mandatory
  18. 9:53 How to start using after SwarmUI is ready and set parameters of Hunyuan fast video model
  19. 12:26 How to stop SwarmUI, load a new model, and start SwarmUI again
  20. 14:02 Restarting SwarmUI on Kaggle
  21. 15:28 Generating an image with a SDXL model as an example
  22. 16:40 Generating a video with fast Hunyuan Q4 model
  23. 16:57 How to set Sigma Shift parameter
  24. 19:45 How to download SwarmUI generated videos and images on Kaggle as a single zip file

About this video

You want to use latest generative AI models but your computer is weak and you don't want to pay money to online services? Then you are at the right tutorial. By utilizing the most advanced UI, the SwarmUI, we are going to use the very best and latest generative AI models on a free Kaggle account. Kaggle provides 2x T4 GPU for free for 30 hours every week. With SwarmUI and my specially crafted notebook and free GPUs of Kaggle, you can use Stable Diffusion 1.5 (SD 1.5), Stable Diffusion XL (SDXL), Stable Diffusion 3 (SD 3), Stable Diffusion 3.5 - Medium and Large, FLUX DEV, FLUX Fill (inpainting), FLUX Redux, FLUX Canny, FLUX Depth, Hunyuan text-to-video, SkyReels text-to-video and image-to-video, Mochi text-to-video and many other generative AI models easily.

🔗 Kaggle Notebook Shared Post (the one used in the tutorial) ⤵️

▶️ https://www.patreon.com/posts/click-to-open-post-used-in-tutorial-106650931

🔗 SwarmUI Mega Tutorials Playlist ⤵️

▶️ https://www.youtube.com/playlist?list=PL_pbwdIyffsku5Rfv2CJZSiFdGXtkkdiB

🔗SECourses 10000+ Members Discord ⤵️

▶️ https://discord.com/servers/software-engineering-courses-secourses-772774097734074388

🔗SECourses Amazing Generative AI GitHub ⤵️

▶️ https://github.com/FurkanGozukara/Stable-Diffusion

🔗SECourses AI APPs Index ⤵️

▶️ https://github.com/FurkanGozukara/Stable-Diffusion/blob/main/Patreon-Posts-Index.md

🔗RTX 5090 Benchmarking Video Series Playlist ⤵️

▶️ https://www.youtube.com/playlist?list=PL_pbwdIyffslNd9aLizjQtHVHAMA6tpfT

0:00 Introduction to the tutorial

0:16 How to download Kaggle notebook and load it into Kaggle and start installation

1:06 Kaggle configuration before starting the notebook

1:24 How to start Kaggle session and start installation of SwarmUI on a free Kaggle account

2:50 How to understand Kaggle cell execution / installation has been completed

3:11 How to clear cell execution outputs / logs

3:42 How to disable of downloading certain models in given cell / preventing that line execution

3:53 How to check how much disk space you have on Kaggle and how much left to use

4:11 Some of the models we preset put into Kaggle

5:10 How to learn more information about SwarmUI and how to use it

5:42 How much model download speed we are reaching with specially crafted downloader for Kaggle

6:01 How to install and start SwarmUI after download of models have been completed

7:03 When do we click visit site to access SwarmUI

7:28 Which options you need to select when installing SwarmUI on Kaggle

8:19 How to set backends of SwarmUI and change root folder path on Kaggle

9:08 How to see detailed logs of what is happening in debug menu of SwarmUI

9:18 How to set root folder path to Kaggle temp path we are using - mandatory

9:53 How to start using after SwarmUI is ready and set parameters of Hunyuan fast video model

12:26 How to stop SwarmUI, load a new model, and start SwarmUI again

14:02 Restarting SwarmUI on Kaggle

15:28 Generating an image with a SDXL model as an example

16:40 Generating a video with fast Hunyuan Q4 model

16:57 How to set Sigma Shift parameter

19:45 How to download SwarmUI generated videos and images on Kaggle as a single zip file

Below songs used with -40 sound level

0 Song: Cartoon, Jéja - Why We Lose (feat. Coleman Trapp) [NCS Release]

Music provided by NoCopyrightSounds