StableSwarmUI Master Tutorial - Use Stable Diffusion 3 (SD3) with Amazing Performance (Patreon)
Downloads
Content
In this tutorial post I will share all the necessary stuff regarding how to use Stable Diffusion 3 on your computer and also on the cloud.
Join discord to get help, chat, discuss and also tell me your discord username to get your special rank : SECourses Discord
Please also Star, Watch and Fork our Stable Diffusion & Generative AI GitHub repository
Free Kaggle Account Notebook for GPU-Poor
Installs latest version of SwarmUI on a free Kaggle account
Works with Dual T4 GPU at the same time
Supports SD 1.5, SDXL, SD3 and Stable Cascade and more
Download from here : https://www.patreon.com/posts/106650931
Windows Tutorial
How to install and use. You have to watch this to learn how to use SwarmUI
Has 70 chapters and manually fixed captions
21 June 2024 Update
Stable Swarm UI migrated into SwarmUI : https://github.com/mcmonkeyprojects/SwarmUI
Links are updated
General Info
To download and install StableSwarmUI : StableSwarmUI
Very important documents : docs
Very important features : Features
Full prompting syntax : Prompt%20Syntax.md
Download very best new upscalers : released-sorted-by-new
All upscalers as a single zip file : all_models
Helaman upscalers with thumbnails : helaman
SD3 Download model : stable-diffusion-3-sd3
SD3 Official Page : stable-diffusion-3-medium
SDXL model RealVis XL 4 : RealVisXL_V4.0.safetensors
SD 1.5 model : Hyper Realism V3
I have converted Fooocus 275 SDXL styles into StableSwarmUI presets with SD3 configuration
The presets also have updated thumbnail / preview image with SD3
Moreover, scripts to generate and update these presets automatically added to the zip file in below post as well
You can download all presets from here : download 275 presets
Official Stable Swarm UI Discord server to contact its developer : https://discord.gg/q2y38cqjNw
Cloud tutorials are in production as well for Massed Compute, RunPod and hopefully a Kaggle
Massed Compute Instructions
Please register Massed Compute from here : https://vm.massedcompute.com/signup?linkId=lp_034338&sourceId=secourses&tenantId=massed-compute
After registering and loading balance go to this link : https://vm.massedcompute.com/deploy
Select RTX A6000, if not available RTX A6000 [ALT Config] (same VRAM, GPU, Disk etc only RAM is 24 GB instead of 48)
Then make the selections as below and deploy your machine
This Massed Compute virtual machine image we have as SECourses has pre-installed SwarmUI with very best SD 1.5, SDXL and SD3 models
You can also increase your GPU quantity to utilize all of them at once with SwarmUI
Don't forget to run SwarmUI (1-click button) update before start using it
If our image gets broken reply to this post and let me know - we will update it ASAP
Also don't forget to apply Coupon code as SECourses to get A6000 GPU as 31 cents per hour (on RunPod cheapest 69 cents per hour)
RunPod Instructions
Follow this tutorial step by step to install on RunPod machine : tutorial link coming
Please use this link to register : https://runpod.io?ref=1aka98lq - (it gives me credits thus i can do more tutorials)
RunPod massive tutorial includes runpodctl for fast download to PC : https://youtu.be/QN1vdGhjcRc
RunPod permanent network storage system tutorial : https://youtu.be/8Qf4x3-DFf4
How to download models very fast to RunPod and how to upload files, folders from RunPod to Hugging Face ultra fast detailed tutorial : https://youtu.be/X5WVZ0NMaTg
Choose template runpod/pytorch:2.1.0-py3.10-cuda11.8.0-devel-ubuntu22.04 and any GPU
Download install-linux.sh and upload into workspace
chmod +x install-linux.sh
./install-linux.sh
Then when you SwarmUI started, restart the pod - first time necessary
Then execute below codes
cd /workspace/SwarmUI
./launch-linux.sh --launch_mode none --host 0.0.0.0
Then connect from 7861 port