Home Artists Posts Import Register

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.

Patreon exclusive posts index

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

  • >> https://youtu.be/HKX8_F1Er_w

21 June 2024 Update

General Info

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)

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

Comments

Neil Francese

I see the SD3 devs recommend and released a sample ComfyUI workflow. They also have a few different text_encoders options. Are you planning to do any experimenting with their flow and the various text encoder options? You do such a great job evaluating and finding ideal settings so I was just curious :)

reaper557

I am excited for this tutorial! A super one-two punch, as I've haven't used the SwarmUI yet either.

Furkan Gözükara

thanks. yes i will show that too. stableswarmui uses comfyui but makes it us many times easier to use :) thus works perfect

Manpreet Singh

Any plans for comparing SD3 with other models (SDXL, SD1.5) for dreambooth training?

Steve

FYI Civitai banned SD3 because of their licensing..."as written the creator license seemed to imply that Stability had edit and takedown power over not just any resource trained on SD3 but also on any resources that used its outputs in their datasets." useful to know if you are posting images created with it or training on it.