Skip to content

Instantly share code, notes, and snippets.

@AshtakaOOf

AshtakaOOf/gui.md

Last active July 14, 2024 18:48
Show Gist options
  • Save AshtakaOOf/d4ee3cc4510dfa1385616eacfcd01652 to your computer and use it in GitHub Desktop.
Save AshtakaOOf/d4ee3cc4510dfa1385616eacfcd01652 to your computer and use it in GitHub Desktop.
Download ZIP
Stable Diffusion GUI list
Raw
gui.md

Stable Diffusion GUIs list

I will try to redo this list because it's getting kind of bad

This will help me and hopefully other to get everything going and generate waifus images with Stable Diffusion, and maybe other txt2img things maybe.

I will probably add shields.io to make it more easier to read (maybe)

Tip

Check out the SD Anime Checkpoints list.

  • Glossary
    • 🟢 active development (based on main branch activity)
      • 🟠 slow development
      • 🔴 development hiatus
    • ❔ unknown/unchecked status
    • ☠️ archived/dead
    • 🚀 must use

🟢 Automatic1111 webui 🚀

A powerful webui based on top of CompVis, with a lot of features in addition of third party extensions.

Supported Versions ☑️
SD 1.5 ✅
SD 2.1 ✅
SDXL 1.0 ✅
Curated Extensions 🧩

My must have extensions on A1111

  • Glossary
    • ⛔ Broken at the moment?
    • ⭐ Extensions that I use

Warning Read the readme of each extension before installing any of them, you don't want to install something you don't need.

Note It is always better to restart your webui completely after installing new extensions instead of restarting, as completely restarting will install whatever is needed by the new extensions, and can fix some random bugs.

Linux specific tips 🐧

  1. Install the google-perftools package on your distro of choice.
    • Ubuntu/Debian: sudo apt-get install google-perftools
    • RHEL/Fedora: sudo dnf install google-perftools
    • Arch (extra repo): sudo pacman -Syu gperftools
  2. You shouldn't have anymore out of memory crash when switching models.

🟢 InvokeAI 🚀

A gorgeous webui for a creative art workflow, based on Diffusers with support for legacy ckpt and a powerful inpainting and outpainting interface.

Supported Versions ☑️
SD 1.5 ✅
SD 2.1 ✅
SDXL 1.0 ✅

🔴 Sygil webui

Originally a Gradio based webui forked from CompVis, is now a Streamlit based webui for Stable Diffusion. One of the first competitor to Automatic1111 webui, currently in development hiatus as the founder has left the online world due to mental issues sadly.

Supported Versions ☑️
SD 1.5 ✅
SD 2.1 ❔
SDXL 1.0 ❌

🟢 ComfyUI 🚀

A node based webui for Stable Diffusion, which has a nodes workflow similar to chaiNNer or UE5 and Blender nodes.

Supported Versions ☑️
SD 1.5 ✅
SD 2.1 ✅
SDXL 1.0 ✅

🟢 SwarmUI 🚀

The official StabilityAI webui for Stable Diffusion. Let you use auto's sd-webui or ComfyUI as backend as well as Stability API.

Supported Versions ☑️
SD 1.5 ✅
SD 2.1 ✅
SDXL 1.0 ✅
  • (previosuly StableSwarmUI)

🔴 StableStudio

The predecessor to StableSwarmUI with a cleaner ui but less features

Supported Versions ☑️
SD 1.5 ✅
SD 2.1 ✅
SDXL 1.0 ✅

🟠 a8r8

An opinionated frontend gui for ComfyUI and Auto1111, support for in/outpainting, controlnet and more.

Supported Versions ☑️
SD 1.5 ✅
SD 2.1 ✅
SDXL 1.0 ✅

🟢 StabilityMatrix

A Windows and Linux Package Manager for Stable Diffusion webui and also a Gui front-end for ComfyUI.

Supported Versions ☑️
SD 1.5 ✅
SD 2.1 ✅
SDXL 1.0 ✅

🟠 Fooocus

SDXL made easy with low system requirements and a simple gui.

Supported Versions ☑️
SD 1.5 ❌
SD 2.1 ❌
SDXL 1.0 ✅

🟠 Easy Diffusion

As the name says, this is an easy way to use Stable Diffusion with a lot of advanced features too.

Previous repo at: https://github.com/cmdr2/stable-diffusion-ui

Supported Versions ☑️
SD 1.5 ✅
SD 2.1 ✅
SDXL 1.0 ✅

🟢 Stable Diffusion Deluxe

Full featured fancy Flet/Flutter Stable Diffusion gui written in notebook.

Supported Versions ☑️
SD 1.5 ✅
SD 2.1 ✅
SDXL 1.0 ✅

🟠 VoltaML

A clean looking stable diffusion webui.

Supported Versions ☑️
SD 1.5 ✅
SD 2.1 ❔
SDXL 1.0 ✅

☠️ Osmosis

A cool simple and clean webui based around Diffusers and CoreML, sadly this project has been discontinued.

Supported Versions ☑️
SD 1.5 ✅
SD 2.1 ❔
SDXL 1.0 ❌

🟢 MochiDiffusion

This is a gui app for M1/2 cpu from Apple, which let you run a quick and efficient implementation of CoreML easily and locally.

Supported Versions ☑️
SD 1.5 ✅
SD 2.1 ✅
SDXL 1.0 ✅

🔴 DiffusionBee

Gui for Macbook that is basically MochiDiffusion but worse at this point.

Supported Versions ☑️
SD 1.5 ✅
SD 2.1 ✅
SDXL 1.0 ❔

🔴 Radiata

Radiata is a stable diffusion webui based on diffusers. It also supports DeepFloyd IF and TensorRT.

Supported Versions ☑️
SD 1.5 ✅
SD 2.1 ✅
SDXL 1.0 ✅

🟢 SHARK AI Studio

AMD(nod-ai) own webui based on Diffusers and super fast on Amd gpus.

Supported Versions ☑️
SD 1.5 ✅
SD 2.1 ✅
SDXL 1.0 ❔

🔴 Paper2Gui

A gui for inferencing various models (video upscaling, stable diffusion etc), the project seems dead sadly.

Supported Versions ☑️
SD 1.5 ✅
SD 2.1 ❔
SDXL 1.0 ❌

🟠 IOPaint

A gui almost identical to cleanup.pictures but more powerful, with more models and Stable Diffusion 1.5 and 2.1 support.

Supported Versions ☑️
SD 1.5 ✅
SD 2.1 ✅
SDXL 1.0 ❔
  • (previosuly Lama Cleaner)

Notebook

Google colab

Other

Note I want to document more Stable Diffusion GUI, so if you know other cool interface that run locally please post a comment about it.

Raw
trainers.md

This is a list of Trainers script for Stable Diffusion

Gui 📺

🟢 derrian-distro/LoRA_Easy_Training_Scripts

A UI made in Pyside6 to make training LoRA/LoCon and other LoRA type models in sd-scripts easy

  • Taken from LETS about section

🟢 Nerogar/OneTrainer

The simplest gui for training LoRAs without hassle

🟢 Akegarasu/LoRA-scripts

Gui and Cli for training LoRAs and LyCORIS

🟠 bmaltais/kohya_ss

Gradio gui based on sd-scripts to train LoRA and LyCORIS

Console ⌨️

🟢 kohya-ss/sd-scripts

This repository contains training, generation and utility scripts for Stable Diffusion.

  • Taken from sd-scripts Readme.md

🟢 EveryDream Trainer

EveryDream is only for full checkpoint but has validation loss and probably other interesting features.

🟠 HCP Diffusion

HCP-Diffusion can unify existing training methods for text-to-image generation (e.g., Prompt-tuning, Fine-tuning, LoRA, ControlNet, etc) and model structures through a single .yaml configuration file.

  • Taken from HCP DIffusion Readme.md

waifuc

haven't really looked into it so I won't put anything here

Raw
x-misc.md
@Ihateyoudattebayo
Copy link

goated

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment