Code Monkey home page Code Monkey logo

comfyui-dockerized's Introduction

ComfyUI Dockerized

Run ComfyUI on your machine/your AI box/your server with a nice UI without any hassle and in isolated environment!

Warning

Only NVIDIA cards supported at this moment since I don't have AMD and Intel ARC card to test it on

Setup | Installing | Build Container

When building the image have be sure that you dont have an existing one already, but however you can always rebuild it via docker-compose command

When building you can use either docker-compose or docker to build it

# Docker Compose
docker-compose build --no-cache --pull

# After build run to save up the space (Optional)
docker builder prune -a -f

Minimum Specifications Required

You will need atleast around 32GB RAM (DDR4 and UP) RAM for this to run, but depended what modules you will run on it. GPU is must required for this as of now this build will only support Nvidia GPUs looks for a GPU that is powerful enought to run Flux or Stable Diffusion Modules on it, suggestion is to use RTX 3060 or RTX 2060 as the minimum.

WSL

Warning

Running this container under WSL is EXPERIMENTAL. USE IT HIGH CAUTION

WSL Distro Supported
Ubuntu Tested (Working)
Arch Linux Not Tested
Debian Not Tested
OracleLinux Not Tested

Ubuntu WSL (Current tested on)

If you have a fresh install of WSL Ubuntu, make sure you have docker and nvidia container runtime installed. The install scripts can be found in the '/wsl/ubuntu' directory in this repository.

Using install-docker.sh will install the docker on the WSL instance so you dont need to install docker for windows since it may cause issues with the windows install

Environment variables

Variables Required Default Value Explanation
WEB_PORT No 7860 ComfyUI Web UI Port
DL_CUI_MANAGER No false Force check for ComfyUI-Manager is installed
CNODE_GIT_CHECK_LATEST No false Check all of the Custom Nodes for latest commit
DEBUG No false Enables extra logging outputs

Libs Used

Contributing

Contributions are welcome! Create a discussion first of what the problem is and what you want to contribute (before you implement anything)

Disclaimer

The authors of this project are not responsible for any content generated using ComfyUI.

comfyui-dockerized's People

Contributors

vooperino avatar

Stargazers

Konstantin Wilms avatar  avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.