KoreTeknology / ComfyUI-Universal-Styler

26 stars 9 forks source link

ComfyUI Universal Styler

VERSION: Pre-Alpha Release: 0.2.1 - Licensed under GNU General Public License v3.0

Hi, this is my first try with comfyUI custom nodes. It is a research Node based project on Artificial Intelligence using ComfyUI[^1] visual editor with Stable diffusion Local processing[^2] focus in mind. This custom node is intended to serve the purpose to offer a large palette of prompting scenrarios, based on Public Checkpoint Models[^3] OR/AND Private custom Models and LoRas[^4]. It includes an integrated learning machine process as well as a set of workflows.

!!! This project and its documentation are (always) in progress !!! stay tuned...
- You may find some errors, please report the issue in the dedicated section, thx
mockup

:radio_button: Working Features

:radio_button: Features Under Development


:radio_button: Objectives

The objectives of this project are to offer different digital creation tools, using ComfyUI as the main platform and only in local environment. Here is a non-exhaustive list of planned features:

utils:


:radio_button: ComfyUI Installation and Custom Nodes

After installing ComfyUI services with your prefered plateform (i am suggesting the use of Stability Matrix as it is easy to install and give a lot of controls), make sure you install the additional and necessary custom nodes. Then you need to install GIT software (if it is not done already) on your computer. To install these custom nodes, open a CMD window in the \ComfyUI\custom_nodes folder. And "git clone" each one of them. By adding the link after "git clone".


:radio_button: Infos

[^1]: ComfyUI is the free and open source AI creation suite. It supports Stable Diffusion 1.5, 2. XL. Please, visit the ComfyUI Github age.

[^2]: Large language models (LLM) are very large deep learning models that are pre-trained on vast amounts of data. The underlying transformer is a set of neural networks that consist of an encoder and a decoder with self-attention capabilities.

[^3]: Public Checkpoint Models

[^4]: Private custom Models and LoRas