sd-scripts VS pyenv

This repository mostly provides a Windows-focused Gradio GUI for Kohya's Stable Diffusion trainers... but support for Linux OS is also provided through community contributions.

Leaving this here because i'm very tired, so this is the file of the ipynb that uses the sdxl_train.py from the https://github.com/kohya-ss/sd-scripts/tree/sdxl repo, if anybody find out why when getting to the training i get this very empty error : " [00:09:11] WARNING The following values were not passed to "

You can try and test training LoRAs now https://github.com/kohya-ss/sd-scripts/tree/sdxl

This might help.

Kohya_ss sd-scripts Seems to be the standard for lora training. The linked page has an English translation, but doesn't really have system specific tips. Someone else has a popular gui for it, but it's designed with windows in mind. There's another, simpler gui, but its still in development and the dev doesn't do any testing on Linux. With any of these, I run into dependency conflicts like crazy.

"Direct training" is already feasible with masking in kohya-ss: https://github.com/kohya-ss/sd-scripts/pull/589

If you have a requirement for multiple, specific Python versions, why not just use pyenv?

https://github.com/pyenv/pyenv

For more information visit: pyenv repository

Note that virtual environments assume you are using the same global version of Python. Often, this is not the case and additional tools like pyenv can be used alongside virtual environments when you need to switch between versions of Python itself on your local machine.

Python version manager pyenv

First of all, install the Python virtual environment from these links: 1 and 2. I developed my GPT-based API in Python version 3.8.18. Pick any Python versions >= 3.7.

Note: Most modern systems will probably have a system environment that meets this requirement, but if yours does not or if you prefer not to install anything in your system environment (even if it's just PDM) check out asdf or pyenv to help install and manage additional Python environments.

When dealing with software development, reproducibility is key. This is why we encourage you to use Python virtual environments to set up an isolated environment for your project. Virtual environments allow the isolation of dependencies, which plays a crucial role to avoid breaking compatibility between different projects. We cannot cover all the details about virtual environments in this post, but we encourage you to learn more about venv, pyenv or conda for a better understanding on how to create and manage virtual environments.

For Python, with your use case I would avoid system packages, no matter the distro. It sounds like it would be worth setting up pyenv and working exclusively with virtual environments.

For OSX there is homebrew or pyenv (pyenv is another solution on Linux). As pyenv compiles from source it will require setting up XCode (the Apple IDE) tools to support this which can be pretty bulky. Windows users have chocolatey but the issue there is it works off the binaries. That means it won't have the latest security release available since those are source only. Conda is also another solution which can be picked up by Visual Studio Code as available versions of Python making development easier. In the end it might be best to consider using WSL on Windows for installing a Linux version and using that instead.