LoRA_Easy_Training_Scripts VS LyCORIS

Hello! I want to run these scripts in Google Colab (https://github.com/derrian-distro/LoRA_Easy_Training_Scripts), but I don't know how. Tried to replace some code in this Colab (https://colab.research.google.com/github/camenduru/kohya_ss-colab/blob/main/kohya_ss_colab.ipynb), but it didn't go anywhere, so that's why I'm asking about it here. Could anyone help with this problem of mine please? I can clone git content, but I don't know how to run needed .bat or .sh file there.

conda create -n lora-easy-ui python=3.10.6 conda activate lora-easy-ui git clone https://github.com/derrian-distro/LoRA_Easy_Training_Scripts cd LoRA_Easy_Training_Scripts conda install -c anaconda cudatoolkit git submodule init git submodule update cd sd_scripts python -m venv venv source venv/bin/activate pip3 install torch torchvision torchaudio pip install -r requirements.txt pip install xformers pip install -r ../requirements_ui.txt pip install ../LyCORIS/. accelerate config

I use this https://github.com/derrian-distro/LoRA_Easy_Training_Scripts on Kubuntu. It works very well.

The same thing happened to me, I could never run it well, but thanks to that I met easy lora, it has a very intuitive interface, it installs very clean, and it works impeccable, it doesn't change almost all of the configuration, just choose the model, your photos and the epocs or steps, and it works great https://github.com/derrian-distro/LoRA_Easy_Training_Scripts

Are there any Repos that actually work? I've attempted https://github.com/derrian-distro/LoRA_Easy_Training_Scripts, as well as a few variations of the kohya_ss ones to no avail.

This is my 3rd one, can someone point me to the right direction? I'm using https://github.com/derrian-distro/LoRA_Easy_Training_Scripts/releases/tag/installers-v5

Then, git clone https://github.com/derrian-distro/LoRA_Easy_Training_Scripts

I'm attempting to train a LoRA using Kohya's SD Scripts and one of Derrian's LoRA Easy Training Scripts (the popup version). I've been able to set everything up fine, boot up the venv, run the script, get everything spinning, etc. until:

Lycoris is another implementation of LoRA done by KohakuBlueleaf: https://github.com/KohakuBlueleaf/LyCORIS

Most guides focus on LoRa training as that has been around for longer. But I think LoHa can give better results. But the training is about half as fas it/s and it requires different training settings.

I've read in some tutorials that it is best that the value should be 64 or below, also here they suggest to not go over 64 ( https://github.com/KohakuBlueleaf/LyCORIS )

Does anyone know how to make LyCORIS models (https://github.com/KohakuBlueleaf/LyCORIS) work with inpainting models?

I think it was linked already but this is also relevant for LoRa: https://github.com/KohakuBlueleaf/LyCORIS Nice work!

There are some WIP evolutions of SD Lora in the works, like locon and lycoris.

https://github.com/KohakuBlueleaf/LyCORIS

You might want to expand LoRA to include LoCon and LoHa, (and also add a column for VRAM requirements) (Think of it as a more complete LoRA that works for the kernels in the convolutional units rather than just the weights for the feed-forward network), support is still quite limited, but it's starting to pick up steam https://github.com/KohakuBlueleaf/LyCORIS