bmaltais

According to chat GPT it might be linked to missing NCCL support in the CUDA version you have installed on your environment. Make sure the CUDA version you have installed...

Yes, you need to install CUDA as specified in the read a under pre requirement for Linux.

This is possible an issue for the author of LyCORIS himself... but just to be sure, what is the output shown on the terminal for the command the extraction would...

Hummm... maybe that is a bug, what is it that is it asking for? Is there a wandb parameter in the list that is displayed?

Regarding the presets there is no such things… would be nice if a civitai for training preset and sample dataset existed… but it is not the case. Consider them as...

@5KilosOfCheese I totally agree. Each dataset require it’s own custom tuning to extract the most out of it. The presets presented in the GUI are starting points of what worked...

There is no documentation about those… there probably need to a major cleanup of those as some are quite old and probably useless… would be nice if there was a...

@5KilosOfCheese I could certainly add this as documentation in the repo for users to access in the GUI if you create it… you would need to learn the basic of...

Run the "5. (Optional) Manually configure Accelerate" option in the setup.bat menu, that will do it. 

Wait... you are on Linux... humm... on linux you 1st need to activate the venv and then manually configure accelerate... It should be something like: ``` source ./venv/bin/activate accelerate config...