So SDXL is a pretty cool diffusion model recently released by stability AI (https://huggingface.co/stabilityai/stable-diffusion-xl-base-...). It's common to train Low-Rank Adaptations (LoRAs) of this base model to generate art that has lower variance and elements that come from outside of the base model's training set (ex: your face, logos, etc.).
The problem is that the "easiest" ways of making these LoRAs is through the CLI, github script webUIs, or docker images on compute providers like Runpod. If your machine doesn't have a GPU with enough vRAM/power, then you pretty much have to pay to run the training script on some cloud compute.
It's a pretty terrible experience for non-technical people (even programmers like me lol).
So I built this app that lets you train regular + SDXL LoRAs in the browser, save them, share them, generate art with them, and configure them.
sometimes you need to generate content that's outside of the base model's training set (ex: paintings of your face).
generally speaking there are two options here: to finetune the entire model (very costly in terms of both compute and monetary cost) or to use a LoRA.
usually the process of making a LoRA would include uploading your training images to some directory, executing some python code via either google colabs or running github scripts.
this process can generally be very error-prone and time consuming (even for a programmer like myself) so i built this app to try to make it easier.
so far, 100s of people have used the app and 9 users are monthly subscribers.
