Diffusion Training Example

This repository contains a simple example of how to use the Diffusers library to train (finetune) a diffusion model. The example we use trains the model on a dataset of pixel-art characters (https://huggingface.co/datasets/m1guelpf/nouns).

All contents are heavily inspired by the Text2Image Training guide (https://huggingface.co/docs/diffusers/training/text2image) by Huggingface and the example code (https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image.py) by the Diffusers team.

Installation

To install the dependencies, run the following command:

pip install -r requirements.txt

Training

All code required for training is in the training_example.ipynb notebook. To run the notebook, run the following command:

jupyter notebook