README.md

metadata

title: Orbgan_demo
emoji: 🔮
colorFrom: pink
colorTo: red
sdk: gradio
sdk_version: 2.9.1
app_file: app.py
pinned: false
license: cc-by-4.0

A demo space for https://huggingface.co/johnowhitaker/orbgan_e1

Runs a lightwieght-gan trained on https://huggingface.co/datasets/johnowhitaker/glid3_orbs. See model card (https://huggingface.co/johnowhitaker/orbgan_e1) for training and inference scripts. n_rows controls how many it makes at a time, the result being an n_rows by n_rows grid.

I've also added two similar models (orbgan_dark and orbgan_light) - the only difference is that they were trained on subsets of the training data to get more consistent outputs.

Feel free to reach out if you have questions or want to replicate this for yourself :)