---
title: Text2Autochrome demo
emoji: 🖼
colorFrom: purple
colorTo: red
sdk: gradio
sdk_version: 5.0.2
app_file: app.py
pinned: false
short_description: 'A tool to generate authentic autochrome images from text.'
---

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

# Digitized autochrome restoration using synthetic data only

 
*Given a green-tinted autochrome image, the algorithm identifies the damaged areas and fixes them while preserving the underlying image features.*

## Setup
* Tested with Windows 11 -> WSL2 -> Docker 
* Host: GPU 4090 RTX | Driver Version: 566.24| CUDA Version: 12.7 
* Docker version 27.2.1, build 9e34c9b
## Getting Started

These instructions will get you a copy of the project up and running on your local machine for development and testing purposes. 
This will start the interactive Hugging Face demo but in a container.

### How to install and run

1. Build the docker image with `sh build_docker.sh`
2. Start the container by `sh start_docker.sh`
3. To test the demo connect to the container 
4. Go to `cd /workspace`
5. Run the interactive demo `python3 demo.py`