ProPainter

ProPainter

Hosts the ProPainter project's code and its Gradio web demo, with scripts to run the model and to train it. Meant for people who want to try the demo or read how the project is built.

Made by sczhou on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: This Space holds the ProPainter project's code and a browser demo built with Gradio. The repository carries the model code, an inference script, a training script, configs and a weights folder, so you can try the demo or study the whole project.

Who it suits: Developers and researchers who want to try the project's demo, then read or run its code on their own machine.

Industry | Who uses it | How they use it | Example
Research | Machine learning researchers | Read the model, configs and training script | Open train.py and the configs folder side by side
Software | Developers | Run the inference script on their own files | Run inference_propainter.py after downloading the weights
Education | Students | Study how a research project is organized | Browse the core, model and utils folders
Product teams | Prototype builders | Try the web demo before deciding to use it | Open the Space page and test it with a sample input

If you only want a finished consumer app, a hosted demo page is a better fit than a code repository.

Where to use it: It runs in two places.

• A web browser, on the Space's page at Hugging Face with nothing to install
• A local copy on Windows, macOS or Linux, which needs Python

Use case | Who | What they get back
Try the demo | Anyone curious | The project's web page running in a browser
Run inference | Developers | Output from the inference script on their own files
Study the code | Researchers | The model, training and utility code in one repository

How to set it up: Using it online needs nothing. A local copy needs a few things.

• Python and pip
• The packages listed in requirements.txt

1. Install the Hugging Face tools.
2. Download the Space into a folder.
3. Move into that folder.
4. Install Gradio and the packages from requirements.txt.
5. Start the web demo.

pip install -U huggingface_hub
hf download sczhou/ProPainter --repo-type space --local-dir ProPainter
cd ProPainter
pip install gradio==6.9.0
pip install -r requirements.txt
python web-demos/hugging_face/app.py

How to use it: Open the Space page and use the controls the demo shows. In a local copy, run the last command above to get the same page on your own computer. The repository also has an inference script and a training script for work outside the web page.

Example: You download the Space, install the requirements and start the web demo. A Gradio page opens in your browser, and you use its controls to try the project on a file of your own.

For newcomers and experts: Open the Space page first, since nothing needs installing. Try one small input and see what the demo returns before you touch any code.

The repository is a full research layout. It has model and core folders, a RAFT folder, configs, dataset helpers, a weights folder, training and inference scripts, and a separate web demo entry point. The web page runs on zero-a10g hardware at Hugging Face.

You open the demo page or a local copy
The Gradio app takes your input
The project's model code processes it
The result shows in the page

Good to know: The README on the Space is only a settings pointer, so the project's purpose and limits are not described there.

• License: Apache 2.0
• Cost to run: none named
• Data it reaches: the files you give it and the weights stored in the repository

On Hugging Face, 13 November 2026

• Likes: 187
• Built with: gradio
• License: apache-2.0

Links

• Space: https://huggingface.co/spaces/sczhou/ProPainter
• Files: https://huggingface.co/spaces/sczhou/ProPainter/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.