MEDFE Inpainting Studio

MEDFE Inpainting Studio

Fills in the masked holes of an image with the MEDFE inpainting model and shows its structure and texture predictions. Compare the result with the masked input and download it as a PNG.

Made by KumaPower 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: MEDFE Inpainting Studio fills in missing regions of an image with the released MEDFE model. MEDFE stands for Mutual Encoder-Decoder with Feature Equalizations, from ECCV 2020. The Space runs on Hugging Face, so you can try it in a browser with nothing to install.

Who it suits: Researchers and students who study image inpainting, and developers who want to see the model on their own pictures.

Industry | Who uses it | How they use it | Example
Computer vision | Researchers | Inspect the structure and texture the model predicts | Paint a hole and open the prediction views
Education | Students | See how a masked region is rebuilt | Try the examples in the gallery
Software | Developers | Run a released inpainting model on test images | Upload an image and a mask of their own
Image editing | Hobbyists | Remove or repair a patch of a picture | Paint over a flaw and run the model

Anyone who needs a commercial editing tool can skip it, since the license is non-commercial.

Where to use it: It runs in these places.

• A web browser, on the Space's page at Hugging Face
• Windows, with Python 3.12.12
• macOS, with Python 3.12.12
• Linux, with Python 3.12.12

Use case | Who | What they get back
Fill a masked region | Anyone | A completed image you can download as a PNG
Compare with the input | Researchers | A wipe slider between the result and the masked input
Inspect predictions | Researchers | The structure and texture outputs of the network

How to set it up: Using the Space online needs only a browser. A copy on your own computer needs the following.

• Python 3.12.12 and pip
• The huggingface_hub package, which gives you the hf command
• Disk space for the repository, which holds 7 files

1. Install the huggingface_hub package.
2. Download the Space's files into a local folder.
3. Move into that folder.
4. Install Gradio at the version the Space uses, then install the packages in requirements.txt.
5. Start the app.

pip install -U huggingface_hub
hf download KumaPower/MEDFE-Inpainting-Studio --repo-type space --local-dir MEDFE-Inpainting-Studio
cd MEDFE-Inpainting-Studio
pip install gradio==6.31.0
pip install -r requirements.txt
python app.py

How to use it: Open the Space's page, or run the app on your computer and open the page Gradio shows. Upload an image and paint the holes, or pick an example from the gallery. You may also bring a ready binary mask, or have the app generate one with the training recipe.

python app.py

Tool | What it does
Paint area | Lets you paint the holes on your uploaded image
Gallery | Offers ready examples to start from
Run MEDFE | Generates the completion of the masked image
Wipe slider | Compares the completion with the masked input
Download | Saves the completion as a PNG

Example: You upload a photo, paint over a small object, and press Run MEDFE. You move the wipe slider to compare the filled image with the masked one, then download the filled image as a PNG.

For newcomers and experts: Inpainting means filling in a missing part of a picture so it blends with the rest. The first small thing to try is a gallery example, so you do not need to make a mask.

The Space runs the released implementation at step 120,994. It scales each input to 256 by 256 first, then leaves every pixel outside the mask as it was. Beside the finished image you can inspect the structure and texture predictions of the network. The example images come from the public MEDFE and CSA releases.

You upload an image and a mask
The image is resized to 256 by 256
MEDFE predicts structure and texture
The masked region is filled in

Good to know: The output size is fixed at 256 by 256, so large photos lose detail.

• License: cc-by-nc-sa-4
• Cost to run: none named
• Data it reaches: the image and mask you upload, plus the model files that Hugging Face supplies
• Not for: commercial use, which the cc-by-nc-sa-4 license rules out
• Hardware: the Space is set to zero-a10g at Hugging Face, and what your own computer needs is not stated

On Hugging Face, 13 November 2026

• Likes: 1
• Built with: gradio
• License: cc-by-nc-sa-4.0

Links

• Space: https://huggingface.co/spaces/KumaPower/MEDFE-Inpainting-Studio
• Files: https://huggingface.co/spaces/KumaPower/MEDFE-Inpainting-Studio/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.