Image Face Upscale Restoration by jhon19792025

Image Face Upscale Restoration by jhon19792025

Restores and enlarges faces in photos, with several restoration models offered in one Gradio page. For people repairing old or blurry portraits. Use only photos you have the right to use.

Made by jhon19792025 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 is a Gradio app for restoring and upscaling faces in pictures. Its full title lists GFPGAN, RestoreFormer++ and CodeFormer, and its address adds GPEN. The model list names GPEN-BFR-512 and ESRGAN, and also a stable-diffusion repository. The README is empty, so the page gives no options or output details. It runs on the basic CPU tier at Hugging Face.

Who it suits: People who want to clean up blurry or old portraits, photo restorers, and developers who want to see several face restoration models in one demo. Use only photos you have the right to use.

Industry | Who uses it | How they use it | Example
Photography | Photo restorers | Sharpen faces in old or low-quality portraits | Restore a scanned family picture
Content | Creators | Improve a face in a low-resolution picture | Upscale a small profile photo
Research | Vision researchers | Compare face restoration models side by side | Run one face through the named models
Software | Developers | Read app.py and utils to see how models are wired | Reuse the layout for another image tool

Skip it if you need exact settings or documented output, since the page lists none.

Where to use it:

• A web browser, on the Space's page at Hugging Face
• Windows, macOS or Linux with Python, as a local copy
• Windows users can also look at webui.bat in the repository, which the page does not explain

Use case | Who | What they get back
Restore a face | Photo restorers | A cleaner, sharper version of the face
Upscale a portrait | Creators | A larger version of the picture
Compare models | Researchers | Results from the face restoration models the page names

How to set it up:

• Nothing at all if you only use the online Space
• Python and pip, for a local copy
• The Python packages listed in requirements.txt
• The system packages listed in packages.txt, which Hugging Face installs with apt-get

1. Open the Space's page at Hugging Face to use it online.
2. For a local copy, install the Hugging Face hub package and download the Space.
3. Move into the new folder and install Gradio at the pinned version.
4. Install the packages from requirements.txt.
5. Start the app with Python.

pip install -U huggingface_hub
hf download jhon19792025/Image_Face_Upscale_Restoration-GFPGAN-RestoreFormer-CodeFormer-GPEN --repo-type space --local-dir Image_Face_Upscale_Restoration-GFPGAN-RestoreFormer-CodeFormer-GPEN
cd Image_Face_Upscale_Restoration-GFPGAN-RestoreFormer-CodeFormer-GPEN
pip install gradio==5.50.0
pip install -r requirements.txt
python app.py

The repository holds 35 files, including an images folder and a utils folder. The page does not say what a local run needs beyond the packages.

How to use it: Online, open the Space and give it a picture through the form on its page. On your own machine, run the app file and open the page Gradio serves in your browser. The page lists no other commands.

Tool | What it does
python app.py | Starts the Gradio app on your computer

Example: You upload a blurry scan of an old portrait that you own. The app returns a version with a sharper, cleaner face, and you compare it with the original before you keep it.

For newcomers and experts: If you are new, open the Space online and try one portrait you own. Restoration models fill in detail by guessing, so check the result against the original.

If you know the field, the title groups GFPGAN, RestoreFormer++ and CodeFormer, which are separate face restoration approaches, with GPEN and ESRGAN also named. The page does not say which is the default or how they are chosen.

Open the Space in a browser
Add a portrait
A restoration model repairs the face
You compare and save the result

Good to know:

• License: apache-2
• Cost to run: none named, and the Space sits on the basic CPU tier at Hugging Face
• Data it reaches: the pictures you upload, and the model files from Hugging Face
• Not for: photos of people you have no right to use, or work that needs documented settings

On Hugging Face, 13 November 2026

• Likes: 23
• Built with: gradio
• License: apache-2.0

Links

• Space: https://huggingface.co/spaces/jhon19792025/Image_Face_Upscale_Restoration-GFPGAN-RestoreFormer-CodeFormer-GPEN
• Files: https://huggingface.co/spaces/jhon19792025/Image_Face_Upscale_Restoration-GFPGAN-RestoreFormer-CodeFormer-GPEN/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.