RealESRGAN Pytorch

RealESRGAN Pytorch

Upscales images and videos with Real-ESRGAN through a friendly Gradio app. It suits photographers, video editors and creators who want sharper, larger versions of low resolution media.

Made by Nick088 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: RealESRGAN Pytorch is a Gradio app that enlarges images and videos using the ai-forever Real-ESRGAN model. Its tagline calls it a user friendly upscaler for both kinds of media. The repository holds app.py, infer.py, a RealESRGAN folder and a weights folder.

Who it suits: People who have small or soft pictures and clips and want larger versions without learning a command line tool.

Industry | Who uses it | How they use it | Example
Photography | Photographers | Enlarge an old or small photo | A scanned family picture
Video | Editors | Upscale low resolution clips | A short archive clip
Marketing | Content creators | Prepare small assets for bigger placements | A web image for print
Software | Developers | Read how an upscaler is wrapped in Gradio | Opening app.py and infer.py

If your media is already at the size you need, you can skip it.

Where to use it:

• A web browser, on the Space's page at Hugging Face
• Windows, macOS or Linux with Python, from a downloaded copy

Use case | Who | What they get back
Image upscaling | Photographers | A larger version of a picture
Video upscaling | Editors | A larger version of a clip
Code reading | Developers | A short Gradio app with its inference script

How to set it up:

• Python on your computer
• Python packages from requirements.txt, with Gradio 4.36.1
• At Hugging Face the Space runs on zero-a10g hardware, so a copy may want a similar GPU

1. Install the Hugging Face hub package.
2. Download the Space with the hf command.
3. Move into the downloaded folder.
4. Install Gradio 4.36.1, then the requirements.
5. Start app.py.

pip install -U huggingface_hub
hf download Nick088/Real-ESRGAN_Pytorch --repo-type space --local-dir Real-ESRGAN_Pytorch
cd Real-ESRGAN_Pytorch
pip install gradio==4.36.1
pip install -r requirements.txt
python app.py

How to use it: Online, open the Space page and give the app an image or a video through its screen. On your own computer, start it with the command below and use the screen it opens.

python app.py

Tool | What it does
app.py | The main Gradio file that starts the app
infer.py | The script that runs the upscaling model
weights/ | A folder that holds the model weights

Example: You upload a small photo and run the app. The source does not show the screen, but an upscaler returns a larger version of the same picture.

For newcomers and experts: Open the Space page and try one small image first. Upscaling makes a picture bigger and tries to add believable detail, and a video takes longer than a still.

The Space names ai-forever/Real-ESRGAN and keeps a RealESRGAN code folder and a weights folder in the repository. It runs on zero-a10g hardware. The source gives no scale factors, size limits or speed figures, so check the app screen for the options it offers.

You give the app an image or video
app.py passes it to infer.py
The Real-ESRGAN model enlarges it
The upscaled result is returned

Good to know:

• Hardware: zero-a10g at Hugging Face, built with Gradio 4.36.1
• License: apache-2
• Cost to run: none named
• Data it reaches: the images and videos you give it, nothing else named
• Not for: the source names no limits

On Hugging Face, 13 November 2026

• Likes: 185
• Built with: gradio
• License: apache-2.0

Links

• Space: https://huggingface.co/spaces/Nick088/Real-ESRGAN_Pytorch
• Files: https://huggingface.co/spaces/Nick088/Real-ESRGAN_Pytorch/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.