Mindket

Image Upscaler by sorabing

Newversion 1 · updated

Overview

Enlarges and sharpens an image by 2x or 4x with the Real-ESRGAN model in a Gradio page on ZeroGPU. For anyone who needs a bigger, cleaner version of a small picture.

Image Upscaler by sorabing is a kit in the Productivity category, listed by Mindket. It is free. This is version 1, last updated on . Download it on this page, a zip of its files. Nothing in it runs by itself.

At a glance

You need
  • Python and pip
  • The packages listed in requirements.txt
Runs in
  • 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
Start with
pip install -U huggingface_hub
hf download sorabing/image-upscaler --repo-type space --local-dir image-upscaler
cd image-upscaler

Platform

WindowsOperating system
macOSOperating system
LinuxOperating system

About

What it is

This Space makes a picture bigger and sharper with AI. It enlarges an image two times or four times using the Real-ESRGAN model, and it runs on ZeroGPU at Hugging Face, which the README describes as free. The README is written in Thai.

Who it suits

Designers, shop owners, photographers and hobbyists who have a small or soft image and want a larger version.

IndustryWho uses itHow they use itExample
E-commerceShop ownersEnlarge a small product photoUpscale a catalog picture four times
DesignGraphic designersPrepare a low resolution asset for larger useDouble the size of a logo mockup
PhotographyHobby photographersSharpen an old or small photoUpscale a scanned family picture
SoftwareDevelopersStudy a small Gradio wrapper around an upscalerRead app.py and requirements.txt

If you need to repair heavy damage or retouch details by hand, an image editor is the better tool.

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 caseWhoWhat they get back
Upscale a pictureAnyone with a small imageA version made two or four times larger
Prepare web imagesShop ownersSharper pictures at a bigger size
Study the codeDevelopersA short app.py around the Real-ESRGAN model

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 app.
pip install -U huggingface_hub
hf download sorabing/image-upscaler --repo-type space --local-dir image-upscaler
cd image-upscaler
pip install gradio
pip install -r requirements.txt
python app.py

How to use it

Open the Space page, add your image and choose a scale of two or four. Run it and the enlarged picture appears on the page. In a local copy, run python app.py to open the same page on your own computer.

Example

You have a small product photo and need a bigger one. You add it, choose four times, and run it. The page returns a picture with four times the size.

For newcomers and experts

Start with a two times upscale on a small image to see the difference. A four times upscale makes a much larger file, so use it when you need the size.

Real-ESRGAN is a model that predicts fine detail when it enlarges a picture. The Space wraps it in a Gradio page and runs it on ZeroGPU, where a GPU is lent for each request. The repository holds only app.py and requirements.txt.

  1. You add an image
  2. You choose a 2x or 4x scale
  3. Real-ESRGAN enlarges and sharpens it
  4. The larger picture shows on the page

Good to know

The README is two lines, so the largest input size and the output format are not described.

  • License: BSD 3-Clause
  • Cost to run: the README calls ZeroGPU free, and no key is named
  • Data it reaches: the images you add to the page

README and files

README

Image Upscaler by sorabing

Enlarges and sharpens an image by 2x or 4x with the Real-ESRGAN model in a Gradio page on ZeroGPU. For anyone who needs a bigger, cleaner version of a small picture.

Made by sorabing 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 makes a picture bigger and sharper with AI. It enlarges an image two times or four times using the Real-ESRGAN model, and it runs on ZeroGPU at Hugging Face, which the README describes as free. The README is written in Thai.

Who it suits: Designers, shop owners, photographers and hobbyists who have a small or soft image and want a larger version.

Industry | Who uses it | How they use it | Example
E-commerce | Shop owners | Enlarge a small product photo | Upscale a catalog picture four times
Design | Graphic designers | Prepare a low resolution asset for larger use | Double the size of a logo mockup
Photography | Hobby photographers | Sharpen an old or small photo | Upscale a scanned family picture
Software | Developers | Study a small Gradio wrapper around an upscaler | Read app.py and requirements.txt

If you need to repair heavy damage or retouch details by hand, an image editor is the better tool.

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
Upscale a picture | Anyone with a small image | A version made two or four times larger
Prepare web images | Shop owners | Sharper pictures at a bigger size
Study the code | Developers | A short app.py around the Real-ESRGAN model

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 app.
pip install -U huggingface_hub
hf download sorabing/image-upscaler --repo-type space --local-dir image-upscaler
cd image-upscaler
pip install gradio
pip install -r requirements.txt
python app.py

How to use it: Open the Space page, add your image and choose a scale of two or four. Run it and the enlarged picture appears on the page. In a local copy, run python app.py to open the same page on your own computer.

Example: You have a small product photo and need a bigger one. You add it, choose four times, and run it. The page returns a picture with four times the size.

For newcomers and experts: Start with a two times upscale on a small image to see the difference. A four times upscale makes a much larger file, so use it when you need the size.

Real-ESRGAN is a model that predicts fine detail when it enlarges a picture. The Space wraps it in a Gradio page and runs it on ZeroGPU, where a GPU is lent for each request. The repository holds only app.py and requirements.txt.

You add an image
You choose a 2x or 4x scale
Real-ESRGAN enlarges and sharpens it
The larger picture shows on the page

Good to know: The README is two lines, so the largest input size and the output format are not described.

  • License: BSD 3-Clause
  • Cost to run: the README calls ZeroGPU free, and no key is named
  • Data it reaches: the images you add to the page

On Hugging Face, 13 November 2026

  • Likes: 2
  • Built with: gradio
  • License: bsd-3-clause

Links

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.

Files
README.md  4 KB

1 file, 4 KB, downloaded as a zip.

What’s new

  • Version 1 · 2026-11-12

Compare with similar

Listed Hugging Face Spaces in the same category that share the most tags with this one.

ProductLikesBuilt withLicenseLast change
Image Upscaler by sorabing This page2gradiobsd-3-clause
MusicGenShares gradio5,116gradiocc-by-nc-4.0
Kokoro TTSShares gradio3,556gradioapache-2.0
Background RemovalShares gradio2,988gradiomit
Omni Image EditorShares gradio2,922gradiomit
Diffusers Image OutpaintShares gradio2,565gradioapache-2.0
Numbers as Mindket last read them, on 2026-11-12.

Reviews

No ratings yet

Write a review

No reviews yet.

More from Mindket

See all from Mindket

Bonsai-27B-GGUF

lmstudio-community · Kit

A GGUF conversion of the 27B Bonsai model for LM Studio, with a 3.80 GB Q1_0 language file and a 0.93 GB BF16 vision projector. Tested for text, vision and par…

New

Runs DeepSeek-V4.1-Flash-1017 as a 2.9 bits-per-weight EXL3 quantization, a 196 GiB copy for people serving large models on their own hardware. Perplexity stay…

New

MusicGen Small

facebook · Kit

Generates short music clips from a text description or an audio prompt, in the small checkpoint of facebook's MusicGen. It suits developers and music hobbyists…

New

Similar in Productivity

See all in Productivity

ACE-Step 1.5 XL SFT

ACE-Step · Kit

Generates music from text with a 4B diffusion decoder, 50 steps and guidance control, aiming for higher audio quality than the base. For creators with a GPU of…

New

Guizang PPT Skill

op7418 · Skill

Skill that makes single-file HTML slide decks, slide illustrations and platform covers in two visual styles, with a presenter mode for rehearsal. For speakers…

New29.8k

Frontend Slides

zarazhangrui · Skill

Builds HTML presentations from scratch or from a PowerPoint file and shows visual style previews to pick from, for people who want web slides with no CSS or Ja…

New32.3k