Tile Upscaler

Tile Upscaler

Enlarges an image with Real-ESRGAN and a diffusion model guided by ControlNet, in a Gradio app. It suits anyone who needs a bigger version of a picture.

Made by gokaygokay 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: Tile Upscaler is a Gradio app that makes a larger version of an image. It names Real-ESRGAN, a Juggernaut Reborn diffusion model and ControlNet 1.1 among its models, along with embeddings and LoRA files. It also names a Stable Diffusion safety checker, and it runs on GPU hardware at Hugging Face.

Who it suits: People who have a small or low-resolution picture and want a bigger one for a design, a print or a post.

Industry | Who uses it | How they use it | Example
Design | Graphic designers | Enlarge artwork for a layout | Upscale a small illustration
Photography | Photographers | Make a bigger copy of an older photo | Upscale a scan of a print
Marketing | Social media teams | Prepare larger versions of campaign images | Enlarge a product shot
Software | Developers | Study an upscaling pipeline in Gradio | Read app.py

People who only need to shrink or crop images can skip it.

Where to use it:

• A browser, by visiting the Space on Hugging Face
• Windows, macOS or Linux with Python, for a copy on your own computer
• A local Gradio page, once app.py is running

Use case | Who | What they get back
Enlarge an image | Designers and photographers | A larger version of the picture
Try the sample images | New users | A quick look at the app with the included pictures

How to set it up:

• Python and pip on Windows, macOS or Linux
• The Python packages in requirements.txt
• Gradio 5.49.1, the version the Space uses
• A GPU, since the Space is set to zero-a10g

1. Install the Hugging Face hub package.
2. Download the Space with the hf command.
3. Move into the new folder.
4. Install gradio at the version the Space uses, then the listed packages.
5. Start the app with Python.

pip install -U huggingface_hub
hf download gokaygokay/Tile-Upscaler --repo-type space --local-dir Tile-Upscaler
cd Tile-Upscaler
pip install gradio==5.49.1
pip install -r requirements.txt
python app.py

How to use it: Online, visit the Space on Hugging Face, give it a picture and read the larger result. On your own computer, run the start command and open the local page Gradio serves.

python app.py

Tool | What it does
app.py | Starts the Gradio interface
requirements.txt | Lists the Python packages to install
image1.jpg | A sample picture kept in the repository
image2.png | A sample picture kept in the repository

Example: You give the app a small photo and ask for a larger one. It returns an enlarged version of the picture.

For newcomers and experts: If you are new, try one of the sample pictures in the repository first. Upscaling means making an image bigger while keeping it looking sharp.

If you know the field, the Space combines Real-ESRGAN with a diffusion model and ControlNet, and it uses embeddings and LoRA files from philz1337x. Gradio is pinned to 5.49.1 and the hardware is zero-a10g. The trade-off is a GPU requirement and several large downloads.

You give the app a picture
The upscaling models enlarge it
The diffusion model adds detail
You get the larger picture back

Good to know:

• Hardware: the Space is set to zero-a10g
• Models: it names six models or model folders on Hugging Face
• Credit: the author asks that academic work cite the Space and its upstream models
• License: apache-2
• Cost to run: GPU hardware, no API key or paid service is named
• Data it reaches: the pictures you give it and the models it fetches from Hugging Face

On Hugging Face, 13 November 2026

• Likes: 1,013
• Built with: gradio
• License: apache-2.0

Links

• Space: https://huggingface.co/spaces/gokaygokay/Tile-Upscaler
• Files: https://huggingface.co/spaces/gokaygokay/Tile-Upscaler/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.