Omni Image Editor

Omni Image Editor

Edits images, makes pictures from text, upscales photos and removes watermarks on a Gradio page that runs in the browser. For anyone who wants quick image fixes with nothing to install.

Made by selfit-camera 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: Omni Image Editor is a Gradio page for four image jobs: editing a picture, making a picture from text, enlarging a picture and removing a watermark. You use it in the browser, so there is nothing to install for a first try.

Who it suits: It suits people who want a quick image fix and would rather not open a full editing program.

Industry | Who uses it | How they use it | Example
Marketing | Content creators | Prepare pictures for posts and pages | Enlarge a small image so it holds up at a bigger size
Design | Designers | Try an edit on a picture before moving to heavier software | Apply a change to a draft image
Photography | Hobbyists | Clean up their own photos | Remove a watermark from a picture you own
Software | Python developers | Read how an image editing app is put together | Look through app.py and pipeline.py

Skip it if you need layers, video editing or batch work, since the page covers only these four jobs.

Where to use it:

• A web browser, on the Space's page at Hugging Face
• Your own Windows, macOS or Linux computer with Python 3.13

Use case | Who | What they get back
Change an existing picture | Creators | An edited version of the image you supplied
Make a new picture from words | Designers | A generated image
Enlarge a picture | Marketers | A larger copy of the image

How to set it up: Using the online page needs nothing. A local copy needs Python and the packages in requirements.txt.

• Python 3.13 and pip
• The packages listed in requirements.txt
• Windows, macOS or Linux

1. Install the Hugging Face hub library.
2. Download the Space's files into a folder named Omni-Image-Editor.
3. Move into that folder.
4. Install Gradio 5.44.1, then the packages from requirements.txt.
5. Start app.py.

pip install -U huggingface_hub
hf download selfit-camera/Omni-Image-Editor --repo-type space --local-dir Omni-Image-Editor
cd Omni-Image-Editor
pip install gradio==5.44.1
pip install -r requirements.txt
python app.py

How to use it: Open the Space's page, or run the last command above for a local copy and open the address it prints. Then pick one of the four jobs and give it your image or your text.

python app.py

Example: You open the page, load one of your own pictures and choose the enlarging job. The page works on it and returns a larger version of the picture for you to look at.

For newcomers and experts: Start with the online page and one picture you do not mind experimenting on. Try the enlarging job first, since it needs no written instruction.

The app is built with Gradio 5.44.1 on Python 3.13, and the Hugging Face copy runs on the cpu-upgrade tier. The repository holds pipeline.py, scheduling_omni.py, labels.json and a filter script for image safety checks. The only model the record names is an image safety detector, and it does not say which model does the editing.

Open the page
Choose one of the four jobs
Give it an image or some text
Look at the result

Good to know:

• Hardware: The Hugging Face copy runs on the cpu-upgrade tier.
• License: mit.
• Cost to run: none named.
• Data it reaches: Images and text you give it. The repository names an image safety detection model and holds a filter script.

On Hugging Face, 13 November 2026

• Likes: 2,922
• Built with: gradio
• License: mit

Links

• Space: https://huggingface.co/spaces/selfit-camera/Omni-Image-Editor
• Files: https://huggingface.co/spaces/selfit-camera/Omni-Image-Editor/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.