IOPaint-LaMA

IOPaint-LaMA

A browser demo that pairs IOPaint with the LaMA model, which by its name points to picture inpainting, meaning removing or filling parts of an image. Suits designers and developers trying image cleanup.

Made by Sanster 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 is a browser demo named IOPaint-LaMA. Going by the name, it pairs the IOPaint tool with the LaMA model, which points to inpainting, the job of removing or filling in part of a picture. The README adds nothing beyond a link to the Spaces configuration reference.

Who it suits: It suits designers, photographers and hobbyists who want to try cleaning up a picture, and developers who want to read a small Gradio app with its own page and style files.

Industry | Who uses it | How they use it | Example
Photography | Photographers | Try removing unwanted objects from a photo | Test a quick cleanup on a travel picture
Design | Graphic designers | Fix up an image before a layout | Clean a spot out of a product picture
E-commerce | Shop owners | Tidy product photos | Remove a stray item from the background
Software | Developers | Read a small app with custom HTML and CSS | Open app.py, index.html and style.css

You can skip it if you need a documented editor with batch tools, since the README holds no usage notes.

Where to use it:

• A web browser: open the Space page on Hugging Face
• Windows, macOS or Linux: run a copy with Python

Use case | Who | What they get back
Clean up a picture | Photographers and designers | An edited version with the chosen area changed
Try the tool online | Anyone curious | A running page with nothing to install
Run your own copy | Developers | The same app on your own computer

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

• A web browser for the online demo
• Python for a local copy
• The packages listed in requirements.txt

1. To use it online, open the Space page on Hugging Face.
2. To run a copy, install the Hugging Face hub package.
3. Download the Space into a local folder.
4. Move into the folder and install Gradio 3.9.1 and the listed packages.
5. Start the app.

pip install -U huggingface_hub
hf download Sanster/iopaint-lama --repo-type space --local-dir iopaint-lama
cd iopaint-lama
pip install gradio==3.9.1
pip install -r requirements.txt
python app.py

How to use it: Start the app from its folder, or open the Space online. Add a picture and follow the controls the page shows to mark what you want changed, then run it. Try a small change first.

python app.py

Example: You add a photo and mark a small unwanted object. The page returns the photo with that area filled in, and you can compare it with the original.

For newcomers and experts: If you are new to this, try one easy picture with a clear background and a small area to change. That shows quickly what the tool can do.

If you know the field, the repository is small: an app file, a requirements list, an HTML page and a stylesheet. It runs on Hugging Face's basic CPU hardware and relies on an old Gradio release, 3.9.1, so a local copy should keep that version.

You add a picture
You mark the area to change
The app runs the model
You get the edited picture

Good to know: The README is empty of notes, so the page and app.py hold the real details. The old Gradio version may limit which features work.

• License: apache-2
• Cost to run: none named
• Data it reaches: the pictures you give it

On Hugging Face, 13 November 2026

• Likes: 262
• Built with: gradio
• License: apache-2.0

Links

• Space: https://huggingface.co/spaces/Sanster/iopaint-lama
• Files: https://huggingface.co/spaces/Sanster/iopaint-lama/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.