Kolors Virtual Try-On

Kolors Virtual Try-On

Lets you see how a garment looks on a person in a picture, in a Gradio page from Kwai-Kolors that opens in a browser. For shoppers, sellers and designers.

Made by Kwai-Kolors 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: Kolors Virtual Try-On is a Gradio Space from Kwai-Kolors for trying clothes on in a picture. You open it in a browser, and nothing needs installing. The repository holds app.py, an assets folder and requirements.txt.

Who it suits: It suits online shoppers, fashion sellers and designers who want to preview how a garment would look on a person before a photo shoot or a purchase.

Industry | Who uses it | How they use it | Example
Fashion retail | Shop owners | Preview a garment on a model photo | Try a new jacket on a sample picture
E-commerce | Sellers | Make quick product previews | Compare two garments on the same person
Design | Designers | Test how an outfit reads on a body | Check a design idea before sewing

If you need exact fit or size advice, you can skip it, since the page works on pictures.

Where to use it:

• A web browser, on the Space's page on Hugging Face
• A local copy of the files, run with Python under Windows, macOS or Linux

Use case | Who | What they get back
Preview an outfit | Shoppers | A picture with the garment shown on the person
Product previews | Sellers | Quick visuals without a photo shoot
Study the code | Developers | A short app.py to read

How to set it up:

• A web browser, which is all the online page needs
• Python, for a local copy
• The Python packages listed in requirements.txt

1. Open the Space's page on Hugging Face to use it online. Nothing needs installing.
2. For a local copy, install the Hugging Face hub package and download the Space's files.
3. Move into the downloaded folder.
4. Install Gradio 4.43.0, then the packages from requirements.txt.
5. Start the app with python app.py.

pip install -U huggingface_hub
hf download Kwai-Kolors/Kolors-Virtual-Try-On --repo-type space --local-dir Kolors-Virtual-Try-On
cd Kolors-Virtual-Try-On
pip install gradio==4.43.0
pip install -r requirements.txt
python app.py

How to use it: Open the page, or the one your local copy starts, and give it a picture of a person and a picture of a garment. The page then shows the person wearing the garment. The README lists no controls, so follow what the page shows.

Example: Give the app a photo of a person and a photo of a shirt. The page returns the person wearing that shirt.

For newcomers and experts: Open the Space page and try one person photo with one garment photo. Nothing needs installing, and a clear front-facing picture is a sensible first test.

The repository is small, with app.py, a requirements.txt and an assets folder, and the Space runs on upgraded CPU hardware at Hugging Face. The app is built with Gradio 4.43.0. The README gives no notes on models or limits, so read app.py for how it produces the result.

You give a person picture and a garment picture
app.py takes both in the Gradio page
The try-on result is produced
The page shows the person wearing the garment

Good to know: The README is only a configuration header, so limits and image requirements are not documented.

• License: Apache 2.0
• Cost to run: none named, and the online copy runs on upgraded CPU hardware at Hugging Face
• Data it reaches: the pictures you give it

On Hugging Face, 13 November 2026

• Likes: 10,223
• Built with: gradio
• License: apache-2.0

Links

• Space: https://huggingface.co/spaces/Kwai-Kolors/Kolors-Virtual-Try-On
• Files: https://huggingface.co/spaces/Kwai-Kolors/Kolors-Virtual-Try-On/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.