InsightFace-Face Swapper-on Video

InsightFace-Face Swapper-on Video

Replaces a face in a video clip with another face, using an InsightFace swapper model behind a small Streamlit page. Runs in the browser on Hugging Face or on your own computer.

Made by zerovic 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 replaces a face in a video clip with a different face. A small Streamlit app in app.py drives the swap, and the model file inswapper_128.onnx sits in the same repository. You can run it in the browser or copy it to your own computer.

Who it suits: People who edit or experiment with video and want a quick way to try a face swap without building a pipeline. Developers who want a short Streamlit example around an ONNX model will also find it handy.

Industry | Who uses it | How they use it | Example
Video editing | Hobby editors | Put a stand-in face into a short clip | Trying a different face on a test clip before real editing
Education | Students of computer vision | Study how a face swap model handles moving pictures | Running one clip through the app and comparing it with the original
Software | Python developers | Read app.py and reuse the idea in their own tool | Copying the Space and changing the input clip

If you never work with video or faces in pictures, you can skip it.

Where to use it:

• A web browser, on the Space's page at Hugging Face
• Windows with Python
• macOS with Python
• Linux with Python

Use case | Who | What they get back
Swap a face in a clip | Video hobbyists | The same clip with a different face in it
Test a swapper model | Students and developers | A working demo to look at and run locally

How to set it up: You need only a little before you start.

• Python on Windows, macOS or Linux
• The pip tool, to install the Python packages from requirements.txt
• Nothing at all if you use the Space online, since it runs in the browser

1. Install the Hugging Face hub package.
2. Download the Space's files into a local folder.
3. Move into that folder.
4. Install Streamlit at the pinned version, then the packages from requirements.txt.
5. Start the app.

pip install -U huggingface_hub
hf download zerovic/InsightFace-Face_Swapper-on_video --repo-type space --local-dir InsightFace-Face_Swapper-on_video
cd InsightFace-Face_Swapper-on_video
pip install streamlit==1.39.0
pip install -r requirements.txt
streamlit run app.py

How to use it: Online, open the Space's page and use the app there. On your own computer, run this command from the project folder and open the page Streamlit shows.

streamlit run app.py

Example: You open the Space and give the app a short video clip along with the face you want to place in it. The app hands back the clip with that face swapped in.

For newcomers and experts: If you are new to this, open the Space's page in your browser and try one short clip first. Nothing needs installing for that, and you will see quickly what the swap does.

If you know the field, the swapper is an ONNX model file stored in the repository next to a single app.py, and the hosted copy runs on basic CPU hardware. A CPU host has no graphics card to speed up video work, so long clips will probably take a while.

Open the Space or run streamlit locally
Give the app a video and a face
app.py loads the inswapper_128.onnx model
The face in the video is swapped
You get the swapped video back

Good to know: The source states few limits, so check the results yourself.

• License: MIT, as the Space's license line says
• Cost to run: none named, and the hosted copy uses Hugging Face's basic CPU hardware
• Data it reaches: the video and face you give it. The online copy runs on Hugging Face's servers, while a copy on your computer works on local files

On Hugging Face, 13 November 2026

• Likes: 5
• Built with: streamlit
• License: mit

Links

• Space: https://huggingface.co/spaces/zerovic/InsightFace-Face_Swapper-on_video
• Files: https://huggingface.co/spaces/zerovic/InsightFace-Face_Swapper-on_video/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.