Free-View Expressive Talking Head Video Editing

Free-View Expressive Talking Head Video Editing

A Gradio demo for editing talking head videos, with free viewpoint and expressive control as its title says. For researchers and developers who want to try the method or read its code.

Made by sky24h 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 Gradio demo for editing talking head videos. Its title points to free viewpoint and expressive editing, which means changing how a speaking face looks in a clip. The repository holds the model code, video preprocessing, face detection and a checkpoints folder.

Who it suits: Researchers and developers who work on face and video models, and students who want to see how such a demo is built.

Industry | Who uses it | How they use it | Example
Research | Computer vision researchers | Try a talking head editing method | Open the demo and test it on a short clip
Software | Video developers | Study how a model, face detector and preprocessing fit together | Read fete_model.py and preprocess_videos.py
Education | Students | Learn the parts of a video editing demo | Browse the face_detection folder
Media | Visual effects teams | Judge a research method before any real use | Review the output on a test video

If you need a tool for commercial video work, the non-commercial license rules this one out.

Where to use it: It runs in two places.

• A web browser, on the Space's page at Hugging Face with nothing to install
• A local copy on Windows, macOS or Linux, which needs Python

Use case | Who | What they get back
Try the method | Researchers | An edited talking head result from the demo
Preprocess a video | Developers | A prepared clip, using the preprocessing script
Study the code | Students | The model, audio and inference helper files

How to set it up: Using it online needs nothing. A local copy needs a few things.

• Python and pip
• The packages listed in requirements.txt
• The checkpoints folder that ships with the repository

1. Install the Hugging Face tools.
2. Download the Space into a folder.
3. Move into that folder.
4. Install Gradio and the packages from requirements.txt.
5. Start the app.

pip install -U huggingface_hub
hf download sky24h/Free-View_Expressive_Talking_Head_Video_Editing --repo-type space --local-dir Free-View_Expressive_Talking_Head_Video_Editing
cd Free-View_Expressive_Talking_Head_Video_Editing
pip install gradio==5.25.2
pip install -r requirements.txt
python app.py

How to use it: Open the Space page and use the controls the demo shows. In a local copy, run python app.py to open the same page on your own computer. The repository also has a script that prepares videos before editing.

Example: You open the demo and add a short clip of a person speaking. You use its controls to change the video, then watch the edited result on the page.

For newcomers and experts: Start with a short, well lit clip of one person facing the camera. Judge the result against the original before trying anything more complex.

The repository splits the work into a model file, an audio module, a face detection folder, inference helpers and a preprocessing script. Trained weights sit in the checkpoints folder. It runs on zero-a10g hardware at Hugging Face.

You add a talking head video
Preprocessing prepares the clip
The model applies the edit
The edited video shows on the page

Good to know: The README is only a settings pointer, so the method's details and limits are not described there.

• License: CC BY-NC 4.0, for non-commercial use only
• Cost to run: none named
• Data it reaches: the videos you add to the page
• Not for: commercial use

On Hugging Face, 13 November 2026

• Likes: 41
• Built with: gradio
• License: cc-by-nc-4.0

Links

• Space: https://huggingface.co/spaces/sky24h/Free-View_Expressive_Talking_Head_Video_Editing
• Files: https://huggingface.co/spaces/sky24h/Free-View_Expressive_Talking_Head_Video_Editing/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.