PrivateFrame · Video face privacy

Share the video.Choose which faces stay visible.

Detect and track faces in your videos, then apply blur or mosaic on your own device. Select everyone or use reference photos to choose who stays visible.

Start a local evaluation Read the documentation

Commercial deployment with InsightFace pretrained models requires a separate commercial model license.

Request Commercial License

Local video processing
Desktop · CLI · Python
Blur & mosaic

Video demo

See PrivateFrame in action.

Watch face tracking and redaction across different scenes, with Gaussian blur and mosaic output.

Actual PrivateFrame output. Review the processed video before sharing.

Open the video

Music: Tears in Rain by Scott Buckley · CC BY 4.0. Excerpted and mixed.

Choose who to blur

Three ways to control face visibility.

Use every detected face, or match people against a folder of reference photos.

All detected faces

Blur every face

Apply redaction to every detected face. No reference photos or identity matching needed.

Matched people

Blur selected people

Blur people matched to your reference photos and keep other people visible.

Everyone else

Keep selected people visible

Keep matched people visible while blurring unmatched or uncertain faces.

Photo matching can miss a person. Review selective results before sharing; an unmatched target can remain visible in the selected-people mode.

Built for video workflows

Local processing. Flexible results.

Keep media on your device

After installing dependencies and models, process videos and reference photos locally without uploading them.

Track faces across frames

Track detected faces and stabilize their regions across frames for more consistent coverage.

Choose blur or mosaic

Adjust the redaction style, strength, and coverage margin to suit your footage.

Analyze once, render again

Reuse the analysis JSON to change rendering settings or edit face boxes without repeating detection and recognition.

A simple workflow

From source video to a separate, redacted copy.

01
Choose a local video
Open PrivateFrame in the InsightFace desktop app, or pass a video to the CLI or Python API.
02
Set who stays visible
Choose a selection mode, add reference photos if needed, and pick blur or mosaic.
03
Process, review, and share
Export a new video and reusable analysis JSON. Review the output before sharing it.

Get started

Use the interface that fits your work.

Start with the desktop app, automate a video workflow, or integrate processing into Python.

Desktop app

Open the PrivateFrame workflow in InsightFace Evaluation Studio. Choose your video, settings, and output folder.

python -m pip install \
  "./python-package[gui]"
insightface-gui

Command line

Process a video in one command, or separate analysis and rendering for review and repeat exports.

python -m pip install \
  "./python-package[privateframe]"
insightface-privateframe process \
  --input video.mp4 --output-dir output

Python API

Integrate analysis and rendering into your own application with progress and cancellation callbacks.

from insightface.app.privateframe import (
    analyze_streaming_pipeline,
    render_streaming_artifacts,
)

Requires Python 3.10+. Install from the updated repository using the guide. Model downloads may be needed on the first run. The supplied pretrained models are for non-commercial research evaluation only. Obtain a model license before commercial deployment.

Request Commercial License

Installation and usage guide

Where it fits

Prepare footage for a wider audience.

Interviews & events

Keep presenters visible while redacting detected faces of other participants or passersby.

Teaching & training

Prepare classroom or workshop recordings with face redaction before distribution.

Workplace video

Redact faces in internal footage before sharing a copy with external collaborators.

Questions & answers

Before your first export.

Does PrivateFrame upload my video?

Video processing runs locally after dependencies and models are installed. Videos and reference photos are not uploaded for processing. Missing models may download on first use.

Can I change the result without analyzing again?

Yes. Keep the original video and the analysis JSON to render again with different blur, mosaic, or encoding settings. You can also edit face boxes in the JSON. Changes to detection or identity matching require a new analysis.

Does face redaction guarantee anonymity?

No. Detection, tracking, and matching can miss faces or make mistakes. Review the exported video, especially brief appearances, scene cuts, and occlusions. Face redaction does not hide voices, names, clothing, or other identifying context.

Can I use PrivateFrame commercially?

The InsightFace code is MIT licensed. The pretrained models supplied by the project are for non-commercial research; commercial use requires appropriate model authorization. Contact us to discuss your deployment.

Bring video face privacy into your workflow.

Commercial deployment with InsightFace pretrained models requires a separate model license. The code is MIT licensed; code and model licenses apply separately.

Request Commercial License Read the getting started guide