OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Image & Video AI

Deep Live Cam

A Python desktop application for real-time face swapping and one-click video deepfake generation from a single source image. It is distributed under AGPL-3.0.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Deep Live Cam — OpenViST project profile in Image & Video AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when a desktop workflow needs real-time face replacement or video generation driven by one approved source image, especially for consent-based creative or prototyping work.

Who it is for

  • Developers exploring image-and-video AI workflows
  • Creators building permitted webcam or video-production tools
  • Teams prototyping consent-based avatars, character animation or visualizations

Documented uses

  • Create real-time face swaps from a single reference image
  • Generate one-click video deepfake output
  • Use webcam-related face replacement workflows
  • Preview face replacement in video production
Before you choose

Requirements & limits

The project is publicly available on GitHub, marked active, and not archived. It is licensed under AGPL-3.0. No verified pricing or account requirement is provided.

  • A single source image is the documented input model.
  • The application is desktop-based and written in Python.
  • Webcam-related workflows are part of the project context.
  • AGPL-3.0 licensing matters for adaptation and redistribution.
  • The repository describes safeguards intended to block inappropriate media.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Use the installed application in image/video or webcam mode

Start the documented GUI workflow for processing a target image or video, or previewing a permitted webcam face swap.

Before you start

  • A completed Deep-Live-Cam installation
  • A source face image
  • A target image or video for image/video mode, or a camera for webcam mode
  • Consent for any real person's face and clear deepfake labeling when sharing outputs

Steps

  1. Run the command below.

    Documented command
    python run.py

  2. For image/video mode, choose a source face image and a target image or video, then click Start.

  3. For webcam mode, select a source face image, click Live, and wait 10–30 seconds for the preview.

  4. For webcam streaming, use a screen-capture tool such as OBS; to change the face, select a new source image.

Expected outcome

Image/video mode saves its output in a directory named after the target video, while webcam mode displays a live preview for screen capture.

Guide limitations

  • The documented command-line arguments are marked unmaintained.
  • Built-in checks prevent processing some inappropriate media, including nudity, graphic content, and sensitive material.
  • Users are responsible for legal and ethical use; consent is required for a real person's face, and shared output should be clearly labeled as a deepfake.
  • The documentation does not establish that every camera, operating system, or hardware configuration will work.
Documentation 1 ↗Documentation 2 ↗
Evidence and transparency

Sources & review

Official repository ↗Guide documentation ↗
Source record details
Source availability
Active
Sources checked
30 September 2026
Original website title
hacksider/Deep-Live-Cam · Official homepage title · retained in its source language
How we review sourcesSuggest a correction