ai-agent

Deep-Live-Cam: Real-time Face Swap

Name: Deep-Live-Cam: Real-time Face Swap
Author: hacksider

Get one-click video deepfakes with Deep-Live-Cam, a tool.

95,255 stars13,879 forksPythonGuide quality 8/10Updated 7/23/2026100% free · open source

What it does

Deep-Live-Cam allows you to create real-time face swaps and one-click video deepfakes using just a single image

When to use it

•Creating interactive marketing content that requires real-time face replacement
•Developing immersive experiences, such as virtual try-on or interactive storytelling
•Generating synthetic video data for training AI models

Ready-to-paste prompt

python deep_live_cam.py --input-video 0 --output-video output.mp4 --face-image images/face.jpg

Heads up: Ensure you have the necessary GPU drivers and CUDA versions installed, as Deep-Live-Cam relies on GPU acceleration for real-time performance

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/deep-live-cam && curl -fsSL https://workflowstacks.com/api/skills/deep-live-cam/claude-skill -o ~/.claude/skills/deep-live-cam/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How Deep-Live-Cam: Real-time Face Swap works

Codeflow

Free to inspect

Deep-Live-Cam: Real-time Face Swap is a medium Python project (~8.1k lines across 33 code files, plus 2 test files). Expect some technical setup — comfortable with a terminal, or ask a developer. Last commit this month, AGPL-3.0 license, has a test suite.

Size

Medium codebase

~8.1k lines · 33 code files · ~1 h to skim

Setup

Some technical setup

Comfortable with a terminal? 20–40 min. Otherwise ask a dev.

Runs on

Python

No API keys detected

Python 100%

What happens, step by step

Face swap happens in real-time

You give

User face

1Select Face

Choose a face to swap

2Run Program

Start the face swap process

run.py

3Use Camera

Select camera to use

4Press Live

Start live face swap

You get

Swapped video

Where to start reading

1
README.md
Start here — what it does and how to install it
2
run.py
Where the program starts running
3
pyproject.toml
Dependencies and the commands it exposes

What's in each folder

modules/Sub-packages / plugins31 files

locales/Translations10 files

models/Data models & types1 files

media/Images & static assets10 files

.github/CI / automation (GitHub Actions)2 files

tests/Tests — proof it works2 files

READMEHas testsDocumentedCI checksAGPL-3.0 licenseUpdated this month