AI tools, scored for your job
Get paid to train AI
🤝 You're in the Free & Open Source library — community-built tools you can use without paying. A different concept from our scored AI directory.
Home › Free & Open Source › Video › LivePortrait
✦ Free & open sourceVideo

LivePortrait

Animates a portrait photo with the head motion and expressions of a driving video, with a Windows installer.

Animate a portrait from a driving video

Transfer head movement and expressions onto a still photo; Windows installer included.

Free forever · open source · MIT
✓ Light setup✓ Browser-based✓ Real-time collaboration
6.9
ZEKAI
Photo animation from video
Free & open source · Video
Ease of setup6
Usefulness6
Maintenance7
Community8.5
★ 19,475
GITHUB
Jun 2026
UPDATED
MIT
LICENSE
🛠 Don't want to self-host? We can set it up →
⚡ Quick answer

LivePortrait is a Kuaishou project that animates a still portrait using the motion of a driving video. It suits creators who want expressive photo animation locally, and it has a one-click Windows installer.

Runs on
Cross-platform
Hosting
Desktop
Languages
Python
License
MIT

What it is

The README describes Humans and Animals modes, retargeting controls, audio-and-video concatenation and driving-video auto-cropping, plus a Gradio UI. It is driven by video or image motion, not by speech, so it does not lip-sync a script.

Who it's for

Suits creators and developers who want portrait animation without a subscription. It does not suit you if you need a speaking presenter from text or audio, since it copies motion from a driving clip.

Key features

Humans mode

Animates a portrait from a driving video.

Animals mode

Animates animal faces on Linux and Windows with an NVIDIA GPU.

Windows installer

A one-click package from Hugging Face.

Apple Silicon support

Humans mode runs on macOS with Apple Silicon.

Gradio interface

A browser UI for tuning the animation.

Driving-video templates

Make templates to protect privacy.

How to start

Up and running in 3 steps

1
On Windows, unzip the one-click installer from the cleardusk/LivePortrait-Windows Hugging Face repo and double-click run_windows.bat.
2
Otherwise create a conda environment, install the PyTorch build for your CUDA version and requirements.txt.
3
Download the pretrained weights, then run inference.py or the Gradio app with a source portrait and driving video.
Real talk

Our honest verdict

What's great

  • MIT code with a one-click Windows installer.
  • Runs on Windows, Linux and Apple Silicon Macs.
  • Well-known project with active community integrations such as ComfyUI.
  • Retargeting controls for eyes and lips.

Where it falls short

  • Not audio-driven: it needs a driving video, so it cannot speak a script by itself.
  • Animals mode needs an NVIDIA GPU and a compiled op on Linux or Windows.
  • Some CUDA versions cause problems on Windows; the README suggests 11.8.
  • The README states no separate model licence, so check the face-detection models it downloads.
Cost

Pricing & license

Free under the MIT licence. The README lists no paid plan, so the cost is your own computer and GPU.

Paid work

Open remote AI-training roles

767 open remote AI-training roles, updated November 14, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.

See all open roles →
Compare

Alternatives

🎁 Free & open-source alternatives

These reviewed AI tools do the same job instantly — from our scored directory.

Get more

Use it, or have us set it up

📄 Free PDF: LivePortrait for Video
A plain-language guide to getting your first result. Sent to your inbox.
🔔 64 people want a full video tutorial — add your vote
🛠 Don't want to set it up yourself?
We'll install, host & configure LivePortrait for you — and train your team.
Get it done for you ↗
Questions

FAQ

Does LivePortrait lip-sync to audio?

No. It transfers motion from a driving video; it does not generate speech or lip-sync to an audio track by itself.

Does it run on a Mac?

Yes, Humans mode runs on Apple Silicon; Animals mode does not.

Is it free for commercial use?

The code is MIT. The README names no separate model licence, so review the models it downloads before commercial use.

Radar

Latest AI news

✉️ The weekly free toolkit
The best new free & open-source tools for Video — one short email a week, in your language.
Free · 1 email/week · unsubscribe anytime
Get paid to train AI →

See Zekai first in Google