LivePortrait
Animate a portrait photo with the expressions of a driving video.
- Stars
- 19.2K
- Forks
- 2K
- Open issues
- 289
- Last commit
- 2026-06-01
Live from the GitHub API · updated 2026-10-15
What is LivePortrait?
LivePortrait from Kuaishou transfers facial expressions and head motion from a driving video onto a still portrait, with stitching and retargeting controls for eyes and lips. It also supports animals.
Key features
- Portrait animation from a driving video
- Eye and lip retargeting sliders
- Animal mode
- Gradio UI
System requirements
- Platforms
- Windows · Linux · macOS
- GPU
- NVIDIA recommended; Apple Silicon supported (slower)
- Python
- 3.10
How to install LivePortrait
Summarized from the project’s README. Projects change quickly — check the GitHub page for the latest instructions.
Python
- 1Clone and install.
git clone https://github.com/KwaiVGI/LivePortrait cd LivePortrait conda create -n LivePortrait python=3.10 conda activate LivePortrait pip install -r requirements.txt - 2Download the weights and launch the UI.
huggingface-cli download KwaiVGI/LivePortrait --local-dir pretrained_weights --exclude "*.git*" "README.md" "docs" python app.py
Strengths
- Natural expressions
- MIT-licensed code
Limitations
- Needs a driving video
- Face detector has its own license terms
LivePortrait alternatives compared
| Software | Stars | License | Platforms | VRAM |
|---|---|---|---|---|
| LivePortrait Animate a portrait photo with the expressions of a driving video. | 19.2K | MIT | — | |
| SadTalker Make a single photo talk from an audio file. | 14.1K | Apache-2.0 | — | |
| FramePack Long image-to-video generation on laptop GPUs with as little as 6 GB VRAM. | 17.3K | Apache-2.0 | 6 GB minimum | |
| Wan 2.2 Alibaba’s open-weight video generation models (text, image and speech to video). | 17.9K | Apache-2.0 | 24 GB for TI2V-5B at 720p; 80 GB-class GPUs (or offloading) for A14B models | |
| HunyuanVideo Tencent’s 13B-parameter open video foundation model. | 12.6K | Tencent Hunyuan Community License | 45 GB minimum, 60–80 GB recommended for 720p (per README); less with community quantizations | |
| CogVideoX Open text-to-video and image-to-video models from Zhipu AI / Tsinghua. | 13.1K | Apache-2.0 | ~12–24 GB depending on model and optimizations (see the README table) |
FAQ
Is LivePortrait free?
Yes — LivePortrait is open-source software released under the MIT license. Check the license (and any model weight licenses) before commercial use.
Does LivePortrait run on Windows, Mac and Linux?
LivePortrait supports: Windows, Linux, macOS.
What hardware do I need for LivePortrait?
NVIDIA recommended; Apple Silicon supported (slower)
How do I install LivePortrait?
1. Clone and install. 2. Download the weights and launch the UI.
What are the best LivePortrait alternatives?
Popular alternatives include SadTalker, FramePack, Wan 2.2, HunyuanVideo. See the comparison table on this page.
Can I use LivePortrait online without installing it?
If you don’t have a large GPU, AiLoft runs Veo 3.1 and Kling 2.5 in the cloud — generate and compare clips in the browser.
No 24 GB GPU? Generate AI video online
Run Veo 3.1 and Kling 2.5 in the cloud and compare clips side by side — pay per clip.