- Home
- AI Photo Animation Tools
- LivePortrait
LivePortrait
What it is
LivePortrait is an open-source portrait animation system that creates video from a single source image. It can use motion from a driving video, audio, text, or generated motion, and it also supports editing portrait video with source and driving videos. Stitching plus eye and lip retargeting modules provide animation controls. The project offers inference code, pretrained weights, and a Gradio interface for local use, along with a Hugging Face Spaces demo. Its PyTorch implementation is released under the MIT License. The project reports 12.8 ms generation speed on an RTX 4090 with PyTorch. Human mode covers Linux, Windows, and Apple Silicon macOS; Intel macOS is untested. Animal models animate cats, dogs, and pandas, but animal mode is tested only on Linux and Windows with an NVIDIA GPU and is unsupported on macOS. Local setup requires git, conda, FFmpeg, Python 3.10, and downloaded weights.
For and against
For
- Open-source MIT-licensed implementation
- Supports image-to-portrait video animation
- Includes eye and lip retargeting
- Offers a Hugging Face demo
- Animal models support cats, dogs, and pandas
Against
- Local setup requires several dependencies
- Intel macOS is untested for human mode
- Animal mode excludes macOS
- Commercial users must replace InsightFace models
The verdict
LivePortrait combines portrait animation, editing controls, local inference, and a web demo. Platform and licensing conditions matter, especially for animal animation and commercial deployments, and maintainers warn about deepfake misuse and visual artifacts.
Who it suits
LivePortrait suits developers and creators seeking local or web-based portrait animation. It also fits users interested in animal animation, provided their system matches the stated hardware and platform limits.
On the record
- Animal animation
- An animal model can animate cats, dogs, and pandas using human-driven motion.liveportrait.github.io · read 2 Oct 2026
- animal limitation
- Animals mode is only tested on Linux and Windows with an NVIDIA GPU and is unsupported on macOS because X-Pose does not support macOS.github.com · read 30 Sep 2026
- animal support
- Fine-tuned models can animate cats, dogs, and pandas using human driving motion.liveportrait.github.io · read 30 Sep 2026
- Animation controls
- The project includes stitching and eye and lip retargeting controls for portrait animation.liveportrait.github.io · read 2 Oct 2026
- commercial licensing
- InsightFace models included in the project are for non-commercial research, and commercial users must replace those detection models.github.com · read 30 Sep 2026
- Community integrations
- The repository lists community-developed ComfyUI nodes, a Stable Diffusion WebUI extension, and FaceFusion processors that use LivePortrait.github.com · read 2 Oct 2026
- controls
- The system includes stitching and eye/lip retargeting modules for improved controllability.liveportrait.github.io · read 30 Sep 2026
- Ethics
- The maintainers warn about deepfake misuse, note that generated results may contain visual artifacts, and disclaim legal responsibility for use of generated results.github.com · read 2 Oct 2026
- Hardware limits
- The repository says animal mode is tested only on Linux and Windows with an NVIDIA GPU, and is unsupported on macOS because its X-Pose dependency does not support macOS.github.com · read 2 Oct 2026
- integrations
- Community resources include FaceFusion, ComfyUI nodes, a Stable Diffusion WebUI extension, Replicate, FAL, Poe, and Hugging Face Spaces.github.com · read 30 Sep 2026
- License and commercial use
- The repository includes an MIT license but says commercial users must remove and replace InsightFace detection models to comply with that license.github.com · read 2 Oct 2026
- local setup
- The project requires git, conda, FFmpeg, Python 3.10, and downloaded pretrained weights.github.com · read 30 Sep 2026
- Local use
- The repository provides inference code, pretrained models, and a Gradio interface for local use.github.com · read 2 Oct 2026
- open source
- The official implementation is provided as a PyTorch repository and is released under the MIT License.github.com · read 30 Sep 2026
- Performance
- The project reports generation speed of 12.8 ms on an RTX 4090 GPU with PyTorch.liveportrait.github.io · read 2 Oct 2026
- platform support
- Humans mode supports Linux, Windows, and macOS with Apple Silicon; Intel macOS is not tested.github.com · read 30 Sep 2026
- Privacy
- The repository says generated motion template files can speed inference and protect privacy.github.com · read 2 Oct 2026
- Purpose
- LivePortrait animates a portrait from a still image using facial expressions and head pose from a driving video, audio, text, or generated motion.liveportrait.github.io · read 2 Oct 2026
