
LivePortrait animates a still portrait using facial expressions and head movements from a driving video. It's for creators who want to animate faces or edit motion in portrait videos on their own hardware. It works with realistic photos as well as portraits in oil paintings, sculptures and 3D renders.
Its controls go beyond copying a performance. Eye and lip retargeting let you adjust how far the eyes and mouth open, while stitching helps apply the motion to the source portrait. The tool also accepts portrait videos as source material. Reusable motion templates let you apply captured movement without supplying the original driving video each time, reducing the need to share that footage.
The Python implementation uses PyTorch and an implicit keypoint approach rather than diffusion, with a focus on efficient animation and direct control over facial movement. A Gradio interface provides browser access to the locally running tool. The project also offers an online demo, separate from the code and pretrained models you can run yourself.
Human portrait animation runs on Linux, Windows and macOS with Apple Silicon. An animal mode transfers human motion to subjects such as cats, dogs and pandas. That mode has been tested on Linux and Windows with NVIDIA GPUs; its separate Gradio interface has been tested on Linux with NVIDIA hardware. Animal mode doesn't support macOS because its X-Pose dependency doesn't run there.
Claim this page and we'll verify you by hand. LivePortrait gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find LivePortrait?Promote it
Something wrong or outdated on this page?
14.1KUpdated 3 years ago
macOS · Windows · Linux · Web#Multimodal input#Works offline
SadTalker generates talking head videos from a single portrait and an audio recording. The project states an Apache 2.0 license and removal of its earlier noncommercial restriction. It runs locally on Windows, Linux and macOS, and suits creators who want to animate a face without recording a person on camera. Its animation includes facial expressions and head movement, with examples covering speech and singing in different languages.
30.1KUpdated 1 day ago
macOS · Windows#Image-to-image
FaceFusion is an AI face manipulation tool for photos and videos that processes media on your own machine. It's aimed at content creators, VFX artists, and film studios that want control over their footage and personal data. Local processing keeps that media on your hardware rather than sending it to a cloud service.
17.3KUpdated 11 months agoApache-2.0
Windows · Linux · Web#Hugging Face integration#Multimodal input
4.8KUpdated 3 weeks agoApache-2.0
macOS · Windows · Linux · Docker · Web#GGUF#Hugging Face integration#llama.cpp backend
1.2KUpdated 9 months agoMIT
macOS · Windows · Linux#Batch processing#Image-to-image
135.6KUpdated 46 minutes agoGPL-3.0
macOS · Windows · Linux · Web#ControlNet#Inpainting#LoRA
FramePack is an open source desktop app for making videos from a still image and a written motion prompt. It runs on Windows and Linux, with generation handled by your own NVIDIA GPU. It suits people who want to make AI video locally and see the clip develop as it renders.
Lollms WebUI is a local, single-user AI interface for people who want text chat and media generation in one place. It runs on Windows, macOS and Linux, with Docker support, and lets writers, developers and other users choose models and task-specific personalities. It's free and open source under Apache 2.0. The project receives minimal maintenance.
AI Render is a Blender add-on that uses your scene and a text prompt to generate an image with Stable Diffusion. It's for Blender artists who want to use their 3D work as the basis for AI images and explore different treatments within the application they already use.
ComfyUI is a local visual AI workspace for artists and technical teams who want to control how images, video, audio, 3D models and text are made. Its node canvas shows each model and processing step, so users can build and adjust workflows without writing code. It runs on your hardware.