yerfor/GeneFacePlusPlus

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1808 stars · 253 forks observed · 2026-10-04

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

GeneFace++ is the official PyTorch implementation of a NeRF-based system for generalized and stable real-time 3D talking face generation. It converts audio input into realistic talking-head videos with high lip-sync accuracy and video realism.

Use cases

• generate a talking head video from an audio clip
• create realistic lip-synced avatar videos from speech
• animate a person's face driven by audio in real time
• build a virtual presenter or digital human from a reference video
• research NeRF-based talking face synthesis
• produce 3D talking face avatars for video content

When to choose

• you need high-quality, lip-synced talking face videos driven by audio
• you want a NeRF-based research-grade talking head system with pretrained checkpoints
• you need real-time 3D talking face generation on GPU hardware

When to avoid

• you need a simple one-click avatar app without model setup or GPU resources
• you want person-specific talking style control (consider MimicTalk instead)
• you need one-shot generation from a single image (consider Real3DPortrait instead)

Facets

library · maturity active

deep-learning machine-learning video-processing audio-processing computer-vision deep-learning computer-vision artificial-intelligence python nerf talking-face-generation audio-driven-animation 3dmm lip-sync pytorch research-code audio linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="yerfor/GeneFacePlusPlus")