AniPortrait

AniPortrait

by Tencent
AniPortrait is an open-source AI framework by Tencent that generates high-quality animated videos from audio and a reference portrait image.

What is AniPortrait?

AniPortrait is an open-source framework developed by Tencent that generates photorealistic, lip-synced animations from audio and a reference portrait image. It is designed to produce high-quality, temporally consistent videos with natural facial expressions and precise lip movements.

Key Features

  • Audio-Driven Animation: Automatically generates facial animations synchronized with input audio, including lip movements, expressions, and head poses.
  • High-Quality Visuals: Uses a diffusion model and motion module to produce realistic, high-resolution animations.
  • Temporal Consistency: Ensures smooth and natural character movements over time.
  • Flexibility: Allows editing and customization of animations using 3D facial representations.
  • Precise Facial Expressions: Captures subtle lip movements and complex facial expressions accurately.
  • Reference Image Consistency: Matches the generated animations visually with the original portrait.

How It Works

AniPortrait consists of two main modules:

1. Audio2Lmk Module

This module extracts 3D facial meshes and head pose information from audio input. It uses a pre-trained wav2vec model to identify pronunciation and intonation, which are crucial for generating realistic animations. These features are then transformed into 3D meshes and converted into 2D facial landmarks.

2. Lmk2Video Module

This module generates temporally consistent videos from the reference portrait and facial landmarks. It uses Stable Diffusion 1.5 as the backbone, combined with a temporal motion module, to produce high-quality video frames. A ReferenceNet ensures consistent facial identity throughout the animation.

Official Links

Getting Started

To get started with AniPortrait, clone the GitHub repository and follow the setup instructions. The repository includes detailed documentation, examples, and pre-trained models to help you generate your own animations.

Framework Features

Supported Tasks
Lip-Syncing Facial Animation Video Generation Audio-Driven Animation
Tags
AI Video Generation Lip Syncing Open Source Facial Animation Audio-Driven Animation Diffusion Models 3D Facial Landmarks Video Editing Photorealistic Animation Tencent

Getting Started

Pricing
free

Screenshots & Images

Primary Screenshot
Additional Images

Stats

0 Views
0 Favorites
4907 GitHub Stars

Community & Support

Similar Frameworks

TPO
0
Phantom by ByteDance
0
AgentSociety by Tsinghua University
0