[CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

[CVPR 2025] EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation

[AAAI 2025] EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning

[ICLR 26 Oral] Stable Video Infinity: Infinite-Length Video Generation with Error Recycling

[CVPR 2024] This is the official source for our paper "SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis"

Wav2Lip UHQ extension for Automatic1111

Diffusion-based Portrait and Animal Animation

CVPR2023 talking face implementation for Identity-Preserving Talking Face Generation With Landmark and Appearance Priors

Wav2Lip version 288 and pipeline to train

JoyHallo: Digital human model for Mandarin

PyTorch Implementation for Paper "Emotionally Enhanced Talking Face Generation" (ICCVW'23 and ACM-MMW'23)

A curated list of resources of audio-driven talking face generation

[ECCV 2024] Dyadic Interaction Modeling for Social Behavior Generation

[AAAI 2026] FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation

One-shot Audio-driven 3D Talking Head Synthesis via Generative Prior, CVPRW 2024

[ECCV 2024] - ScanTalk: 3D Talking Heads from Unregistered Scans

Using a single image and just 10 seconds of sample audio, our project enables you to create a video where it appears as if you're speaking the desired text.

Using a single image and just 10 seconds of sample audio, our project enables you to create a video where it appears as if you're speaking the desired text.

Use one line code to call SadTalker API with modelscope

DoyenTalker uses deep learning techniques to generate personalized avatar videos that speak user-provided text in a specified voice. The system utilizes Coqui TTS for text-to-speech generation, along with various face rendering and animation techniques to create a video where the given avatar articulates the speech.