audio-driven-portrait-animations

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

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

[ACM MM 2025] Ditto: Motion-Space Diffusion for Controllable Realtime Talking Head Synthesis

[ICCV 2025] Official Pytorch Implementation of FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portrait.

EchoMimicV3: 1.3B Parameters are All You Need for Unified Multi-Modal and Multi-Task Human Animation

Generative Motion Latent Flow Matching for Audio-driven Talking Portrait

MoDA: Multi-modal Diffusion Architecture for Talking Head Generation

FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation

Modern Twitter-like social media app built with Node.js, TypeScript, Express, and EJS.