Tag
开源了「神佬知识大赏」Agent Skill（Digital Human Koubo），只需一张照片加一句话即可全自动生成带口播、配音、字幕和包装的数字人短视频，已在 GitHub 上发布。
PD-GS introduces a phoneme-driven 3D Gaussian Splatting approach for audio-driven talking heads, using a Linguistic Fusion Module to improve lip articulation and reduce closure violations.
Ultralight Digital Human is an open-source Python project that lets you train a person-specific, audio-driven talking head from a 3–5 minute video, with support for HuBERT/WeNet audio features, ONNX export, and streaming inference.