jiahao6635 / HeyGemWebLinks
☆31Updated 4 months ago
Alternatives and similar repositories for HeyGemWeb
Users that are interested in HeyGemWeb are comparing it to the libraries listed below
Sorting:
- 开源的LstmSync数字人泛化模型,只做最好的泛化模型!☆129Updated last week
- A docker free offline version for HeyGem; Python and Linux is all you need!☆379Updated 4 months ago
- The fastest digital human algorithm, now on your desktop.☆558Updated 2 months ago
- [NeurIPS 2025] OmniTalker: Real-Time Text-Driven Talking Head Generation with In-Context Audio-Visual Style Replication☆397Updated 2 months ago
- project page for ChatAnyone☆115Updated 8 months ago
- ☆391Updated 5 months ago
- [AAAI 2026] EchoMimicV3: 1.3B Parameters are All You Need for Unified Multi-Modal and Multi-Task Human Animation☆638Updated last week
- 私有化自动数字人排队训练、短视频排队生成的微信小程序、web运营后台管理系统一键部署,基于单人训练的音频驱动唇形,比wav2lip、deepfacelab、liveportrait、musetalk等等唇形方案更好,直接可以商业化,支持中日英韩多种语音 复刻☆52Updated 7 months ago
- JoyHallo: Digital human model for Mandarin☆516Updated 2 months ago
- wav2lip384生成器网格权重——来自不蠢不蠢☆139Updated 8 months ago
- ☆79Updated 4 months ago
- DICE-Talk is a diffusion-based emotional talking head generation method that can generate vivid and diverse emotions for speaking portrai…☆275Updated 3 months ago
- 一个用于CosyVoice的api接口项目☆321Updated 3 months ago
- MagicTryOn is a video virtual try-on framework based on a large-scale video diffusion Transformer.☆484Updated last week
- ☆58Updated 11 months ago
- Added vLLM support to IndexTTS for faster inference.☆887Updated last month
- ☆129Updated last year
- HeyGem for RTX50 series☆32Updated 6 months ago
- CosyVoice2 功能扩充(预训练音色推理/3s极速复刻/自然语言控制/自动识别/音色模型保存/API)☆175Updated 8 months ago
- This project provides a production-ready, real-time inference server for LatentSync, enabling high-quality, low-latency 2D digital human …☆20Updated 3 months ago
- ☆24Updated 8 months ago
- Web UI for OpenAvatarChat☆45Updated 3 months ago
- Real time streaming talking head☆481Updated last year
- ☆636Updated last week
- ☆43Updated 4 months ago
- 通过此代码可以免训练模型并通过轻量级服务器定制数字人形象☆106Updated last year
- 🚀 AI 全自动短视频引擎 | AI Fully Automated Short Video Engine☆305Updated this week
- talking-face video editing☆406Updated 9 months ago
- 基于MuseTalk的数字人代码。☆31Updated last year
- [真诚套壳]东半球最强的套壳数字人系统,前后端分离,可对接硅基、飞影、闪剪、壹定开放平台等所有市面上的数字人API接口,开箱即用,star交个朋友。☆97Updated last year