优化wav2lip的执行步骤，将头脸分离、嘴型替换、回补背景三个步骤分离，添加gfpgan强化面部功能，实现提前解帧，流式循环处理，对接obs
☆82Dec 16, 2024Updated last year
Alternatives and similar repositories for stream-wav2lip
Users that are interested in stream-wav2lip are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Full version of wav2lip-onnx including face alignment and face enhancement and more...☆162Jun 10, 2025Updated last year
- 基于wav2lip进行虚拟数字人训练，唇形驱动，包括数据处理流程等，模型包括96x96，192x192，192x288，288x288。☆22May 7, 2024Updated 2 years ago
- 1080p高清模型，直接推 理，无需高清修复☆74Jan 13, 2025Updated last year
- ☆43Jan 4, 2024Updated 2 years ago
- This is a project about talking faces. We use 576X576 sized facial images for training, which can generate 2k, 4k, 6k, and 8k digital hum…☆56Mar 18, 2024Updated 2 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆95Jul 21, 2025Updated last year
- Simple and fast wav2lip using new 256x256 resolution trained onnx-converted model for inference. Easy installation☆47Oct 13, 2024Updated 2 years ago
- ☆246Dec 26, 2023Updated 2 years ago
- Considering the original Wav2Lip was trained on LSR2 and didn't have good performance on Chinese. I preprocessed CMLR Dataset and would t…☆63Sep 23, 2023Updated 3 years ago
- This project is based on an improved Wav2Lip model, achieving synchronization between audio and video lip movements to enhance video prod…☆17Jul 10, 2024Updated 2 years ago
- [ICCV'23] Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis☆1,264Mar 14, 2025Updated last year
- ☆49Oct 24, 2023Updated 3 years ago
- 主要写er-nerf从零到一所有部署过程☆44Aug 28, 2024Updated 2 years ago
- Wav2Lip version 288 and pipeline to train☆652Aug 13, 2025Updated last year
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- JoyHallo: Digital human model for Mandarin☆519Sep 21, 2025Updated last year
- ☆42Jul 21, 2025Updated last year
- wav2lip384生成器网格权重——来自不蠢不蠢☆171Mar 7, 2025Updated last year
- High-Fidelity Lip-Syncing with Wav2Lip and Real-ESRGAN☆510Mar 27, 2024Updated 2 years ago
- simple and fast wav2lip using onnx models for face-detection and inference. Easy installation☆31Oct 14, 2024Updated 2 years ago
- GFPGAN face reconstruction with ncnn on a bare Raspberry Pi☆13Jan 4, 2023Updated 3 years ago
- Colab for making Wav2Lip high quality and easy to use☆850May 17, 2024Updated 2 years ago
- ☆12Jun 15, 2024Updated 2 years ago
- wav2lip训练数据预处理综合工具☆40Nov 18, 2023Updated 2 years ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Just a suturing monster project.☆38Nov 21, 2023Updated 2 years ago
- 每个人都能用的数字人☆2,226Aug 16, 2026Updated 2 months ago
- 将Wav2Lip和GFPGAN进行结合实现高清数字人说话视频☆38Jun 2, 2025Updated last year
- ☆39Sep 5, 2023Updated 3 years ago
- python库，实现推送实时rtmp音视频流☆141Mar 21, 2026Updated 7 months ago
- 基于MuseTalk的数字人代码。☆33Sep 14, 2024Updated 2 years ago
- optimized wav2lip☆18Jan 6, 2024Updated 2 years ago
- PersonaTalk Hack☆15Jan 10, 2025Updated last year
- [CVPR 2024] This is the official source for our paper "SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis"☆1,626Sep 18, 2025Updated last year
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- 一个超轻量级、可以在移动端实时运行的数字人模型☆2,667Jul 22, 2026Updated 3 months ago
- [ECCV'24] TalkingGaussian: Structure-Persistent 3D Talking Head Synthesis via Gaussian Splatting☆386Mar 15, 2025Updated last year
- ☆10Feb 17, 2023Updated 3 years ago
- GeneFace++: Generalized and Stable Real-Time 3D Talking Face Generation; Official Code☆1,806Oct 18, 2024Updated 2 years ago
- The fastest digital human algorithm, now on your desktop.☆586Sep 29, 2025Updated last year
- KAN-based Fusion of Dual Domain for Audio-Driven Landmarks Generation of the model can help you generate an sequence of facial lanmarks f…☆32Oct 28, 2025Updated last year
- 这是一个在wav2lip，使用wav2lip、gfpgan、yolov5等模型用RT加速的超快推理！经测试在2070显卡上可达到0.03秒每帧实现实时推理。☆32Sep 23, 2025Updated last year