oneCodeSuperman / wav2lip_hq_trtLinks
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。
☆31Updated last month
Alternatives and similar repositories for wav2lip_hq_trt
Users that are interested in wav2lip_hq_trt are comparing it to the libraries listed below
Sorting:
- wav2lip训练数据预处理综合工具☆39Updated last year
- ☆28Updated 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…☆54Updated last year
- ☆43Updated 3 months ago
- ☆49Updated 2 years ago
- ☆24Updated 4 years ago
- Just a suturing monster project.☆41Updated last year
- An optimized pipeline for DINet reducing inference latency for up to 60% 🚀. Kudos for the authors of the original repo for this amazing …☆108Updated 2 years ago
- ☆75Updated last year
- ☆10Updated 2 years ago
- ☆36Updated 2 years ago
- R2-Talker: Realistic Real-Time Talking Head Synthesis with Hash Grid Landmarks Encoding and Progressive Multilayer Conditioning☆82Updated last year
- Considering the original Wav2Lip was trained on LSR2 and didn't have good performance on Chinese. I preprocessed CMLR Dataset and would t…☆62Updated 2 years ago
- ☆10Updated last year
- ☆35Updated 2 years ago
- ☆78Updated 3 months ago
- ☆33Updated 8 months ago
- PyTorch implementation of "StyleSync: High-Fidelity Generalized and Personalized Lip Sync in Style-based Generator"☆212Updated 2 years ago
- Wav2Lip-Emotion extends Wav2Lip to modify facial expressions of emotions via L1 reconstruction and pre-trained emotion objectives. We als…☆95Updated 3 years ago
- ☆59Updated 2 years ago
- ☆52Updated 2 years ago
- Pytorch official implementation for our paper "HyperLips: Hyper Control Lips with High Resolution Decoder for Talking Face Generation".☆212Updated last year
- A simple face restoration TensorRT deployment solution.☆86Updated last year
- ☆27Updated 2 years ago
- ☆42Updated last year
- Faster Talking Face Animation on Xeon CPU☆129Updated last year
- 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☆80Updated 10 months ago
- Simple and fast wav2lip using new 256x256 resolution trained onnx-converted model for inference. Easy installation☆45Updated last year
- Psyche AI Inc release source "CVCUDA_FaceStoreHelper"☆66Updated 2 years ago
- 基于MuseTalk的数字人代码。☆31Updated last year