oneCodeSuperman / wav2lip_hq_trt
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。
☆27Updated last year
Alternatives and similar repositories for wav2lip_hq_trt:
Users that are interested in wav2lip_hq_trt are comparing it to the libraries listed below
- wav2lip训练数据预处理综合工具☆40Updated last year
- Just a suturing monster project.☆38Updated last year
- ☆24Updated 3 years ago
- ☆33Updated last year
- 基于MuseTalk的数字人代码。☆28Updated 5 months ago
- ☆40Updated last year
- 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…☆51Updated 11 months ago
- ☆32Updated last week
- ☆11Updated 2 years ago
- ☆75Updated 4 months ago
- ☆34Updated last year
- ☆27Updated last year
- ☆49Updated last year
- ☆37Updated last month
- ☆10Updated last year
- ☆52Updated last year
- 复现Wav2Lip作者新的论文☆20Updated last year
- R2-Talker: Realistic Real-Time Talking Head Synthesis with Hash Grid Landmarks Encoding and Progressive Multilayer Conditioning☆80Updated 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…☆60Updated last year
- simple and fast wav2lip using onnx models for face-detection and inference. Easy installation☆24Updated 4 months ago
- ☆50Updated last year
- Full version of wav2lip-onnx including face alignment and face enhancement and more...☆86Updated last week
- Simple and fast wav2lip using new 256x256 resolution trained onnx-converted model for inference. Easy installation☆38Updated 4 months ago
- 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☆61Updated 2 months ago
- Spliting the ASR probability distribution results into the chinese pinyin, so as to extract more effective feature for the chinese speech…☆21Updated last year
- One-shot Audio-driven 3D Talking Head Synthesis via Generative Prior, CVPRW 2024☆60Updated 3 months ago
- PyTorch implementation of "StyleSync: High-Fidelity Generalized and Personalized Lip Sync in Style-based Generator"☆211Updated 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 …☆105Updated last year
- ONNX-Powered Inference for State-of-the-Art Face Upscalers☆89Updated 6 months ago