instant-high / wav2lip-onnx
simple and fast wav2lip using onnx models for face-detection and inference. Easy installation
☆22Updated last month
Related projects ⓘ
Alternatives and complementary repositories for wav2lip-onnx
- ☆27Updated last year
- wav2lip训练数据预处理综合工具☆37Updated last year
- Just a suturing monster project.☆37Updated 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…☆49Updated 8 months ago
- 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。☆26Updated last year
- 复现Wav2Lip作 者新的论文☆20Updated last year
- ☆46Updated last year
- optimized wav2lip☆19Updated 10 months ago
- 基于DINet的推理服务，推理视频流和视频☆13Updated last year
- ☆10Updated last year
- ONNX-Powered Inference for State-of-the-Art Face Upscalers☆81Updated 3 months ago
- Considering the original Wav2Lip was trained on LSR2 and didn't have good performance on Chinese. I preprocessed CMLR Dataset and would t…☆59Updated last year
- Full version of wav2lip-onnx including face alignment and face enhancement and more...☆71Updated last month
- Talking head animation☆27Updated 11 months ago
- 基于大模型的高质量情感虚拟人系统(Gradio+FUNASR+ChatGLM2-6B+GPT-SOVITS+EAT+GFPGAN)☆15Updated 3 months ago
- Simple and fast wav2lip using new 256x256 resolution trained onnx-converted model for inference. Easy installation☆27Updated last month
- ☆32Updated last year
- ☆11Updated last year
- ☆31Updated last year
- wav2lip in a Vector Quantized (VQ) space☆28Updated last year
- Face_lib separate from AI_Power☆17Updated 3 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
- ☆70Updated last month
- ☆38Updated 10 months ago
- ☆27Updated last year
- ☆53Updated last year
- Optimized Syncnet and Chinese enhanced version, EN and CN checkpoints released☆13Updated 3 years ago
- ☆30Updated 10 months ago