Aruen24 / wav2lip_288x288_test
☆47Updated 10 months ago
Related projects: ⓘ
- wav2lip训练数据预处理综合工具☆35Updated 10 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…☆53Updated 11 months ago
- ☆32Updated 8 months ago
- ☆42Updated this week
- Just a suturing monster project.☆33Updated 9 months ago
- ☆165Updated 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 10 months ago
- ☆30Updated last year
- ☆29Updated 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…☆44Updated 6 months ago
- ☆58Updated 7 months ago
- ☆61Updated this week
- R2-Talker: Realistic Real-Time Talking Head Synthesis with Hash Grid Landmarks Encoding and Progressive Multilayer Conditioning☆77Updated 8 months ago
- ☆29Updated 8 months ago
- ☆24Updated 2 years ago
- 复现Wav2Lip作者新的论文☆20Updated 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 …☆98Updated last year
- ☆53Updated last year
- Psyche AI Inc release source "CVCUDA_FaceStoreHelper"☆66Updated last year
- ☆25Updated 11 months ago
- ☆89Updated this week
- wav2lip in a Vector Quantized (VQ) space☆28Updated last year
- ☆187Updated last year
- ☆50Updated 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☆35Updated 3 months ago
- ☆56Updated this week
- ☆16Updated this week
- ☆27Updated last year