wwdok / SadTalker_ModelScope
Use one line code to call SadTalker API with modelscope
☆18Updated 10 months ago
Related projects: ⓘ
- 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
- simple and fast wav2lip using onnx models for face-detection and inference. Easy installation☆21Updated 7 months ago
- Full version of wav2lip-onnx including face alignment and face enhancement and more...☆42Updated 5 months ago
- Faster Talking Face Animation on Xeon CPU☆118Updated 10 months ago
- ☆27Updated last year
- ☆61Updated this week
- Cloned repository from Hugging Face Spaces (CVPR 2022 Demo)☆54Updated last year
- ☆29Updated 8 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)☆14Updated last month
- ☆53Updated last year
- ☆25Updated 11 months ago
- 基于DINet的推理服务,推理视频流和视频☆13Updated 10 months ago
- ☆13Updated 6 months ago
- 📖 A curated list of resources dedicated to avatar.☆51Updated last week
- ☆50Updated last year
- ☆20Updated last year
- code for paper "Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motion" in the conference of IJCAI 2021☆8Updated 2 years 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
- Preprocessing Scipts for Talking Face Generation☆66Updated last month
- Wav2Lip-Emotion extends Wav2Lip to modify facial expressions of emotions via L1 reconstruction and pre-trained emotion objectives. We als…☆93Updated 2 years ago
- ☆58Updated 7 months ago
- Talking Face Generation system☆19Updated 11 months ago
- A modified version of vid2vid for Speech2Video, Text2Video Paper☆35Updated last year
- AI toolbox and pretrain models.☆36Updated 7 months ago
- [ICASSP 2024] DiffDub: Person-generic visual dubbing using inpainting renderer with diffusion auto-encoder☆37Updated 2 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 11 months ago
- A curated list of 'Talking Head Generation' resources. Features influential papers, groundbreaking algorithms, crucial GitHub repositorie…☆67Updated 11 months ago
- optimized wav2lip☆18Updated 8 months ago
- The API server version of the SadTalker project. Runs in Docker, 10 times faster than the original!☆115Updated last year
- Collections of papers, databases, and codes targeted at Digital Human☆28Updated 5 months ago