SadTalker
https://gyazo.com/5bc97639ae3c95019973579c78a3dd40
GitHub :
https://github.com/Winfredy/SadTalker
画像と音声から、
talking head
映像を生成する
Stable Diffusion web UIに統合予定
https://sadtalker.github.io
https://colab.research.google.com/github/Winfredy/SadTalker/blob/main/quick_demo.ipynb
Acknowledgements
https://github.com/zhanglonghao1992/One-Shot_Free-View_Neural_Talking_Head_Synthesis
One-Shot Free-View Neural Talking Head Synthesis
https://github.com/RenYurui/PIRender
PIRenderer
https://github.com/microsoft/Deep3DFaceReconstruction
Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set
https://github.com/Rudrabha/Wav2Lip
Wav2Lip
demo:
https://huggingface.co/spaces/vinthony/SadTalker
paper:
https://arxiv.org/pdf/2211.12194.pdf