| license: mit | |
| pipeline_tag: image-to-video | |
| This repository contains the model of the paper [Unlock Pose Diversity: Accurate and Efficient Implicit Keypoint-based Spatiotemporal Diffusion for Audio-driven Talking Portrait](https://huggingface.co/papers/2503.12963). | |
| Code: https://github.com/chaolongy/KDTalker | |