# DiffTalk: Crafting Diffusion Models for Generalized Audio-Driven Portraits Animation

> Research article (2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023) · cited 112× · AI/ML

**Wikidata**: [openalex:W4386075487](https://www.wikidata.org/wiki/openalex:W4386075487)  
**Source**: https://4ort.xyz/entity/difftalk-crafting-diffusion-models-for-generalized-audio-driven-portraits-animation