SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.03786 · CVPR · 2023

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

Wenliang Zhao, Jiwen Lu, Jie Zhou, Zheng Zhu, Wanhua Li, Zibin Meng, Shuai Shen

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Figure 1. We present a crafted conditional Diffusion model for generalized Talking head synthesis (DiffTalk). Given a driven audio, the DiffTalk is capable of synthesizing high-fidelity and synchronized talking videos for multiple identities without further fine-tuning.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2301.03786")
get_code_for_paper("2301.03786")
have("2301.03786")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2301.03786.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2301.03786.svg)](https://syntology.ai/paper/2301.03786)

Connect an agent — have() is free.