# DiffTalker: Co-driven audio-image diffusion for talking faces via intermediate landmarks

arXiv: https://arxiv.org/abs/2309.07509 · HTML: https://mlsanity.com/paper/2309.07509/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 15 of its 19 references that are in the map.
- First posted on arXiv 14 Sep 2023.

## Placed in

- Diffusion models / [Audio, speech and music](https://mlsanity.com/diffusion/audio-speech-and-music/)

## Builds on (most cited first, 15 of 15)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild](https://mlsanity.com/paper/2008.10010/) (2020)
- [Deep Speech 2: End-to-End Speech Recognition in English and Mandarin](https://mlsanity.com/paper/1512.02595/) (2015)
- [One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing](https://mlsanity.com/paper/2011.15126/) (2020)
- [AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis](https://mlsanity.com/paper/2103.11078/) (2021)
- [MakeItTalk: Speaker-Aware Talking-Head Animation](https://mlsanity.com/paper/2004.12992/) (2020)
- [Capture, Learning, and Synthesis of 3D Speaking Styles](https://mlsanity.com/paper/1905.03079/) (2019)
- [Hierarchical Cross-Modal Talking Face Generationwith Dynamic Pixel-Wise Loss](https://mlsanity.com/paper/1905.03820/) (2019)
- [StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN](https://mlsanity.com/paper/2203.04036/) (2022)
- [EAMM: One-Shot Emotional Talking Face via Audio-Based Emotion-Aware Motion Model](https://mlsanity.com/paper/2205.15278/) (2022)
- [StyleSync: High-Fidelity Generalized and Personalized Lip Sync in Style-based Generator](https://mlsanity.com/paper/2305.05445/) (2023)
- [Talking Face Generation by Conditional Recurrent Adversarial Network](https://mlsanity.com/paper/1804.04786/) (2018)
- [DAE-Talker: High Fidelity Speech-Driven Talking Face Generation with Diffusion Autoencoder](https://mlsanity.com/paper/2303.17550/) (2023)

## Built on by (most cited first, 10 of 10)

- [LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control](https://mlsanity.com/paper/2407.03168/) (2024)
- [IPDreamer: Appearance-Controllable 3D Object Generation with Complex Image Prompts](https://mlsanity.com/paper/2310.05375/) (2023)
- [A Simple and Efficient Baseline for Zero-Shot Generative Classification](https://mlsanity.com/paper/2412.12594/) (2024)
- [MagicPortrait: Temporally Consistent Face Reenactment with 3D Geometric Guidance](https://mlsanity.com/paper/2504.21497/) (2025)
- [Identity-Consistent Video Generation under Large Facial-Angle Variations](https://mlsanity.com/paper/2603.21299/) (2026)
- [EmoGene: Audio-Driven Emotional 3D Talking-Head Generation](https://mlsanity.com/paper/2410.17262/) (2024)
- [LiveNeRF: Efficient Face Replacement Through Neural Radiance Fields Integration](https://mlsanity.com/paper/2511.07552/) (2025)
- [G4G:A Generic Framework for High Fidelity Talking Face Generation with Fine-grained Intra-modal Alignment](https://mlsanity.com/paper/2402.18122/) (2024)
- [RealTalk: Realistic Emotion-Aware Lifelike Talking-Head Synthesis](https://mlsanity.com/paper/2508.12163/) (2025)
- [CatPortrait: Taming Video Generative Models for Portrait Animation via In-context Conditioning](https://mlsanity.com/paper/2610.14957/) (2026)

## Abstract (arXiv)

Generating realistic talking faces is a complex and widely discussed task with numerous applications. In this paper, we present DiffTalker, a novel model designed to generate lifelike talking faces through audio and landmark co-driving. DiffTalker addresses the challenges associated with directly applying diffusion models to audio control, which are traditionally trained on text-image pairs. DiffTalker consists of two agent networks: a transformer-based landmarks completion network for geometric accuracy and a diffusion-based face generation network for texture details. Landmarks play a pivotal role in establishing a seamless connection between the audio and image domains, facilitating the incorporation of knowledge from pre-trained diffusion models. This innovative approach efficiently produces articulate-speaking faces. Experimental results showcase DiffTalker's superior performance in producing clear and geometrically accurate talking faces, all without the need for additional alignment between audio and image features.