# ConsistentAvatar: Learning to Diffuse Fully Consistent Talking Head Avatar with Temporal Guidance

arXiv: https://arxiv.org/abs/2411.15436 · HTML: https://mlsanity.com/paper/2411.15436/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 34 of its 47 references that are in the map.
- First posted on arXiv 23 Nov 2024.

## Placed in

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

## Builds on (most cited first, 30 of 34)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference](https://mlsanity.com/paper/2310.04378/) (2023)
- [First Order Motion Model for Image Animation](https://mlsanity.com/paper/2003.00196/) (2020)
- [Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set](https://mlsanity.com/paper/1903.08527/) (2019)
- [Learning an Animatable Detailed 3D Face Model from In-The-Wild Images](https://mlsanity.com/paper/2012.04012/) (2020)
- [Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction](https://mlsanity.com/paper/2012.03065/) (2020)
- [SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation](https://mlsanity.com/paper/2211.12194/) (2022)
- [StyleRig: Rigging StyleGAN for 3D Control over Portrait Images](https://mlsanity.com/paper/2004.00121/) (2020)
- [GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians](https://mlsanity.com/paper/2312.02069/) (2023)
- [EMOCA: Emotion Driven Monocular Face Capture and Animation](https://mlsanity.com/paper/2204.11312/) (2022)
- [I M Avatar: Implicit Morphable Head Avatars from Videos](https://mlsanity.com/paper/2112.07471/) (2021)
- [Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning](https://mlsanity.com/paper/2004.11660/) (2020)
- [Neural Head Avatars from Monocular RGB Videos](https://mlsanity.com/paper/2112.01554/) (2021)
- [PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering](https://mlsanity.com/paper/2109.08379/) (2021)
- [Audio-Driven Emotional Video Portraits](https://mlsanity.com/paper/2104.07452/) (2021)
- [Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision](https://mlsanity.com/paper/1905.06817/) (2019)
- [BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images](https://mlsanity.com/paper/2002.08988/) (2020)
- [RigNeRF: Fully Controllable Neural 3D Portraits](https://mlsanity.com/paper/2206.06481/) (2022)
- [Realistic One-shot Mesh-based Head Avatars](https://mlsanity.com/paper/2206.08343/) (2022)
- [DCFace: Synthetic Face Generation with Dual Condition Diffusion Model](https://mlsanity.com/paper/2304.07060/) (2023)
- [DiffusionRig: Learning Personalized Priors for Facial Appearance Editing](https://mlsanity.com/paper/2304.06711/) (2023)
- [AvatarMAV: Fast 3D Head Avatar Reconstruction Using Motion-Aware Neural Voxels](https://mlsanity.com/paper/2211.13206/) (2022)
- [Unsupervised Learning of Efficient Geometry-Aware Neural Articulated Representations](https://mlsanity.com/paper/2204.08839/) (2022)
- [Emotion-Controllable Generalized Talking Face Generation](https://mlsanity.com/paper/2205.01155/) (2022)
- [DiffusionAvatars: Deferred Diffusion for High-fidelity 3D Head Avatars](https://mlsanity.com/paper/2311.18635/) (2023)

## Built on by (most cited first, 7 of 7)

- [Controlling Avatar Diffusion with Learnable Gaussian Embedding](https://mlsanity.com/paper/2503.15809/) (2025)
- [A Unit Enhancement and Guidance Framework for Audio-Driven Avatar Video Generation](https://mlsanity.com/paper/2505.03603/) (2025)
- [Follow Your Motion: A Generic Temporal Consistency Portrait Editing Framework with Trajectory Guidance](https://mlsanity.com/paper/2503.22225/) (2025)
- [FactorPortrait: Controllable Portrait Animation via Disentangled Expression, Pose, and Viewpoint](https://mlsanity.com/paper/2512.11645/) (2025)
- [ALIVE: An Avatar-Lecture Interactive Video Engine with Content-Aware Retrieval for Real-Time Interaction](https://mlsanity.com/paper/2512.20858/) (2025)
- [Facial Expression Generation Aligned with Human Preference for Natural Dyadic Interaction](https://mlsanity.com/paper/2603.07093/) (2026)
- [Proxy Avatar Meets Low-Rank Caching: Real-Time One-Shot Emotion-Controllable Portrait Animation](https://mlsanity.com/paper/2608.01978/) (2026)

## Abstract (arXiv)

Diffusion models have shown impressive potential on talking head generation. While plausible appearance and talking effect are achieved, these methods still suffer from temporal, 3D or expression inconsistency due to the error accumulation and inherent limitation of single-image generation ability. In this paper, we propose ConsistentAvatar, a novel framework for fully consistent and high-fidelity talking avatar generation. Instead of directly employing multi-modal conditions to the diffusion process, our method learns to first model the temporal representation for stability between adjacent frames. Specifically, we propose a Temporally-Sensitive Detail (TSD) map containing high-frequency feature and contours that vary significantly along the time axis. Using a temporal consistent diffusion module, we learn to align TSD of the initial result to that of the video frame ground truth. The final avatar is generated by a fully consistent diffusion module, conditioned on the aligned TSD, rough head normal, and emotion prompt embedding. We find that the aligned TSD, which represents the temporal patterns, constrains the diffusion process to generate temporally stable talking head. Further, its reliable guidance complements the inaccuracy of other conditions, suppressing the accumulated error while improving the consistency on various aspects. Extensive experiments demonstrate that ConsistentAvatar outperforms the state-of-the-art methods on the generated appearance, 3D, expression and temporal consistency. Project page: https://njust-yang.github.io/ConsistentAvatar.github.io/