# Long-Term TalkingFace Generation via Motion-Prior Conditional Diffusion Model

arXiv: https://arxiv.org/abs/2502.09533 · HTML: https://mlsanity.com/paper/2502.09533/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 17 of its 54 references that are in the map.
- First posted on arXiv 13 Feb 2025.

## Placed in

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

## Builds on (most cited first, 17 of 17)

- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Rethinking Attention with Performers](https://mlsanity.com/paper/2009.14794/) (2020)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [EMO: Emote Portrait Alive -- Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions](https://mlsanity.com/paper/2402.17485/) (2024)
- [LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control](https://mlsanity.com/paper/2407.03168/) (2024)
- [Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation](https://mlsanity.com/paper/2406.08801/) (2024)
- [EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditions](https://mlsanity.com/paper/2407.08136/) (2024)
- [AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation](https://mlsanity.com/paper/2403.17694/) (2024)
- [Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animation](https://mlsanity.com/paper/2406.01900/) (2024)
- [Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motion](https://mlsanity.com/paper/2107.09293/) (2021)
- [GeneFace: Generalized and High-Fidelity Audio-Driven 3D Talking Face Synthesis](https://mlsanity.com/paper/2301.13430/) (2023)
- [Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency](https://mlsanity.com/paper/2409.02634/) (2024)
- [Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis](https://mlsanity.com/paper/2401.08503/) (2024)
- [Sample and Computation Redistribution for Efficient Face Detection](https://mlsanity.com/paper/2105.04714/) (2021)
- [V-Express: Conditional Dropout for Progressive Training of Portrait Video Generation](https://mlsanity.com/paper/2406.02511/) (2024)
- [VividTalk: One-Shot Audio-Driven Talking Head Generation Based on 3D Hybrid Prior](https://mlsanity.com/paper/2312.01841/) (2023)
- [MegActor-Sigma: Unlocking Flexible Mixed-Modal Control in Portrait Animation with Diffusion Transformer](https://mlsanity.com/paper/2408.14975/) (2024)

## Built on by (most cited first, 30 of 49)

- [Controllable Video Generation: A Survey](https://mlsanity.com/paper/2507.16869/) (2025)
- [FaceShot: Bring Any Character into Life](https://mlsanity.com/paper/2503.00740/) (2025)
- [Advanced Sign Language Video Generation with Compressed and Quantized Multi-Condition Tokenization](https://mlsanity.com/paper/2506.15980/) (2025)
- [PSR: Scaling Multi-Subject Personalized Image Generation with Pairwise Subject-Consistency Rewards](https://mlsanity.com/paper/2512.01236/) (2025)
- [WildActor: Unconstrained Identity-Preserving Video Generation](https://mlsanity.com/paper/2603.00586/) (2026)
- [FreqU-FNet: Frequency-Aware U-Net for Imbalanced Medical Image Segmentation](https://mlsanity.com/paper/2505.17544/) (2025)
- [MultiMotion: Multi Subject Video Motion Transfer via Video Diffusion Transformer](https://mlsanity.com/paper/2512.07500/) (2025)
- [HDM: Hybrid Diffusion Model for Unified Image Anomaly Detection](https://mlsanity.com/paper/2502.19200/) (2025)
- [An improved EfficientNetV2 for garbage classification](https://mlsanity.com/paper/2503.21208/) (2025)
- [FaceEditTalker: Controllable Talking Head Generation with Facial Attribute Editing](https://mlsanity.com/paper/2505.22141/) (2025)
- [MCFNet: A Multimodal Collaborative Fusion Network for Fine-Grained Semantic Classification](https://mlsanity.com/paper/2505.23365/) (2025)
- [YOLO-FDA: Integrating Hierarchical Attention and Detail Enhancement for Surface Defect Detection](https://mlsanity.com/paper/2506.21135/) (2025)
- [RefAdGen: High-Fidelity Advertising Image Generation](https://mlsanity.com/paper/2508.11695/) (2025)
- [AUHead: Realistic Emotional Talking Head Generation via Action Units Control](https://mlsanity.com/paper/2602.09534/) (2026)
- [Normality-Preserving Continual Industrial Anomaly Detection via Orthogonal LoRA Banks](https://mlsanity.com/paper/2606.02042/) (2026)
- [2DMCG:2DMambawith Change Flow Guidance for Change Detection in Remote Sensing](https://mlsanity.com/paper/2503.00521/) (2025)
- [CFMD: Dynamic Cross-layer Feature Fusion for Salient Object Detection](https://mlsanity.com/paper/2504.01326/) (2025)
- [Photovoltaic Defect Image Generator with Boundary Alignment Smoothing Constraint for Domain Shift Mitigation](https://mlsanity.com/paper/2505.06117/) (2025)
- [Dual Attention Residual U-Net for Accurate Brain Ultrasound Segmentation in IVH Detection](https://mlsanity.com/paper/2505.17683/) (2025)
- [YOLO-SPCI: Enhancing Remote Sensing Object Detection via Selective-Perspective-Class Integration](https://mlsanity.com/paper/2505.21370/) (2025)
- [ACM-UNet: Adaptive Integration of CNNs and Mamba for Efficient Medical Image Segmentation](https://mlsanity.com/paper/2505.24481/) (2025)
- [O2Former:Direction-Aware and Multi-Scale Query Enhancement for SAR Ship Instance Segmentation](https://mlsanity.com/paper/2506.11913/) (2025)
- [DGE-YOLO: Dual-Branch Gathering and Attention for Accurate UAV Object Detection](https://mlsanity.com/paper/2506.23252/) (2025)
- [DiffFit: Disentangled Garment Warping and Texture Refinement for Virtual Try-On](https://mlsanity.com/paper/2506.23295/) (2025)
- [OptiPrune: Boosting Prompt-Image Consistency with Attention-Guided Noise and Dynamic Token Selection](https://mlsanity.com/paper/2507.00789/) (2025)
- [FashionPose: Unified Text-Driven Fashion Synthesis with Joint Geometric and Photometric Control](https://mlsanity.com/paper/2507.13311/) (2025)
- [Conditional Diffusion Model with Anatomical-Dose Dual Constraints for End-to-End Multi-Tumor Dose Prediction](https://mlsanity.com/paper/2508.02043/) (2025)
- [Animalbooth: multimodal feature enhancement for animal subject personalization](https://mlsanity.com/paper/2509.16702/) (2025)
- [DENet: Dual-Path Edge Network with Global-Local Attention for Infrared Small Target Detection](https://mlsanity.com/paper/2509.20701/) (2025)
- [Instruction Guided Multi Object Image Editing with Quantity and Layout Consistency](https://mlsanity.com/paper/2509.24514/) (2025)

## Abstract (arXiv)

Recent advances in conditional diffusion models have shown promise for generating realistic TalkingFace videos, yet challenges persist in achieving consistent head movement, synchronized facial expressions, and accurate lip synchronization over extended generations. To address these, we introduce the Motion-priors Conditional Diffusion Model (MCDM), which utilizes both archived and current clip motion priors to enhance motion prediction and ensure temporal consistency. The model consists of three key elements: (1) an archived-clip motion-prior that incorporates historical frames and a reference frame to preserve identity and context; (2) a present-clip motion-prior diffusion model that captures multimodal causality for accurate predictions of head movements, lip sync, and expressions; and (3) a memory-efficient temporal attention mechanism that mitigates error accumulation by dynamically storing and updating motion features. We also release the TalkingFace-Wild dataset, a multilingual collection of over 200 hours of footage across 10 languages. Experimental results demonstrate the effectiveness of MCDM in maintaining identity and motion continuity for long-term TalkingFace generation. Code, models, and datasets will be publicly available.