# EasyGenNet: An Efficient Framework for Audio-Driven Gesture Video Generation Based on Diffusion Model

arXiv: https://arxiv.org/abs/2504.08344 · HTML: https://mlsanity.com/paper/2504.08344/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 24 of its 32 references that are in the map.
- First posted on arXiv 11 Apr 2025.

## Placed in

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

## Builds on (most cited first, 24 of 24)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation](https://mlsanity.com/paper/2311.17117/) (2023)
- [Video-to-Video Synthesis](https://mlsanity.com/paper/1808.06601/) (2018)
- [MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model](https://mlsanity.com/paper/2311.16498/) (2023)
- [Everybody Dance Now](https://mlsanity.com/paper/1808.07371/) (2018)
- [Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance](https://mlsanity.com/paper/2403.14781/) (2024)
- [Capture, Learning, and Synthesis of 3D Speaking Styles](https://mlsanity.com/paper/1905.03079/) (2019)
- [EMO: Emote Portrait Alive -- Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions](https://mlsanity.com/paper/2402.17485/) (2024)
- [FaceFormer: Speech-Driven 3D Facial Animation with Transformers](https://mlsanity.com/paper/2112.05329/) (2021)
- [Learning Individual Styles of Conversational Gesture](https://mlsanity.com/paper/1906.04160/) (2019)
- [3D Hand Shape and Pose from Images in the Wild](https://mlsanity.com/paper/1902.03451/) (2019)
- [MeshTalk: 3D Face Animation from Speech using Cross-Modality Disentanglement](https://mlsanity.com/paper/2104.08223/) (2021)
- [Generating Holistic 3D Human Motion from Speech](https://mlsanity.com/paper/2212.04420/) (2022)
- [GestureDiffuCLIP: Gesture Diffusion Model with CLIP Latents](https://mlsanity.com/paper/2303.14613/) (2023)
- [TryOnDiffusion: A Tale of Two UNets](https://mlsanity.com/paper/2306.08276/) (2023)
- [Robust High-Resolution Video Matting with Temporal Guidance](https://mlsanity.com/paper/2108.11515/) (2021)
- [Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation](https://mlsanity.com/paper/2303.09119/) (2023)
- [Audio-Driven Co-Speech Gesture Video Generation](https://mlsanity.com/paper/2212.02350/) (2022)
- [VLOGGER: Multimodal Diffusion for Embodied Avatar Synthesis](https://mlsanity.com/paper/2403.08764/) (2024)
- [CyberHost: Taming Audio-driven Avatar Diffusion Model with Region Codebook Attention](https://mlsanity.com/paper/2409.01876/) (2024)
- [Make-Your-Anchor: A Diffusion-based 2D Avatar Generation Framework](https://mlsanity.com/paper/2403.16510/) (2024)

## Abstract (arXiv)

Audio-driven cospeech video generation typically involves two stages: speech-to-gesture and gesture-to-video. While significant advances have been made in speech-to-gesture generation, synthesizing natural expressions and gestures remains challenging in gesture-to-video systems. In order to improve the generation effect, previous works adopted complex input and training strategies and required a large amount of data sets for pre-training, which brought inconvenience to practical applications. We propose a simple one-stage training method and a temporal inference method based on a diffusion model to synthesize realistic and continuous gesture videos without the need for additional training of temporal modules.The entire model makes use of existing pre-trained weights, and only a few thousand frames of data are needed for each character at a time to complete fine-tuning. Built upon the video generator, we introduce a new audio-to-video pipeline to synthesize co-speech videos, using 2D human skeleton as the intermediate motion representation. Our experiments show that our method outperforms existing GAN-based and diffusion-based methods.