HunyuanVideo-Foley

---

👥 Authors

Sizhe Shan1,2* • Qiulin Li1,3* • Yutao Cui1 • Miles Yang1 • Yuehai Wang2 • Qun Yang3 • Jin Zhou1† • Zhao Zhong1

🏢 1Tencent Hunyuan • 🎓 2Zhejiang University • ✈️ 3Nanjing University of Aeronautics and Astronautics

*Equal contribution • †Project lead

---

🔥🔥🔥 News

• [2025.9.29] 🚀 HunyuanVideo-Foley-XL Model Release - Release XL-sized model with offload inference support, significantly reducing VRAM requirements.
• [2025.8.28] 🌟 HunyuanVideo-Foley Open Source Release - Inference code and model weights publicly available.

---

🎥 Demo & Showcase

Experience the magic of AI-generated Foley audio in perfect sync with video content!

---

🤝 Community Contributions

ComfyUI Integration - Thanks to the amazing community for creating ComfyUI nodes:

• if-ai/ComfyUI_HunyuanVideoFoley - ComfyUI workflow integration which supports cpu offloading and FP8 quantization
• phazei/ComfyUI-HunyuanVideo-Foley - Alternative ComfyUI node implementation which supports different precision modes

🌟 We encourage and appreciate community contributions that make HunyuanVideo-Foley more accessible!

---

✨ Key Highlights

🎭 Multi-scenario Sync
High-quality audio synchronized with complex video scenes

🧠 Multi-modal Balance
Perfect harmony between visual and textual information

🎵 48kHz Hi-Fi Output
Professional-grade audio generation with crystal clarity

---

📄 Abstract

🚀 Tencent Hunyuan open-sources HunyuanVideo-Foley an end-to-end video sound effect generation model!

A professional-grade AI tool specifically designed for video content creators, widely applicable to diverse scenarios including short video creation, film production, advertising creativity, and game development.

🎯 Core Highlights

🎬 Multi-scenario Audio-Visual Synchronization
Supports generating high-quality audio that is synchronized and semantically aligned with complex video scenes, enhancing realism and immersive experience for film/TV and gaming applications.

⚖️ Multi-modal Semantic Balance
Intelligently balances visual and textual information analysis, comprehensively orchestrates sound effect elements, avoids one-sided generation, and meets personalized dubbing requirements.

🎵 High-fidelity Audio Output
Self-developed 48kHz audio VAE perfectly reconstructs sound effects, music, and vocals, achieving professional-grade audio generation quality.

🏆 SOTA Performance Achieved

HunyuanVideo-Foley comprehensively leads the field across multiple evaluation benchmarks, achieving new state-of-the-art levels in audio fidelity, visual-semantic alignment, temporal alignment, and distribution matching - surpassing all open-source solutions!

📊 Performance comparison across different evaluation metrics - HunyuanVideo-Foley leads in all categories

---

🔧 Technical Architecture

📊 Data Pipeline Design

🔄 Comprehensive data processing pipeline for high-quality text-video-audio datasets

The TV2A (Text-Video-to-Audio) task presents a complex multimodal generation challenge requiring large-scale, high-quality datasets. Our comprehensive data pipeline systematically identifies and excludes unsuitable content to produce robust and generalizable audio generation capabilities.

🏗️ Model Architecture

🧠 HunyuanVideo-Foley hybrid architecture with multimodal and unimodal transformer blocks

HunyuanVideo-Foley employs a sophisticated hybrid architecture:

• 🔄 Multimodal Transformer Blocks: Process visual-audio streams simultaneously
• 🎵 Unimodal Transformer Blocks: Focus on audio stream refinement
• 👁️ Visual Encoding: Pre-trained encoder extracts visual features from video frames
• 📝 Text Processing: Semantic features extracted via pre-trained text encoder
• 🎧 Audio Encoding: Latent representations with Gaussian noise perturbation
• ⏰ Temporal Alignment: Synchformer-based frame-level synchronization with gated modulation

---

📈 Performance Benchmarks

🎬 MovieGen-Audio-Bench Results

Objective and Subjective evaluation results demonstrating superior performance across all metrics

🏆 Method	PQ ↑	PC ↓	CE ↑	CU ↑	IB ↑	DeSync ↓	CLAP ↑	MOS-Q ↑	MOS-S ↑	MOS-T ↑
FoleyGrafter	6.27	2.72	3.34	5.68	0.17	1.29	0.14	3.36±0.78	3.54±0.88	3.46±0.95
V-AURA	5.82	4.30	3.63	5.11	0.23	1.38	0.14	2.55±0.97	2.60±1.20	2.70±1.37
Frieren	5.71	2.81	3.47	5.31	0.18	1.39	0.16	2.92±0.95	2.76±1.20	2.94±1.26
MMAudio	6.17	2.84	3.59	5.62	0.27	0.80	0.35	3.58±0.84	3.63±1.00	3.47±1.03
ThinkSound	6.04	3.73	3.81	5.59	0.18	0.91	0.20	3.20±0.97	3.01±1.04	3.02±1.08
HunyuanVideo-Foley (ours)	6.59	2.74	3.88	6.13	0.35	0.74	0.33	4.14±0.68	4.12±0.77	4.15±0.75

🎯 Kling-Audio-Eval Results

Comprehensive objective evaluation showcasing state-of-the-art performance

🏆 Method	FD_PANNs ↓	FD_PASST ↓	KL ↓	IS ↑	PQ ↑	PC ↓	CE ↑	CU ↑	IB ↑	DeSync ↓	CLAP ↑
FoleyGrafter	22.30	322.63	2.47	7.08	6.05	2.91	3.28	5.44	0.22	1.23	0.22
V-AURA	33.15	474.56	3.24	5.80	5.69	3.98	3.13	4.83	0.25	0.86	0.13
Frieren	16.86	293.57	2.95	7.32	5.72	2.55	2.88	5.10	0.21	0.86	0.16
MMAudio	9.01	205.85	2.17	9.59	5.94	2.91	3.30	5.39	0.30	0.56	0.27
ThinkSound	9.92	228.68	2.39	6.86	5.78	3.23	3.12	5.11	0.22	0.67	0.22
HunyuanVideo-Foley (ours)	6.07	202.12	1.89	8.30	6.12	2.76	3.22	5.53	0.38	0.54	0.24

🎉 Outstanding Results! HunyuanVideo-Foley achieves the best scores across ALL evaluation metrics, demonstrating significant improvements in audio quality, synchronization, and semantic alignment.

---

🚀 Quick Start

📦 Installation

🔧 System Requirements

• CUDA: 12.4 or 11.8 recommended
• Python: 3.8+
• OS: Linux (primary support)
• VRAM: 20GB for XXL model (or 12GB with --enable_offload), 16GB for XL model (or 8GB with --enable_offload)

Step 1: Clone Repository

# 📥 Clone the repository
git clone https://github.com/Tencent-Hunyuan/HunyuanVideo-Foley
cd HunyuanVideo-Foley

Step 2: Environment Setup

💡 Tip: We recommend using Conda for Python environment management.

# 🔧 Install dependencies
pip install -r requirements.txt

Step 3: Download Pretrained Models

🔗 Download Model weights from Huggingface

# using git-lfs
git clone https://huggingface.co/tencent/HunyuanVideo-Foley

# using huggingface-cli
huggingface-cli download tencent/HunyuanVideo-Foley

---

💻 Usage

📊 Model Specifications

Model	Checkpoint	VRAM (Normal)	VRAM (Offload)
XXL (Default)	hunyuanvideo_foley.pth	20GB	12GB
XL	hunyuanvideo_foley_xl.pth	16GB	8GB

🎬 Single Video Generation

Generate Foley audio for a single video file with text description:

# Use XXL model (default, best quality)
python3 infer.py \
    --model_path PRETRAINED_MODEL_PATH_DIR \
    --single_video video_path \
    --single_prompt "audio description" \
    --output_dir OUTPUT_DIR \
    # --enable_offload  

# Use XL model (memory-friendly)
python3 infer.py \
    --model_path PRETRAINED_MODEL_PATH_DIR \
    --model_size xl \
    --single_video video_path \
    --single_prompt "audio description" \
    --output_dir OUTPUT_DIR \
    # --enable_offload

📂 Batch Processing

Process multiple videos using a CSV file with video paths and descriptions:

# Download sample test videos
bash ./download_test_videos.sh

# Batch processing
python3 infer.py \
    --model_path PRETRAINED_MODEL_PATH_DIR \
    --csv_path assets/test.csv \
    --output_dir OUTPUT_DIR \
    # --enable_offload

🌐 Interactive Web Interface

Launch a user-friendly Gradio web interface for easy interaction:

# Launch with XXL model (default)
export HIFI_FOLEY_MODEL_PATH=PRETRAINED_MODEL_PATH_DIR
python3 gradio_app.py

# Launch with XL model (memory-friendly)
export HIFI_FOLEY_MODEL_PATH=PRETRAINED_MODEL_PATH_DIR
MODEL_SIZE=xl python3 gradio_app.py

# Optional: Enable offload to reduce memory usage
ENABLE_OFFLOAD=true python3 gradio_app.py

🚀 Then open your browser and navigate to the provided local URL to start generating Foley audio!

---

📚 Citation

If you find HunyuanVideo-Foley useful for your research, please consider citing our paper:

@misc{shan2025hunyuanvideofoleymultimodaldiffusionrepresentation,
      title={HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation}, 
      author={Sizhe Shan and Qiulin Li and Yutao Cui and Miles Yang and Yuehai Wang and Qun Yang and Jin Zhou and Zhao Zhong},
      year={2025},
      eprint={2508.16930},
      archivePrefix={arXiv},
      primaryClass={eess.AS},
      url={https://arxiv.org/abs/2508.16930}, 
}

Star History

🙏 Acknowledgements

We extend our heartfelt gratitude to the open-source community!

🎨 Stable Diffusion 3
Foundation diffusion models

⚡ FLUX
Advanced generation techniques

🎵 MMAudio
Multimodal audio generation

🤗 HuggingFace
Platform & diffusers library

🗜️ DAC
High-Fidelity Audio Compression

🔗 Synchformer
Audio-Visual Synchronization

🌟 Special thanks to all researchers and developers who contribute to the advancement of AI-generated audio and multimodal learning!

---

🔗 Connect with Us

© 2025 Tencent Hunyuan. All rights reserved. | Made with ❤️ for the AI community