LatentSync - GitLite

KO | EN

gitlite — search

#python #ai #go #golang #rust #deep-learning #macos #nodejs #windows #awesome #kubernetes #pytorch #openai #mcp

LatentSync

(★ 6,012)

Taming Stable Diffusion for Lip Sync!

파일 탐색기

최종 버전 다운로드 (.zip)

- demo1_audio.wav
- demo1_video.mp4
- demo2_audio.wav
- demo2_video.mp4
- demo3_audio.wav
- demo3_video.mp4
- - syncnet_16_latent.yaml
  - syncnet_16_pixel.yaml
  - syncnet_16_pixel_attn.yaml
  - syncnet_25_pixel.yaml
- - stage1.yaml
  - stage1_512.yaml
  - stage2.yaml
  - stage2_512.yaml
  - stage2_efficient.yaml
- audio.yaml
- scheduler_config.json
- changelog_v1.5.md
- changelog_v1.6.md
- framework.png
- syncnet_arch.md
- - __init__.py
  - README.md
- - __init__.py
  - syncnet.py
  - syncnet_eval.py
- draw_syncnet_lines.py
- eval_fvd.py
- eval_sync_conf.py
- eval_sync_conf.sh
- eval_syncnet_acc.py
- eval_syncnet_acc.sh
- fvd.py
- hyper_iqa.py
- inference_videos.py
- syncnet_detect.py
- - syncnet_dataset.py
  - unet_dataset.py
- - attention.py
  - motion_module.py
  - resnet.py
  - stable_syncnet.py
  - unet.py
  - unet_blocks.py
  - utils.py
  - wav2lip_syncnet.py
- - lipsync_pipeline.py
- - loss.py
- - affine_transform.py
  - audio.py
  - av_reader.py
  - face_detector.py
  - image_processor.py
  - mask.png
  - mask2.png
  - mask3.png
  - mask4.png
  - util.py
- - audio2feature.py
- affine_transform.py
- data_processing_pipeline.py
- detect_shot.py
- filter_high_resolution.py
- filter_visual_quality.py
- remove_broken_videos.py
- remove_incorrect_affined.py
- resample_fps_hz.py
- segment_videos.py
- sync_av.py
- inference.py
- train_syncnet.py
- train_unet.py
- count_total_videos_time.py
- download_web_videos.py
- move_files_recur.py
- occupy_gpu.py
- plot_videos_time_distribution.py
- remove_outdated_files.py
- write_fileslist.py
.gitignore
cog.yaml
data_processing_pipeline.sh
gradio_app.py
inference.sh
LICENSE
predict.py
README.md
requirements.txt
setup_env.sh
train_syncnet.sh
train_unet.sh

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

<h1 align="center">LatentSync</h1>

<div align="center">

[![arXiv](https://img.shields.io/badge/arXiv-Paper-b31b1b.svg?logo=arXiv)](https://arxiv.org/abs/2412.09262)
[![arXiv](https://img.shields.io/badge/%F0%9F%A4%97%20HuggingFace-Model-yellow)](https://huggingface.co/ByteDance/LatentSync-1.6)
[![arXiv](https://img.shields.io/badge/%F0%9F%A4%97%20HuggingFace-Space-yellow)](https://huggingface.co/spaces/fffiloni/LatentSync)
<a href="https://replicate.com/lucataco/latentsync"><img src="https://replicate.com/lucataco/latentsync/badge" alt="Replicate"></a>

</div>

## 🔥 Updates

- `2025/06/11`: We released **LatentSync 1.6**, which is trained on 512 $\times$ 512 resolution videos to mitigate the blurriness problem. Watch the demo [here](docs/changelog_v1.6.md).

- `2025/03/14`: We released **LatentSync 1.5**, which **(1)** improves temporal consistency via adding temporal layer, **(2)** improves performance on Chinese videos and **(3)** reduces the VRAM requirement of the stage2 training to **20 GB** through a series of optimizations. Learn more details [here](docs/changelog_v1.5.md).

## 📖 Introduction

We present *LatentSync*, an end-to-end lip-sync method based on audio-conditioned latent diffusion models without any intermediate motion representation, diverging from previous diffusion-based lip-sync methods based on pixel-space diffusion or two-stage generation. Our framework can leverage the powerful capabilities of Stable Diffusion to directly model complex audio-visual correlations.

## 🏗️ Framework

<p align="center">
<img src="docs/framework.png" width=100%>
<p>

LatentSync uses the [Whisper](https://github.com/openai/whisper) to convert melspectrogram into audio embeddings, which are then integrated into the U-Net via cross-attention layers. The reference and masked frames are channel-wise concatenated with noised latents as the input of U-Net. In the training process, we use a one-step method to get estimated clean latents from predicted noises, which are then decoded to obtain the estimated clean frames. The TREPA, [LPIPS](https://arxiv.org/abs/1801.03924) and [SyncNet](https://www.robots.ox.ac.uk/~vgg/publications/2016/Chung16a/chung16a.pdf) losses are added in the pixel space.

## 🎬 Demo

<table class="center">
  <tr style="font-weight: bolder;text-align:center;">
        <td width="50%"><b>Original video</b></td>
        <td width="50%"><b>Lip-synced video</b></td>
  </tr>
  <tr>
    <td>
      <video src=https://github.com/user-attachments/assets/b778e3c3-ba25-455d-bdf3-d89db0aa75f4 controls preload></video>
    </td>
    <td>
      <video src=https://github.com/user-attachments/assets/ac791682-1541-4e6a-aa11-edd9427b977e controls preload></video>
    </td>
  </tr>
  <tr>
    <td>
      <video src=https://github.com/user-attachments/assets/6d4f4afd-6547-428d-8484-09dc53a19ecf controls preload></video>
    </td>
    <td>
      <video src=https://github.com/user-attachments/assets/b4723d08-c1d4-4237-8251-09c43eb77a6a controls preload></video>
    </td>
  </tr>
  <tr>
    <td>
      <video src=https://github.com/user-attachments/assets/fb4dc4c1-cc98-43dd-a211-1ff8f843fcfa controls preload></video>
    </td>
    <td>
      <video src=https://github.com/user-attachments/assets/7c6ca513-d068-4aa9-8a82-4dfd9063ac4e controls preload></video>
    </td>
  </tr>
  <tr>
    <td width=300px>
      <video src=https://github.com/user-attachments/assets/0756acef-2f43-4b66-90ba-6dc1d1216904 controls preload></video>
    </td>
    <td width=300px>
      <video src=https://github.com/user-attachments/assets/663ff13d-d716-4a35-8faa-9dcfe955e6a5 controls preload></video>
    </td>
  </tr>
  <tr>
    <td>
      <video src=https://github.com/user-attachments/assets/0f7f9845-68b2-4165-bd08-c7bbe01a0e52 controls preload></video>
    </td>
    <td>
      <video src=https://github.com/user-attachments/assets/c34fe89d-0c09-4de3-8601-3d01229a69e3 controls preload></video>
    </td>
  </tr>
</table>

(Photorealistic videos are filmed by contracted models, and anime videos are from [VASA-1](https://www.microsoft.com/en-us/research/project/vasa-1/))

## 📑 Open-source Plan

- [x] Inference code and checkpoints
- [x] Data processing pipeline
- [x] Training code

## 🔧 Setting up the Environment

Install the required packages and download the checkpoints via:

```bash
source setup_env.sh
```

If the download is successful, the checkpoints should appear as follows:

```
./checkpoints/
|-- latentsync_unet.pt
|-- whisper
|   `-- tiny.pt
```

Or you can download `latentsync_unet.pt` and `tiny.pt` manually from our [HuggingFace repo](https://huggingface.co/ByteDance/LatentSync-1.6)

## 🚀 Inference

Minimum VRAM for inference:

- **8 GB** with LatentSync 1.5
- **18 GB** with LatentSync 1.6

There are two ways to perform inference:

### 1. Gradio App

Run the Gradio app for inference:

```bash
python gradio_app.py
```

### 2. Command Line Interface

Run the script for inference:

```bash
./inference.sh
```

You can try adjusting the following inference parameters to achieve better results:

- `inference_steps` [20-50]: A higher value improves visual quality but slows down the generation speed.
- `guidance_scale` [1.0-3.0]: A higher value improves lip-sync accuracy but may cause the video distortion or jitter.

## 🔄 Data Processing Pipeline

The complete data processing pipeline includes the following steps:

1. Remove the broken video files.
2. Resample the video FPS to 25, and resample the audio to 16000 Hz.
3. Scene detect via [PySceneDetect](https://github.com/Breakthrough/PySceneDetect).
4. Split each video into 5-10 second segments.
5. Affine transform the faces according to the landmarks detected by [InsightFace](https://github.com/deepinsight/insightface), then resize to 256 $\times$ 256.
6. Remove videos with [sync confidence score](https://www.robots.ox.ac.uk/~vgg/publications/2016/Chung16a/chung16a.pdf) lower than 3, and adjust the audio-visual offset to 0.
7. Calculate [hyperIQA](https://openaccess.thecvf.com/content_CVPR_2020/papers/Su_Blindly_Assess_Image_Quality_in_the_Wild_Guided_by_a_CVPR_2020_paper.pdf) score, and remove videos with scores lower than 40.

Run the script to execute the data processing pipeline:

```bash
./data_processing_pipeline.sh
```

You should change the parameter `input_dir` in the script to specify the data directory to be processed. The processed videos will be saved in the `high_visual_quality` directory. Each step will generate a new directory to prevent the need to redo the entire pipeline in case the process is interrupted by an unexpected error.

## 🏋️‍♂️ Training U-Net

Before training, you should process the data as described above. We released a pretrained SyncNet with 94% accuracy on both VoxCeleb2 and HDTF datasets for the supervision of U-Net training. You can execute the following command to download this SyncNet checkpoint:

```bash
huggingface-cli download ByteDance/LatentSync-1.6 stable_syncnet.pt --local-dir checkpoints
```

If all the preparations are complete, you can train the U-Net with the following script:

```bash
./train_unet.sh
```

We prepared several UNet configuration files in the ``configs/unet`` directory, each corresponding to a specific training setup:

- `stage1.yaml`: Stage1 training, requires **23 GB** VRAM.
- `stage2.yaml`: Stage2 training with optimal performance, requires **30 GB** VRAM.
- `stage2_efficient.yaml`: Efficient Stage 2 training, requires **20 GB** VRAM. It may lead to slight degradation in visual quality and temporal consistency compared with `stage2.yaml`, suitable for users with consumer-grade GPUs, such as the RTX 3090.
- `stage1_512.yaml`: Stage1 training on 512 $\times$ 512 resolution videos, requires **30 GB** VRAM.
- `stage2_512.yaml`: Stage2 training on 512 $\times$ 512 resolution videos, requires **55 GB** VRAM.

Also remember to change the parameters in U-Net config file to specify the data directory, checkpoint save path, and other training hyperparameters. For convenience, we prepared a script for writing a data files list. Run the following command:

```bash
python -m tools.write_fileslist
```

## 🏋️‍♂️ Training SyncNet

In case you want to train SyncNet on your own datasets, you can run the following script. The data processing pipeline for SyncNet is the same as U-Net.

```bash
./train_syncnet.sh
```

After `validations_steps` training, the loss charts will be saved in `train_output_dir`. They contain both the training and validation loss. If you want to customize the architecture of SyncNet for different image resolutions and input frame lengths, please follow the [guide](docs/syncnet_arch.md).

## 📊 Evaluation

You can evaluate the [sync confidence score](https://www.robots.ox.ac.uk/~vgg/publications/2016/Chung16a/chung16a.pdf) of a generated video by running the following script:

```bash
./eval/eval_sync_conf.sh
```

You can evaluate the accuracy of SyncNet on a dataset by running the following script:

```bash
./eval/eval_syncnet_acc.sh
```

Note that our released SyncNet is trained on data processed through our data processing pipeline, which includes special operations such as affine transformation and audio-visual adjustment. Therefore, before evaluation, the test data must first be processed using the provided pipeline.

## 🙏 Acknowledgement

- Our code is built on [AnimateDiff](https://github.com/guoyww/AnimateDiff). 
- Some code are borrowed from [MuseTalk](https://github.com/TMElyralab/MuseTalk), [StyleSync](https://github.com/guanjz20/StyleSync), [SyncNet](https://github.com/joonson/syncnet_python), [Wav2Lip](https://github.com/Rudrabha/Wav2Lip).

Thanks for their generous contributions to the open-source community!

## 📖 Citation

If you find our repo useful for your research, please consider citing our paper:

```bibtex
@article{li2024latentsync,
  title={LatentSync: Taming Audio-Conditioned Latent Diffusion Models for Lip Sync with SyncNet Supervision},
  author={Li, Chunyu and Zhang, Chao and Xu, Weikai and Lin, Jingyu and Xie, Jinghui and Feng, Weiguo and Peng, Bingyue and Chen, Cunjian and Xing, Weiwei},
  journal={arXiv preprint arXiv:2412.09262},
  year={2024}
}
```