Metadata-Version: 2.1
Name: videosys
Version: 2.0.0
Summary: VideoSys
License: Apache Software License 2.0
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Environment :: GPU :: NVIDIA CUDA
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: System :: Distributed Computing
Requires-Python: >=3.6
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: click
Requires-Dist: colossalai
Requires-Dist: contexttimer
Requires-Dist: diffusers==0.30.0
Requires-Dist: einops
Requires-Dist: fabric
Requires-Dist: ftfy
Requires-Dist: imageio
Requires-Dist: imageio-ffmpeg
Requires-Dist: matplotlib
Requires-Dist: ninja
Requires-Dist: numpy<2.0.0
Requires-Dist: omegaconf
Requires-Dist: packaging
Requires-Dist: psutil
Requires-Dist: pydantic
Requires-Dist: ray
Requires-Dist: rich
Requires-Dist: safetensors
Requires-Dist: timm
Requires-Dist: torch>=1.13
Requires-Dist: tqdm
Requires-Dist: transformers
An easy and efficient system for video generation
### Latest News 🔥
- [2024/08] 🔥 Evole from [OpenDiT](https://github.com/NUS-HPC-AI-Lab/VideoSys/tree/v1.0.0) to VideoSys: An easy and efficient system for video generation.
- [2024/08] 🔥 Release PAB paper: [Real-Time Video Generation with Pyramid Attention Broadcast](https://arxiv.org/abs/2408.12588).
- [2024/06] Propose Pyramid Attention Broadcast (PAB)[[paper](https://arxiv.org/abs/2408.12588)][[blog](https://oahzxl.github.io/PAB/)][[doc](./docs/pab.md)], the first approach to achieve real-time DiT-based video generation, delivering negligible quality loss without requiring any training.
- [2024/06] Support [Open-Sora-Plan](https://github.com/PKU-YuanGroup/Open-Sora-Plan) and [Latte](https://github.com/Vchitect/Latte).
- [2024/03] Propose Dynamic Sequence Parallel (DSP)[[paper](https://arxiv.org/abs/2403.10266)][[doc](./docs/dsp.md)], achieves **3x** speed for training and **2x** speed for inference in Open-Sora compared with sota sequence parallelism.
- [2024/03] Support [Open-Sora: Democratizing Efficient Video Production for All](https://github.com/hpcaitech/Open-Sora).
- [2024/02] 🎉 Release [OpenDiT](https://github.com/NUS-HPC-AI-Lab/VideoSys/tree/v1.0.0): An Easy, Fast and Memory-Efficent System for DiT Training and Inference.
# About
VideoSys is an open-source project that provides a user-friendly and high-performance infrastructure for video generation. This comprehensive toolkit will support the entire pipeline from training and inference to serving and compression.
We are committed to continually integrating cutting-edge open-source video models and techniques. Stay tuned for exciting enhancements and new features on the horizon!
## Installation
Prerequisites:
- Python >= 3.10
- PyTorch >= 1.13 (We recommend to use a >2.0 version)
- CUDA >= 11.6
We strongly recommend using Anaconda to create a new environment (Python >= 3.10) to run our examples:
```shell
conda create -n videosys python=3.10 -y
conda activate videosys
```
Install VideoSys:
```shell
git clone https://github.com/NUS-HPC-AI-Lab/VideoSys
cd VideoSys
pip install -e .
```
## Usage
VideoSys supports many diffusion models with our various acceleration techniques, enabling these models to run faster and consume less memory.
You can find all available models and their supported acceleration techniques in the following table. Click `Doc` to see how to use them.
## Acceleration Techniques
### Pyramid Attention Broadcast (PAB) [[paper](https://arxiv.org/abs/2408.12588)][[blog](https://arxiv.org/abs/2403.10266)][[doc](./docs/pab.md)]
Real-Time Video Generation with Pyramid Attention Broadcast
Authors: [Xuanlei Zhao](https://oahzxl.github.io/)1*, [Xiaolong Jin]()2*, [Kai Wang](https://kaiwang960112.github.io/)1*, and [Yang You](https://www.comp.nus.edu.sg/~youy/)1 (* indicates equal contribution)
1National University of Singapore, 2Purdue University
PAB is the first approach to achieve real-time DiT-based video generation, delivering lossless quality without requiring any training. By mitigating redundant attention computation, PAB achieves up to 21.6 FPS with 10.6x acceleration, without sacrificing quality across popular DiT-based video generation models including [Open-Sora](https://github.com/hpcaitech/Open-Sora), [Latte](https://github.com/Vchitect/Latte) and [Open-Sora-Plan](https://github.com/PKU-YuanGroup/Open-Sora-Plan).
See its details [here](./docs/pab.md).
----
### Dyanmic Sequence Parallelism (DSP) [[paper](https://arxiv.org/abs/2403.10266)][[doc](./docs/dsp.md)]
DSP is a novel, elegant and super efficient sequence parallelism for [Open-Sora](https://github.com/hpcaitech/Open-Sora), [Latte](https://github.com/Vchitect/Latte) and other multi-dimensional transformer architecture.
It achieves **3x** speed for training and **2x** speed for inference in Open-Sora compared with sota sequence parallelism ([DeepSpeed Ulysses](https://arxiv.org/abs/2309.14509)). For a 10s (80 frames) of 512x512 video, the inference latency of Open-Sora is:
| Method | 1xH800 | 8xH800 (DS Ulysses) | 8xH800 (DSP) |
| ------ | ------ | ------ | ------ |
| Latency(s) | 106 | 45 | 22 |
See its details [here](./docs/dsp.md).
## Contributing
We welcome and value any contributions and collaborations. Please check out [CONTRIBUTING.md](./CONTRIBUTING.md) for how to get involved.
## Contributors
## Star History
[](https://star-history.com/#NUS-HPC-AI-Lab/VideoSys&Date)
## Citation
```
@misc{videosys2024,
author={VideoSys Team},
title={VideoSys: An Easy and Efficient System for Video Generation},
year={2024},
publisher={GitHub},
url = {https://github.com/NUS-HPC-AI-Lab/VideoSys},
}
@misc{zhao2024pab,
title={Real-Time Video Generation with Pyramid Attention Broadcast},
author={Xuanlei Zhao and Xiaolong Jin and Kai Wang and Yang You},
year={2024},
eprint={2408.12588},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2408.12588},
}
@misc{zhao2024dsp,
title={DSP: Dynamic Sequence Parallelism for Multi-Dimensional Transformers},
author={Xuanlei Zhao and Shenggan Cheng and Chang Chen and Zangwei Zheng and Ziming Liu and Zheming Yang and Yang You},
year={2024},
eprint={2403.10266},
archivePrefix={arXiv},
primaryClass={cs.DC},
url={https://arxiv.org/abs/2403.10266},
}
@misc{zhao2024opendit,
author={Xuanlei Zhao, Zhongkai Zhao, Ziming Liu, Haotian Zhou, Qianli Ma, and Yang You},
title={OpenDiT: An Easy, Fast and Memory-Efficient System for DiT Training and Inference},
year={2024},
publisher={GitHub},
url={https://github.com/NUS-HPC-AI-Lab/VideoSys/tree/v1.0.0},
}
```