Optimized inference pipeline based on FlashVSR project

Authors: Junhao Zhuang, Shi Guo, Xin Cai, Xiaohui Li, Yihao Liu, Chun Yuan, Tianfan Xue

Modified: lihaoyun6

Your star means a lot for us to develop this project! ⭐

• Replaced Block-Sparse-Attention with Sparse_SageAttention to avoid building complex cuda kernels.
• With the new tile_dit method, you can even output 1080P video on 8GB of VRAM.
• Support copying audio tracks to output files (powered by FFmpeg).
• Introduced Blackwell GPU support for FlashVSR.

Follow these steps to set up and run FlashVSR on your local machine:

⚠️ Note: This project is primarily designed and optimized for 4× video super-resolution.
We strongly recommend using the 4× SR setting to achieve better results and stability. ✅

git clone https://github.com/lihaoyun6/FlashVSR_plus
cd FlashVSR_plus

Create and activate the environment:

conda create -n flashvsr
conda activate flashvsr

Install project dependencies:

# for CUDA 12.8
pip install -r requirements.txt --index-url https://download.pytorch.org/whl/cu128

# for CUDA 13.0
pip install -r requirements.txt --index-url https://download.pytorch.org/whl/cu130

• When you run FlashVSR+ for the first time, it will automatically download all required models from HuggingFace.

• You can also manually download all files from FlashVSR and put them in the following location:

./models/FlashVSR/
│
├── LQ_proj_in.ckpt                                   
├── TCDecoder.ckpt                                    
├── Wan2.1_VAE.pth                                    
├── diffusion_pytorch_model_streaming_dmd.safetensors 
└── README.md

CLI example:

python run.py -i ./inputs/example0.mp4 -s 4 ./

Or use gradio web ui:

python webui.py

We welcome feedback and issues. Thank you for trying FlashVSR+

We gratefully acknowledge the following open-source projects:

• FlashVSR — https://github.com/OpenImagingLab/FlashVSR
• DiffSynth Studio — https://github.com/modelscope/DiffSynth-Studio
• Sparse_SageAttention — https://github.com/jt-zhang/Sparse_SageAttention_API
• taehv — https://github.com/madebyollin/taehv

• Junhao Zhuang Email: [email protected]

@misc{zhuang2025flashvsrrealtimediffusionbasedstreaming,
      title={FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution}, 
      author={Junhao Zhuang and Shi Guo and Xin Cai and Xiaohui Li and Yihao Liu and Chun Yuan and Tianfan Xue},
      year={2025},
      eprint={2510.12747},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2510.12747}, 
}