ComfyUI_FlashVSR

FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution,this node ,you can use it in comfyUI

Upadte

• Test cu128 torch2.8.0 Vram 12G
• Choice vae infer full mode ，encoder infer tiny mode 选择vae跑full模式 效果最好，tiny则是速度
• 如果觉得项目有用，请给官方项目FlashVSR 打星； if you Like it ， star the official project link

1.Installation

In the ./ComfyUI/custom_nodes directory, run the following:

git clone https://github.com/smthemex/ComfyUI_FlashVSR

2.requirements

pip install -r requirements.txt

• 如果不追求极致速度，也可以不装Block-Sparse-Attention

git clone https://github.com/mit-han-lab/Block-Sparse-Attention
cd Block-Sparse-Attention
pip install packaging
pip install ninja
python setup.py install

3.checkpoints

• 3.1 FlashVSR all checkpoints 所有模型，vae 用常规的wan2.1
• 3.2 emb posi_prompt.pth 4M而已

├── ComfyUI/models/FlashVSR
|     ├── LQ_proj_in.ckpt
|     ├── TCDecoder.ckpt
|     ├── diffusion_pytorch_model_streaming_dmd.safetensors
|     ├── posi_prompt.pth
├── ComfyUI/models/vae
|        ├──Wan2.1_VAE.pth

Example

• tiny

Acknowledgements

DiffSynth Studio
Block-Sparse-Attention
taehv

Citation

@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}, 
}

``

``