FlashVSR#

Project page

arXiv paper

Official code

FlashVSR is a one-diffusion-step streaming diffusion framework for real-time video super-resolution (VSR). It combines a train-friendly three-stage distillation pipeline, locality-constrained sparse attention that bridges the train-test resolution gap, and a tiny conditional decoder for fast reconstruction.

FlashVSR teaser figure.

Teaser image source: FlashVSR official repository.

Requirements#

  • Minimum VRAM: ~24 GB.

  • PyTorch: >= 2.9.

Installation#

# from the repo root
uv sync --package flashdreams-flashvsr --inexact

Running the method#

The v2 v2v application accepts a video and writes the super-resolved video through the standard application/session runtime:

uv run --no-sync flashdreams-run-v2 \
    v2v-flashvsr-v1.1-sparse-ratio-2.0 \
    --output-path upscaled.mp4 \
    -- --video-path input.mp4

Omit --video-path to download and process the bounded Big Buck Bunny fallback.

We provide the following variants:

To inspect all supported CLI arguments and their default values, run:

uv run --no-sync flashdreams-run-v2 \
    v2v-flashvsr-v1.1-sparse-ratio-2.0 -- --help

A generated sample from the above commands:

FlashVSR 2x output (1280x768) from flashvsr-v1.1-sparse-ratio-2.0; low-resolution input (672x384) inset at bottom-left. Input from the FlashVSR examples.

Profiling benchmark#

Here is the profiling benchmark on per-chunk 2x upsampling time for FlashDreams FlashVSR compared to the official FlashVSR implementation under matched settings.

This chart shows per-chunk 2x upsampling time in milliseconds on a single GB200 GPU with a chunk size of 8 frames. For the official FlashVSR implementation, see this instruction.

Citation#

If you use FlashVSR, please cite the original work:

@inproceedings{zhuang2026flashvsr,
  title={FlashVSR: Towards Real-time Diffusion-Based Streaming Video Super Resolution},
  author={Zhuang, Junhao and Guo, Shi and Cai, Xin and Li, Xiaohui and Liu, Yihao and Yuan, Chun and Xue, Tianfan},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={43482--43493},
  year={2026}
}