Skip to content
SPECIFICTION
Get listed

FlashVSR

github.com

Free plan Self-hosted
Visit github.com
Spec score 7.7 #21 of 32 in AI Video Upscalers

Spec sheet

Purpose
FlashVSR is a one-step diffusion framework for streaming video super-resolution.Read 9 Oct 2026 · github.com
Support
The maintainers welcome feedback and issues, and list Junhao Zhuang as a contact.Read 9 Oct 2026 · github.com
License
The GitHub repository identifies its license as Apache-2.0.Read 9 Oct 2026 · github.com
Community integrations
The README lists community ComfyUI implementations and WanVideoWrapper integration, and says WanVideoWrapper has known issues.Read 9 Oct 2026 · github.com
Core methods
Its framework combines a three-stage distillation pipeline, locality-constrained sparse attention, and a tiny conditional decoder.Read 9 Oct 2026 · github.com
Hardware requirements
The required Block-Sparse Attention backend is reported to work correctly on NVIDIA A100 and A800, while H200 runs with limited acceleration and compatibility on other listed GPUs is unknown.Read 9 Oct 2026 · github.com
Install requirements
The setup instructions use Python 3.11.13 and require installing the Block-Sparse Attention backend.Read 9 Oct 2026 · github.com
Model versions
The repository provides v1 and v1.1 model weights through Hugging Face, and recommends v1.1.Read 9 Oct 2026 · github.com
Performance
The project reports about 17 FPS for 768 × 1408 video on a single A100 GPU.Read 9 Oct 2026 · github.com
Quality limitation
The project says implementations without its sparse attention module may have noticeable quality degradation, especially at higher resolutions.Read 9 Oct 2026 · github.com
Recommended setting
The project is primarily designed and optimized for 4× video super-resolution, which it recommends for better results and stability.Read 9 Oct 2026 · github.com
Third-party inference
The README lists third-party cloud and API deployments and cautions that their model versions or pipeline completeness may differ from the official implementation.Read 9 Oct 2026 · github.com
Training dataset
VSR-120K is described as containing 120,000 videos and 180,000 images for joint image and video training.Read 9 Oct 2026 · github.com

Plans and prices

FlashVSR Free Open-source code and model weights · Requires a local Python environment and Block-Sparse Attention backend · GPU compatibility varies Read 9 Oct 2026 · github.com

Every FlashVSR plan and price →

Where Specifiction places it

Alternatives to FlashVSRAll alternatives →