Specifiction
For vendors
AdvertiseTop spots, featured rows, home sponsor Get listedAdd a product we don't cover yet Claim a listingFree: verify the domain, then correct your page Vendor dashboardNumbers, orders and placements
List your tool
Vendor dashboard
Tech riderRev. 9 Oct 2026

FlashVSR

Ch 276.3of 33AI Video Upscalers
  1. 1Runs onself-hosted
  2. 2CostsFree plan
  3. 3Enhancement modesv1; v1.1; full; tiny; tiny long video
  4. 4Batch processingYes
  5. 5Supported video formatsMP4; MOV; AVI; MKV
5 lines stated Written from the maker's own pages: github.com
Visit site Alternatives
The FlashVSR homepage

Overview

FlashVSR is ranked #27 of 33 in AI video upscalers on Specifiction. It runs on Self-hosted. There is a free plan.

FlashVSR plans and pricing

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

Compared on AI video upscalers

Free plan
Yesgithub.com
Enhancement modes
v1; v1.1; full; tiny; tiny long videogithub.com
Batch processing
Yesgithub.com
Supported video formats
MP4; MOV; AVI; MKVgithub.com

Facts

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

Best FlashVSR alternatives

See all 20
All accessCh 01 Cutout.Pro Free planAndroidAPI from $4.99/mo8.0 All accessCh 02 Media.io AI Video Upscaler Free planFree trialAndroid Free to start7.9 All accessCh 03 NextGenUp Free planFree trialLinux Free to start7.5 All accessCh 04 HitPaw VikPea Free trialAndroidAPI from $8.33/mo7.2 All accessCh 05 Aiarty Video Enhancer Free planFree trialMac from $6.58/mo7.1 All accessCh 06 Real-CUGAN Free planAndroidLinux Free to start7.1

Where it ranks on Specifiction

Is FlashVSR yours?

Claim it for free: prove the domain, then correct facts, plans and screenshots. An editor reviews every change.

Claim it free Promote FlashVSR

Sources