OpenImagingLab/FlashVSR
[CVPR 2026] Towards Real-Time Diffusion-Based Streaming Video Super-Resolution — An efficient one-step diffusion framework for streaming VSR with locality-constrained sparse attention and a tiny conditional decoder.
This tool takes streaming, low-resolution video and transforms it into sharp, high-resolution video in real-time. It's designed for workflows that need immediate, enhanced video quality without significant delays. Video editors, content creators, and those managing live video feeds would find this beneficial for improving visual clarity.
1,430 stars.
Use this if you need to upscale live or streaming video footage quickly and efficiently, especially for 4x super-resolution, to improve visual fidelity for viewers or analysis.
Not ideal if you need to process static images or require extreme precision for highly specialized scientific imaging, as its primary focus is on real-time video and 4x upscaling.
Stars
1,430
Forks
119
Language
Python
License
Apache-2.0
Category
Last pushed
Dec 23, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/OpenImagingLab/FlashVSR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
milad1378yz/MOTFM
Flow Matching for Medical Image Synthesis: Bridging the Gap Between Speed and Quality
X-GenGroup/Flow-Factory
A unified framework for easy reinforcement learning in Flow-Matching models
fallenshock/FlowEdit
Official implementation of the paper: "FlowEdit: Inversion-Free Text-Based Editing Using...
haidog-yaqub/MeanFlow
Pytorch Implementation (unofficial) of the paper "Mean Flows for One-step Generative Modeling"...
jy0205/Pyramid-Flow
[ICLR 2025] Pyramidal Flow Matching for Efficient Video Generative Modeling