Real-Time Diffusion-Based Streaming Video Super-Resolution
Diffusion-based video upscalers produce beautiful results, but they are usually far too slow to use on real footage — many denoising passes per frame add up fast. FlashVSR-v1.1 collapses that into a single step and streams frames as it goes, so diffusion-quality upscaling becomes practical at scale, even at ultra-high resolutions. It is the first diffusion-based one-step streaming VSR framework, built by researchers at Tsinghua University / OpenImagingLab.
🏆 Up to ~17 FPS at 768×1408 on a single A100 — and up to ~12× faster than prior one-step diffusion VSR models
📹 See it in action
What it does
FlashVSR-v1.1 is a diffusion-based video super-resolution (VSR) model that takes low-resolution video and reconstructs it at significantly higher resolution (optimized for 4× upscaling). What sets FlashVSR apart from other diffusion-based VSR tools is its speed: instead of running many denoising passes per frame, it produces results in a single step and processes frames in a streaming fashion. This makes diffusion-quality video super-resolution practical at scale, even at ultra-high output resolutions.
Problem it solves
- Low-resolution video sources – Upscales legacy, web-compressed, or low-bitrate footage to sharp, high-resolution output (4× recommended)
- Slow diffusion VSR pipelines – Most diffusion-based super-resolution tools are far too slow for practical use on video. FlashVSR completes super-resolution in a single inference step, achieving up to ~12× speedup over prior one-step diffusion VSR models
- Streaming / real-time use cases – Built as a streaming framework, enabling near real-time processing rather than batch-only workflows
- Ultra-high resolutions – Scales reliably to very large output resolutions where competing tools tend to break down or introduce artifacts
- Stability across aspect ratios and content types – v1.1 specifically targets improved stability and fidelity over the initial v1 release
Input/Output
- Input:
- A low-resolution video (optimized for 4× super-resolution input)
- Output: A high-resolution MP4 video file
- Sharp, detailed reconstruction with preserved fine structures and textures
- Temporally coherent motion across frames, processed in a streaming pass
- Parameters:
- Scale — fixed at 4× (this build uses the FlashVSR Tiny pipeline optimized for 4× super-resolution, so the scale is not user-selectable)
- Random seed (-1 = random, default 1) — set a fixed integer to reproduce the same result across runs
- Advanced Options:
- LCSA top-k ratio (range 1.0 – 4.0, default 2) — how aggressively the model's Locality-Constrained Sparse Attention selects tokens per window. Higher = more tokens attended to (potentially better quality, more compute); lower = sparser attention (faster, may lose some fine detail)
- LCSA window (range 5 – 15, odd values only, default 11) — the spatial window size used by LCSA. Larger windows capture more surrounding context per token (better structural coherence for large objects and long motion); smaller windows are faster and focus on local detail. Only odd numbers are valid so the window has a clean center pixel
- Input resolution — up to 720 × 720 (per the studio node's Tiny pipeline)
A sample workflow from community
Accuracy & Speed
Processing speed | ~17 FPS for 768 × 1408 video on a single NVIDIA A100 GPU |
Speedup vs. prior work | Up to ~12× faster than previous one-step diffusion VSR models |
Infrastructure needed | Single GPU; optimized for NVIDIA A100 / A800 (Ampere). Runs on H200 (Hopper) with reduced acceleration. Other GPUs (RTX 40/50, H800) currently unverified |
Output quality | State-of-the-art among diffusion-based VSR models |
How FlashVSR-v1.1 compares
FlashVSR-v1.1 is one of four VSR models in CNAPS Studio's Video Upscaling lineup — reach for it when speed matters most:
SparkVSR | FlashVSR-v1.1 | SeedVR2-3B / 7B | |
Best for | Creative control via reference keyframes | Fastest, near real-time upscaling | High-quality automatic restoration |
Reference-image steering | ✅ Yes (optional) | ❌ No | ❌ No |
Blind / no-reference mode | ✅ Yes | ✅ Yes | ✅ Yes |
Scale factors | 2×, 3×, 4× | up to 4× | up to 4× |
All four run inside CNAPS Studio — compare them side-by-side with the Video Compare tool, or chain them into a larger pipeline.
Model Variants
FlashVSR is available in two released versions:
Version | Best For |
FlashVSR v1 | Original release (Oct 2025) |
FlashVSR v1.1 | Recommended — enhanced stability and fidelity (Nov 2025) |
Each version also ships full and tiny inference variants, including a long-video tiny variant for extended sequences.
Model Source
- HuggingFace:
Compliance & Provenance
Provider | Open-source |
Provider type | Specialized |
License | |
EU AI Act risk class | Minimal Risk |
Art. 50 transparency | Not applicable |
Region availability | Available globally |
Training data summary | Pending — provider has not yet published per Art. 53(d) |
For more on how we classify models and mark outputs, see our AI Policy.
Related Video Upscaling Models
- SparkVSR — Reference-Guided Upscaling for Short Clips
- SeedVR2 7B — Upscale & Restore Video up to 4K, highest-quality variant
- SeedVR2 3B — Upscale & Restore Video up to 4K, lighter/faster variant
New to CNAPS Studio? Start with the Quickstart Guide, or browse the full AI Model Hub.