# InstaVSR: Taming Diffusion for Efficient and Temporally Consistent Video Super-Resolution

arXiv: https://arxiv.org/abs/2603.26134 · HTML: https://mlsanity.com/paper/2603.26134/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 65 references that are in the map.
- First posted on arXiv 27 Mar 2026.

## Builds on (most cited first, 5 of 5)

- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Open-Sora: Democratizing Efficient Video Production for All](https://mlsanity.com/paper/2412.20404/) (2024)
- [Open-Sora Plan: Open-Source Large Video Generation Model](https://mlsanity.com/paper/2412.00131/) (2024)
- [SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training](https://mlsanity.com/paper/2506.05301/) (2025)
- [OMGSR: You Only Need One Mid-timestep Guidance for Real-World Image Super-Resolution](https://mlsanity.com/paper/2508.08227/) (2025)

## Abstract (arXiv)

Video super-resolution (VSR) seeks to reconstruct high-resolution frames from low-resolution inputs. While diffusion-based methods have substantially improved perceptual quality, extending them to video remains challenging for two reasons: strong generative priors can introduce temporal instability, and multi-frame diffusion pipelines are often too expensive for practical deployment. To address both challenges simultaneously, we propose InstaVSR, a lightweight diffusion framework for efficient video super-resolution. InstaVSR combines three ingredients: (1) a pruned one-step diffusion backbone that removes several costly components from conventional diffusion-based VSR pipelines, (2) recurrent training with flow-guided temporal regularization to improve frame-to-frame stability, and (3) dual-space adversarial learning in latent and pixel spaces to preserve perceptual quality after backbone simplification. On an NVIDIA RTX 4090, InstaVSR processes a 30-frame video at 2K×2K resolution in under one minute with only 7 GB of memory usage, substantially reducing the computational cost compared to existing diffusion-based methods while maintaining favorable perceptual quality with significantly smoother temporal transitions.