# You Only Need One Step: Fast Super-Resolution with Stable Diffusion via Scale Distillation

arXiv: https://arxiv.org/abs/2401.17258 · HTML: https://mlsanity.com/paper/2401.17258/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 32 of its 40 references that are in the map.
- First posted on arXiv 30 Jan 2024.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Builds on (most cited first, 30 of 32)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021)
- [DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models](https://mlsanity.com/paper/2211.01095/) (2022)
- [On Distillation of Guided Diffusion Models](https://mlsanity.com/paper/2210.03142/) (2022)
- [Designing a Practical Degradation Model for Deep Blind Image Super-Resolution](https://mlsanity.com/paper/2103.14006/) (2021)
- [Exploiting Diffusion Prior for Real-World Image Super-Resolution](https://mlsanity.com/paper/2305.07015/) (2023)
- [Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform](https://mlsanity.com/paper/1804.02815/) (2018)
- ["Zero-Shot" Super-Resolution using Deep Internal Learning](https://mlsanity.com/paper/1712.06087/) (2017)
- [Component Divide-and-Conquer for Real-World Image Super-Resolution](https://mlsanity.com/paper/2008.01928/) (2020)
- [Gotta Go Fast When Generating Data with Score-Based Models](https://mlsanity.com/paper/2105.14080/) (2021)
- [Unsupervised Degradation Representation Learning for Blind Super-Resolution](https://mlsanity.com/paper/2104.00416/) (2021)
- [Solving Linear Inverse Problems Provably via Posterior Sampling with Latent Diffusion Models](https://mlsanity.com/paper/2307.00619/) (2023)
- [DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networks](https://mlsanity.com/paper/1704.02470/) (2017)
- [Frequency Separation for Real-World Super-Resolution](https://mlsanity.com/paper/1911.07850/) (2019)
- [Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priors](https://mlsanity.com/paper/2202.13142/) (2022)
- [Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution](https://mlsanity.com/paper/2203.14216/) (2022)
- [Bringing Old Photos Back to Life](https://mlsanity.com/paper/2004.09484/) (2020)
- [Blind Image Super-Resolution: A Survey and Beyond](https://mlsanity.com/paper/2107.03055/) (2021)
- [Flow-based Kernel Prior with Application to Blind Super-Resolution](https://mlsanity.com/paper/2103.15977/) (2021)
- [Prompt-tuning latent diffusion models for inverse problems](https://mlsanity.com/paper/2310.01110/) (2023)
- [Unpaired Image Super-Resolution using Pseudo-Supervision](https://mlsanity.com/paper/2002.11397/) (2020)
- [Denoising Diffusion Probabilistic Models for Robust Image Super-Resolution in the Wild](https://mlsanity.com/paper/2302.07864/) (2023)

## Built on by (most cited first, 24 of 24)

- [Arbitrary-steps Image Super-resolution via Diffusion Inversion](https://mlsanity.com/paper/2412.09013/) (2024)
- [DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolution](https://mlsanity.com/paper/2503.23580/) (2025)
- [Adversarial Diffusion Compression for Real-World Image Super-Resolution](https://mlsanity.com/paper/2411.13383/) (2024)
- [SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training](https://mlsanity.com/paper/2506.05301/) (2025)
- [Unleashing the Power of One-Step Diffusion based Image Super-Resolution via a Large-Scale Diffusion Discriminator](https://mlsanity.com/paper/2410.04224/) (2024)
- [The Power of Context: How Multimodality Improves Image Super-Resolution](https://mlsanity.com/paper/2503.14503/) (2025)
- [FAM Diffusion: Frequency and Attention Modulation for High-Resolution Image Generation with Stable Diffusion](https://mlsanity.com/paper/2411.18552/) (2024)
- [Edge-SD-SR: Low Latency and Parameter Efficient On-device Super-Resolution with Stable Diffusion via Bidirectional Conditioning](https://mlsanity.com/paper/2412.06978/) (2024)
- [Fast Image Super-Resolution via Consistency Rectified Flow](https://mlsanity.com/paper/2605.12377/) (2026)
- [One-Step Diffusion-based Real-World Image Super-Resolution with Visual Perception Distillation](https://mlsanity.com/paper/2506.02605/) (2025)
- [Hallucination Score: Towards Mitigating Hallucinations in Generative Image Super-Resolution](https://mlsanity.com/paper/2507.14367/) (2025)
- [Test-Time Anchoring for Discrete Diffusion Posterior Sampling](https://mlsanity.com/paper/2510.02291/) (2025)
- [DUO-VSR: Dual-Stream Distillation for One-Step Video Super-Resolution](https://mlsanity.com/paper/2603.22271/) (2026)
- [Upcycling Text-to-Image Diffusion Models for Multi-Task Capabilities](https://mlsanity.com/paper/2503.11905/) (2025)
- [Efficient High-Resolution Image Editing with Hallucination-Aware Loss and Adaptive Tiling](https://mlsanity.com/paper/2510.06295/) (2025)
- [FraQAT: Quantization Aware Training with Fractional bits](https://mlsanity.com/paper/2510.14823/) (2025)
- [F2IDiff: Real-world Image Super-resolution using Feature to Image Diffusion Foundation Model](https://mlsanity.com/paper/2512.24473/) (2025)
- [Multi-scale Image Super Resolution with a Single Auto-Regressive Model](https://mlsanity.com/paper/2506.04990/) (2025)
- [ChopGrad: Pixel-Wise Losses for Latent Video Diffusion via Truncated Backpropagation](https://mlsanity.com/paper/2603.17812/) (2026)
- [DreamSR: Towards Ultra-High-Resolution Image Super-Resolution via a Receptive-Field Enhanced Diffusion Transformer](https://mlsanity.com/paper/2605.15682/) (2026)
- [MedPCFM: Improving Medical Point Cloud Completion by Integrating Point Transformers and Flow Matching](https://mlsanity.com/paper/2606.24433/) (2026)
- [RFMSR: Residual Flow Matching for Image Super-Resolution](https://mlsanity.com/paper/2607.12753/) (2026)
- [Hierarchical Image Tokenization for Multi-Scale Image Super Resolution](https://mlsanity.com/paper/2605.14891/) (2026)
- [TGSR: Text-Grounded Diffusion for Faithful Image Super-Resolution](https://mlsanity.com/paper/2610.14281/) (2026)

## Abstract (arXiv)

In this paper, we introduce YONOS-SR, a novel stable diffusion-based approach for image super-resolution that yields state-of-the-art results using only a single DDIM step. We propose a novel scale distillation approach to train our SR model. Instead of directly training our SR model on the scale factor of interest, we start by training a teacher model on a smaller magnification scale, thereby making the SR problem simpler for the teacher. We then train a student model for a higher magnification scale, using the predictions of the teacher as a target during the training. This process is repeated iteratively until we reach the target scale factor of the final model. The rationale behind our scale distillation is that the teacher aids the student diffusion model training by i) providing a target adapted to the current noise level rather than using the same target coming from ground truth data for all noise levels and ii) providing an accurate target as the teacher has a simpler task to solve. We empirically show that the distilled model significantly outperforms the model trained for high scales directly, specifically with few steps during inference. Having a strong diffusion model that requires only one step allows us to freeze the U-Net and fine-tune the decoder on top of it. We show that the combination of spatially distilled U-Net and fine-tuned decoder outperforms state-of-the-art methods requiring 200 steps with only one single step.