# FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale Fusion

arXiv: https://arxiv.org/abs/2412.09626 · HTML: https://mlsanity.com/paper/2412.09626/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 55 of its 59 references that are in the map.
- First posted on arXiv 12 Dec 2024.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 30 of 55)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2304.08818/) (2023)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021)
- [PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis](https://mlsanity.com/paper/2310.00426/) (2023)
- [Adversarial Diffusion Distillation](https://mlsanity.com/paper/2311.17042/) (2023)
- [VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models](https://mlsanity.com/paper/2401.09047/) (2024)
- [MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation](https://mlsanity.com/paper/2302.08113/) (2023)
- [VideoCrafter1: Open Diffusion Models for High-Quality Video Generation](https://mlsanity.com/paper/2310.19512/) (2023)
- [VideoComposer: Compositional Video Synthesis with Motion Controllability](https://mlsanity.com/paper/2306.02018/) (2023)
- [Lumiere: A Space-Time Diffusion Model for Video Generation](https://mlsanity.com/paper/2401.12945/) (2024)
- [Simple diffusion: End-to-end diffusion for high resolution images](https://mlsanity.com/paper/2301.11093/) (2023)
- [Pyramidal Flow Matching for Efficient Video Generative Modeling](https://mlsanity.com/paper/2410.05954/) (2024)
- [FreeU: Free Lunch in Diffusion U-Net](https://mlsanity.com/paper/2309.11497/) (2023)

## Built on by (most cited first, 30 of 30)

- [Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance](https://mlsanity.com/paper/2512.08765/) (2025)
- [HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance](https://mlsanity.com/paper/2504.06232/) (2025)
- [Token-Shuffle: Towards High-Resolution Image Generation with Autoregressive Models](https://mlsanity.com/paper/2504.17789/) (2025)
- [TTS-VAR: A Test-Time Scaling Framework for Visual Auto-Regressive Generation](https://mlsanity.com/paper/2507.18537/) (2025)
- [DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusion](https://mlsanity.com/paper/2510.20766/) (2025)
- [UltraImage: Rethinking Resolution Extrapolation in Image Diffusion Transformers](https://mlsanity.com/paper/2512.04504/) (2025)
- [HiStream: Efficient High-Resolution Video Generation via Redundancy-Eliminated Streaming](https://mlsanity.com/paper/2512.21338/) (2025)
- [ScaleDiff: Higher-Resolution Image Synthesis via Efficient and Model-Agnostic Diffusion](https://mlsanity.com/paper/2510.25818/) (2025)
- [FreeSwim: Revisiting Sliding-Window Attention Mechanisms for Training-Free Ultra-High-Resolution Video Generation](https://mlsanity.com/paper/2511.14712/) (2025)
- [Exploring Position Encoding in Diffusion U-Net for Training-free High-resolution Image Generation](https://mlsanity.com/paper/2503.09830/) (2025)
- [UltraImageGen: Efficient Ultra-High-Resolution Image Generation with Hierarchical Local Attention](https://mlsanity.com/paper/2510.16325/) (2025)
- [SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformers](https://mlsanity.com/paper/2605.22668/) (2026)
- [Taming Consistency Distillation for Accelerated Human Image Animation](https://mlsanity.com/paper/2504.11143/) (2025)
- [Phase-Aligned RoPE for Mixed-Resolution Diffusion Transformer](https://mlsanity.com/paper/2511.19778/) (2025)
- [Low-Resolution Editing is All You Need for High-Resolution Editing](https://mlsanity.com/paper/2511.19945/) (2025)
- [UPLiFT: Efficient Pixel-Dense Feature Upsampling with Local Attenders](https://mlsanity.com/paper/2601.17950/) (2026)
- [PixelWizard: Towards Efficient High-Fidelity Video Generation at Ultra-Large Spatial Resolution](https://mlsanity.com/paper/2605.25801/) (2026)
- [CineScale: Tuning-Free High-Resolution Video Generation](https://mlsanity.com/paper/2508.15774/) (2025)
- [InfoScale: Unleashing Training-free Variable-scaled Image Generation via Effective Utilization of Information](https://mlsanity.com/paper/2509.01421/) (2025)
- [PixelRush: Ultra-Fast, Training-Free High-Resolution Image Generation via One-step Diffusion](https://mlsanity.com/paper/2602.12769/) (2026)
- [EruDiff: Refactoring Knowledge in Diffusion Models for Advanced Text-to-Image Synthesis](https://mlsanity.com/paper/2603.20828/) (2026)
- [EDITBRIDGE: Towards Faithful and Efficient Ultra-High-Resolution Image Editing](https://mlsanity.com/paper/2608.18063/) (2026)
- [NoiseShift: Resolution-Aware Noise Recalibration for Better Low-Resolution Image Generation](https://mlsanity.com/paper/2510.02307/) (2025)
- [EditCrafter: Tuning-free High-Resolution Image Editing via Pretrained Diffusion Model](https://mlsanity.com/paper/2604.10268/) (2026)
- [ExtraVAR: Stage-Aware RoPE Remapping for Resolution Extrapolation in Visual Autoregressive Models](https://mlsanity.com/paper/2605.10045/) (2026)
- [HierEdit: Region-Aware Hierarchical Diffusion for Efficient High-Resolution Editing](https://mlsanity.com/paper/2605.17294/) (2026)
- [PhotoQuilt: Training-Free Arbitrary-Resolution Photomosaics via Bootstrapped Tiled Denoising](https://mlsanity.com/paper/2606.30968/) (2026)
- [HRDiT: Training-Free High-Resolution Image Generation with Off-the-Shelf Diffusion Transformer Models](https://mlsanity.com/paper/2608.07003/) (2026)
- [MagnifiQ: Patch-aware Text Guided Progressive Upscaling for High-Resolution Image Restoration](https://mlsanity.com/paper/2608.14543/) (2026)
- [BigCell: Generating Gigapixel Whole-Slide Images](https://mlsanity.com/paper/2610.14261/) (2026)

## Abstract (arXiv)

Visual diffusion models achieve remarkable progress, yet they are typically trained at limited resolutions due to the lack of high-resolution data and constrained computation resources, hampering their ability to generate high-fidelity images or videos at higher resolutions. Recent efforts have explored tuning-free strategies to exhibit the untapped potential higher-resolution visual generation of pre-trained models. However, these methods are still prone to producing low-quality visual content with repetitive patterns. The key obstacle lies in the inevitable increase in high-frequency information when the model generates visual content exceeding its training resolution, leading to undesirable repetitive patterns deriving from the accumulated errors. To tackle this challenge, we propose FreeScale, a tuning-free inference paradigm to enable higher-resolution visual generation via scale fusion. Specifically, FreeScale processes information from different receptive scales and then fuses it by extracting desired frequency components. Extensive experiments validate the superiority of our paradigm in extending the capabilities of higher-resolution visual generation for both image and video models. Notably, compared with previous best-performing methods, FreeScale unlocks the 8k-resolution text-to-image generation for the first time.