# Relay Diffusion: Unifying diffusion process across resolutions for image synthesis

arXiv: https://arxiv.org/abs/2309.03350 · HTML: https://mlsanity.com/paper/2309.03350/

## Key facts

- Cited by 79 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 32 of its 36 references that are in the map.
- First posted on arXiv 4 Sep 2023.

## Placed in

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

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

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [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)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Cascaded Diffusion Models for High Fidelity Image Generation](https://mlsanity.com/paper/2106.15282/) (2021)
- [Improved Precision and Recall Metric for Assessing Generative Models](https://mlsanity.com/paper/1904.06991/) (2019)
- [eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers](https://mlsanity.com/paper/2211.01324/) (2022)
- [CogView: Mastering Text-to-Image Generation via Transformers](https://mlsanity.com/paper/2105.13290/) (2021)
- [Score-based Generative Modeling in Latent Space](https://mlsanity.com/paper/2106.05931/) (2021)
- [StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets](https://mlsanity.com/paper/2202.00273/) (2022)
- [Simple diffusion: End-to-end diffusion for high resolution images](https://mlsanity.com/paper/2301.11093/) (2023)
- [Generating Images with Sparse Representations](https://mlsanity.com/paper/2103.03841/) (2021)
- [MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer](https://mlsanity.com/paper/2303.14389/) (2023)
- [On the Importance of Noise Scheduling for Diffusion Models](https://mlsanity.com/paper/2301.10972/) (2023)
- [Generative Modelling With Inverse Heat Dissipation](https://mlsanity.com/paper/2206.13397/) (2022)
- [StyleSwin: Transformer-based GAN for High-resolution Image Generation](https://mlsanity.com/paper/2112.10762/) (2021)

## Built on by (most cited first, 30 of 79)

- [Pyramidal Flow Matching for Efficient Video Generative Modeling](https://mlsanity.com/paper/2410.05954/) (2024)
- [Diffusion Transformers with Representation Autoencoders](https://mlsanity.com/paper/2510.11690/) (2025)
- [Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers](https://mlsanity.com/paper/2405.05945/) (2024)
- [ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Models](https://mlsanity.com/paper/2310.07702/) (2023)
- [DDT: Decoupled Diffusion Transformer](https://mlsanity.com/paper/2504.05741/) (2025)
- [Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis](https://mlsanity.com/paper/2402.14797/) (2024)
- [PixelFlow: Pixel-Space Generative Models with Flow](https://mlsanity.com/paper/2504.07963/) (2025)
- [PixNerd: Pixel Neural Field Diffusion](https://mlsanity.com/paper/2507.23268/) (2025)
- [Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusion](https://mlsanity.com/paper/2410.19324/) (2024)
- [CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusion](https://mlsanity.com/paper/2403.05121/) (2024)
- [DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation](https://mlsanity.com/paper/2511.19365/) (2025)
- [FouriScale: A Frequency Perspective on Training-Free High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.12963/) (2024)
- [Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptation](https://mlsanity.com/paper/2402.10491/) (2024)
- [Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers](https://mlsanity.com/paper/2510.07316/) (2025)
- [DiP: Taming Diffusion Models in Pixel Space](https://mlsanity.com/paper/2511.18822/) (2025)
- [RodinHD: High-Fidelity 3D Avatar Generation with Diffusion Models](https://mlsanity.com/paper/2407.06938/) (2024)
- [FlashVideo: Flowing Fidelity to Detail for Efficient High-Resolution Video Generation](https://mlsanity.com/paper/2502.05179/) (2025)
- [Causal Diffusion Transformers for Generative Modeling](https://mlsanity.com/paper/2412.12095/) (2024)
- [Stretching Each Dollar: Diffusion Training from Scratch on a Micro-Budget](https://mlsanity.com/paper/2407.15811/) (2024)
- [FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale Fusion](https://mlsanity.com/paper/2412.09626/) (2024)
- [HiDiffusion: Unlocking Higher-Resolution Creativity and Efficiency in Pretrained Diffusion Models](https://mlsanity.com/paper/2311.17528/) (2023)
- [MegaFusion: Extend Diffusion Models towards Higher-resolution Image Generation without Further Tuning](https://mlsanity.com/paper/2408.11001/) (2024)
- [Training-free Diffusion Acceleration with Bottleneck Sampling](https://mlsanity.com/paper/2503.18940/) (2025)
- [Hierarchical Patch Diffusion Models for High-Resolution Video Generation](https://mlsanity.com/paper/2406.07792/) (2024)
- [RDEIC: Accelerating Diffusion-Based Extreme Image Compression with Relay Residual Diffusion](https://mlsanity.com/paper/2410.02640/) (2024)
- [I-Max: Maximize the Resolution Potential of Pre-trained Rectified Flow Transformers with Projected Flow](https://mlsanity.com/paper/2410.07536/) (2024)
- [ResMaster: Mastering High-Resolution Image Generation via Structural and Fine-Grained Guidance](https://mlsanity.com/paper/2406.16476/) (2024)
- [HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance](https://mlsanity.com/paper/2504.06232/) (2025)
- [FreCaS: Efficient Higher-Resolution Image Generation via Frequency-aware Cascaded Sampling](https://mlsanity.com/paper/2410.18410/) (2024)
- [Is One GPU Enough? Pushing Image Generation at Higher-Resolutions with Foundation Models](https://mlsanity.com/paper/2406.07251/) (2024)

## Abstract (arXiv)

Diffusion models achieved great success in image synthesis, but still face challenges in high-resolution generation. Through the lens of discrete cosine transformation, we find the main reason is that the same noise level on a higher resolution results in a higher Signal-to-Noise Ratio in the frequency domain. In this work, we present Relay Diffusion Model (RDM), which transfers a low-resolution image or noise into an equivalent high-resolution one for diffusion model via blurring diffusion and block noise. Therefore, the diffusion process can continue seamlessly in any new resolution or model without restarting from pure noise or low-resolution conditioning. RDM achieves state-of-the-art FID on CelebA-HQ and sFID on ImageNet 256×256, surpassing previous works such as ADM, LDM and DiT by a large margin. All the codes and checkpoints are open-sourced at urlhttps://github.com/THUDM/RelayDiffusion.