# Exploring Magnitude Preservation and Rotation Modulation in Diffusion Transformers

arXiv: https://arxiv.org/abs/2505.19122 · HTML: https://mlsanity.com/paper/2505.19122/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 14 of its 17 references that are in the map.
- First posted on arXiv 25 May 2025.

## Placed in

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

## Builds on (most cited first, 14 of 14)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning](https://mlsanity.com/paper/1702.03118/) (2017)
- [Analyzing and Improving the Training Dynamics of Diffusion Models](https://mlsanity.com/paper/2312.02696/) (2023)
- [Generating Images with Sparse Representations](https://mlsanity.com/paper/2103.03841/) (2021)
- [Cosine Normalization: Using Cosine Similarity Instead of Dot Product in Neural Networks](https://mlsanity.com/paper/1702.05870/) (2017)
- [Enhancing Few-shot Image Classification with Cosine Transformer](https://mlsanity.com/paper/2211.06828/) (2022)

## Abstract (arXiv)

Denoising diffusion models exhibit remarkable generative capabilities, but remain challenging to train due to their inherent stochasticity, where high-variance gradient estimates lead to slow convergence. Previous works have shown that magnitude preservation helps with stabilizing training in the U-net architecture. This work explores whether this effect extends to the Diffusion Transformer (DiT) architecture. As such, we propose a magnitude-preserving design that stabilizes training without normalization layers. Motivated by the goal of maintaining activation magnitudes, we additionally introduce rotation modulation, which is a novel conditioning method using learned rotations instead of traditional scaling or shifting. Through empirical evaluations and ablation studies on small-scale models, we show that magnitude-preserving strategies significantly improve performance, notably reducing FID scores by ~12.8%. Further, we show that rotation modulation combined with scaling is competitive with AdaLN, while requiring ~5.4% fewer parameters. This work provides insights into conditioning strategies and magnitude control. We will publicly release the implementation of our method.