# Remix-DiT: Mixing Diffusion Transformers for Multi-Expert Denoising

arXiv: https://arxiv.org/abs/2412.05628 · HTML: https://mlsanity.com/paper/2412.05628/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 35 of its 39 references that are in the map.
- First posted on arXiv 7 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 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [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)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers](https://mlsanity.com/paper/2211.01324/) (2022)
- [Vector Quantized Diffusion Model for Text-to-Image Synthesis](https://mlsanity.com/paper/2111.14822/) (2021)
- [Latte: Latent Diffusion Transformer for Video Generation](https://mlsanity.com/paper/2401.03048/) (2024)
- [All are Worth Words: A ViT Backbone for Diffusion Models](https://mlsanity.com/paper/2209.12152/) (2022)
- [DeepCache: Accelerating Diffusion Models for Free](https://mlsanity.com/paper/2312.00858/) (2023)
- [MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer](https://mlsanity.com/paper/2303.14389/) (2023)
- [Structural Pruning for Diffusion Models](https://mlsanity.com/paper/2305.10924/) (2023)
- [Fast Training of Diffusion Models with Masked Transformers](https://mlsanity.com/paper/2306.09305/) (2023)
- [Diffusion Probabilistic Model Made Slim](https://mlsanity.com/paper/2211.17106/) (2022)
- [DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation](https://mlsanity.com/paper/2307.01831/) (2023)
- [Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis](https://mlsanity.com/paper/2402.14797/) (2024)
- [VDT: General-purpose Video Diffusion Transformers via Mask Modeling](https://mlsanity.com/paper/2305.13311/) (2023)
- [Deep Model Reassembly](https://mlsanity.com/paper/2210.17409/) (2022)
- [Factorizing Knowledge in Neural Networks](https://mlsanity.com/paper/2207.03337/) (2022)
- [Your ViT is Secretly a Hybrid Discriminative-Generative Diffusion Model](https://mlsanity.com/paper/2208.07791/) (2022)
- [OMS-DPM: Optimizing the Model Schedule for Diffusion Probabilistic Models](https://mlsanity.com/paper/2306.08860/) (2023)
- [Multi-Architecture Multi-Expert Diffusion Models](https://mlsanity.com/paper/2306.04990/) (2023)
- [T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching](https://mlsanity.com/paper/2402.14167/) (2024)

## Built on by (most cited first, 5 of 5)

- [DiffusionBlocks: Block-wise Neural Network Training via Diffusion Interpretation](https://mlsanity.com/paper/2506.14202/) (2025)
- [TimeStep Master: Asymmetrical Mixture of Timestep LoRA Experts for Versatile and Efficient Diffusion Models in Vision](https://mlsanity.com/paper/2503.07416/) (2025)
- [Monte Carlo Tree Diffusion with Multiple Experts for Protein Design](https://mlsanity.com/paper/2509.15796/) (2025)
- [LaTtE-Flow: Layerwise Timestep-Expert Flow-based Transformer](https://mlsanity.com/paper/2506.06952/) (2025)
- [DUET: A Diversity-Quality Duet of Distillation Experts for Two-Step Video Generation](https://mlsanity.com/paper/2608.09637/) (2026)

## Abstract (arXiv)

Transformer-based diffusion models have achieved significant advancements across a variety of generative tasks. However, producing high-quality outputs typically necessitates large transformer models, which result in substantial training and inference overhead. In this work, we investigate an alternative approach involving multiple experts for denoising, and introduce Remix-DiT, a novel method designed to enhance output quality at a low cost. The goal of Remix-DiT is to craft N diffusion experts for different denoising timesteps, yet without the need for expensive training of N independent models. To achieve this, Remix-DiT employs K basis models (where K < N) and utilizes learnable mixing coefficients to adaptively craft expert models. This design offers two significant advantages: first, although the total model size is increased, the model produced by the mixing operation shares the same architecture as a plain model, making the overall model as efficient as a standard diffusion transformer. Second, the learnable mixing adaptively allocates model capacity across timesteps, thereby effectively improving generation quality. Experiments conducted on the ImageNet dataset demonstrate that Remix-DiT achieves promising results compared to standard diffusion transformers and other multiple-expert methods. The code is available at https://github.com/VainF/Remix-DiT.