# Towards Faster Training of Diffusion Models: An Inspiration of A Consistency Phenomenon

arXiv: https://arxiv.org/abs/2404.07946 · HTML: https://mlsanity.com/paper/2404.07946/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 36 of its 44 references that are in the map.
- First posted on arXiv 14 Mar 2024.

## Placed in

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

## Builds on (most cited first, 30 of 36)

- [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)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (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)
- [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)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2304.08818/) (2023)
- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [Imagic: Text-Based Real Image Editing with Diffusion Models](https://mlsanity.com/paper/2210.09276/) (2022)
- [Visualizing the Loss Landscape of Neural Nets](https://mlsanity.com/paper/1712.09913/) (2017)
- [Optimizing Neural Networks with Kronecker-factored Approximate Curvature](https://mlsanity.com/paper/1503.05671/) (2015)
- [All are Worth Words: A ViT Backbone for Diffusion Models](https://mlsanity.com/paper/2209.12152/) (2022)
- [VideoComposer: Compositional Video Synthesis with Motion Controllability](https://mlsanity.com/paper/2306.02018/) (2023)
- [Shampoo: Preconditioned Stochastic Tensor Optimization](https://mlsanity.com/paper/1802.09568/) (2018)
- [Perception Prioritized Training of Diffusion Models](https://mlsanity.com/paper/2204.00227/) (2022)
- [Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training](https://mlsanity.com/paper/2305.14342/) (2023)
- [Efficient Diffusion Training via Min-SNR Weighting Strategy](https://mlsanity.com/paper/2303.09556/) (2023)
- [Competence-based Curriculum Learning for Neural Machine Translation](https://mlsanity.com/paper/1903.09848/) (2019)
- [On the Importance of Noise Scheduling for Diffusion Models](https://mlsanity.com/paper/2301.10972/) (2023)
- [RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation](https://mlsanity.com/paper/2211.09869/) (2022)

## Built on by (most cited first, 14 of 14)

- [Curriculum Direct Preference Optimization for Diffusion and Consistency Models](https://mlsanity.com/paper/2405.13637/) (2024)
- [A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training](https://mlsanity.com/paper/2405.17403/) (2024)
- [Avoiding mode collapse in diffusion models fine-tuned with reinforcement learning](https://mlsanity.com/paper/2410.08315/) (2024)
- [Multi-scale Latent Point Consistency Models for 3D Shape Generation](https://mlsanity.com/paper/2412.19413/) (2024)
- [Efficient Generative Model Training via Embedded Representation Warmup](https://mlsanity.com/paper/2504.10188/) (2025)
- [UltraFlux: Data-Model Co-Design for High-quality Native 4K Text-to-Image Generation across Diverse Aspect Ratios](https://mlsanity.com/paper/2511.18050/) (2025)
- [Towards Dataset Copyright Evasion Attack against Personalized Text-to-Image Diffusion Models](https://mlsanity.com/paper/2505.02824/) (2025)
- [When Are Two Scores Better Than One? Investigating Ensembles of Diffusion Models](https://mlsanity.com/paper/2601.11444/) (2026)
- [Diffusion-based subsurface CO2 multiphysics monitoring and forecasting](https://mlsanity.com/paper/2407.18426/) (2024)
- [ProGen: Revisiting Probabilistic Spatial-Temporal Time Series Forecasting from a Continuous Generative Perspective Using Stochastic Differential Equations](https://mlsanity.com/paper/2411.01267/) (2024)
- [Disentanglement in T-space for Faster and Distributed Training of Diffusion Models with Fewer Latent-states](https://mlsanity.com/paper/2508.14413/) (2025)
- [Curriculum-DPO++: Direct Preference Optimization via Data and Model Curricula for Text-to-Image Generation](https://mlsanity.com/paper/2602.13055/) (2026)
- [Elucidating Representation Degradation Problem in Diffusion Model Training](https://mlsanity.com/paper/2605.10790/) (2026)
- [CenSynCMB: Centre Maps and Physics-Guided Synthesis for Microbleed Detection](https://mlsanity.com/paper/2607.05325/) (2026)

## Abstract (arXiv)

Diffusion models (DMs) are a powerful generative framework that have attracted significant attention in recent years. However, the high computational cost of training DMs limits their practical applications. In this paper, we start with a consistency phenomenon of DMs: we observe that DMs with different initializations or even different architectures can produce very similar outputs given the same noise inputs, which is rare in other generative models. We attribute this phenomenon to two factors: (1) the learning difficulty of DMs is lower when the noise-prediction diffusion model approaches the upper bound of the timestep (the input becomes pure noise), where the structural information of the output is usually generated; and (2) the loss landscape of DMs is highly smooth, which implies that the model tends to converge to similar local minima and exhibit similar behavior patterns. This finding not only reveals the stability of DMs, but also inspires us to devise two strategies to accelerate the training of DMs. First, we propose a curriculum learning based timestep schedule, which leverages the noise rate as an explicit indicator of the learning difficulty and gradually reduces the training frequency of easier timesteps, thus improving the training efficiency. Second, we propose a momentum decay strategy, which reduces the momentum coefficient during the optimization process, as the large momentum may hinder the convergence speed and cause oscillations due to the smoothness of the loss landscape. We demonstrate the effectiveness of our proposed strategies on various models and show that they can significantly reduce the training time and improve the quality of the generated images.