# A Simple Early Exiting Framework for Accelerated Sampling in Diffusion Models

arXiv: https://arxiv.org/abs/2408.05927 · HTML: https://mlsanity.com/paper/2408.05927/

## Key facts

- Cited by 13 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 47 references that are in the map.
- First posted on arXiv 12 Aug 2024.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)
- Efficient LLM inference and serving / [Visual token pruning in multimodal models](https://mlsanity.com/inference/visual-token-pruning-in-multimodal-models/)

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [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)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [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)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (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 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)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [Cascaded Diffusion Models for High Fidelity Image Generation](https://mlsanity.com/paper/2106.15282/) (2021)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [Diffusion Probabilistic Models for 3D Point Cloud Generation](https://mlsanity.com/paper/2103.01458/) (2021)
- [Fast Sampling of Diffusion Models with Exponential Integrator](https://mlsanity.com/paper/2204.13902/) (2022)
- [Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion](https://mlsanity.com/paper/2310.02279/) (2023)
- [Improved Techniques for Training Consistency Models](https://mlsanity.com/paper/2310.14189/) (2023)
- [Confident Adaptive Language Modeling](https://mlsanity.com/paper/2207.07061/) (2022)
- [DynaBERT: Dynamic BERT with Adaptive Width and Depth](https://mlsanity.com/paper/2004.04037/) (2020)
- [Token Merging for Fast Stable Diffusion](https://mlsanity.com/paper/2303.17604/) (2023)

## Built on by (most cited first, 13 of 13)

- [Dynamic Diffusion Transformer](https://mlsanity.com/paper/2410.03456/) (2024)
- [Efficient Diffusion Models: A Survey](https://mlsanity.com/paper/2502.06805/) (2025)
- [Presto! Distilling Steps and Layers for Accelerating Music Generation](https://mlsanity.com/paper/2410.05167/) (2024)
- [TC-Pad'e: Trajectory-Consistent Pad'e Approximation for Diffusion Acceleration](https://mlsanity.com/paper/2603.02943/) (2026)
- [DC-DiT: Adaptive Compute and Elastic Inference for Visual Generation via Dynamic Chunking](https://mlsanity.com/paper/2603.06351/) (2026)
- [Toward Early Quality Assessment of Text-to-Image Diffusion Models](https://mlsanity.com/paper/2603.02829/) (2026)
- [DyDiT++: Diffusion Transformers with Timestep and Spatial Dynamics for Efficient Visual Generation](https://mlsanity.com/paper/2504.06803/) (2025)
- [Progressive Refinement Regulation for Accelerating Diffusion Language Model Decoding](https://mlsanity.com/paper/2603.04514/) (2026)
- [SoundWeaver: Semantic Warm-Starting for Text-to-Audio Diffusion Serving](https://mlsanity.com/paper/2603.07865/) (2026)
- [PhysEdit: Physically-Consistent Region-Aware Image Editing via Adaptive Spatio-Temporal Reasoning](https://mlsanity.com/paper/2605.00707/) (2026)
- [Muninn: Your Trajectory Diffusion Model But Faster](https://mlsanity.com/paper/2605.09999/) (2026)
- [Toward a mechanistic understanding of inference in visual cortex and diffusion models](https://mlsanity.com/paper/2607.15693/) (2026)
- [ReAL: Accelerating Flow Matching through Segment Advancement with Shared Lookahead](https://mlsanity.com/paper/2609.33202/) (2026)

## Abstract (arXiv)

Diffusion models have shown remarkable performance in generation problems over various domains including images, videos, text, and audio. A practical bottleneck of diffusion models is their sampling speed, due to the repeated evaluation of score estimation networks during the inference. In this work, we propose a novel framework capable of adaptively allocating compute required for the score estimation, thereby reducing the overall sampling time of diffusion models. We observe that the amount of computation required for the score estimation may vary along the time step for which the score is estimated. Based on this observation, we propose an early-exiting scheme, where we skip the subset of parameters in the score estimation network during the inference, based on a time-dependent exit schedule. Using the diffusion models for image synthesis, we show that our method could significantly improve the sampling throughput of the diffusion models without compromising image quality. Furthermore, we also demonstrate that our method seamlessly integrates with various types of solvers for faster sampling, capitalizing on their compatibility to enhance overall efficiency. The source code and our experiments are available at urlhttps://github.com/taehong-moon/ee-diffusion