# Token Merging for Fast Stable Diffusion

arXiv: https://arxiv.org/abs/2303.17604 · HTML: https://mlsanity.com/paper/2303.17604/

## Key facts

- Cited by 224 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 17 of its 27 references that are in the map.
- First posted on arXiv 30 Mar 2023.

## 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, 17 of 17)

- [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)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [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)
- [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)
- [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)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [Pseudo Numerical Methods for Diffusion Models on Manifolds](https://mlsanity.com/paper/2202.09778/) (2022)
- [AdaViT: Adaptive Tokens for Efficient Vision Transformer](https://mlsanity.com/paper/2112.07658/) (2021)
- [AdaViT: Adaptive Vision Transformers for Efficient Image Recognition](https://mlsanity.com/paper/2111.15668/) (2021)
- [Token Pooling in Vision Transformers](https://mlsanity.com/paper/2110.03860/) (2021)

## Built on by (most cited first, 30 of 224)

- [DeepCache: Accelerating Diffusion Models for Free](https://mlsanity.com/paper/2312.00858/) (2023)
- [Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model](https://mlsanity.com/paper/2411.19108/) (2024)
- [Accelerating Diffusion Transformers with Token-wise Feature Caching](https://mlsanity.com/paper/2410.05317/) (2024)
- [Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning](https://mlsanity.com/paper/2308.06038/) (2023)
- [From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers](https://mlsanity.com/paper/2503.06923/) (2025)
- [Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiT](https://mlsanity.com/paper/2406.18583/) (2024)
- [Token Fusion: Bridging the Gap between Token Pruning and Token Merging](https://mlsanity.com/paper/2312.01026/) (2023)
- [FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality](https://mlsanity.com/paper/2410.19355/) (2024)
- [VidToMe: Video Token Merging for Zero-Shot Video Editing](https://mlsanity.com/paper/2312.10656/) (2023)
- [Adaptive Caching for Faster Video Generation with Diffusion Transformers](https://mlsanity.com/paper/2411.02397/) (2024)
- [FastVGGT: Training-Free Acceleration of Visual Geometry Transformer](https://mlsanity.com/paper/2509.02560/) (2025)
- [Agent Attention: On the Integration of Softmax and Linear Attention](https://mlsanity.com/paper/2312.08874/) (2023)
- [RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models](https://mlsanity.com/paper/2412.07679/) (2024)
- [DiffRate : Differentiable Compression Rate for Efficient Vision Transformers](https://mlsanity.com/paper/2305.17997/) (2023)
- [Training-free and Adaptive Sparse Attention for Efficient Long Video Generation](https://mlsanity.com/paper/2502.21079/) (2025)
- [LD-Pruner: Efficient Pruning of Latent Diffusion Models using Task-Agnostic Insights](https://mlsanity.com/paper/2404.11936/) (2024)
- [QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models](https://mlsanity.com/paper/2310.08041/) (2023)
- [Zero-TPrune: Zero-Shot Token Pruning through Leveraging of the Attention Graph in Pre-Trained Transformers](https://mlsanity.com/paper/2305.17328/) (2023)
- [Dynamic Diffusion Transformer](https://mlsanity.com/paper/2410.03456/) (2024)
- [OminiControl2: Efficient Conditioning for Diffusion Transformers](https://mlsanity.com/paper/2503.08280/) (2025)
- [Faster Diffusion via Temporal Attention Decomposition](https://mlsanity.com/paper/2404.02747/) (2024)
- [Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodality](https://mlsanity.com/paper/2505.18227/) (2025)
- [EEdit: Rethinking the Spatial and Temporal Redundancy for Efficient Image Editing](https://mlsanity.com/paper/2503.10270/) (2025)
- [Less is Enough: Training-Free Video Diffusion Acceleration via Runtime-Adaptive Caching](https://mlsanity.com/paper/2507.02860/) (2025)
- [Diffusion Model-Based Video Editing: A Survey](https://mlsanity.com/paper/2407.07111/) (2024)
- [Follow-Your-Emoji-Faster: Towards Efficient, Fine-Controllable, and Expressive Freestyle Portrait Animation](https://mlsanity.com/paper/2509.16630/) (2025)
- [vid-TLDR: Training Free Token merging for Light-weight Video Transformer](https://mlsanity.com/paper/2403.13347/) (2024)
- [MagCache: Fast Video Generation with Magnitude-Aware Cache](https://mlsanity.com/paper/2506.09045/) (2025)
- [LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence](https://mlsanity.com/paper/2605.25979/) (2026)
- [Attention-Driven Training-Free Efficiency Enhancement of Diffusion Models](https://mlsanity.com/paper/2405.05252/) (2024)

## Abstract (arXiv)

The landscape of image generation has been forever changed by open vocabulary diffusion models. However, at their core these models use transformers, which makes generation slow. Better implementations to increase the throughput of these transformers have emerged, but they still evaluate the entire model. In this paper, we instead speed up diffusion models by exploiting natural redundancy in generated images by merging redundant tokens. After making some diffusion-specific improvements to Token Merging (ToMe), our ToMe for Stable Diffusion can reduce the number of tokens in an existing Stable Diffusion model by up to 60% while still producing high quality images without any extra training. In the process, we speed up image generation by up to 2x and reduce memory consumption by up to 5.6x. Furthermore, this speed-up stacks with efficient implementations such as xFormers, minimally impacting quality while being up to 5.4x faster for large images. Code is available at https://github.com/dbolya/tomesd.