# Importance-Based Token Merging for Efficient Image and Video Generation

arXiv: https://arxiv.org/abs/2411.16720 · HTML: https://mlsanity.com/paper/2411.16720/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 101 of its 117 references that are in the map.
- First posted on arXiv 23 Nov 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 101)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [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)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [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)
- [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)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [Zero-1-to-3: Zero-shot One Image to 3D Object](https://mlsanity.com/paper/2303.11328/) (2023)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [DiffWave: A Versatile Diffusion Model for Audio Synthesis](https://mlsanity.com/paper/2009.09761/) (2020)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models](https://mlsanity.com/paper/2211.01095/) (2022)
- [eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers](https://mlsanity.com/paper/2211.01324/) (2022)
- [WorldSimBench: Towards Video Generation Models as World Simulators](https://mlsanity.com/paper/2410.18072/) (2024)

## Built on by (most cited first, 22 of 22)

- [A Survey on Cache Methods in Diffusion Models: Toward Efficient Multi-Modal Generation](https://mlsanity.com/paper/2510.19755/) (2025)
- [Sparse Forcing: Native Trainable Sparse Attention for Real-time Autoregressive Diffusion Video Generation](https://mlsanity.com/paper/2604.21221/) (2026)
- [Motion Prior Distillation in Time Reversal Sampling for Generative Inbetweening](https://mlsanity.com/paper/2602.12679/) (2026)
- [Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms](https://mlsanity.com/paper/2603.28489/) (2026)
- [One Model, Many Budgets: Elastic Latent Interfaces for Diffusion Transformers](https://mlsanity.com/paper/2603.12245/) (2026)
- [AccelAes: Accelerating Diffusion Transformers for Training-Free Aesthetic-Enhanced Image Generation](https://mlsanity.com/paper/2603.12575/) (2026)
- [Foveated Diffusion: Efficient Spatially Adaptive Image and Video Generation](https://mlsanity.com/paper/2603.23491/) (2026)
- [DC-DiT: Adaptive Compute and Elastic Inference for Visual Generation via Dynamic Chunking](https://mlsanity.com/paper/2603.06351/) (2026)
- [Phase-Aligned RoPE for Mixed-Resolution Diffusion Transformer](https://mlsanity.com/paper/2511.19778/) (2025)
- [Stay Unique, Stay Efficient: Preserving Model Personality in Multi-Task Merging](https://mlsanity.com/paper/2512.01461/) (2025)
- [Token Pruning for In-Context Generation in Diffusion Transformers](https://mlsanity.com/paper/2602.01609/) (2026)
- [Shiva-DiT: Residual-Based Differentiable Top-k Selection for Efficient Diffusion Transformers](https://mlsanity.com/paper/2602.05605/) (2026)
- [Elastic Token Compression for Pixel-Space Diffusion Transformers](https://mlsanity.com/paper/2608.29281/) (2026)
- [ReGATE: Learning Faster and Better with Fewer Tokens in MLLMs](https://mlsanity.com/paper/2507.21420/) (2025)
- [Video Compression Meets Video Generation: Latent Inter-Frame Pruning with Attention Recovery](https://mlsanity.com/paper/2603.05811/) (2026)
- [Cast and Attached Shadow Detection via Iterative Light and Geometry Reasoning](https://mlsanity.com/paper/2512.06179/) (2025)
- [NanoFLUX: Distillation-Driven Compression of Large Text-to-Image Generation Models for Mobile Devices](https://mlsanity.com/paper/2602.06879/) (2026)
- [Latent Inter-Frame Pruning: A Training-Free Method Bridging Traditional Video Compression and Modern Diffusion Transformers for Efficient Generation](https://mlsanity.com/paper/2604.23858/) (2026)
- [Keep The Essentials: Efficient Reference Conditioned Generation via Token Dropping](https://mlsanity.com/paper/2606.23682/) (2026)
- [Importance-Aware OBS Pruning for Diffusion Models](https://mlsanity.com/paper/2607.20048/) (2026)
- [Level-of-Token Diffusion](https://mlsanity.com/paper/2610.05816/) (2026)
- [BigCell: Generating Gigapixel Whole-Slide Images](https://mlsanity.com/paper/2610.14261/) (2026)

## Abstract (arXiv)

Token merging can effectively accelerate various vision systems by processing groups of similar tokens only once and sharing the results across them. However, existing token grouping methods are often ad hoc and random, disregarding the actual content of the samples. We show that preserving high-information tokens during merging - those essential for semantic fidelity and structural details - significantly improves sample quality, producing finer details and more coherent, realistic generations. Despite being simple and intuitive, this approach remains underexplored. To do so, we propose an importance-based token merging method that prioritizes the most critical tokens in computational resource allocation, leveraging readily available importance scores, such as those from classifier-free guidance in diffusion models. Experiments show that our approach significantly outperforms baseline methods across multiple applications, including text-to-image synthesis, multi-view image generation, and video generation with various model architectures such as Stable Diffusion, Zero123++, AnimateDiff, or PixArt-α.