mlsanityData to 14 Oct 2026

CAT Pruning: Cluster-Aware Token Pruning For Text-to-Image Diffusion Models

arXiv 2502.00433 ↗First posted 1 Feb 2025cs.CVcited by 16

On the map: Diffusion models → Diffusion foundations and sampling

also in 1 more
Abstract (arXiv)

Diffusion models have revolutionized generative tasks, especially in the domain of text-to-image synthesis; however, their iterative denoising process demands substantial computational resources. In this paper, we present a novel acceleration strategy that integrates token-level pruning with caching techniques to tackle this computational challenge. By employing noise relative magnitude, we identify significant token changes across denoising iterations. Additionally, we enhance token selection by incorporating spatial clustering and ensuring distributional balance. Our experiments demonstrate reveal a 50%-60% reduction in computational costs while preserving the performance of the model, thereby markedly increasing the efficiency of diffusion models. The code is available at https://github.com/ada-cheng/CAT-Pruning

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 25 of its 36 references that are in the map. First posted on arXiv 1 Feb 2025.

Builds on

25 of 36 references.

Closest ancestors · 17

Same direction, newest first

  1. 2024FORA: Fast-Forward Caching in Diffusion Transformer Acceleration1 Jul
  2. 2024Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching3 Jun
  3. 2024Attention-Driven Training-Free Efficiency Enhancement of Diffusion Models8 May
  4. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesis5 Mar
  5. 2024DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models29 Feb
  6. 2023Cache Me if You Can: Accelerating Diffusion Models through Block Caching6 Dec
  7. 2023DeepCache: Accelerating Diffusion Models for Free1 Dec
  8. 2023Improved Techniques for Training Consistency Models22 Oct
  9. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis30 Sep
  10. 2023Consistency Models2 Mar
  11. 2022Scalable Diffusion Models with Transformers19 Dec
  12. 2022Classifier-Free Diffusion Guidance26 Jul
5 more
  1. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps2 Jun
  2. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  3. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  5. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 8

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  5. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,424
  6. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,295
  7. 2024Faster Diffusion via Temporal Attention Decompositioncited by 54
  8. 2015Staleness-aware Async-SGD for Distributed Deep Learningcited by 43

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 7; 2026: 9.

16 papers.

Sort:

By area:

  1. 2025From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeerscited by 136
  2. 2025Training-free and Adaptive Sparse Attention for Efficient Long Video Generationcited by 69
  3. 2025Playing with Transformer at 30+ FPS via Next-Frame Diffusioncited by 20
  4. 2025Let Features Decide Their Own Solvers: Hybrid Feature Caching for Diffusion Transformerscited by 10
  5. 2025Don't Run with Scissors: Pruning Breaks VLA Models but They Can Be Recoveredcited by 8
  6. 2026DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Cachingcited by 7
  7. 2026Adaptive Spectral Feature Forecasting for Diffusion Sampling Accelerationcited by 7
  8. 2025Forecasting When to Forecast: Accelerating Diffusion Models with Confidence-Gated Taylorcited by 6
  9. 2026Forecast the Principal, Stabilize the Residual: Subspace-Aware Feature Caching for Efficient Diffusion Transformerscited by 4
  10. 2026DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformerscited by 4
  11. 2026LinCa: Accelerating Diffusion Models via Learnable Decomposed Feature Cachingcited by 1
  12. 2025CorGi: Contribution-Guided Block-Wise Interval Caching for Training-Free Acceleration of Diffusion Transformerscited by 0
4 more
  1. 2026RemEdit: Efficient Diffusion Editing with Riemannian Geometrycited by 0
  2. 2026NanoFLUX: Distillation-Driven Compression of Large Text-to-Image Generation Models for Mobile Devicescited by 0
  3. 2026SODA: Sensitivity-Oriented Dynamic Acceleration for Diffusion Transformercited by 0
  4. 2026Dynamic Video Generation: Shaping Video Generation Across Time and Spacecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Token Pruning for Caching Better: 9 Times Acceleration on Stable Diffusion for Free
  2. 2024Efficient Pruning of Text-to-Image Models: Insights from Pruning Stable Diffusion
  3. 2025Reusing Computation in Text-to-Image Diffusion for Efficient Generation of Image Sets
  4. 2025FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings
  5. 2025Cached Adaptive Token Merging: Dynamic Token Reduction and Redundant Computation Elimination in Diffusion Model
  6. 2023Adaptive Training Meets Progressive Scaling: Elevating Efficiency in Diffusion Models
  7. 2024Not All Prompts Are Made Equal: Prompt-based Pruning of Text-to-Image Diffusion Models
  8. 2023TokenCompose: Text-to-Image Diffusion with Token-level Supervision