mlsanityData to 14 Oct 2026

Modulated Diffusion: Accelerating Generative Modeling with Modulated Quantization

arXiv 2506.22463 ↗First posted 18 Jun 2025cs.CV cs.LGcited by 5

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Diffusion models have emerged as powerful generative models, but their high computation cost in iterative sampling remains a significant bottleneck. In this work, we present an in-depth and insightful study of state-of-the-art acceleration techniques for diffusion models, including caching and quantization, revealing their limitations in computation error and generation quality. To break these limits, this work introduces Modulated Diffusion (MoDiff), an innovative, rigorous, and principled framework that accelerates generative modeling through modulated quantization and error compensation. MoDiff not only inherents the advantages of existing caching and quantization methods but also serves as a general framework to accelerate all diffusion models. The advantages of MoDiff are supported by solid theoretical insight and analysis. In addition, extensive experiments on CIFAR-10 and LSUN demonstrate that MoDiff significant reduces activation quantization from 8 bits to 3 bits without performance degradation in post-training quantization (PTQ). Our code implementation is available at https://github.com/WeizhiGao/MoDiff.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 37 of its 40 references that are in the map. First posted on arXiv 18 Jun 2025.

Builds on

37 of 40 references.

Closest ancestors · 24

Same direction, newest first

  1. 2024MPQ-DM: Mixed Precision Quantization for Extremely Low Bit Diffusion Models16 Dec
  2. 2024D4M: Dataset Distillation via Disentangled Diffusion Model21 Jul
  3. 2024ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation4 Jun
  4. 2024Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching3 Jun
  5. 2024Delta-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers3 Jun
  6. 2024MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization28 May
  7. 2024PTQ4DiT: Post-training Quantization for Diffusion Transformers25 May
  8. 2023Cache Me if You Can: Accelerating Diffusion Models through Block Caching6 Dec
  9. 2023DeepCache: Accelerating Diffusion Models for Free1 Dec
  10. 2023TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models27 Nov
  11. 2023EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models5 Oct
  12. 2023Towards Accurate Post-training Quantization for Diffusion Models30 May
12 more
  1. 2023PTQD: Accurate Post-Training Quantization for Diffusion Models18 May
  2. 2023Q-Diffusion: Quantizing Diffusion Models8 Feb
  3. 2022Scalable Diffusion Models with Transformers19 Dec
  4. 2022Post-training Quantization on Diffusion Models28 Nov
  5. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps2 Jun
  6. 2022Pseudo Numerical Methods for Diffusion Models on Manifolds20 Feb
  7. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  8. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  9. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  10. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  11. 2020Denoising Diffusion Implicit Models6 Oct
  12. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 13

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  3. 2016Improved Techniques for Training GANscited by 2,970
  4. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  5. 2022SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Modelscited by 1,386
  6. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  7. 2022LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scalecited by 906
  8. 2022Equivariant Diffusion for Molecule Generation in 3Dcited by 677
  9. 2021BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstructioncited by 479
  10. 2021A White Paper on Neural Network Quantizationcited by 472
  11. 2018Assessing Generative Models via Precision and Recallcited by 406
  12. 2019Quantization Networkscited by 153
1 more
  1. 2022Overcoming Oscillations in Quantization-Aware Trainingcited by 119

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 2.

5 papers.

  1. 2025Are Image-to-Video Models Good Zero-Shot Image Editors?cited by 4
  2. 2025Decoding Memories: An Efficient Pipeline for Self-Consistency Hallucination Detectioncited by 2
  3. 2026Stratified Consistency Distillation for Natural Language Formalizationcited by 1
  4. 2025HQ-DM: Single Hadamard Transformation-Based Quantization-Aware Training for Low-Bit Diffusion Modelscited by 0
  5. 2026ManifoldCache: Training-Free Diffusion Acceleration via Constraint Manifold Cachingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Diffusion Model Quantization: A Review
  2. 2024Memory-Efficient Fine-Tuning for Quantized Diffusion Model
  3. 2024PQD: Post-training Quantization for Efficient Diffusion Models
  4. 2025CacheQuant: Comprehensively Accelerated Diffusion Models
  5. 2025SQ-DM: Accelerating Diffusion Models with Aggressive Quantization and Temporal Sparsity
  6. 2024TMPQ-DM: Joint Timestep Reduction and Quantization Precision Selection for Efficient Diffusion Models
  7. 2023Effective Quantization for Diffusion Models on CPUs
  8. 2026Chameleon: Dynamic Format Adapter for Efficient Diffusion