mlsanityData to 14 Oct 2026

PQCAD-DM: Progressive Quantization and Calibration-Assisted Distillation for Extremely Efficient Diffusion Model

arXiv 2506.16776 ↗First posted 20 Jun 2025cs.CV cs.AIcited by 0

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Diffusion models excel in image generation but are computational and resource-intensive due to their reliance on iterative Markov chain processes, leading to error accumulation and limiting the effectiveness of naive compression techniques. In this paper, we propose PQCAD-DM, a novel hybrid compression framework combining Progressive Quantization (PQ) and Calibration-Assisted Distillation (CAD) to address these challenges. PQ employs a two-stage quantization with adaptive bit-width transitions guided by a momentum-based mechanism, reducing excessive weight perturbations in low-precision. CAD leverages full-precision calibration datasets during distillation, enabling the student to match full-precision performance even with a quantized teacher. As a result, PQCAD-DM achieves a balance between computational efficiency and generative quality, halving inference time while maintaining competitive performance. Extensive experiments validate PQCAD-DM's superior generative capabilities and efficiency across diverse datasets, outperforming fixed-bit quantization methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 28 of its 30 references that are in the map. First posted on arXiv 20 Jun 2025.

Builds on

28 of 30 references.

Closest ancestors · 14

Same direction, newest first

  1. 2024LD-Pruner: Efficient Pruning of Latent Diffusion Models using Task-Agnostic Insights18 Apr
  2. 2023TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models27 Nov
  3. 2023Temporal Dynamic Quantization for Diffusion Models4 Jun
  4. 2023Structural Pruning for Diffusion Models18 May
  5. 2023Q-Diffusion: Quantizing Diffusion Models8 Feb
  6. 2022Post-training Quantization on Diffusion Models28 Nov
  7. 2022On Distillation of Guided Diffusion Models6 Oct
  8. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  9. 2021Variational Diffusion Models1 Jul
  10. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  11. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  12. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
2 more
  1. 2020Denoising Diffusion Implicit Models6 Oct
  2. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 14

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  2. 2022Generative Adversarial Networkscited by 5,627
  3. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,430
  4. 2019Learned Step Size Quantizationcited by 628
  5. 2020Up or Down? Adaptive Rounding for Post-Training Quantizationcited by 621
  6. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generationcited by 516
  7. 2021BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstructioncited by 479
  8. 2020Permutation Invariant Graph Generation via Score-Based Generative Modelingcited by 270
  9. 2022QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantizationcited by 180
  10. 2018Learning to Quantize Deep Networks by Optimizing Quantization Intervals with Task Losscited by 160
  11. 2017Towards Effective Low-bitwidth Convolutional Neural Networkscited by 78
  12. 2019Adaptive Loss-aware Quantization for Multi-bit Networkscited by 30
2 more
  1. 2019Effective Training of Convolutional Neural Networks with Low-bitwidth Weights and Activationscited by 18
  2. 2022CTMQ: Cyclic Training of Convolutional Neural Networks with Multiple Quantization Stepscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024PQD: Post-training Quantization for Efficient Diffusion Models
  2. 2024Efficiency Meets Fidelity: A Novel Quantization Framework for Stable Diffusion
  3. 2023Towards Accurate Post-training Quantization for Diffusion Models
  4. 2023Post-training Quantization for Text-to-Image Diffusion Models with Progressive Calibration and Activation Relaxing
  5. 2024BiDM: Pushing the Limit of Quantization for Diffusion Models
  6. 2024MPQ-DM: Mixed Precision Quantization for Extremely Low Bit Diffusion Models
  7. 2024Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers
  8. 2024Diffusion Product Quantization