mlsanityData to 7 Oct 2026

PQD: Post-training Quantization for Efficient Diffusion Models

arXiv 2501.00124 ↗First posted 30 Dec 2024cs.CV cs.LGcited by 6

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Diffusionmodels(DMs)havedemonstratedremarkableachievements in synthesizing images of high fidelity and diversity. However, the extensive computational requirements and slow generative speed of diffusion models have limited their widespread adoption. In this paper, we propose a novel post-training quantization for diffusion models (PQD), which is a time-aware optimization framework for diffusion models based on post-training quantization. The proposed framework optimizes the inference process by selecting representative samples and conducting time-aware calibration. Experimental results show that our proposed method is able to directly quantize full-precision diffusion models into 8-bit or 4-bit models while maintaining comparable performance in a training-free manner, achieving a few FID change on ImageNet for unconditional image generation. Our approach demonstrates compatibility and can also be applied to 512x512 text-guided image generation for the first time.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 34 of its 41 references that are in the map. First posted on arXiv 30 Dec 2024.

Builds on

34 of 41 references.

Closest ancestors · 17

Same direction, newest first

  1. 2023PTQD: Accurate Post-Training Quantization for Diffusion Models18 May
  2. 2023TRACT: Denoising Diffusion Models with Transitive Closure Time-Distillation7 Mar
  3. 2023Consistency Models2 Mar
  4. 2022Post-training Quantization on Diffusion Models28 Nov
  5. 2022Blurring Diffusion Models12 Sep
  6. 2022Soft Diffusion: Score Matching for General Corruptions12 Sep
  7. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  8. 2022Accelerating Diffusion Models via Early Stop of the Diffusion Process25 May
  9. 2022Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models17 Jan
  10. 2022DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents2 Jan
  11. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  12. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANs15 Dec
5 more
  1. 2021On Fast Sampling of Diffusion Probabilistic Models31 May
  2. 2021UNIT-DDPM: UNpaired Image Translation with Denoising Diffusion Probabilistic Models12 Apr
  3. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  4. 2020Denoising Diffusion Implicit Models6 Oct
  5. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 17

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  4. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  5. 2016Improved Techniques for Training GANscited by 2,938
  6. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 620
  7. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generationcited by 511
  8. 2021BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstructioncited by 464
  9. 2019Data-Free Quantization Through Weight Equalization and Bias Correctioncited by 328
  10. 2020Permutation Invariant Graph Generation via Score-Based Generative Modelingcited by 263
  11. 2019Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networkscited by 234
  12. 2022QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantizationcited by 175
5 more
  1. 2022DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detectioncited by 153
  2. 2017Towards Effective Low-bitwidth Convolutional Neural Networkscited by 76
  3. 2022Patch Similarity Aware Data-Free Quantization for Vision Transformerscited by 55
  4. 2022Zero-Shot Voice Conditioning for Denoising Diffusion TTS Modelscited by 20
  5. 2019A Generative Map for Image-based Camera Localizationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 5.

6 papers.

  1. 2025TS-DP: Reinforcement Speculative Decoding For Temporal Adaptive Diffusion Policy Accelerationcited by 6
  2. 2026AdaCluster: Adaptive Query-Key Clustering for Sparse Attention in Video Generationcited by 5
  3. 2026Holding the FP8 Quality Ceiling at 8-Bit Weights and Activations: INT8 and GGUF Post-Training Quantization of Ideogram 4.0 for Consumer GPUscited by 1
  4. 2026TMPDiff: Temporal Mixed-Precision for Diffusion Modelscited by 0
  5. 2026Realizing Native INT8 Compute for Diffusion Transformers on Consumer GPUs: A Fused INT8 GEMM Kernel for Ideogram 4.0cited by 0
  6. 2026Post-training Quantization for Hybrid Iterative Generative Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Towards Accurate Post-training Quantization for Diffusion Models
  2. 2024Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers
  3. 2023Q-Diffusion: Quantizing Diffusion Models
  4. 2023Post-training Quantization for Text-to-Image Diffusion Models with Progressive Calibration and Activation Relaxing
  5. 2025Diffusion Model Quantization: A Review
  6. 2023EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models
  7. 2025PQCAD-DM: Progressive Quantization and Calibration-Assisted Distillation for Extremely Efficient Diffusion Model
  8. 2024TMPQ-DM: Joint Timestep Reduction and Quantization Precision Selection for Efficient Diffusion Models