mlsanityData to 7 Oct 2026

DGQ: Distribution-Aware Group Quantization for Text-to-Image Diffusion Models

arXiv 2501.04304 ↗First posted 8 Jan 2025cs.CV cs.LGcited by 11

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Despite the widespread use of text-to-image diffusion models across various tasks, their computational and memory demands limit practical applications. To mitigate this issue, quantization of diffusion models has been explored. It reduces memory usage and computational costs by compressing weights and activations into lower-bit formats. However, existing methods often struggle to preserve both image quality and text-image alignment, particularly in lower-bit(< 8bits) quantization. In this paper, we analyze the challenges associated with quantizing text-to-image diffusion models from a distributional perspective. Our analysis reveals that activation outliers play a crucial role in determining image quality. Additionally, we identify distinctive patterns in cross-attention scores, which significantly affects text-image alignment. To address these challenges, we propose Distribution-aware Group Quantization (DGQ), a method that identifies and adaptively handles pixel-wise and channel-wise outliers to preserve image quality. Furthermore, DGQ applies prompt-specific logarithmic quantization scales to maintain text-image alignment. Our method demonstrates remarkable performance on datasets such as MS-COCO and PartiPrompts. We are the first to successfully achieve low-bit quantization of text-to-image diffusion models without requiring additional fine-tuning of weight quantization parameters. Code is available at https://github.com/ugonfor/DGQ.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 38 of its 42 references that are in the map. First posted on arXiv 8 Jan 2025.

Builds on

38 of 42 references.

Closest ancestors · 14

Same direction, newest first

  1. 2024BitsFusion: 1.99 bits Weight Quantization of Diffusion Model6 Jun
  2. 2024MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization28 May
  3. 2024QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning6 Feb
  4. 2024Memory-Efficient Fine-Tuning for Quantized Diffusion Model9 Jan
  5. 2023TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models27 Nov
  6. 2023Post-training Quantization for Text-to-Image Diffusion Models with Progressive Calibration and Activation Relaxing10 Nov
  7. 2023EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models5 Oct
  8. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis4 Jul
  9. 2023Temporal Dynamic Quantization for Diffusion Models4 Jun
  10. 2023PTQD: Accurate Post-Training Quantization for Diffusion Models18 May
  11. 2023Q-Diffusion: Quantizing Diffusion Models8 Feb
  12. 2022Post-training Quantization on Diffusion Models28 Nov
2 more
  1. 2022Efficient Diffusion Models for Vision: A Survey7 Oct
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec

Other references · 24

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  3. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  4. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  5. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  6. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  7. 2016Improved Techniques for Training GANscited by 2,938
  8. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,287
  9. 2023ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generationcited by 1,010
  10. 2023Vision Transformers Need Registerscited by 844
  11. 2023GLIGEN: Open-Set Grounded Text-to-Image Generationcited by 774
  12. 2019Learned Step Size Quantizationcited by 604
12 more
  1. 2020Up or Down? Adaptive Rounding for Post-Training Quantizationcited by 600
  2. 2022MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessmentcited by 514
  3. 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 507
  4. 2021BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstructioncited by 464
  5. 2023A Survey on Model Compression for Large Language Modelscited by 263
  6. 2022QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantizationcited by 175
  7. 2018Learning to Quantize Deep Networks by Optimizing Quantization Intervals with Task Losscited by 157
  8. 2021FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformercited by 148
  9. 2021Understanding and Overcoming the Challenges of Efficient Transformer Quantizationcited by 139
  10. 2022RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformerscited by 134
  11. 2023Memory-Efficient Fine-Tuning of Compressed Large Language Models via sub-4-bit Integer Quantizationcited by 97
  12. 2022I-ViT: Integer-only Quantization for Efficient Vision Transformer Inferencecited by 93

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 6; 2026: 5.

11 papers.

  1. 2025Low-bit Model Quantization for Deep Neural Networks: A Surveycited by 11
  2. 2025Diffusion Model Quantization: A Reviewcited by 6
  3. 2026PersonalQ: Select, Quantize, and Serve Personalized Diffusion Models for Efficient Inferencecited by 6
  4. 2025Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image Generationcited by 4
  5. 2025Are Image-to-Video Models Good Zero-Shot Image Editors?cited by 4
  6. 2026Q-Drift: Quantization-Aware Drift Correction for Diffusion Model Samplingcited by 3
  7. 2026DiRotQ: Rotation-Aware Quantization for 4-bit Diffusion Transformerscited by 3
  8. 2025Post-Training Quantization via Residual Truncation and Zero Suppression for Diffusion Modelscited by 1
  9. 2025HQ-DM: Single Hadamard Transformation-Based Quantization-Aware Training for Low-Bit Diffusion Modelscited by 0
  10. 2026TMPDiff: Temporal Mixed-Precision for Diffusion Modelscited by 0
  11. 2026JustQuant: You Don't Need Smoothing, SVD, or Rotation for 4-Bit Activation Quantizationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Accurate Compression of Text-to-Image Diffusion Models via Vector Quantization
  2. 2025DMQ: Dissecting Outliers of Diffusion Models for Post-Training Quantization
  3. 2024Data-Free Group-Wise Fully Quantized Winograd Convolution via Learnable Scales
  4. 2026PermuQuant: Lowering Per-Group Quantization Error by Reordering Channels for Diffusion Models
  5. 2024Debiasing Text-to-Image Diffusion Models
  6. 2026i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models
  7. 2025LRQ-DiT: Log-Rotation Post-Training Quantization of Diffusion Transformers for Image and Video Generation
  8. 2024Efficiency Meets Fidelity: A Novel Quantization Framework for Stable Diffusion