# QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning

arXiv: https://arxiv.org/abs/2402.03666 · HTML: https://mlsanity.com/paper/2402.03666/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 34 of its 52 references that are in the map.
- First posted on arXiv 6 Feb 2024.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 30 of 34)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop](https://mlsanity.com/paper/1506.03365/) (2015)
- [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022)
- [A Survey of Quantization Methods for Efficient Neural Network Inference](https://mlsanity.com/paper/2103.13630/) (2021)
- [Up or Down? Adaptive Rounding for Post-Training Quantization](https://mlsanity.com/paper/2004.10568/) (2020)
- [BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction](https://mlsanity.com/paper/2102.05426/) (2021)
- [Perception Prioritized Training of Diffusion Models](https://mlsanity.com/paper/2204.00227/) (2022)
- [Q-Diffusion: Quantizing Diffusion Models](https://mlsanity.com/paper/2302.04304/) (2023)
- [Post-training Quantization on Diffusion Models](https://mlsanity.com/paper/2211.15736/) (2022)
- [Generating Images with Sparse Representations](https://mlsanity.com/paper/2103.03841/) (2021)
- [Pruning and Quantization for Deep Neural Network Acceleration: A Survey](https://mlsanity.com/paper/2101.09671/) (2021)
- [A Note on the Inception Score](https://mlsanity.com/paper/1801.01973/) (2018)
- [Visual Attention Network](https://mlsanity.com/paper/2202.09741/) (2022)
- [Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models](https://mlsanity.com/paper/2209.13325/) (2022)
- [QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization](https://mlsanity.com/paper/2203.05740/) (2022)
- [ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model with Knowledge-Enhanced Mixture-of-Denoising-Experts](https://mlsanity.com/paper/2210.15257/) (2022)
- [Loss Aware Post-training Quantization](https://mlsanity.com/paper/1911.07190/) (2019)
- [Temporal Dynamic Quantization for Diffusion Models](https://mlsanity.com/paper/2306.02316/) (2023)
- [EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models](https://mlsanity.com/paper/2310.03270/) (2023)
- [PD-Quant: Post-Training Quantization based on Prediction Difference Metric](https://mlsanity.com/paper/2212.07048/) (2022)
- [TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models](https://mlsanity.com/paper/2311.16503/) (2023)

## Built on by (most cited first, 30 of 49)

- [SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models](https://mlsanity.com/paper/2411.05007/) (2024)
- [DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs](https://mlsanity.com/paper/2406.01721/) (2024)
- [Adaptive Caching for Faster Video Generation with Diffusion Transformers](https://mlsanity.com/paper/2411.02397/) (2024)
- [PTQ4DiT: Post-training Quantization for Diffusion Transformers](https://mlsanity.com/paper/2405.16005/) (2024)
- [MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization](https://mlsanity.com/paper/2405.17873/) (2024)
- [BitsFusion: 1.99 bits Weight Quantization of Diffusion Model](https://mlsanity.com/paper/2406.04333/) (2024)
- [MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization](https://mlsanity.com/paper/2406.00800/) (2024)
- [Q-VDiT: Towards Accurate Quantization and Distillation of Video-Generation Diffusion Transformers](https://mlsanity.com/paper/2505.22167/) (2025)
- [DKDM: Data-Free Knowledge Distillation for Diffusion Models with Any Architecture](https://mlsanity.com/paper/2409.03550/) (2024)
- [Importance-Based Token Merging for Efficient Image and Video Generation](https://mlsanity.com/paper/2411.16720/) (2024)
- [MPQ-DM: Mixed Precision Quantization for Extremely Low Bit Diffusion Models](https://mlsanity.com/paper/2412.11549/) (2024)
- [Timestep-Aware Correction for Quantized Diffusion Models](https://mlsanity.com/paper/2407.03917/) (2024)
- [CacheQuant: Comprehensively Accelerated Diffusion Models](https://mlsanity.com/paper/2503.01323/) (2025)
- [VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion Transformers](https://mlsanity.com/paper/2408.17131/) (2024)
- [MPQ-DMv2: Flexible Residual Mixed Precision Quantization for Low-Bit Diffusion Models with Temporal Distillation](https://mlsanity.com/paper/2507.04290/) (2025)
- [LRQ-DiT: Log-Rotation Post-Training Quantization of Diffusion Transformers for Image and Video Generation](https://mlsanity.com/paper/2508.03485/) (2025)
- [DGQ: Distribution-Aware Group Quantization for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2501.04304/) (2025)
- [PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution](https://mlsanity.com/paper/2411.17106/) (2024)
- [HierarchicalPrune: Position-Aware Compression for Large-Scale Diffusion Models](https://mlsanity.com/paper/2508.04663/) (2025)
- [Qua2SeDiMo: Quantifiable Quantization Sensitivity of Diffusion Models](https://mlsanity.com/paper/2412.14628/) (2024)
- [TerDiT: Ternary Diffusion Models with Transformers](https://mlsanity.com/paper/2405.14854/) (2024)
- [Diffusion Model Quantization: A Review](https://mlsanity.com/paper/2505.05215/) (2025)
- [Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning](https://mlsanity.com/paper/2505.21591/) (2025)
- [Temporal Feature Matters: A Framework for Diffusion Model Quantization](https://mlsanity.com/paper/2407.19547/) (2024)
- [Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image Generation](https://mlsanity.com/paper/2502.08690/) (2025)
- [DLFR-VAE: Dynamic Latent Frame Rate VAE for Video Generation](https://mlsanity.com/paper/2502.11897/) (2025)
- [Test-Time Iterative Error Correction for Efficient Diffusion Models](https://mlsanity.com/paper/2511.06250/) (2025)
- [Are Image-to-Video Models Good Zero-Shot Image Editors?](https://mlsanity.com/paper/2511.19435/) (2025)
- [Just-in-Time: Training-Free Spatial Acceleration for Diffusion Transformers](https://mlsanity.com/paper/2603.10744/) (2026)
- [Q-Drift: Quantization-Aware Drift Correction for Diffusion Model Sampling](https://mlsanity.com/paper/2603.18095/) (2026)

## Abstract (arXiv)

The practical deployment of diffusion models is still hindered by the high memory and computational overhead. Although quantization paves a way for model compression and acceleration, existing methods face challenges in achieving low-bit quantization efficiently. In this paper, we identify imbalanced activation distributions as a primary source of quantization difficulty, and propose to adjust these distributions through weight finetuning to be more quantization-friendly. We provide both theoretical and empirical evidence supporting finetuning as a practical and reliable solution. Building on this approach, we further distinguish two critical types of quantized layers: those responsible for retaining essential temporal information and those particularly sensitive to bit-width reduction. By selectively finetuning these layers under both local and global supervision, we mitigate performance degradation while enhancing quantization efficiency. Our method demonstrates its efficacy across three high-resolution image generation tasks, obtaining state-of-the-art performance across multiple bit-width settings.