Q-Drift: Quantization-Aware Drift Correction for Diffusion Model Sampling

• URL: http://arxiv.org/abs/2603.18095v1
• Date: Wed, 18 Mar 2026 10:19:36 GMT
• Title: Q-Drift: Quantization-Aware Drift Correction for Diffusion Model Sampling
• Abstract summary: Post-training quantization (PTQ) is a practical path to deploy large diffusion models.<n>We propose Q-Drift, a principled sampler-side correction that treats quantization error as an implicit perturbation.<n>Q-Drift estimates a time-wise variance statistic from calibration, in practice requiring as few as 5 full-precision/quantized calibration runs.
• Score: 45.88028371034407
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Post-training quantization (PTQ) is a practical path to deploy large diffusion models, but quantization noise can accumulate over the denoising trajectory and degrade generation quality. We propose Q-Drift, a principled sampler-side correction that treats quantization error as an implicit stochastic perturbation on each denoising step and derives a marginal-distribution-preserving drift adjustment. Q-Drift estimates a timestep-wise variance statistic from calibration, in practice requiring as few as 5 paired full-precision/quantized calibration runs. The resulting sampler correction is plug-and-play with common samplers, diffusion models, and PTQ methods, while incurring negligible overhead at inference. Across six diverse text-to-image models (spanning DiT and U-Net), three samplers (Euler, flow-matching, DPM-Solver++), and two PTQ methods (SVDQuant, MixDQ), Q-Drift improves FID over the corresponding quantized baseline in most settings, with up to 4.59 FID reduction on PixArt-Sigma (SVDQuant W3A4), while preserving CLIP scores.

Related papers

• CAGE: Curvature-Aware Gradient Estimation For Accurate Quantization-Aware Training [73.46600457802693]
  We introduce a new method that counteracts the loss induced by quantization.<n>CAGE significantly improves upon the state-of-theart methods in terms of accuracy, for similar computational cost.<n>For QAT pre-training of Llama models, CAGE matches the accuracy achieved at 4-bits (W4A4) with the prior best method.
  arXiv  Detail & Related papers  (2025-10-21T16:33:57Z)
• Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling [17.912877295127355]
  We introduce Q-Sched, a new paradigm for post-training quantization that modifies the diffusion model scheduler rather than model weights.<n>Q-Sched achieves full-precision accuracy with a 4x reduction in model size.<n>A large-scale user study with more than 80,000 annotations confirms Q-Sched's effectiveness on both FLUX.1[schnell] and SDXL-Turbo.
  arXiv  Detail & Related papers  (2025-09-01T17:09:22Z)
• Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning [14.145862114439831]
  Model quantization reduces the bit-width of weights and activations, improving memory efficiency and inference speed.<n>Existing methods, primarily based on integer quantization and post-training quantization fine-tuning, struggle with inconsistent performance.<n>We propose a mixup-sign floating-point quantization framework, first introducing unsigned FP quantization in model quantization, along with timestep-aware LoRA and denoising-factor loss alignment.
  arXiv  Detail & Related papers  (2025-05-27T13:40:47Z)
• MergeQuant: Accurate 4-bit Static Quantization of Large Language Models by Channel-wise Calibration [23.752021919501207]
  We propose MergeQuant, an accurate and efficient per-channel static quantization framework.<n> MergeQuant integrates the per-channel quantization steps with the corresponding scalings and linear mappings through a Quantization Step Migration (QSM) method.<n>On Llama-2-7B model, MergeQuant achieves up to 1.77x speedup in decoding, and up to 2.06x speedup in end-to-end compared to FP16 baseline.
  arXiv  Detail & Related papers  (2025-03-07T04:52:28Z)
• TCAQ-DM: Timestep-Channel Adaptive Quantization for Diffusion Models [49.65286242048452]
  We propose a novel method dubbed Timestep-Channel Adaptive Quantization for Diffusion Models (TCAQ-DM)<n>The proposed method substantially outperforms the state-of-the-art approaches in most cases.
  arXiv  Detail & Related papers  (2024-12-21T16:57:54Z)
• 2DQuant: Low-bit Post-Training Quantization for Image Super-Resolution [83.09117439860607]
  Low-bit quantization has become widespread for compressing image super-resolution (SR) models for edge deployment. It is notorious that low-bit quantization degrades the accuracy of SR models compared to their full-precision (FP) counterparts. We present a dual-stage low-bit post-training quantization (PTQ) method for image super-resolution, namely 2DQuant, which achieves efficient and accurate SR under low-bit quantization.
  arXiv  Detail & Related papers  (2024-06-10T06:06:11Z)
• QNCD: Quantization Noise Correction for Diffusion Models [15.189069680672239]
  Diffusion models have revolutionized image synthesis, setting new benchmarks in quality and creativity. Post-training quantization presents a solution to accelerate sampling, aibeit at the expense of sample quality. We introduce a unified Quantization Noise Correction Scheme (QNCD) aimed at minishing quantization noise throughout the sampling process.
  arXiv  Detail & Related papers  (2024-03-28T04:24:56Z)
• Post-training Quantization for Text-to-Image Diffusion Models with Progressive Calibration and Activation Relaxing [49.800746112114375]
  We propose a novel post-training quantization method (Progressive and Relaxing) for text-to-image diffusion models. We are the first to achieve quantization for Stable Diffusion XL while maintaining the performance.
  arXiv  Detail & Related papers  (2023-11-10T09:10:09Z)
• PTQD: Accurate Post-Training Quantization for Diffusion Models [22.567863065523902]
  Post-training quantization of diffusion models can significantly reduce the model size and accelerate the sampling process without re-training. Applying existing PTQ methods directly to low-bit diffusion models can significantly impair the quality of generated samples. We propose a unified formulation for the quantization noise and diffusion perturbed noise in the quantized denoising process.
  arXiv  Detail & Related papers  (2023-05-18T02:28:42Z)
• Q-Diffusion: Quantizing Diffusion Models [52.978047249670276]
  Post-training quantization (PTQ) is considered a go-to compression method for other tasks. We propose a novel PTQ method specifically tailored towards the unique multi-timestep pipeline and model architecture. We show that our proposed method is able to quantize full-precision unconditional diffusion models into 4-bit while maintaining comparable performance.
  arXiv  Detail & Related papers  (2023-02-08T19:38:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.