Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling
- URL: http://arxiv.org/abs/2509.01624v1
- Date: Mon, 01 Sep 2025 17:09:22 GMT
- Title: Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling
- Authors: Natalia Frumkin, Diana Marculescu,
- Abstract summary: 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.
- Score: 17.912877295127355
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Text-to-image diffusion models are computationally intensive, often requiring dozens of forward passes through large transformer backbones. For instance, Stable Diffusion XL generates high-quality images with 50 evaluations of a 2.6B-parameter model, an expensive process even for a single batch. Few-step diffusion models reduce this cost to 2-8 denoising steps but still depend on large, uncompressed U-Net or diffusion transformer backbones, which are often too costly for full-precision inference without datacenter GPUs. These requirements also limit existing post-training quantization methods that rely on full-precision calibration. We introduce Q-Sched, a new paradigm for post-training quantization that modifies the diffusion model scheduler rather than model weights. By adjusting the few-step sampling trajectory, Q-Sched achieves full-precision accuracy with a 4x reduction in model size. To learn quantization-aware pre-conditioning coefficients, we propose the JAQ loss, which combines text-image compatibility with an image quality metric for fine-grained optimization. JAQ is reference-free and requires only a handful of calibration prompts, avoiding full-precision inference during calibration. Q-Sched delivers substantial gains: a 15.5% FID improvement over the FP16 4-step Latent Consistency Model and a 16.6% improvement over the FP16 8-step Phased Consistency Model, showing that quantization and few-step distillation are complementary for high-fidelity generation. A large-scale user study with more than 80,000 annotations further confirms Q-Sched's effectiveness on both FLUX.1[schnell] and SDXL-Turbo.
Related papers
- MPQ-DMv2: Flexible Residual Mixed Precision Quantization for Low-Bit Diffusion Models with Temporal Distillation [74.34220141721231]
We present MPQ-DMv2, an improved textbfMixed textbfPrecision textbfQuantization framework for extremely low-bit textbfDiffusion textbfModels.
arXiv Detail & Related papers (2025-07-06T08:16:50Z) - 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) - MPQ-DM: Mixed Precision Quantization for Extremely Low Bit Diffusion Models [37.061975191553]
This paper presents MPQ-DM, a Mixed-Precision Quantization method for Diffusion Models.<n>To mitigate the quantization error caused by outlier severe weight channels, we propose an Outlier-Driven Mixed Quantization technique.<n>To robustly learn representations crossing time steps, we construct a Time-Smoothed Relation Distillation scheme.
arXiv Detail & Related papers (2024-12-16T08:31:55Z) - PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution [95.98801201266099]
Diffusion-based image super-resolution (SR) models have shown superior performance at the cost of multiple denoising steps.<n>We propose a novel post-training quantization approach with adaptive scale in one-step diffusion (OSD) image SR, PassionSR.<n>Our PassionSR achieves significant advantages over recent leading low-bit quantization methods for image SR.
arXiv Detail & Related papers (2024-11-26T04:49:42Z) - 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) - MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization [16.83403134551842]
Recent few-step diffusion models reduce the inference time by reducing the denoising steps.
The Post Training Quantization (PTQ) replaces high bit-width FP representation with low-bit integer values.
However, when applying to few-step diffusion models, existing quantization methods face challenges in preserving both the image quality and text alignment.
arXiv Detail & Related papers (2024-05-28T06:50:58Z) - 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) - 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) - Q-ASR: Integer-only Zero-shot Quantization for Efficient Speech
Recognition [65.7040645560855]
We propose Q-ASR, an integer-only, zero-shot quantization scheme for ASR models.
We show negligible WER change as compared to the full-precision baseline models.
Q-ASR exhibits a large compression rate of more than 4x with small WER degradation.
arXiv Detail & Related papers (2021-03-31T06:05:40Z)
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.