paper-with-me

Papers

PQD: Post-training Quantization for Efficient Diffusion Models

2024-12-30 · Jiaojiao Ye, Zhen Wang, Linnan Jiang

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.

📄 PDF Abstract BibTeX arXiv:2501.00124

Code (0)

등록된 구현이 없습니다.

Tasks

DiversityImage GenerationQuantizationUnconditional Image Generation

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Post-training Quantization for Text-to-Image Diffusion Models with Progressive Calibration and Activation Relaxing

2023-11-10 · Siao Tang, Xin Wang, Hong Chen, Chaoyu Guan 외

High computational overhead is a troublesome problem for diffusion models. Recent studies have leveraged post-training quantization (PTQ) to compress diffusion models. However, most of them only focus on unconditional mo…

Quantization

Towards Accurate Post-training Quantization for Diffusion Models

2023-05-30 · CVPR 2024 1 · Changyuan Wang, Ziwei Wang, Xiuwei Xu, Yansong Tang 외

In this paper, we propose an accurate data-free post-training quantization framework of diffusion models (ADP-DM) for efficient image generation. Conventional data-free quantization methods learn shared quantization func…

Data Free QuantizationImage GenerationQuantization

Hardware-Friendly Static Quantization Method for Video Diffusion Transformers

2025-02-20 · Sanghyun Yi, Qingfeng Liu, Mostafa El-Khamy

Diffusion Transformers for video generation have gained significant research interest since the impressive performance of SORA. Efficient deployment of such generative-AI models on GPUs has been demonstrated with dynamic…

QuantizationVideo GenerationVisual Question Answering (VQA)

PTQD: Accurate Post-Training Quantization for Diffusion Models

2023-05-18 · NeurIPS 2023 11 · Yefei He, Luping Liu, Jing Liu, Weijia Wu 외

Diffusion models have recently dominated image synthesis tasks. However, the iterative denoising process is expensive in computations at inference time, making diffusion models less practical for low-latency and scalable…

DenoisingImage GenerationQuantization

Temporal Dynamic Quantization for Diffusion Models

2023-06-04 · NeurIPS 2023 11 · Junhyuk So, Jungwon Lee, Daehyun Ahn, HyungJun Kim 외

The diffusion model has gained popularity in vision applications due to its remarkable generative performance and versatility. However, high storage and computation demands, resulting from the model size and iterative ge…

Quantization