PQD: Post-training Quantization for Efficient Diffusion Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909445796134912 |
|---|---|
| author | Ye, Jiaojiao Wang, Zhen Jiang, Linnan |
| author_facet | Ye, Jiaojiao Wang, Zhen Jiang, Linnan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_00124 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PQD: Post-training Quantization for Efficient Diffusion Models Ye, Jiaojiao Wang, Zhen Jiang, Linnan Computer Vision and Pattern Recognition Machine Learning 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. |
| title | PQD: Post-training Quantization for Efficient Diffusion Models |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2501.00124 |