Saved in:
Bibliographic Details
Main Authors: Gong, Jingzhi, Li, Sisi, d'Aloisio, Giordano, Ding, Zishuo, Ye, Yulong, Langdon, William B., Sarro, Federica
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.14982
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929429332099072
author Gong, Jingzhi
Li, Sisi
d'Aloisio, Giordano
Ding, Zishuo
Ye, Yulong
Langdon, William B.
Sarro, Federica
author_facet Gong, Jingzhi
Li, Sisi
d'Aloisio, Giordano
Ding, Zishuo
Ye, Yulong
Langdon, William B.
Sarro, Federica
contents Tuning the parameters and prompts for improving AI-based text-to-image generation has remained a substantial yet unaddressed challenge. Hence we introduce GreenStableYolo, which improves the parameters and prompts for Stable Diffusion to both reduce GPU inference time and increase image generation quality using NSGA-II and Yolo. Our experiments show that despite a relatively slight trade-off (18%) in image quality compared to StableYolo (which only considers image quality), GreenStableYolo achieves a substantial reduction in inference time (266% less) and a 526% higher hypervolume, thereby advancing the state-of-the-art for text-to-image generation.
format Preprint
id arxiv_https___arxiv_org_abs_2407_14982
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GreenStableYolo: Optimizing Inference Time and Image Quality of Text-to-Image Generation
Gong, Jingzhi
Li, Sisi
d'Aloisio, Giordano
Ding, Zishuo
Ye, Yulong
Langdon, William B.
Sarro, Federica
Computer Vision and Pattern Recognition
Artificial Intelligence
Tuning the parameters and prompts for improving AI-based text-to-image generation has remained a substantial yet unaddressed challenge. Hence we introduce GreenStableYolo, which improves the parameters and prompts for Stable Diffusion to both reduce GPU inference time and increase image generation quality using NSGA-II and Yolo. Our experiments show that despite a relatively slight trade-off (18%) in image quality compared to StableYolo (which only considers image quality), GreenStableYolo achieves a substantial reduction in inference time (266% less) and a 526% higher hypervolume, thereby advancing the state-of-the-art for text-to-image generation.
title GreenStableYolo: Optimizing Inference Time and Image Quality of Text-to-Image Generation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2407.14982