%0 Generic
%A Gong, Jingzhi
%A Li, Sisi
%A D’Aloisio, Giordano
%A Ding, Zishuo
%A Yulong, Ye
%A Langdon, William B
%A Sarro, Federica
%C Cham, Switzerland
%D 2024
%E Jahangirova, Gunel
%E Khomh, Foutse
%F discovery:10192852
%I Springer
%K SBSE; ANN; GenAI;   Text2Image; Stable Diffusion;   Yolo
%P 70-76
%T GreenStableYolo: Optimizing Inference Time and Image Quality of Text-to-Image Generation
%U https://discovery.ucl.ac.uk/id/eprint/10192852/
%V 14767
%X 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.
%Z This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and conditions.