@inproceedings{discovery10192852, title = {GreenStableYolo: Optimizing Inference Time and Image Quality of Text-to-Image Generation}, journal = {International Symposium on Search Based Software Engineering}, booktitle = {Search-Based Software Engineering: SSBSE 2024}, year = {2024}, editor = {Gunel Jahangirova and Foutse Khomh}, publisher = {Springer}, pages = {70--76}, note = {This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and conditions.}, volume = {14767}, series = {Lecture Notes in Computer Science}, month = {July}, address = {Cham, Switzerland}, url = {https://doi.org/10.1007/978-3-031-64573-0\%5f7}, issn = {0302-9743}, author = {Gong, Jingzhi and Li, Sisi and D'Aloisio, Giordano and Ding, Zishuo and Yulong, Ye and Langdon, William B and Sarro, Federica}, abstract = {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.}, keywords = {SBSE; ANN; GenAI; Text2Image; Stable Diffusion; Yolo} }