?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.title=GreenStableYolo%3A+Optimizing+Inference+Time+and+Image+Quality+of+Text-to-Image+Generation&rft.creator=Gong%2C+Jingzhi&rft.creator=Li%2C+Sisi&rft.creator=D%E2%80%99Aloisio%2C+Giordano&rft.creator=Ding%2C+Zishuo&rft.creator=Yulong%2C+Ye&rft.creator=Langdon%2C+William+B&rft.creator=Sarro%2C+Federica&rft.description=Tuning+the+parameters+and+prompts+for+improving+AI-based+text-to-image+generation+has+remained+a+substantial+yet+unaddressed+challenge.+Hence+we+introduce+GreenStableYolo%2C+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%25)+in+image+quality+compared+to+StableYolo+(which+only+considers+image+quality)%2C+GreenStableYolo+achieves+a+substantial+reduction+in+inference+time+(266%25+less)+and+a+526%25+higher+hypervolume%2C+thereby+advancing+the+state-of-the-art+for+text-to-image+generation.&rft.subject=SBSE%3B+ANN%3B+GenAI%3B+%0D%0AText2Image%3B+Stable+Diffusion%3B+%0D%0AYolo&rft.publisher=Springer&rft.contributor=Jahangirova%2C+Gunel&rft.contributor=Khomh%2C+Foutse&rft.date=2024-07-02&rft.type=Proceedings+paper&rft.language=eng&rft.source=+++++In%3A+Jahangirova%2C+Gunel+and+Khomh%2C+Foutse%2C+(eds.)+Search-Based+Software+Engineering%3A+SSBSE+2024.++(pp.+pp.+70-76).++Springer%3A+Cham%2C+Switzerland.+(2024)+++++&rft.identifier=https%3A%2F%2Fdiscovery.ucl.ac.uk%2Fid%2Feprint%2F10192852%2F