@inproceedings{49a6de7042dd4f8784b6a2cd9016ad3b,
title = "StableYolo: Optimizing Image Generation for Large Language Models",
abstract = "AI-based image generation is bounded by system parameters and the way users define prompts. Both prompt engineering and AI tuning configuration are current open research challenges and they require a significant amount of manual effort to generate good quality images. We tackle this problem by applying evolutionary computation to Stable Diffusion, tuning both prompts and model parameters simultaneously. We guide our search process by using Yolo. Our experiments show that our system, dubbed StableYolo, significantly improves image quality (52% on average compared to the baseline), helps identify relevant words for prompts, reduces the number of GPU inference steps per image (from 100 to 45 on average), and keeps the length of the prompt short (≈ 7 keywords).",
keywords = "Image Generation, LLMS, SBSE, Stable Diffusion, Yolo",
author = "Harel Berger and Aidan Dakhama and Zishuo Ding and Karine Even-Mendoza and David Kelly and Hector Menendez and Rebecca Moussa and Federica Sarro",
note = "Publisher Copyright: {\textcopyright} 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 15th International Symposium on Search-Based Software Engineering, SSBSE 2023 ; Conference date: 08-12-2023 Through 08-12-2023",
year = "2024",
doi = "10.1007/978-3-031-48796-5_10",
language = "אנגלית",
isbn = "9783031487958",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "133--139",
editor = "Paolo Arcaini and Tao Yue and Fredericks, {Erik M.}",
booktitle = "Search-Based Software Engineering - 15th International Symposium, SSBSE 2023, Proceedings",
address = "גרמניה",
}