Gong, Jingzhi;
Li, Sisi;
D’Aloisio, Giordano;
Ding, Zishuo;
Yulong, Ye;
Langdon, William B;
Sarro, Federica;
(2024)
GreenStableYolo: Optimizing Inference Time and Image Quality of Text-to-Image Generation.
In: Jahangirova, Gunel and Khomh, Foutse, (eds.)
Search-Based Software Engineering: SSBSE 2024.
(pp. pp. 70-76).
Springer: Cham, Switzerland.
![[thumbnail of GreenStableYolo.pdf]](https://discovery.ucl.ac.uk/style/images/fileicons/text.png) |
Text
GreenStableYolo.pdf - Accepted Version Access restricted to UCL open access staff until 3 July 2025. Download (371kB) |
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.
| Type: | Proceedings paper |
|---|---|
| Title: | GreenStableYolo: Optimizing Inference Time and Image Quality of Text-to-Image Generation |
| Event: | 16th International Symposium, SSBSE 2024 |
| ISBN-13: | 978-3-031-64572-3 |
| DOI: | 10.1007/978-3-031-64573-0_7 |
| Publisher version: | https://doi.org/10.1007/978-3-031-64573-0_7 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and conditions. |
| Keywords: | SBSE; ANN; GenAI; Text2Image; Stable Diffusion; Yolo |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10192852 |
Archive Staff Only
 |
View Item |
