GimmBO: Interactive Generative Image Model Merging via Bayesian Optimization
ACM Transactions on Graphics · 03.07.2026 · 45 (4) · 1-12
DOI: 10.1145/3811293 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 03.07.2026. Verfasst von Chenxi Liu und 2 weiteren Autor:innen. Die Arbeit nennt 75 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NSERC Discovery, Ontario Early Research Award Program, Canada Research Chairs Program.
Abstract (Originalsprache)
Fine-tuning-based adaptation is widely used to customize diffusion-based image generation, leading to large collections of community-created adapters that capture diverse subjects and styles. Adapters derived from the same base model can be merged linearly, enabling the synthesis of new visual results within a vast and continuous design space. To explore this space, current workflows rely on manual slider-based tuning, an approach that scales poorly and makes merging coefficient selection difficult, even when the candidate set is limited to 20–30 adapters. We propose GimmBO to support interactive exploration of adapter merging for image generation through Preferential Bayesian Optimization (PBO). Motivated by observations from real-world usage, including sparsity and constrained coefficient ranges, we introduce a two-stage BO backend that improves sampling efficiency and convergence in high-dimensional spaces. We evaluate our approach with simulated users and a user study, demonstrating improved convergence, high success rates, and consistent gains over BO and line-search baselines, and further show the flexibility of the framework through several extensions.
Förderung
- NSERC Discovery
- Ontario Early Research Award Program
- Canada Research Chairs Program
- Sloan Research Fellowship
- DSI Catalyst Grant Program
- Adobe Inc.
Zitieren
APA
Liu, C., Ling, S., & Jacobson, A. (2026). GimmBO: Interactive Generative Image Model Merging via Bayesian Optimization. ACM Transactions on Graphics, 45(4), 1-12. https://doi.org/10.1145/3811293
Vancouver
Liu C, Ling S, Jacobson A. GimmBO: Interactive Generative Image Model Merging via Bayesian Optimization. ACM Transactions on Graphics. 2026;45(4):1-12. doi:10.1145/3811293
BibTeX
@article{Liu2026,
author = {Liu, Chenxi and Ling, Selena and Jacobson, Alec},
title = {GimmBO: Interactive Generative Image Model Merging via Bayesian Optimization},
journal = {ACM Transactions on Graphics},
year = {2026},
volume = {45},
number = {4},
pages = {1--12},
doi = {10.1145/3811293}
}
EUVIMED