# GimmBO: Interactive Generative Image Model Merging via Bayesian Optimization

arXiv: https://arxiv.org/abs/2601.18585 · HTML: https://mlsanity.com/paper/2601.18585/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 45 of its 78 references that are in the map.
- First posted on arXiv 26 Jan 2026.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 30 of 45)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [TIES-Merging: Resolving Interference When Merging Models](https://mlsanity.com/paper/2306.01708/) (2023)
- [Linear Mode Connectivity and the Lottery Ticket Hypothesis](https://mlsanity.com/paper/1912.05671/) (2019)
- [Merging Models with Fisher-Weighted Averaging](https://mlsanity.com/paper/2111.09832/) (2021)
- [BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing](https://mlsanity.com/paper/2305.14720/) (2023)
- [DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data](https://mlsanity.com/paper/2306.09344/) (2023)
- [Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models](https://mlsanity.com/paper/2305.18292/) (2023)
- [Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model](https://mlsanity.com/paper/2311.13231/) (2023)
- [StyleDrop: Text-to-Image Generation in Any Style](https://mlsanity.com/paper/2306.00983/) (2023)
- [ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAs](https://mlsanity.com/paper/2311.13600/) (2023)
- [Bayesian Optimization in a Billion Dimensions via Random Embeddings](https://mlsanity.com/paper/1301.1942/) (2013)
- [InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation](https://mlsanity.com/paper/2404.02733/) (2024)
- [High-Dimensional Bayesian Optimization with Sparse Axis-Aligned Subspaces](https://mlsanity.com/paper/2103.00349/) (2021)
- [A Neural Space-Time Representation for Text-to-Image Personalization](https://mlsanity.com/paper/2305.15391/) (2023)
- [Measuring Style Similarity in Diffusion Models](https://mlsanity.com/paper/2404.01292/) (2024)
- [Orthogonal Adaptation for Modular Customization of Diffusion Models](https://mlsanity.com/paper/2312.02432/) (2023)
- [Promptify: Text-to-Image Generation through Interactive Prompt Exploration with Large Language Models](https://mlsanity.com/paper/2304.09337/) (2023)
- [The reparameterization trick for acquisition functions](https://mlsanity.com/paper/1712.00424/) (2017)
- [PromptMagician: Interactive Prompt Engineering for Text-to-Image Creation](https://mlsanity.com/paper/2307.09036/) (2023)
- [A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning](https://mlsanity.com/paper/2408.07057/) (2024)
- [K-LoRA: Unlocking Training-Free Fusion of Any Subject and Style LoRAs](https://mlsanity.com/paper/2502.18461/) (2025)
- [StyleAdapter: A Unified Stylized Image Generation Model](https://mlsanity.com/paper/2309.01770/) (2023)
- [Customizing Text-to-Image Models with a Single Image Pair](https://mlsanity.com/paper/2405.01536/) (2024)
- [TREGO: a Trust-Region Framework for Efficient Global Optimization](https://mlsanity.com/paper/2101.06808/) (2021)
- [A Survey on Personalized Content Synthesis with Diffusion Models](https://mlsanity.com/paper/2405.05538/) (2024)
- [Sequential Gallery for Interactive Visual Design Optimization](https://mlsanity.com/paper/2005.04107/) (2020)
- [Nested Attention: Semantic-aware Attention Values for Concept Personalization](https://mlsanity.com/paper/2501.01407/) (2025)

## Abstract (arXiv)

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 with weights, 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 weight 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 weight 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.