GimmBO: Interactive Generative Image Model Merging via Bayesian Optimization
Researchers have developed GimmBO, a new method for interactively merging adapters in generative image models. This approach uses Preferential Bayesian Optimization (PBO) to navigate the complex design space created by combining multiple adapters, which is currently a manual and inefficient process. GimmBO aims to improve the efficiency and success rate of finding optimal adapter combinations, outperforming existing methods in user studies. AI
IMPACT This method could simplify the creation of custom image generation models by making adapter merging more efficient and accessible.