Infusion: Preventing Customized Text-to-Image Diffusion from Overfitting
This addresses a key challenge in text-to-image generation for users needing reliable customization, though it appears incremental as it builds on existing methods to mitigate overfitting.
The paper tackles the problem of concept overfitting in text-to-image customization, proposing Infusion to learn target concepts without being constrained by limited training modalities while preserving non-customized knowledge, achieving this with only 11KB of trained parameters and outperforming state-of-the-art methods in experiments.
Text-to-image (T2I) customization aims to create images that embody specific visual concepts delineated in textual descriptions. However, existing works still face a main challenge, concept overfitting. To tackle this challenge, we first analyze overfitting, categorizing it into concept-agnostic overfitting, which undermines non-customized concept knowledge, and concept-specific overfitting, which is confined to customize on limited modalities, i.e, backgrounds, layouts, styles. To evaluate the overfitting degree, we further introduce two metrics, i.e, Latent Fisher divergence and Wasserstein metric to measure the distribution changes of non-customized and customized concept respectively. Drawing from the analysis, we propose Infusion, a T2I customization method that enables the learning of target concepts to avoid being constrained by limited training modalities, while preserving non-customized knowledge. Remarkably, Infusion achieves this feat with remarkable efficiency, requiring a mere 11KB of trained parameters. Extensive experiments also demonstrate that our approach outperforms state-of-the-art methods in both single and multi-concept customized generation.