ImageGem: In-the-wild Generative Image Interaction Dataset for Generative Model Personalization

TL;DR

ImageGem is a comprehensive dataset of real-world user interactions and preferences that enables personalized generative image modeling, retrieval, and editing, advancing the development of user-aligned generative models.

Contribution

We introduce ImageGem, the first large-scale in-the-wild dataset with detailed user preferences, facilitating personalized generative model training and editing.

Findings

Improved preference alignment models trained with ImageGem data

Enhanced personalized image retrieval and model recommendation performance

Effective end-to-end framework for editing diffusion models based on user preferences

Abstract

We introduce ImageGem, a dataset for studying generative models that understand fine-grained individual preferences. We posit that a key challenge hindering the development of such a generative model is the lack of in-the-wild and fine-grained user preference annotations. Our dataset features real-world interaction data from 57K users, who collectively have built 242K customized LoRAs, written 3M text prompts, and created 5M generated images. With user preference annotations from our dataset, we were able to train better preference alignment models. In addition, leveraging individual user preference, we investigated the performance of retrieval models and a vision-language model on personalized image retrieval and generative model recommendation. Finally, we propose an end-to-end framework for editing customized diffusion models in a latent weight space to align with individual user preferences. Our results demonstrate that the ImageGem dataset enables, for the first time, a new paradigm for generative model personalization.