Research
RankT2I: A Submodular Framework for Discovering Interpretable and Diverse Semantics in Text-to-Image Models
arXiv:2608.14226v1 Announce Type: new Abstract: Recent advances in text-to-image (T2I) models have revolutionized the field of image generation and editing. However, identifying semantics that a T2I m
arXiv:2608.14226v1 Announce Type: new Abstract: Recent advances in text-to-image (T2I) models have revolutionized the field of image generation and editing. However, identifying semantics that a T2I model can successfully edit in an image continues to be a challenging task. Most existing approaches require users to manually specify semantics to modify a particular image, a time-consuming process that often involves extensive trial and error. In this paper, we present RankT2I, a novel, training-free, and model-agnostic framework that automates the discovery of editable semantics in diffusion and FLUX-based models. Given a visual domain, we first utilize a multimodal vision-language model to gather a broad set of candidate semantics. We then frame semantic discovery as a set selection problem and use a submodular objective to identify semantics that are relevant, editable, and diverse. Our method helps users efficiently identify a wide range of semantics for text-to-image editing models across several domains while outperforming existing methods.
Related
- MASCOT: Model-Aware Submodular Coverage for Composite-Attribute Text-to-Image Retrieval
- MythraGen: Two-Stage Retrieval Augmented Art Generation Framework
- From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models
Source: arXiv cs.CV | 2026-08-17