# Unsupervised Compositional Concepts Discovery with Text-to-Image Generative Models Source: [Unsupervised Compositional Concepts Discovery with Text-to-Image Generative Models]() Collection index: [llms.txt]() Data updated: 2025-10-26T01:37:08.974Z Authors: Nan Liu, Yilun Du, Shuang Li, Joshua B. Tenenbaum, Antonio Torralba Published: 2023-06-08T17:02:15.000Z ## Abstract Text-to-image generative models have enabled high-resolution image synthesis across different domains, but require users to specify the content they wish to generate. In this paper, we consider the inverse problem -- given a collection of different images, can we discover the generative concepts that represent each image? We present an unsupervised approach to discover generative concepts from a collection of images, disentangling different art styles in paintings, objects, and lighting from kitchen scenes, and discovering image classes given ImageNet images. We show how such generative concepts can accurately represent the content of images, be recombined and composed to generate new artistic and hybrid images, and be further used as a representation for downstream classification tasks. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Multimodal Controversy Detection on MMCD rich comments](): Multimodal Controversy Detection; MMCD rich comments; F1 Score: 63.44. - [Multimodal Controversy Detection on MMCD limited comments](): Multimodal Controversy Detection; MMCD limited comments; F1 Score: 60.46. ## Original sources and implementation [Original paper]() [PDF]()