Fashion-Gen: The Generative Fashion Dataset and Challenge

TL;DR

Fashion-Gen presents a large high-resolution fashion image dataset with professional descriptions, enabling research in text-conditioned image generation and fostering a community challenge to advance the field.

Contribution

The paper introduces a novel high-resolution fashion dataset with detailed descriptions and baseline results, facilitating progress in generative models for fashion imagery.

Findings

Baseline high-resolution image generation results

Text-conditioned image generation benchmarks

Community challenge for model improvement

Abstract

We introduce a new dataset of 293,008 high definition (1360 x 1360 pixels) fashion images paired with item descriptions provided by professional stylists. Each item is photographed from a variety of angles. We provide baseline results on 1) high-resolution image generation, and 2) image generation conditioned on the given text descriptions. We invite the community to improve upon these baselines. In this paper, we also outline the details of a challenge that we are launching based upon this dataset.