LOTS of Fashion! Multi-Conditioning for Image Generation via Sketch-Text Pairing

TL;DR

This paper introduces LOTS, a novel method for fashion image generation that combines sketch and text conditioning to produce highly customizable fashion outlooks, leveraging a new dataset and diffusion guidance.

Contribution

The paper presents a new approach that integrates localized sketch-text conditioning with diffusion models for fashion image synthesis, along with a new dataset, Sketchy, for training and evaluation.

Findings

Achieves state-of-the-art performance on global and localized metrics

Enables unprecedented levels of design customization

Demonstrates effective multi-condition diffusion guidance

Abstract

Fashion design is a complex creative process that blends visual and textual expressions. Designers convey ideas through sketches, which define spatial structure and design elements, and textual descriptions, capturing material, texture, and stylistic details. In this paper, we present LOcalized Text and Sketch for fashion image generation (LOTS), an approach for compositional sketch-text based generation of complete fashion outlooks. LOTS leverages a global description with paired localized sketch + text information for conditioning and introduces a novel step-based merging strategy for diffusion adaptation. First, a Modularized Pair-Centric representation encodes sketches and text into a shared latent space while preserving independent localized features; then, a Diffusion Pair Guidance phase integrates both local and global conditioning via attention-based guidance within the diffusion model's multi-step denoising process. To validate our method, we build on Fashionpedia to release Sketchy, the first fashion dataset where multiple text-sketch pairs are provided per image. Quantitative results show LOTS achieves state-of-the-art image generation performance on both global and localized metrics, while qualitative examples and a human evaluation study highlight its unprecedented level of design customization.