Cross-Cultural Fashion Design via Interactive Large Language Models and Diffusion Models

TL;DR

This paper introduces a novel AI framework combining Large Language Models and Diffusion Models to generate culturally diverse fashion content, addressing bias and scalability issues in fashion content creation.

Contribution

It presents a new integrated approach that refines textual prompts with LLMs and employs weak supervision for better visual generation, achieving state-of-the-art results.

Findings

Outperforms baselines with lower FID and higher IS scores.

Generates culturally diverse and semantically relevant fashion images.

Human evaluations confirm improved content diversity and relevance.

Abstract

Fashion content generation is an emerging area at the intersection of artificial intelligence and creative design, with applications ranging from virtual try-on to culturally diverse design prototyping. Existing methods often struggle with cultural bias, limited scalability, and alignment between textual prompts and generated visuals, particularly under weak supervision. In this work, we propose a novel framework that integrates Large Language Models (LLMs) with Latent Diffusion Models (LDMs) to address these challenges. Our method leverages LLMs for semantic refinement of textual prompts and introduces a weak supervision filtering module to effectively utilize noisy or weakly labeled data. By fine-tuning the LDM on an enhanced DeepFashion+ dataset enriched with global fashion styles, the proposed approach achieves state-of-the-art performance. Experimental results demonstrate that our method significantly outperforms baselines, achieving lower Frechet Inception Distance (FID) and higher Inception Scores (IS), while human evaluations confirm its ability to generate culturally diverse and semantically relevant fashion content. These results highlight the potential of LLM-guided diffusion models in driving scalable and inclusive AI-driven fashion innovation.