Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Prompt2Fashion: An automatically generated fashion dataset

Georgia Argyrou, Angeliki Dimitriou, Maria Lymperaiou, Giorgos Filandrianos, Giorgos Stamou

TL;DR

This work uses generative models to automatically construct a fashion image dataset tailored to various occasions, styles, and body types as instructed by users, and extends the discussion on the importance of expert knowledge for the evaluation of artistic AI-generated datasets such as this one.

Abstract

Despite the rapid evolution and increasing efficacy of language and vision generative models, there remains a lack of comprehensive datasets that bridge the gap between personalized fashion needs and AI-driven design, limiting the potential for truly inclusive and customized fashion solutions. In this work, we leverage generative models to automatically construct a fashion image dataset tailored to various occasions, styles, and body types as instructed by users. We use different Large Language Models (LLMs) and prompting strategies to offer personalized outfits of high aesthetic quality, detail, and relevance to both expert and non-expert users' requirements, as demonstrated by qualitative analysis. Up until now the evaluation of the generated outfits has been conducted by non-expert human subjects. Despite the provided fine-grained insights on the quality and relevance of generation, we extend the discussion on the importance of expert knowledge for the evaluation of artistic AI-generated datasets such as this one. Our dataset is publicly available on GitHub at https://github.com/georgiarg/Prompt2Fashion.

Prompt2Fashion: An automatically generated fashion dataset

TL;DR

This work uses generative models to automatically construct a fashion image dataset tailored to various occasions, styles, and body types as instructed by users, and extends the discussion on the importance of expert knowledge for the evaluation of artistic AI-generated datasets such as this one.

Abstract

Despite the rapid evolution and increasing efficacy of language and vision generative models, there remains a lack of comprehensive datasets that bridge the gap between personalized fashion needs and AI-driven design, limiting the potential for truly inclusive and customized fashion solutions. In this work, we leverage generative models to automatically construct a fashion image dataset tailored to various occasions, styles, and body types as instructed by users. We use different Large Language Models (LLMs) and prompting strategies to offer personalized outfits of high aesthetic quality, detail, and relevance to both expert and non-expert users' requirements, as demonstrated by qualitative analysis. Up until now the evaluation of the generated outfits has been conducted by non-expert human subjects. Despite the provided fine-grained insights on the quality and relevance of generation, we extend the discussion on the importance of expert knowledge for the evaluation of artistic AI-generated datasets such as this one. Our dataset is publicly available on GitHub at https://github.com/georgiarg/Prompt2Fashion.
Paper Structure (10 sections, 3 figures, 1 table)

This paper contains 10 sections, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related work
  3. AI in fashion
  4. Evaluation of generative models
  5. A generated fashion dataset
  6. Qualitative results
  7. Can LLMs-as-Judges be used somewhere?
  8. Non-expert evaluation
  9. Discussion: Expert evaluation
  10. Conclusion

Figures (3)

  • Figure 1: Images produced by Stable Diffusion with descriptions generated with 5 different methods
  • Figure 2: Descriptions and images produced by Stable Diffusion with descriptions generated by 2 different LLMs for Zero-shot learning, Few-shot learning and Chain-of-Thought (left column for Falcon-7B model, right column for Mistral-7B model).
  • Figure 3: Descriptions and images produced by Stable Diffusion with descriptions generated by 2 different LLMs for RAG with PDFs and with BLOGs as sources(left column for Falcon-7B model, right column for Mistral-7B model)