FLORA
收藏资源简介:
FLORA数据集由印度理工学院的研究团队创建,是首个包含4330对时尚服装草图及其详细文本描述的综合数据集。每条描述使用行业专用术语,捕捉了服装设计中的细微特征和风格元素。数据集通过网络爬虫收集图像,经过多阶段过滤和手动检查,确保图像质量。FLORA旨在通过文本生成高保真时尚草图,减少传统手绘需求,加速设计流程,适用于AI驱动的时尚设计,帮助设计师和终端用户将创意变为现实。
The FLORA dataset, created by a research team at the Indian Institute of Technology, is the first comprehensive dataset containing 4330 pairs of fashion clothing sketches and their detailed textual descriptions. Each description uses industry-specific terminology to capture the subtle features and stylistic elements in fashion design. The dataset collects images via web crawling, and undergoes multi-stage filtering and manual inspection to ensure image quality. FLORA aims to generate high-fidelity fashion sketches from text, reducing the need for traditional hand-drawing, accelerating the design process, and is applicable to AI-driven fashion design, helping designers and end users turn their creative ideas into reality.

- 1Dressing the Imagination: A Dataset for AI-Powered Translation of Text into Fashion Outfits and A Novel KAN Adapter for Enhanced Feature Adaptation印度理工学院 · 2024年



