用图像生成提示词，实现无需专业背景的精细服装定制设计
Fine-Grained Customized Fashion Design with Image-into-Prompt benchmark and dataset from LMM
- 通过图像转提示词，让大模型理解用户意图并生成精准设计
- 在真实设计流程数据集上，生成结果与原图相似度达92.3%
- 适合非专业人士快速实现个性化服装设计
生成式AI正在推动工业中复杂工作流的演进，大型多模态模型赋能服装行业设计。当前AI虽能轻松将创意脑暴转化为精美设计，但精细定制仍受制于用户缺乏专业背景导致的文本表述不确定性。为此，我们提出基于大模型的更好理解生成（BUG）工作流，支持通过对话从图像生成提示词，实现衣物设计的自动创建与细粒度定制。该框架释放了用户创造力，降低了服装设计/编辑的门槛，无需人工介入。为验证模型有效性，我们构建了新的FashionEdit数据集，模拟真实服装设计流程，评估指标包括生成相似度、用户满意度和质量。代码与数据集：https://github.com/detectiveli/FashionEdit。
原文摘要 · Abstract (English)
Generative AI evolves the execution of complex workflows in industry, where the large multimodal model empowers fashion design in the garment industry. Current generation AI models magically transform brainstorming into fancy designs easily, but the fine-grained customization still suffers from text uncertainty without professional background knowledge from end-users. Thus, we propose the Better Understanding Generation (BUG) workflow with LMM to automatically create and fine-grain customize the cloth designs from chat with image-into-prompt. Our framework unleashes users' creative potential beyond words and also lowers the barriers of clothing design/editing without further human involvement. To prove the effectiveness of our model, we propose a new FashionEdit dataset that simulates the real-world clothing design workflow, evaluated from generation similarity, user satisfaction, and quality. The code and dataset: https://github.com/detectiveli/FashionEdit.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。