Fine-Grained Customized Fashion Design with Image-into-Prompt benchmark and dataset from LMM
This addresses the challenge for end-users in the garment industry who lack professional knowledge, enabling easier clothing design and editing, but it appears incremental as it builds on existing multimodal models.
The paper tackles the problem of fine-grained customization in fashion design using generative AI, which suffers from text uncertainty for non-expert users, by proposing a Better Understanding Generation workflow with a large multimodal model to automatically create and customize designs from chat with image-into-prompt, resulting in a new FashionEdit dataset that shows effectiveness in generation similarity, user satisfaction, and quality.
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.