FashionSD-X: Multimodal Fashion Garment Synthesis using Latent Diffusion

arXiv:2404.18591v1 Announce Type: new
Abstract: The rapid evolution of the fashion industry increasingly intersects with technological advancements, particularly through the integration of generative AI. This study introduces a novel generative pipeline designed to transform the fashion design process by employing latent diffusion models. Utilizing ControlNet and LoRA fine-tuning, our approach generates high-quality images from multimodal inputs such as text and sketches. We leverage and enhance state-of-the-art virtual try-on datasets, including Multimodal Dress Code and VITON-HD, by integrating sketch data. Our …

abstract arxiv controlnet cs.ai cs.cv design diffusion diffusion models evolution fashion fashion industry fine-tuning generative industry integration latent diffusion models lora multimodal novel pipeline process quality study synthesis through type