MMTryon: Multi-Modal Multi-Reference Control for High-Quality Fashion Generation

arXiv:2405.00448v1 Announce Type: new
Abstract: This paper introduces MMTryon, a multi-modal multi-reference VIrtual Try-ON (VITON) framework, which can generate high-quality compositional try-on results by taking as inputs a text instruction and multiple garment images. Our MMTryon mainly addresses two problems overlooked in prior literature: 1) Support of multiple try-on items and dressing styleExisting methods are commonly designed for single-item try-on tasks (e.g., upper/lower garments, dresses) and fall short on customizing dressing styles (e.g., zipped/unzipped, tuck-in/tuck-out, etc.) 2) Segmentation Dependency. They …

abstract arxiv control cs.cv fashion framework generate images inputs literature modal multi-modal multiple paper prior quality reference results support text type virtual virtual try-on