AnyDressing: Customizable Multi-Garment Virtual Dressing via Latent Diffusion Models

TL;DR

AnyDressing introduces a scalable, plug-in friendly framework for Multi-Garment Virtual Dressing by decoupling garment feature extraction (GarmentsNet) from image synthesis (DressingNet). The Garment-Specific Feature Extractor encodes per-garment textures via parallel self-attention with LoRA, preventing garment confusion and enabling easy scaling to more items. DressingNet employs an Adaptive Dressing-Attention mechanism coupled with Instance-Level Garment Localization to inject features precisely into corresponding regions, and Garment-Enhanced Texture Learning to enforce fine-grained garment textures with perceptual and high-frequency losses. The method achieves state-of-the-art performance on single- and multi-garment tasks and remains compatible with community controls like ControlNet and IP-Adapter, enabling diverse, controllable synthetic dressing for practical applications.

Abstract

Recent advances in garment-centric image generation from text and image prompts based on diffusion models are impressive. However, existing methods lack support for various combinations of attire, and struggle to preserve the garment details while maintaining faithfulness to the text prompts, limiting their performance across diverse scenarios. In this paper, we focus on a new task, i.e., Multi-Garment Virtual Dressing, and we propose a novel AnyDressing method for customizing characters conditioned on any combination of garments and any personalized text prompts. AnyDressing comprises two primary networks named GarmentsNet and DressingNet, which are respectively dedicated to extracting detailed clothing features and generating customized images. Specifically, we propose an efficient and scalable module called Garment-Specific Feature Extractor in GarmentsNet to individually encode garment textures in parallel. This design prevents garment confusion while ensuring network efficiency. Meanwhile, we design an adaptive Dressing-Attention mechanism and a novel Instance-Level Garment Localization Learning strategy in DressingNet to accurately inject multi-garment features into their corresponding regions. This approach efficiently integrates multi-garment texture cues into generated images and further enhances text-image consistency. Additionally, we introduce a Garment-Enhanced Texture Learning strategy to improve the fine-grained texture details of garments. Thanks to our well-craft design, AnyDressing can serve as a plug-in module to easily integrate with any community control extensions for diffusion models, improving the diversity and controllability of synthesized images. Extensive experiments show that AnyDressing achieves state-of-the-art results.

Figures (18)

• Figure 1: Customizable virtual dressing results of our AnyDressing. Reliability: AnyDressing is well-suited for a variety of scenes and complex garments. Compatibility: AnyDressing is compatible with LoRA hu2021lora and plugins such as ControlNet zhang2023adding and FaceID ye2023ip.
• Figure 2: Overview of AnyDressing. Given $N$ target garments, AnyDressing customizes a character dressed in multiple target garments. The GarmentsNet leverages the Garment-Specific Feature Extractor (GFE) module to extract detailed features from multiple garments. The DressingNet integrates these features for virtual dressing using a Dressing-Attention (DA) module and an Instance-Level Garment Localization Learning mechanism. Moreover, the Garment-Enhanced Texture Learning (GTL) strategy further enhances texture details.
• Figure 3: Qualitative comparisons with state-of-the-art methods. Please zoom in for more details.
• Figure 4: Examples of plug-in results of AnyDressing.
• Figure 5: Ablation results on GFE and IGL modules.