FashionComposer: Compositional Fashion Image Generation

TL;DR

FashionComposer introduces a flexible, multi-modal framework for compositional fashion image generation, enabling personalized, multi-garment, and pose customization in a single pass, with robust handling of diverse inputs.

Contribution

It develops a universal, scalable framework with a reference UNet and subject-binding attention for seamless multi-modal and multi-reference fashion image synthesis.

Findings

Supports arbitrary numbers and types of reference images.

Enables personalized human appearance and pose customization.

Facilitates diverse applications like virtual try-on and human album generation.

Abstract

We present FashionComposer for compositional fashion image generation. Unlike previous methods, FashionComposer is highly flexible. It takes multi-modal input (i.e., text prompt, parametric human model, garment image, and face image) and supports personalizing the appearance, pose, and figure of the human and assigning multiple garments in one pass. To achieve this, we first develop a universal framework capable of handling diverse input modalities. We construct scaled training data to enhance the model's robust compositional capabilities. To accommodate multiple reference images (garments and faces) seamlessly, we organize these references in a single image as an "asset library" and employ a reference UNet to extract appearance features. To inject the appearance features into the correct pixels in the generated result, we propose subject-binding attention. It binds the appearance features from different "assets" with the corresponding text features. In this way, the model could understand each asset according to their semantics, supporting arbitrary numbers and types of reference images. As a comprehensive solution, FashionComposer also supports many other applications like human album generation, diverse virtual try-on tasks, etc.