FashionComposer: Compositional Fashion Image Generation
This addresses the need for more flexible and personalized fashion image generation tools, though it appears incremental as it builds on existing diffusion models with specific enhancements for fashion applications.
The paper tackles the problem of generating compositional fashion images by introducing FashionComposer, a method that takes multi-modal inputs (text, human model, garment, and face images) to personalize appearance, pose, and figure while assigning multiple garments in one pass, achieving flexible and robust generation capabilities.
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.