StableGarment: Garment-Centric Generation via Stable Diffusion
It addresses the problem of generating realistic garment images for applications like virtual try-on, but it is incremental as it builds on pre-trained Stable Diffusion.
The paper tackles garment-centric image generation tasks, such as virtual try-on, by developing StableGarment, a framework that retains intricate garment textures using a garment encoder with additive self-attention layers, achieving state-of-the-art results in virtual try-on.
In this paper, we introduce StableGarment, a unified framework to tackle garment-centric(GC) generation tasks, including GC text-to-image, controllable GC text-to-image, stylized GC text-to-image, and robust virtual try-on. The main challenge lies in retaining the intricate textures of the garment while maintaining the flexibility of pre-trained Stable Diffusion. Our solution involves the development of a garment encoder, a trainable copy of the denoising UNet equipped with additive self-attention (ASA) layers. These ASA layers are specifically devised to transfer detailed garment textures, also facilitating the integration of stylized base models for the creation of stylized images. Furthermore, the incorporation of a dedicated try-on ControlNet enables StableGarment to execute virtual try-on tasks with precision. We also build a novel data engine that produces high-quality synthesized data to preserve the model's ability to follow prompts. Extensive experiments demonstrate that our approach delivers state-of-the-art (SOTA) results among existing virtual try-on methods and exhibits high flexibility with broad potential applications in various garment-centric image generation.