TexControl: Sketch-Based Two-Stage Fashion Image Generation Using Diffusion Model
This work addresses a domain-specific challenge in fashion design by providing an incremental improvement to sketch-to-clothing generation, though it focuses on texture enhancement rather than broader applicability.
The authors tackled the problem of generating detailed fashion images from sparse, ambiguous freehand sketches by proposing TexControl, a two-stage diffusion model framework that first generates stable outlines using ControlNet and then optimizes textures through image-to-image methods, resulting in high-quality texture generation as fine-grained image output.
Deep learning-based sketch-to-clothing image generation provides the initial designs and inspiration in the fashion design processes. However, clothing generation from freehand drawing is challenging due to the sparse and ambiguous information from the drawn sketches. The current generation models may have difficulty generating detailed texture information. In this work, we propose TexControl, a sketch-based fashion generation framework that uses a two-stage pipeline to generate the fashion image corresponding to the sketch input. First, we adopt ControlNet to generate the fashion image from sketch and keep the image outline stable. Then, we use an image-to-image method to optimize the detailed textures of the generated images and obtain the final results. The evaluation results show that TexControl can generate fashion images with high-quality texture as fine-grained image generation.