ColorwAI: Generative Colorways of Textiles through GAN and Diffusion Disentanglement
This work addresses the creative problem of textile design for fashion and textile industries, offering a novel approach but with incremental technical contributions.
The paper tackled the task of generating textile colorways with minimal shape modifications by proposing ColorwAI, a framework using color disentanglement on StyleGAN and Diffusion models, and found that StyleGAN's W space best aligns with human color notions as evaluated through expert questionnaires.
Colorway creation is the task of generating textile samples in alternate color variations maintaining an underlying pattern. The individuation of a suitable color palette for a colorway is a complex creative task, responding to client and market needs, stylistic and cultural specifications, and mood. We introduce a modification of this task, the "generative colorway" creation, that includes minimal shape modifications, and propose a framework, "ColorwAI", to tackle this task using color disentanglement on StyleGAN and Diffusion. We introduce a variation of the InterfaceGAN method for supervised disentanglement, ShapleyVec. We use Shapley values to subselect a few dimensions of the detected latent direction. Moreover, we introduce a general framework to adopt common disentanglement methods on any architecture with a semantic latent space and test it on Diffusion and GANs. We interpret the color representations within the models' latent space. We find StyleGAN's W space to be the most aligned with human notions of color. Finally, we suggest that disentanglement can solicit a creative system for colorway creation, and evaluate it through expert questionnaires and creativity theory.