This study focuses on the implementation and evaluation of generative models for the generation of textile designs using Generative Adversar ial Networks (GANs). The appro ach involved developing both unconditional and conditional vers ions of Wasserstein GANs (WGA Ns) and Wasserstein GANs with Gradient Penalty (WGAN-GP), as we ll as adaptations for higher r esolution outputs. A diverse dataset of 13,000 textile patterns was compiled, and the models were trained on this data, with architectures designed to optimize image generation in terms of both resolution and fe ature learning. The training process was analyzed using loss stability assessments, visual evaluation, a nd accuracy metrics. Results showed that WGAN-GP models demonstrated great er loss stabilization but lowe r overall accuracy since the discriminator learned faster, while conditional models showed i mprovement in image fidelity but with some divergence issues during training. Additionally, efforts to upscale output resolution to 256x256 pixels were largely unsuccessful, with significant loss oscillations and poor constructed generated samples. This study concludes with recommendations for further refinement of the model architectures and training strategies to improve the generation of high-quality, high-resolution textile designs.