The fashion industry’s linear production model generates significant pre-consumer textile waste, especially during pattern cutting. In response to the environmental impact of fashion consumption, strategies such as reuse, recycling, and refashioning aim to divert textiles from landfills and promote sustainable practices. However, challenges in the textile sector—such as raw material variability and complex manufacturing—require more targeted solutions. Recent studies have identified Artificial Intelligence (AI) as a promising tool to enhance sustainability, streamline production, and enable personalised design. One such advancement is Generative AI (GenAI), which supports applications like virtual try-ons, fabric-to-garment transformations, and multimodal garment design via tools such as FashionGAN, StyleGAN, and Latent Diffusion Models. Despite these developments, current image generation methods struggle with preserving fabric detail and structural accuracy. This research proposes an image generation pipeline that accurately reflects specific fabric textures and visual attributes, offering designers greater creative control while reducing the need for physical samples—thereby minimising process waste. The system is implemented using ComfyUI and LoRA-enhanced Stable Diffusion 1.5 models to overcome limitations found in existing methods. To evaluate performance, quantitative metrics such as FID, KID, SSIM, LPIPS, and CLIP-S were used to assess visual quality, structural similarity, and semantic alignment. A qualitative comparison was also conducted to evaluate fabric texture preservation and prompt consistency across models. Among the tested models, Realistic Vision v5.1 delivered the best results across most metrics and is recommended for photorealistic applications in sustainable fashion. DreamShaper v8 excelled in preserving fabric texture, while MajicMix v5 produced stylised outputs more suitable for conceptual design stages. This study aims to empower fashion designers with a flexible and sustainable design model, to reduce waste, accelerate prototyping, and explore AI-driven innovation in digital fashion.
Ghori et al. (Fri,) studied this question.