Fig. 15: Schematic diagram of ablation experiments for Cantonese embroidery artistic style simulation. | npj Heritage Science

Fig. 15: Schematic diagram of ablation experiments for Cantonese embroidery artistic style simulation.

From: Diffusion model-based image generation method for Cantonese embroidery artistic styles

Fig. 15: Schematic diagram of ablation experiments for Cantonese embroidery artistic style simulation.The alternative text for this image may have been generated using AI.

a Output of the base Stable Diffusion (SD) model. b SD model fine-tuned with LoRA (SD+LoRA). c SD model guided by LineArt condition and Depth condition (SD+LineArt+Depth). d SD model guided by Color condition (SD+Color). e SD+LoRA integrated with LineArt, Depth and Color conditions (SD+LoRA+LineArt+Depth+Color). f Full model (SD+LoRA+LineArt+Depth+Color+SAM) incorporating all modules. g Local texture details of the result generated by the full model (from (f)). Compared with other ablation combinations, the SD + LoRA + LineArt + Depth + Color + SAM configuration yielded optimal results with significant improvements in quantitative metrics (LPIPS: 0.244, FID: 95.57, PSNR: 16.38); removing the LoRA module eliminated embroidery textures, LineArt and Depth ensured structural fidelity, Color enabled correct chromatic mapping, and the SAM achieved semantic region alignment.

Back to article page