生成语法
人工智能
计算机科学
自然语言处理
主题(音乐)
生成模型
代表(政治)
编织
图像(数学)
语言学
文化遗产
语义学(计算机科学)
计算机视觉
模式识别(心理学)
字体
结构化
工程制图
作者
Humasak Tommy Argo Simanjuntak,Tamara Yunika Sianipar,Bronson T. M Siallagan,Difya Laurensya Ambarita,Arlinta Barus
标识
DOI:10.48550/arxiv.2609.17987
摘要
The traditional Batak Ulos weaving industry faces growing challenges in producing diverse, innovative motifs due to limitations in conventional, manually driven design methods. This study proposes a multimodal generative framework integrating a fine-tuned Latent Diffusion Model (Stable Diffusion XL v1.0 via LoRA) with a Multimodal Large Language Model (LLaMA 1.5-7B) to enable controllable, culturally faithful Ulos motif generation. Four complementary conditioning mechanisms: text, image, representation, and semantic map (via ControlNet) jointly guide the generation process, each governing a distinct aspect from semantic intent to spatial layout. A five level ablation study across three scenarios (shape transformation, colour variation, and high-complexity input) shows that conditioning effectiveness is not proportional to the number of mechanisms combined: Text + Image + Semantic Map achieved the best FID (270) and CLIP Score (0.65 - 0.70) but the weakest SSIM (0.65), while Text + Image + Representation offered the best overall balance, with stable SSIM (0.84) and competitive FID (280). Combining all four mechanisms yielded the weakest FID (330), indicating conflicting optimization signals. Qualitative evaluation by nine weavers and thirty public participants confirmed statistically significant positive acceptance (Wilcoxon, p=0.007 and p<0.001, respectively). A web-based prototype supporting text-to-image and image-to-image generation was also developed, offering a practical digital design tool for cultural heritage preservation.
科研通智能强力驱动
Strongly Powered by AbleSci AI