Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2507.00459 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917094853967872 |
|---|---|
| author | Phan, Hoang Cuong Tran, Minh Tien Lee, Chihun Kim, Hoheok Oh, Sehyeok Kim, Dong-Kyu Lee, Ho Won |
| author_facet | Phan, Hoang Cuong Tran, Minh Tien Lee, Chihun Kim, Hoheok Oh, Sehyeok Kim, Dong-Kyu Lee, Ho Won |
| contents | Synthesizing realistic microstructure images conditioned on processing parameters is crucial for understanding process-structure relationships in materials design. However, this task remains challenging due to limited training micrographs and the continuous nature of processing variables. To overcome these challenges, we present a novel process-aware generative modeling approach based on Stable Diffusion 3.5 Large (SD3.5-Large), a state-of-the-art text-to-image diffusion model adapted for microstructure generation. Our method introduces numeric-aware embeddings that encode continuous variables (annealing temperature, time, and magnification) directly into the model's conditioning, enabling controlled image generation under specified process conditions and capturing process-driven microstructural variations. To address data scarcity and computational constraints, we fine-tune only a small fraction of the model's weights via DreamBooth and Low-Rank Adaptation (LoRA), efficiently transferring the pre-trained model to the materials domain. We validate realism using a semantic segmentation model based on a fine-tuned U-Net with a VGG16 encoder on 24 labeled micrographs. It achieves 97.1% accuracy and 85.7% mean IoU, outperforming previous methods. Quantitative analyses using physical descriptors and spatial statistics show strong agreement between synthetic and real microstructures. Specifically, two-point correlation and lineal-path errors remain below 2.1% and 0.6%, respectively. Our method represents the first adaptation of SD3.5-Large for process-aware microstructure generation, offering a scalable approach for data-driven materials design. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_00459 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Parameter-aware high-fidelity microstructure generation using stable diffusion Phan, Hoang Cuong Tran, Minh Tien Lee, Chihun Kim, Hoheok Oh, Sehyeok Kim, Dong-Kyu Lee, Ho Won Materials Science Artificial Intelligence Synthesizing realistic microstructure images conditioned on processing parameters is crucial for understanding process-structure relationships in materials design. However, this task remains challenging due to limited training micrographs and the continuous nature of processing variables. To overcome these challenges, we present a novel process-aware generative modeling approach based on Stable Diffusion 3.5 Large (SD3.5-Large), a state-of-the-art text-to-image diffusion model adapted for microstructure generation. Our method introduces numeric-aware embeddings that encode continuous variables (annealing temperature, time, and magnification) directly into the model's conditioning, enabling controlled image generation under specified process conditions and capturing process-driven microstructural variations. To address data scarcity and computational constraints, we fine-tune only a small fraction of the model's weights via DreamBooth and Low-Rank Adaptation (LoRA), efficiently transferring the pre-trained model to the materials domain. We validate realism using a semantic segmentation model based on a fine-tuned U-Net with a VGG16 encoder on 24 labeled micrographs. It achieves 97.1% accuracy and 85.7% mean IoU, outperforming previous methods. Quantitative analyses using physical descriptors and spatial statistics show strong agreement between synthetic and real microstructures. Specifically, two-point correlation and lineal-path errors remain below 2.1% and 0.6%, respectively. Our method represents the first adaptation of SD3.5-Large for process-aware microstructure generation, offering a scalable approach for data-driven materials design. |
| title | Parameter-aware high-fidelity microstructure generation using stable diffusion |
| topic | Materials Science Artificial Intelligence |
| url | https://arxiv.org/abs/2507.00459 |