Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Phan, Hoang Cuong, Tran, Minh Tien, Lee, Chihun, Kim, Hoheok, Oh, Sehyeok, Kim, Dong-Kyu, Lee, Ho Won
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