无需训练即可生成满足物理约束的图像，提升扩散模型在科学设计中的实用性。
Training-Free Constrained Generation With Stable Diffusion Models
- 将扩散模型与约束优化结合，实现无训练约束生成。
- 在材料设计中精确控制形态特征与力学响应，满足严格物理要求。
- 适用于材料逆设计、版权受限内容生成，适合科研与工程应用。
稳定扩散模型在多个领域代表数据生成的最先进水平，具有推动科学与工程应用的变革潜力，例如促进新解决方案的发现及模拟计算上不可行的系统。尽管已有研究尝试将基于物理的约束融入生成模型，但现有方法或仅适用于潜在扩散框架，或无法严格施加特定领域的约束。为此，本文提出一种新型稳定扩散模型与约束优化框架的集成方法，可生成满足严苛物理和功能要求的输出。该方法的有效性通过材料设计实验得到验证：需精确遵循形态学特性、挑战性的逆向设计任务（生成特定应力-应变响应的材料），以及版权约束的内容生成任务。所有代码已开源至 https://github.com/RAISELab-atUVA/Constrained-Stable-Diffusion。
原文摘要 · Abstract (English)
Stable diffusion models represent the state-of-the-art in data synthesis across diverse domains and hold transformative potential for applications in science and engineering, e.g., by facilitating the discovery of novel solutions and simulating systems that are computationally intractable to model explicitly. While there is increasing effort to incorporate physics-based constraints into generative models, existing techniques are either limited in their applicability to latent diffusion frameworks or lack the capability to strictly enforce domain-specific constraints. To address this limitation this paper proposes a novel integration of stable diffusion models with constrained optimization frameworks, enabling the generation of outputs satisfying stringent physical and functional requirements. The effectiveness of this approach is demonstrated through material design experiments requiring adherence to precise morphometric properties, challenging inverse design tasks involving the generation of materials inducing specific stress-strain responses, and copyright-constrained content generation tasks. All code has been released at https://github.com/RAISELab-atUVA/Constrained-Stable-Diffusion.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。