手法を比較

	説明可能な拡散モデル	ファインチューニングされた拡散モデル
分野	深層学習	深層学習
系統	Machine learning	Machine learning
提唱年	2020–2022	2020–2023
提唱者	Ho, J., Jain, A., & Abbeel, P. (DDPM, 2020); XAI augmentation by subsequent researchers	Ho, J., Jain, A., Abbeel, P. (base DDPM); Ruiz et al. (DreamBooth fine-tuning paradigm)
種類	Generative model with post-hoc or intrinsic explainability	Generative model (fine-tuned via subject-specific or domain-specific data)
原典	Ho, J., Jain, A., & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. Advances in Neural Information Processing Systems, 33, 6840–6851.	Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., & Aberman, K. (2023). DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 22500–22510.
別名	XAI-DDPM, interpretable diffusion model, transparent diffusion model, explainable DDPM	DDPM fine-tuning, diffusion model adaptation, personalized diffusion model, subject-driven diffusion fine-tuning
関連	6	5
概要	An Explainable Diffusion Model couples a denoising diffusion probabilistic model with post-hoc or intrinsic explainability techniques — such as SHAP, gradient-based saliency, attention analysis, or concept-based probing — so that each generative or predictive decision can be audited and justified rather than treated as a black box.	A fine-tuned diffusion model adapts a large pretrained denoising diffusion model — such as Stable Diffusion or DALL-E — to a specific subject, style, or domain by continuing training on a small curated dataset. Techniques such as DreamBooth, textual inversion, and LoRA make this adaptation feasible on consumer hardware while preserving general generative capability.