방법 비교

	미세조정 확산 모델	확산 모델을 이용한 전이 학습
분야	딥러닝	딥러닝
계열	Machine learning	Machine learning
기원 연도	2020–2023	2020–2023
창시자	Ho, J., Jain, A., Abbeel, P. (base DDPM); Ruiz et al. (DreamBooth fine-tuning paradigm)	Ho et al. (DDPM); transfer application popularized by Rombach et al. (Stable Diffusion) and Ruiz et al. (DreamBooth), 2020–2023
유형	Generative model (fine-tuned via subject-specific or domain-specific data)	Generative model with transfer learning
원전	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.	Ho, J., Jain, A., & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. Advances in Neural Information Processing Systems (NeurIPS), 33, 6840–6851.
별칭	DDPM fine-tuning, diffusion model adaptation, personalized diffusion model, subject-driven diffusion fine-tuning	diffusion model fine-tuning, pre-trained diffusion transfer, TL-DM, domain-adapted diffusion model
관련	5	5
요약	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.	Transfer Learning with Diffusion Models adapts a large pre-trained diffusion model — such as Stable Diffusion or DALL-E 2 — to a new target domain or task by continuing training on a smaller domain-specific dataset. Rather than learning the full generative process from scratch, practitioners leverage knowledge already encoded in millions of training steps to achieve high-quality domain-adapted generation with modest data and compute.