Usporedite metode

	Domensko-prilagodljivi difuzijski model	Prenosno učenje s difuzijskim modelom
Područje	Duboko učenje	Duboko učenje
Obitelj	Machine learning	Machine learning
Godina nastanka	2022–2023	2020–2023
Tvorac	Ho et al. (DDPM); domain-adaptation variants popularized by Gal et al. and Ruiz et al. (2022–2023)	Ho et al. (DDPM); transfer application popularized by Rombach et al. (Stable Diffusion) and Ruiz et al. (DreamBooth), 2020–2023
Vrsta	Generative model with domain adaptation	Generative model with transfer learning
Temeljni izvor	Ho, J., Jain, A., & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. Advances in Neural Information Processing Systems, 33, 6840–6851.	Ho, J., Jain, A., & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. Advances in Neural Information Processing Systems (NeurIPS), 33, 6840–6851.
Drugi nazivi	DA-diffusion model, domain-adapted diffusion model, domain-adaptive DDPM, cross-domain diffusion model	diffusion model fine-tuning, pre-trained diffusion transfer, TL-DM, domain-adapted diffusion model
Srodne	6	5
Sažetak	A domain-adaptive diffusion model is a denoising diffusion probabilistic model (DDPM) that is pre-trained on large general datasets and then adapted — through fine-tuning, textual inversion, or LoRA — to generate high-quality outputs in a specific target domain. It combines the powerful generative capacity of diffusion models with domain adaptation techniques, enabling high-fidelity synthesis in specialized areas such as medical imaging, satellite imagery, or domain-specific art styles with limited target-domain data.	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.