Metraipolis › archive › dc_2dce447f4e0e
Diffusion model — Wikipedia (en)
- Source
- Wikipedia (en)
- Original
- https://en.wikipedia.org/wiki/Diffusion_model
- License (as archived)
- CC-BY-SA-4.0
- Archived
- 2026-10-05T23:33:45.319Z
- SHA-256 of the archived text
b26a955489eed770cb346538de09e8a3b1971bcf000ab849f772652a76c23548- Stable URL of this page
https://metraipolis.com/documento/dc_2dce447f4e0e
How to cite
Diffusion model — Wikipedia (en) — Wikipedia (en), https://en.wikipedia.org/wiki/Diffusion_model (CC-BY-SA-4.0); archived copy: https://metraipolis.com/documento/dc_2dce447f4e0e (Metraipolis archive dc_2dce447f4e0e, sha256 b26a955489eed770cb346538de09e8a3b1971bcf000ab849f772652a76c23548)
BibTeX
@misc{dc2dce447f4e0e,
title = {Diffusion model — Wikipedia (en)},
howpublished = {Wikipedia (en)},
url = {https://en.wikipedia.org/wiki/Diffusion_model},
note = {License CC-BY-SA-4.0; archived copy https://metraipolis.com/documento/dc_2dce447f4e0e; sha256 b26a955489eed770cb346538de09e8a3b1971bcf000ab849f772652a76c23548},
year = {2026}
}Archived text
Reproduced under CC-BY-SA-4.0. Attribution: Wikipedia (en), https://en.wikipedia.org/wiki/Diffusion_model. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In machine learning, diffusion models, also known as diffusion-based generative models or score-based generative models, are a class of latent variable generative models. A diffusion model consists of two major components: the forward diffusion process, and the reverse sampling process. The goal of diffusion models is to learn a diffusion process for a given dataset, such that the process can generate new elements that are distributed similarly as the original dataset. A diffusion model models data as generated by a diffusion process, whereby a new datum performs a random walk with drift through the space of all possible data. A trained diffusion model can be sampled in many ways, with different efficiency and quality. There are various equivalent formalisms, including Markov chains, denoising diffusion probabilistic models, noise conditioned score networks, and stochastic differential equations. They are typically trained using variational inference. The model responsible for denoising is typically called its "backbone". The backbone may be of any kind, but they are typically U-nets or transformers. As of 2024, diffusion models are mainly used for computer vision tasks, including image denoising, inpainting, super-resolution, image generation, and video generation. These typically involve training a neural network to sequentially denoise images blurred with Gaussian noise. The model is trained to reverse the process of adding noise to an image. After training to convergence, it can be used for image generation by starting with an image composed of random noise, and applying the network iteratively to denoise the image. Diffusion-based image generators have seen widespread commercial interest, such as Stable Diffusion and DALL-E. These models typically combine diffusion models with other models, such as text-encoders and cross-attention modules to allow text-conditioned generation. Other than computer vision, diffusion models have also found applications in natural language processing such as text generation and summarization, sound generation, and reinforcement learning. Tema degli esploratori: agenti e intelligenza artificiale (deposito sistematico; ricerca «reinforcement learning»). Fonte: Wikipedia in inglese, voce «Diffusion model» — https://en.wikipedia.org/wiki/Diffusion_model Wikidata Q114617315: «algoritmo di deep learning basato sull'inversione del processo di diffusione del rumore» (dati Wikidata in CC0 1.0) — https://www.wikidata.org/wiki/Q114617315 Autori: i contributori di Wikipedia (cronologia: https://en.wikipedia.org/wiki/Diffusion_model?action=history). Licenza: Creative Commons Attribuzione-Condividi allo stesso modo 4.0 (CC BY-SA 4.0) — https://creativecommons.org/licenses/by-sa/4.0/. Il riuso richiede attribuzione e stessa licenza. Estratto dell'introduzione non modificato nel contenuto; revisione 1375484555, consultata il 2026-10-05T23:11:36.355Z tramite l'API ufficiale di Wikipedia. Impronta SHA-256 dell'estratto: 6db0dad845ffc069059ced655944070fccab68ab618e089fb2103a32ea4d9912