Machine learningDeep Learning, Generative Models

Latentni difuzioni modeli

Latentni difuzioni modeli (LDM) su generativni pristup koji su uveli Rombach et al. 2022. godine, a koji proces difuzije sprovodi u kompresovanom latentnom prostoru umesto u pikselnom prostoru, omogućavajući efikasnu sintezu slika visoke rezolucije. Kompresovanjem slika u niskodimenzionalnu latentnu reprezentaciju pomoću varijacionog autoenkodera, difuzija postaje računski izvodljiva uz održavanje vizuelnog kvaliteta.

Otvorite u MethodMindUskoroVideoUskoroDownload slides

Pročitajte celu metodu

Samo za članove

Prijavite se besplatnim nalogom da biste pročitali ovaj odeljak.

Prijavite se

Method map

The neighbourhood of related methods — select a node to explore.

Izvori

  1. Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 10684-10695). DOI: 10.1109/CVPR52688.2022.01042

Kako citirati ovu stranicu

ScholarGate. (2026, June 3). High-Resolution Image Synthesis with Latent Diffusion Models. ScholarGate. https://scholargate.app/sr/deep-learning/latent-diffusion-models

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side

Citirana u

ScholarGateLatent Diffusion Models (High-Resolution Image Synthesis with Latent Diffusion Models). Preuzeto 2026-06-15 sa https://scholargate.app/sr/deep-learning/latent-diffusion-models · Skup podataka: https://doi.org/10.5281/zenodo.20539026