prikaz prve stranice dokumenta Automatizirano generiranje setova portreta primjenom Stable Diffusion biblioteke
  Download
PDF 1.96 MB
master's thesis
Automatizirano generiranje setova portreta primjenom Stable Diffusion biblioteke
2023. urn:nbn:hr:200:224947
Šrempf, Michael
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Software Engineering
Chair of Visual Computing

Cite this document

Šrempf, M. (2023). Automatizirano generiranje setova portreta primjenom Stable Diffusion biblioteke (Master's thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek. Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:224947

Šrempf, Michael. "Automatizirano generiranje setova portreta primjenom Stable Diffusion biblioteke." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2023. https://urn.nsk.hr/urn:nbn:hr:200:224947

Šrempf, Michael. "Automatizirano generiranje setova portreta primjenom Stable Diffusion biblioteke." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2023. https://urn.nsk.hr/urn:nbn:hr:200:224947

Šrempf, M. (2023). 'Automatizirano generiranje setova portreta primjenom Stable Diffusion biblioteke', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 13 July 2024, https://urn.nsk.hr/urn:nbn:hr:200:224947

Šrempf M. Automatizirano generiranje setova portreta primjenom Stable Diffusion biblioteke [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2023 [cited 2024 July 13] Available at: https://urn.nsk.hr/urn:nbn:hr:200:224947

M. Šrempf, "Automatizirano generiranje setova portreta primjenom Stable Diffusion biblioteke", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:200:224947

Please login to the repository to save this object to your list.
Metadata
TitleAutomatizirano generiranje setova portreta primjenom Stable Diffusion biblioteke
Title (english)Automated generation of portrait sets using the Stable Diffusion library
AuthorMichael Šrempf
MentorČaslav Livada (mentor)
Committee memberČaslav Livada (član povjerenstva)
Committee memberKrešimir Nenadić (predsjednik povjerenstva)
Committee memberRobert Šojo (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Software Engineering)
(Chair of Visual Computing)
Osijek
Defense date and country2023-10-03, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Data Processing
Abstract
Cilj rada je bio napraviti program za generiranje portreta koristeći Stable Diffuison biblioteku. U radu su istražene vrste generativnih modela, kako se treniraju generativni modeli, te njihove prednosti i mane. U radu također prikazan način na koji Stable Diffusion koristi difuzijske modele za generiranje slika. Na osnovu stečenih znanja napravljena je desktop aplikacija za generiranje portreta pomoću koje je testirano kako različiti parametri utječu na generiranje slike.
Abstract (english)
The aim of this project isto create a program for generating portraits using Stable Diffusion library. This paper explores the types of generative models, how generative models are trained and their advantages and disadvantages. The paper also shows the way in which Stable Diffusion uses diffusion models to generate images. Based on the acquired knowledge, a desktop application for generating portraits was created, which was used to test how different parameters affect image generation.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:224947
Study programmeTitle: Graduate University Study Programme in Computer Engineering
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2023-10-17 10:45:32