Tehisintellekti abiga joonistamine kasutades Stable Diffusion Img2Img mudelit

dc.contributor.advisorTampuu, Ardi, juhendaja
dc.contributor.authorKõiv, Rainer
dc.contributor.otherTartu Ülikool. Loodus- ja täppisteaduste valdkondet
dc.contributor.otherTartu Ülikool. Arvutiteaduse instituutet
dc.date.accessioned2025-10-20T09:51:03Z
dc.date.available2025-10-20T09:51:03Z
dc.date.issued2025
dc.description.abstractThe goal of this bachelor’s thesis was to develop an interactive demo application that allows users to draw simple sketches, from which AI models detect objects and generate enhanced images in a selected style. The demo is intended for display in the Delta academic building and for presentation at various events. The thesis consists of a theoretical part, introducing the components and models required to implement the demo, and a practical part, which provides an overview of the developed solution and analyzes the results. The application’s user interface was built using the Gradio framework, and image processing was performed using the Florence-2-large, Stable Diffusion v1.5, and SD ControlNet – Scribble models.
dc.identifier.urihttps://hdl.handle.net/10062/116892
dc.language.isoet
dc.publisherTartu Ülikoolet
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectGeneratiivne tehisintellekt
dc.subjectlihtsad joonistused
dc.subjectdemorakendus
dc.subjectStable Diffusion
dc.subjectSD ControlNet
dc.subjectFlorence
dc.subjectGradio
dc.subjectGenerative AI
dc.subjectsimple sketches
dc.subject.otherbakalaureusetöödet
dc.subject.otherinformaatikaet
dc.subject.otherinfotehnoloogiaet
dc.subject.otherinformaticsen
dc.subject.otherinfotechnologyen
dc.titleTehisintellekti abiga joonistamine kasutades Stable Diffusion Img2Img mudelit
dc.typeThesis

Failid

Originaal pakett

Nüüd näidatakse 1 - 1 1
Laen...
Pisipilt
Nimi:
koiv_informaatika_2025.pdf
Suurus:
12.73 MB
Formaat:
Adobe Portable Document Format