Training-free style transfer in diffusion models

Κακούρης, Δημήτριος; Kakouris, Dimitrios

dc.contributor.author	Κακούρης, Δημήτριος	el
dc.contributor.author	Kakouris, Dimitrios	en
dc.date.accessioned	2025-01-31T10:29:57Z
dc.date.available	2025-01-31T10:29:57Z
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/61017
dc.identifier.uri	http://dx.doi.org/10.26240/heal.ntua.28713
dc.rights	Default License
dc.subject	Μηχανική Μάθηση	el
dc.subject	Νευρωνικά Δίκτυα	el
dc.subject	Μοντέλα διάχυσης	el
dc.subject	Μηχανισμός Προσοχής	el
dc.subject	Diffusion Models	en
dc.subject	Style Transfer	en
dc.subject	Generative AI	en
dc.subject	Τransformers	en
dc.subject	Μachine learning	en
dc.title	Training-free style transfer in diffusion models	en
heal.type	bachelorThesis	el
heal.secondaryTitle	Via Attention-Key Injection and Initial Noise Optimization	en
heal.classification	Computer science	en
heal.language	en	el
heal.access	free	el
heal.recordProvider	ntua	el
heal.publicationDate	2024-09-12
heal.abstract	Diffusion models are a novel class of generative models that have shown promising results in various applications, including image synthesis, natural language processing, and audio generation. Diffusion models operate by gradually transforming a sample from a simple distribution (e.g., Gaussian noise) into a complex data distribution through a series of iterative, noise-adding, and noise-removing steps. This diploma thesis extends the application of diffusion models to the domain of style transfer, a technique pivotal to altering the output of the diffusion model and effectively guiding into producing an image that closely resembles our desired art style. It is crucial to handle semantic alignment while also preserving the texture and nuances of the desired art style. This thesis aims to achieve a fine-balance between these two components.	en
heal.abstract	Diffusion models are a novel class of generative models that have shown promising results in various applications, including image synthesis, natural language processing, and audio generation. Diffusion models operate by gradually transforming a sample from a simple distribution (e.g., Gaussian noise) into a complex data distribution through a series of iterative, noise-adding, and noise-removing steps. This diploma thesis extends the application of diffusion models to the domain of style transfer, a technique pivotal to altering the output of the diffusion model and effectively guiding into producing an image that closely resembles our desired art style. It is crucial to handle semantic alignment while also preserving the texture and nuances of the desired art style. This thesis aims to achieve a fine-balance between these two components.	en
heal.abstract	Diffusion models are a novel class of generative models that have shown promising results in various applications, including image synthesis, natural language processing, and audio generation. Diffusion models operate by gradually transforming a sample from a simple distribution (e.g., Gaussian noise) into a complex data distribution through a series of iterative, noise-adding, and noise-removing steps. This diploma thesis extends the application of diffusion models to the domain of style transfer, a technique pivotal to altering the output of the diffusion model and effectively guiding into producing an image that closely resembles our desired art style. It is crucial to handle semantic alignment while also preserving the texture and nuances of the desired art style. This thesis aims to achieve a fine-balance between these two components.	en
heal.advisorName	Βουλόδημος, Αθανάσιος	el
heal.committeeMemberName	Στάμου, Γεώργιος	el
heal.academicPublisher	Εθνικό Μετσόβιο Πολυτεχνείο. Σχολή Ηλεκτρολόγων Μηχανικών και Μηχανικών Υπολογιστών. Τομέας Τεχνολογίας Πληροφορικής και Υπολογιστών	el
heal.academicPublisherID	ntua	el
heal.numberOfPages	99 σ.	el
heal.fullTextAvailability	false