Sökning: "Latent Diffusion"

Hittade 4 uppsatser innehållade orden Latent Diffusion.

  1. 1. Text to Music Audio Generation using Latent Diffusion Model : A re-engineering of AudioLDM Model

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Ernan Wang; [2023]
    Nyckelord :Text to Music Audio Generation; Latent Diffusion; AudioLDM; Sampling Methods; Denoising Diffusion Probabilistic Model DDPM ; Denoising Diffusion Implicit Model DDIM ; Text till musik Ljudgenerering; Latent Diffusion; AudioLDM; Samplingsmetoder; DDPM; DDIM;

    Sammanfattning : In the emerging field of audio generation using diffusion models, this project pioneers the adaptation of the AudioLDM model framework, initially designed for text-to-daily sounds generation, towards text-to-music audio generation. This shift addresses a gap in the current scope of audio diffusion models, predominantly focused on everyday sounds. LÄS MER

  3. 2. AI learn, AI do : En konstvetenskaplig studie om AI-modellers materialbetingade förmågor, aktörskap och deltagande inom konstnärliga processer

    Master-uppsats, Uppsala universitet/Konstvetenskapliga institutionen

    Författare :Cornelius Persson; [2023]
    Nyckelord :actor network theory; AI-art; AI-image; artificial intelligence; diffusion art; prompt; prompting; Stable Diffusion; GAN; midjourney; ANT; aktör nätverks teori; AI-konst; AI-bild; AI-modell; AI; artificiell intelligens; diffusions-konst; GAN-konst; bildmaterial; träningsdata; appropriering; latent utrymme; generativ; Latour;

    Sammanfattning : This master’s thesis investigates generative AI-art through the lens of actor network theory. By focusing on the role of images in datasets as a material that effects both AI-models and artworks, the decisively non-human agencies generative AI-models can be said to possess, and the traces and associations that generative AI-models imbue artworks with, this thesis aims to investigate art that has been created with GAN-models as well as contemporary text-to-image diffusion-models, by way of similar premises. LÄS MER

  4. 3. Diffusion models for anomaly detection in digital pathology

    Magister-uppsats, Linköpings universitet/Medie- och Informationsteknik; Linköpings universitet/Tekniska fakulteten

    Författare :Ruben Bromée; [2023]
    Nyckelord :out-of-distribution detection; digital pathology data; latent diffusion model; machine learning; neural network; pathology;

    Sammanfattning : Challenges within the field of pathology leads to a high workload for pathologists. Machine learning has the ability to assist pathologists in their daily work and has shown good performance in a research setting. LÄS MER

  5. 4. Klassificering av latent diffusion genererade bilder : En metod som använder ett konvolutionellt neuralt nätverk för att klassificera latent diffusion genererade bilder

    Kandidat-uppsats, Högskolan i Skövde/Institutionen för informationsteknologi

    Författare :Sacharias Karlsson; Niklas Johansson; Mikael Freden; [2023]
    Nyckelord :Diffusion; AI; Deep learning; Image; CNN; ResNet50;

    Sammanfattning : Previous studies have used convolutional neural networks (CNN) to classify synthetic images created by generative adversarial networks (GANs) to confirm images as either being synthetic or natural. Similar to other research, this thesis will cover the classification of synthetic images witha CNN. LÄS MER